List of my publications. You can also find me on Google Scholar, DBLP, or Cristin.
2022
Bach, Kerstin; Kongsvold, Atle; Bårdstu, Hilde; Bardal, Ellen Marie; Kjærnli, Håkon S.; Herland, Sverre; Logacjov, Aleksej; Mork, Paul Jarle
A Machine Learning Classifier for Detection of Physical Activity Types and Postures During Free-Living Journal Article
In: Journal for the Measurement of Physical Behaviour, vol. 5, no. 1, pp. 24 - 31, 2022.
@article{HUNT4Valid2022,
title = {A Machine Learning Classifier for Detection of Physical Activity Types and Postures During Free-Living},
author = {Kerstin Bach and Atle Kongsvold and Hilde Bårdstu and Ellen Marie Bardal and Håkon S. Kjærnli and Sverre Herland and Aleksej Logacjov and Paul Jarle Mork},
url = {https://journals.humankinetics.com/view/journals/jmpb/5/1/article-p24.xml},
doi = {10.1123/jmpb.2021-0015},
year = {2022},
date = {2022-12-31},
urldate = {2022-01-01},
journal = {Journal for the Measurement of Physical Behaviour},
volume = {5},
number = {1},
pages = {24 - 31},
publisher = {Human Kinetics},
address = {Champaign IL, USA},
abstract = {Introduction: Accelerometer-based measurements of physical activity types are commonly used to replace self-reports. To advance the field, it is desirable that such measurements allow accurate detection of key daily physical activity types. This study aimed to evaluate the performance of a machine learning classifier for detecting sitting, standing, lying, walking, running, and cycling based on a dual versus single accelerometer setups during free-living. Methods: Twenty-two adults (mean age [SD, range] 38.7 [14.4, 25–68] years) were wearing two Axivity AX3 accelerometers positioned on the low back and thigh along with a GoPro camera positioned on the chest to record lower body movements during free-living. The labeled videos were used as ground truth for training an eXtreme Gradient Boosting classifier using window lengths of 1, 3, and 5 s. Performance of the classifier was evaluated using leave-one-out cross-validation. Results: Total recording time was ∼38 hr. Based on 5-s windowing, the overall accuracy was 96% for the dual accelerometer setup and 93% and 84% for the single thigh and back accelerometer setups, respectively. The decreased accuracy for the single accelerometer setup was due to a poor precision in detecting lying based on the thigh accelerometer recording (77%) and standing based on the back accelerometer recording (64%). Conclusion: Key daily physical activity types can be accurately detected during free-living based on dual accelerometer recording, using an eXtreme Gradient Boosting classifier. The overall accuracy decreases marginally when predictions are based on single thigh accelerometer recording, but detection of lying is poor.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Introduction: Accelerometer-based measurements of physical activity types are commonly used to replace self-reports. To advance the field, it is desirable that such measurements allow accurate detection of key daily physical activity types. This study aimed to evaluate the performance of a machine learning classifier for detecting sitting, standing, lying, walking, running, and cycling based on a dual versus single accelerometer setups during free-living. Methods: Twenty-two adults (mean age [SD, range] 38.7 [14.4, 25–68] years) were wearing two Axivity AX3 accelerometers positioned on the low back and thigh along with a GoPro camera positioned on the chest to record lower body movements during free-living. The labeled videos were used as ground truth for training an eXtreme Gradient Boosting classifier using window lengths of 1, 3, and 5 s. Performance of the classifier was evaluated using leave-one-out cross-validation. Results: Total recording time was ∼38 hr. Based on 5-s windowing, the overall accuracy was 96% for the dual accelerometer setup and 93% and 84% for the single thigh and back accelerometer setups, respectively. The decreased accuracy for the single accelerometer setup was due to a poor precision in detecting lying based on the thigh accelerometer recording (77%) and standing based on the back accelerometer recording (64%). Conclusion: Key daily physical activity types can be accurately detected during free-living based on dual accelerometer recording, using an eXtreme Gradient Boosting classifier. The overall accuracy decreases marginally when predictions are based on single thigh accelerometer recording, but detection of lying is poor.
Marín-Veites, Paola; Bach, Kerstin
Explaining CBR Systems Through Retrieval and Similarity Measure Visualizations: A Case Study Inproceedings Forthcoming
In: Keane, Mark; Wiratunga, Nirmalie (Ed.): Case-Based Reasoning Research and Development, Springer, Cham, Forthcoming.
@inproceedings{SupportPrimICCBR2022,
title = {Explaining CBR Systems Through Retrieval and Similarity Measure Visualizations: A Case Study},
author = {Paola Marín-Veites and Kerstin Bach},
editor = {Mark Keane and Nirmalie Wiratunga},
year = {2022},
date = {2022-09-15},
booktitle = {Case-Based Reasoning Research and Development},
publisher = {Springer, Cham},
abstract = {Explainability in AI is becoming increasingly important as we delegate more safety-critical tasks to intelligent decision support systems. Case-Based Reasoning (CBR) systems are one way to build such systems. Understanding how results are created by a CBR system has become an important task in their development process. In this work, we
present how visualizations can help developers and domain experts to evaluate the CBR systems behavior and provide insights to further develop CBR systems in their application scenarios. This paper presents an overview of SupportPrim, a CBR system for the management of musculoskeletal pain complaints, and presents methods that explain its retrieval and similarity measures through visualizations that help to evaluate the
system’s performance. In the case study, we conduct experiments within the SupportPrim CBR system using differently weighted global similarity measures to compare their effect on the retrieval. This work shows that providing suitable explanations for the CBR system’s stakeholders increases the likelihood of its adoption, and visualizations allow the creation of different explanations for the different users throughout the development phase, thus allowing for better modeling and usage of the system.},
keywords = {},
pubstate = {forthcoming},
tppubtype = {inproceedings}
}
Explainability in AI is becoming increasingly important as we delegate more safety-critical tasks to intelligent decision support systems. Case-Based Reasoning (CBR) systems are one way to build such systems. Understanding how results are created by a CBR system has become an important task in their development process. In this work, we
present how visualizations can help developers and domain experts to evaluate the CBR systems behavior and provide insights to further develop CBR systems in their application scenarios. This paper presents an overview of SupportPrim, a CBR system for the management of musculoskeletal pain complaints, and presents methods that explain its retrieval and similarity measures through visualizations that help to evaluate the
system’s performance. In the case study, we conduct experiments within the SupportPrim CBR system using differently weighted global similarity measures to compare their effect on the retrieval. This work shows that providing suitable explanations for the CBR system’s stakeholders increases the likelihood of its adoption, and visualizations allow the creation of different explanations for the different users throughout the development phase, thus allowing for better modeling and usage of the system.
present how visualizations can help developers and domain experts to evaluate the CBR systems behavior and provide insights to further develop CBR systems in their application scenarios. This paper presents an overview of SupportPrim, a CBR system for the management of musculoskeletal pain complaints, and presents methods that explain its retrieval and similarity measures through visualizations that help to evaluate the
system’s performance. In the case study, we conduct experiments within the SupportPrim CBR system using differently weighted global similarity measures to compare their effect on the retrieval. This work shows that providing suitable explanations for the CBR system’s stakeholders increases the likelihood of its adoption, and visualizations allow the creation of different explanations for the different users throughout the development phase, thus allowing for better modeling and usage of the system.
Flogard, Eirik Lund; Mengshoel, Ole Jakob; Bach, Kerstin
Creating Dynamic Checklists via Bayesian Case-Based Reasoning: Towards Decent Working Conditions for All Inproceedings Forthcoming
In: IJCAI International Joint Conference on Artificial Intelligence., Forthcoming.
@inproceedings{FlogardIJCAI22,
title = {Creating Dynamic Checklists via Bayesian Case-Based Reasoning: Towards Decent Working Conditions for All},
author = {Eirik Lund Flogard and Ole Jakob Mengshoel and Kerstin Bach},
year = {2022},
date = {2022-07-31},
booktitle = {IJCAI International Joint Conference on Artificial Intelligence.},
keywords = {},
pubstate = {forthcoming},
tppubtype = {inproceedings}
}
Vonstad, Elise Klæbo; Bach, Kerstin; Vereijken, Beatrix; Su, Xiaomeng; Nilsen, Jan Harald
Performance of machine learning models in estimation of ground reaction forces during balance exergaming Journal Article
In: Journal of Neuro Engineering and Rehabilitation, vol. 19, iss. 2022, no. 18, 2022, ISSN: 1743-0003.
@article{vonstad2021estimation,
title = {Performance of machine learning models in estimation of ground reaction forces during balance exergaming},
author = {Elise Klæbo Vonstad and Kerstin Bach and Beatrix Vereijken and Xiaomeng Su and Jan Harald Nilsen },
url = {https://jneuroengrehab.biomedcentral.com/articles/10.1186/s12984-022-00998-5},
doi = {10.1186/s12984-022-00998-5},
issn = {1743-0003},
year = {2022},
date = {2022-02-13},
urldate = {2021-01-01},
journal = {Journal of Neuro Engineering and Rehabilitation},
volume = {19},
number = {18},
issue = {2022},
publisher = {Elsevier},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
2021
Murad, Abdulmajid; Kraemer, Frank Alexander; Bach, Kerstin; Taylor, Gavin
Probabilistic Deep Learning to Quantify Uncertainty in Air Quality Forecasting Journal Article
In: Sensors, vol. 21, no. 23, 2021, ISSN: 1424-8220.
@article{Murad2021,
title = {Probabilistic Deep Learning to Quantify Uncertainty in Air Quality Forecasting},
author = {Abdulmajid Murad and Frank Alexander Kraemer and Kerstin Bach and Gavin Taylor},
editor = {Yeh Hsi-Jen James},
url = {https://www.mdpi.com/1424-8220/21/23/8009},
doi = {10.3390/s21238009},
issn = {1424-8220},
year = {2021},
date = {2021-11-30},
urldate = {2021-01-01},
journal = {Sensors},
volume = {21},
number = {23},
abstract = {Data-driven forecasts of air quality have recently achieved more accurate short-term predictions. However, despite their success, most of the current data-driven solutions lack proper quantifications of model uncertainty that communicate how much to trust the forecasts. Recently, several practical tools to estimate uncertainty have been developed in probabilistic deep learning. However, there have not been empirical applications and extensive comparisons of these tools in the domain of air quality forecasts. Therefore, this work applies state-of-the-art techniques of uncertainty quantification in a real-world setting of air quality forecasts. Through extensive experiments, we describe training probabilistic models and evaluate their predictive uncertainties based on empirical performance, reliability of confidence estimate, and practical applicability. We also propose improving these models using “free” adversarial training and exploiting temporal and spatial correlation inherent in air quality data. Our experiments demonstrate that the proposed models perform better than previous works in quantifying uncertainty in data-driven air quality forecasts. Overall, Bayesian neural networks provide a more reliable uncertainty estimate but can be challenging to implement and scale. Other scalable methods, such as deep ensemble, Monte Carlo (MC) dropout, and stochastic weight averaging-Gaussian (SWAG), can perform well if applied correctly but with different tradeoffs and slight variations in performance metrics. Finally, our results show the practical impact of uncertainty estimation and demonstrate that, indeed, probabilistic models are more suitable for making informed decisions.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Data-driven forecasts of air quality have recently achieved more accurate short-term predictions. However, despite their success, most of the current data-driven solutions lack proper quantifications of model uncertainty that communicate how much to trust the forecasts. Recently, several practical tools to estimate uncertainty have been developed in probabilistic deep learning. However, there have not been empirical applications and extensive comparisons of these tools in the domain of air quality forecasts. Therefore, this work applies state-of-the-art techniques of uncertainty quantification in a real-world setting of air quality forecasts. Through extensive experiments, we describe training probabilistic models and evaluate their predictive uncertainties based on empirical performance, reliability of confidence estimate, and practical applicability. We also propose improving these models using “free” adversarial training and exploiting temporal and spatial correlation inherent in air quality data. Our experiments demonstrate that the proposed models perform better than previous works in quantifying uncertainty in data-driven air quality forecasts. Overall, Bayesian neural networks provide a more reliable uncertainty estimate but can be challenging to implement and scale. Other scalable methods, such as deep ensemble, Monte Carlo (MC) dropout, and stochastic weight averaging-Gaussian (SWAG), can perform well if applied correctly but with different tradeoffs and slight variations in performance metrics. Finally, our results show the practical impact of uncertainty estimation and demonstrate that, indeed, probabilistic models are more suitable for making informed decisions.
Logacjov, Aleksej; Bach, Kerstin; Kongsvold, Atle; Bårdstu, Hilde Bremseth; Mork, Paul Jarle
HARTH: A Human Activity Recognition Dataset for Machine Learning Journal Article
In: Sensors, vol. 21, no. 23, 2021, ISSN: 1424-8220.
@article{LogacjovHARTH21,
title = {HARTH: A Human Activity Recognition Dataset for Machine Learning},
author = {Aleksej Logacjov and Kerstin Bach and Atle Kongsvold and Hilde Bremseth Bårdstu and Paul Jarle Mork},
editor = {Kevin Bell},
url = {https://www.mdpi.com/1424-8220/21/23/7853},
doi = {10.3390/s21237853},
issn = {1424-8220},
year = {2021},
date = {2021-11-25},
urldate = {2021-01-01},
journal = {Sensors},
volume = {21},
number = {23},
abstract = {Existing accelerometer-based human activity recognition (HAR) benchmark datasets that were recorded during free living suffer from non-fixed sensor placement, the usage of only one sensor, and unreliable annotations. We make two contributions in this work. First, we present the publicly available Human Activity Recognition Trondheim dataset (HARTH). Twenty-two participants were recorded for 90 to 120 min during their regular working hours using two three-axial accelerometers, attached to the thigh and lower back, and a chest-mounted camera. Experts annotated the data independently using the camera’s video signal and achieved high inter-rater agreement (Fleiss’ Kappa =0.96). They labeled twelve activities. The second contribution of this paper is the training of seven different baseline machine learning models for HAR on our dataset. We used a support vector machine, k-nearest neighbor, random forest, extreme gradient boost, convolutional neural network, bidirectional long short-term memory, and convolutional neural network with multi-resolution blocks. The support vector machine achieved the best results with an F1-score of 0.81 (standard deviation: ±0.18), recall of 0.85±0.13, and precision of 0.79±0.22 in a leave-one-subject-out cross-validation. Our highly professional recordings and annotations provide a promising benchmark dataset for researchers to develop innovative machine learning approaches for precise HAR in free living.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Existing accelerometer-based human activity recognition (HAR) benchmark datasets that were recorded during free living suffer from non-fixed sensor placement, the usage of only one sensor, and unreliable annotations. We make two contributions in this work. First, we present the publicly available Human Activity Recognition Trondheim dataset (HARTH). Twenty-two participants were recorded for 90 to 120 min during their regular working hours using two three-axial accelerometers, attached to the thigh and lower back, and a chest-mounted camera. Experts annotated the data independently using the camera’s video signal and achieved high inter-rater agreement (Fleiss’ Kappa =0.96). They labeled twelve activities. The second contribution of this paper is the training of seven different baseline machine learning models for HAR on our dataset. We used a support vector machine, k-nearest neighbor, random forest, extreme gradient boost, convolutional neural network, bidirectional long short-term memory, and convolutional neural network with multi-resolution blocks. The support vector machine achieved the best results with an F1-score of 0.81 (standard deviation: ±0.18), recall of 0.85±0.13, and precision of 0.79±0.22 in a leave-one-subject-out cross-validation. Our highly professional recordings and annotations provide a promising benchmark dataset for researchers to develop innovative machine learning approaches for precise HAR in free living.
Vonstad, Elise Klæbo; Vereijken, Beatrix; Bach, Kerstin; Su, Xiaomeng; Nilsen, Jan Harald
Assessment of Machine Learning Models for Classification of Movement Patterns During a Weight-Shifting Exergame Journal Article
In: IEEE Transactions on Human-Machine Systems, vol. 51, no. 3, pp. 242 - 252, 2021.
@article{Vonstad21b,
title = {Assessment of Machine Learning Models for Classification of Movement Patterns During a Weight-Shifting Exergame},
author = {Elise Klæbo Vonstad and Beatrix Vereijken and Kerstin Bach and Xiaomeng Su and Jan Harald Nilsen},
url = {https://ieeexplore.ieee.org/abstract/document/9381522},
doi = {10.1109/THMS.2021.3059716},
year = {2021},
date = {2021-09-15},
urldate = {2021-09-15},
journal = {IEEE Transactions on Human-Machine Systems},
volume = {51},
number = {3},
pages = {242 - 252},
abstract = {In exercise gaming (exergaming), reward systems are typically based on rules/templates from joint movement patterns. These rules or templates need broad ranges in definitions of correct movement patterns to accommodate varying body shapes and sizes. This can lead to inaccurate rewards and, thus, inefficient exercise, which can be detrimental to progress. If exergames are to be used in serious settings like rehabilitation, accurate rewards for correctly performed movements are crucial. This article aims to investigate the level of accuracy machine learning/deep learning models can achieve in classification of correct repetitions naturally elicited from a weight-shifting exergame. Twelve healthy elderly (10F, age 70.4 SD 11.4) are recruited. Movements are captured using a marker-based 3-D motion-capture system. Random forest (RF), support vector machine, k-nearest neighbors, and multilayer perceptron (MLP) are the employed models, trained and tested on whole body movement patterns and on subsets of joints. MLP and RF reached the highest recall and F1-score, respectively, when using combined data from joint subsets. MLP recall range are 91% to 94%, and RF F1-score range 79% to 80%. MLP and RF also reached the highest recall and F1-score in each joint subset, respectively. Here, MLP ranged from 93% to 97% recall, while RF ranged from 73% to 80% F1-score. Recall results, show that >9 out of 10 repetitions are classified correctly, indicating that MLP/RF can be used to identify correctly performed repetitions of a weight-shifting exercise when using full-body data and when using joint subset data.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
In exercise gaming (exergaming), reward systems are typically based on rules/templates from joint movement patterns. These rules or templates need broad ranges in definitions of correct movement patterns to accommodate varying body shapes and sizes. This can lead to inaccurate rewards and, thus, inefficient exercise, which can be detrimental to progress. If exergames are to be used in serious settings like rehabilitation, accurate rewards for correctly performed movements are crucial. This article aims to investigate the level of accuracy machine learning/deep learning models can achieve in classification of correct repetitions naturally elicited from a weight-shifting exergame. Twelve healthy elderly (10F, age 70.4 SD 11.4) are recruited. Movements are captured using a marker-based 3-D motion-capture system. Random forest (RF), support vector machine, k-nearest neighbors, and multilayer perceptron (MLP) are the employed models, trained and tested on whole body movement patterns and on subsets of joints. MLP and RF reached the highest recall and F1-score, respectively, when using combined data from joint subsets. MLP recall range are 91% to 94%, and RF F1-score range 79% to 80%. MLP and RF also reached the highest recall and F1-score in each joint subset, respectively. Here, MLP ranged from 93% to 97% recall, while RF ranged from 73% to 80% F1-score. Recall results, show that >9 out of 10 repetitions are classified correctly, indicating that MLP/RF can be used to identify correctly performed repetitions of a weight-shifting exercise when using full-body data and when using joint subset data.
Verma, Deepika; Bach, Kerstin; Mork, Paul Jarle
Application of Machine Learning Methods on Patient Reported Outcome Measurements for Predicting Outcomes: A Literature Review Journal Article
In: Informatics, vol. 8, no. 3, pp. 56, 2021.
@article{VermaEtAl21a,
title = {Application of Machine Learning Methods on Patient Reported Outcome Measurements for Predicting Outcomes: A Literature Review},
author = {Deepika Verma and Kerstin Bach and Paul Jarle Mork},
editor = {Kamran Sedig},
url = {https://www.mdpi.com/2227-9709/8/3/56},
doi = {10.3390/informatics8030056},
year = {2021},
date = {2021-08-25},
urldate = {2021-08-25},
journal = {Informatics},
volume = {8},
number = {3},
pages = {56},
abstract = {The field of patient-centred healthcare has, during recent years, adopted machine learning and data science techniques to support clinical decision making and improve patient outcomes. We conduct a literature review with the aim of summarising the existing methodologies that apply machine learning methods on patient-reported outcome measures datasets for predicting clinical outcomes to support further research and development within the field. We identify 15 articles published within the last decade that employ machine learning methods at various stages of exploiting datasets consisting of patient-reported outcome measures for predicting clinical outcomes, presenting promising research and demonstrating the utility of patient-reported outcome measures data for developmental research, personalised treatment and precision medicine with the help of machine learning-based decision-support systems. Furthermore, we identify and discuss the gaps and challenges, such as inconsistency in reporting the results across different articles, use of different evaluation metrics, legal aspects of using the data, and data unavailability, among others, which can potentially be addressed in future studies.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
The field of patient-centred healthcare has, during recent years, adopted machine learning and data science techniques to support clinical decision making and improve patient outcomes. We conduct a literature review with the aim of summarising the existing methodologies that apply machine learning methods on patient-reported outcome measures datasets for predicting clinical outcomes to support further research and development within the field. We identify 15 articles published within the last decade that employ machine learning methods at various stages of exploiting datasets consisting of patient-reported outcome measures for predicting clinical outcomes, presenting promising research and demonstrating the utility of patient-reported outcome measures data for developmental research, personalised treatment and precision medicine with the help of machine learning-based decision-support systems. Furthermore, we identify and discuss the gaps and challenges, such as inconsistency in reporting the results across different articles, use of different evaluation metrics, legal aspects of using the data, and data unavailability, among others, which can potentially be addressed in future studies.
Veiga, Tiago; Ljunggren, Erling; Bach, Kerstin; Akselsen, Sigmund
Blind Calibration of Air Quality Wireless Sensor Networks Using Deep Neural Networks Conference
2021 IEEE International Conference on Omni-Layer Intelligent Systems (COINS), IEEE, 2021.
@conference{VeigaEtAl21b,
title = {Blind Calibration of Air Quality Wireless Sensor Networks Using Deep Neural Networks},
author = {Tiago Veiga and Erling Ljunggren and Kerstin Bach and Sigmund Akselsen},
url = {https://ieeexplore.ieee.org/abstract/document/9524276},
doi = {10.1109/COINS51742.2021.9524276},
year = {2021},
date = {2021-08-23},
urldate = {2021-08-23},
booktitle = {2021 IEEE International Conference on Omni-Layer Intelligent Systems (COINS)},
pages = {1-6},
publisher = {IEEE},
abstract = {Temporal drift of low-cost sensors is crucial for the applicability of wireless sensor networks (WSN) to measure highly local phenomenon such as air quality. The emergence of wireless sensor networks in locations without available reference data makes calibrating such networks without the aid of true values a key area of research. While deep learning (DL) has proved successful on numerous other tasks, it is under-researched in the context of blind WSN calibration, particularly in scenarios with networks that mix static and mobile sensors. In this paper we investigate the use of DL architectures for such scenarios, including the effects of weather in both drifting and sensor measurement. New models are proposed and compared against a baseline, based on a previous proposed model and extended to include mobile sensors and weather data. Also, a procedure for generating simulated air quality data is presented, including the emission, dispersion and measurement of the two most common particulate matter pollutants: PM 2.5 and PM 10 . Results show that our models reduce the calibration error with an order of magnitude compared to the baseline, showing that DL is a suitable method for WSN calibration and that these networks can be remotely calibrated with minimal cost for the deployer.},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
Temporal drift of low-cost sensors is crucial for the applicability of wireless sensor networks (WSN) to measure highly local phenomenon such as air quality. The emergence of wireless sensor networks in locations without available reference data makes calibrating such networks without the aid of true values a key area of research. While deep learning (DL) has proved successful on numerous other tasks, it is under-researched in the context of blind WSN calibration, particularly in scenarios with networks that mix static and mobile sensors. In this paper we investigate the use of DL architectures for such scenarios, including the effects of weather in both drifting and sensor measurement. New models are proposed and compared against a baseline, based on a previous proposed model and extended to include mobile sensors and weather data. Also, a procedure for generating simulated air quality data is presented, including the emission, dispersion and measurement of the two most common particulate matter pollutants: PM 2.5 and PM 10 . Results show that our models reduce the calibration error with an order of magnitude compared to the baseline, showing that DL is a suitable method for WSN calibration and that these networks can be remotely calibrated with minimal cost for the deployer.
Sandal, Louise Fleng; Bach, Kerstin; Øverås, Cecilie K.; Svendsen, Malene Jagd; Dalager, Tina; Jensen, Jesper Stejnicher Drongstrup; Kongsvold, Atle; Nordstoga, Anne Lovise; Bardal, Ellen Marie; Ashikhmin, Ilya; Wood, Karen; Rasmussen, Charlotte Diana Nørregaard; Stochkendahl, Mette Jensen; Nicholl, Barbara I.; Wiratunga, Nirmalie; Cooper, Kay; Hartvigsen, Jan; Kjær, Per; Sjøgaard, Gisela; Nilsen, Tom I. L.; Mair, Frances S.; Søgaard, Karen; Mork, Paul Jarle
In: JAMA Internal Medicine, 2021.
@article{selfback21,
title = {Effectiveness of App-Delivered, Tailored Self-management Support for Adults With Lower Back Pain–Related Disability A selfBACK Randomized Clinical Trial},
author = {Louise Fleng Sandal and Kerstin Bach and Cecilie K. Øverås and Malene Jagd Svendsen and Tina Dalager and Jesper Stejnicher Drongstrup Jensen and Atle Kongsvold and Anne Lovise Nordstoga and Ellen Marie Bardal and Ilya Ashikhmin and Karen Wood and Charlotte Diana Nørregaard Rasmussen and Mette Jensen Stochkendahl and Barbara I. Nicholl and Nirmalie Wiratunga and Kay Cooper and Jan Hartvigsen and Per Kjær and Gisela Sjøgaard and Tom I. L. Nilsen and Frances S. Mair and Karen Søgaard and Paul Jarle Mork},
url = {https://jamanetwork.com/journals/jamainternalmedicine/fullarticle/2782459?utm_source=twitter&utm_campaign=content-shareicons&utm_content=article_engagement&utm_medium=social&utm_term=080221#.YQgKH8dDh },
doi = {10.1001/jamainternmed.2021.4097},
year = {2021},
date = {2021-08-02},
urldate = {2021-08-02},
journal = {JAMA Internal Medicine},
abstract = {Importance Lower back pain (LBP) is a prevalent and challenging condition in primary care. The effectiveness of an individually tailored self-management support tool delivered via a smartphone app has not been rigorously tested.
Objective To investigate the effectiveness of selfBACK, an evidence-based, individually tailored self-management support system delivered through an app as an adjunct to usual care for adults with LBP-related disability.
Design, Setting, and Participants This randomized clinical trial with an intention-to-treat data analysis enrolled eligible individuals who sought care for LBP in a primary care or an outpatient spine clinic in Denmark and Norway from March 8 to December 14, 2019. Participants were 18 years or older, had nonspecific LBP, scored 6 points or higher on the Roland-Morris Disability Questionnaire (RMDQ), and had a smartphone and access to email.
Interventions The selfBACK app provided weekly recommendations for physical activity, strength and flexibility exercises, and daily educational messages. Self-management recommendations were tailored to participant characteristics and symptoms. Usual care included advice or treatment offered to participants by their clinician.
Main Outcomes and Measures Primary outcome was the mean difference in RMDQ scores between the intervention group and control group at 3 months. Secondary outcomes included average and worst LBP intensity levels in the preceding week as measured on the numerical rating scale, ability to cope as assessed with the Pain Self-Efficacy Questionnaire, fear-avoidance belief as assessed by the Fear-Avoidance Beliefs Questionnaire, cognitive and emotional representations of illness as assessed by the Brief Illness Perception Questionnaire, health-related quality of life as assessed by the EuroQol-5 Dimension questionnaire, physical activity level as assessed by the Saltin-Grimby Physical Activity Level Scale, and overall improvement as assessed by the Global Perceived Effect scale. Outcomes were measured at baseline, 6 weeks, 3 months, 6 months, and 9 months.
Results A total of 461 participants were included in the analysis; the population had a mean [SD] age of 47.5 [14.7] years and included 255 women (55%). Of these participants, 232 were randomized to the intervention group and 229 to the control group. By the 3-month follow-up, 399 participants (87%) had completed the trial. The adjusted mean difference in RMDQ score between the 2 groups at 3 months was 0.79 (95% CI, 0.06-1.51; P = .03), favoring the selfBACK intervention. The percentage of participants who reported a score improvement of at least 4 points on the RMDQ was 52% in the intervention group vs 39% in the control group (adjusted odds ratio, 1.76; 95% CI, 1.15-2.70; P = .01).
Conclusions and Relevance Among adults who sought care for LBP in a primary care or an outpatient spine clinic, those who used the selfBACK system as an adjunct to usual care had reduced pain-related disability at 3 months. The improvement in pain-related disability was small and of uncertain clinical significance. Process evaluation may provide insights into refining the selfBACK app to increase its effectiveness.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Importance Lower back pain (LBP) is a prevalent and challenging condition in primary care. The effectiveness of an individually tailored self-management support tool delivered via a smartphone app has not been rigorously tested.
Objective To investigate the effectiveness of selfBACK, an evidence-based, individually tailored self-management support system delivered through an app as an adjunct to usual care for adults with LBP-related disability.
Design, Setting, and Participants This randomized clinical trial with an intention-to-treat data analysis enrolled eligible individuals who sought care for LBP in a primary care or an outpatient spine clinic in Denmark and Norway from March 8 to December 14, 2019. Participants were 18 years or older, had nonspecific LBP, scored 6 points or higher on the Roland-Morris Disability Questionnaire (RMDQ), and had a smartphone and access to email.
Interventions The selfBACK app provided weekly recommendations for physical activity, strength and flexibility exercises, and daily educational messages. Self-management recommendations were tailored to participant characteristics and symptoms. Usual care included advice or treatment offered to participants by their clinician.
Main Outcomes and Measures Primary outcome was the mean difference in RMDQ scores between the intervention group and control group at 3 months. Secondary outcomes included average and worst LBP intensity levels in the preceding week as measured on the numerical rating scale, ability to cope as assessed with the Pain Self-Efficacy Questionnaire, fear-avoidance belief as assessed by the Fear-Avoidance Beliefs Questionnaire, cognitive and emotional representations of illness as assessed by the Brief Illness Perception Questionnaire, health-related quality of life as assessed by the EuroQol-5 Dimension questionnaire, physical activity level as assessed by the Saltin-Grimby Physical Activity Level Scale, and overall improvement as assessed by the Global Perceived Effect scale. Outcomes were measured at baseline, 6 weeks, 3 months, 6 months, and 9 months.
Results A total of 461 participants were included in the analysis; the population had a mean [SD] age of 47.5 [14.7] years and included 255 women (55%). Of these participants, 232 were randomized to the intervention group and 229 to the control group. By the 3-month follow-up, 399 participants (87%) had completed the trial. The adjusted mean difference in RMDQ score between the 2 groups at 3 months was 0.79 (95% CI, 0.06-1.51; P = .03), favoring the selfBACK intervention. The percentage of participants who reported a score improvement of at least 4 points on the RMDQ was 52% in the intervention group vs 39% in the control group (adjusted odds ratio, 1.76; 95% CI, 1.15-2.70; P = .01).
Conclusions and Relevance Among adults who sought care for LBP in a primary care or an outpatient spine clinic, those who used the selfBACK system as an adjunct to usual care had reduced pain-related disability at 3 months. The improvement in pain-related disability was small and of uncertain clinical significance. Process evaluation may provide insights into refining the selfBACK app to increase its effectiveness.
Objective To investigate the effectiveness of selfBACK, an evidence-based, individually tailored self-management support system delivered through an app as an adjunct to usual care for adults with LBP-related disability.
Design, Setting, and Participants This randomized clinical trial with an intention-to-treat data analysis enrolled eligible individuals who sought care for LBP in a primary care or an outpatient spine clinic in Denmark and Norway from March 8 to December 14, 2019. Participants were 18 years or older, had nonspecific LBP, scored 6 points or higher on the Roland-Morris Disability Questionnaire (RMDQ), and had a smartphone and access to email.
Interventions The selfBACK app provided weekly recommendations for physical activity, strength and flexibility exercises, and daily educational messages. Self-management recommendations were tailored to participant characteristics and symptoms. Usual care included advice or treatment offered to participants by their clinician.
Main Outcomes and Measures Primary outcome was the mean difference in RMDQ scores between the intervention group and control group at 3 months. Secondary outcomes included average and worst LBP intensity levels in the preceding week as measured on the numerical rating scale, ability to cope as assessed with the Pain Self-Efficacy Questionnaire, fear-avoidance belief as assessed by the Fear-Avoidance Beliefs Questionnaire, cognitive and emotional representations of illness as assessed by the Brief Illness Perception Questionnaire, health-related quality of life as assessed by the EuroQol-5 Dimension questionnaire, physical activity level as assessed by the Saltin-Grimby Physical Activity Level Scale, and overall improvement as assessed by the Global Perceived Effect scale. Outcomes were measured at baseline, 6 weeks, 3 months, 6 months, and 9 months.
Results A total of 461 participants were included in the analysis; the population had a mean [SD] age of 47.5 [14.7] years and included 255 women (55%). Of these participants, 232 were randomized to the intervention group and 229 to the control group. By the 3-month follow-up, 399 participants (87%) had completed the trial. The adjusted mean difference in RMDQ score between the 2 groups at 3 months was 0.79 (95% CI, 0.06-1.51; P = .03), favoring the selfBACK intervention. The percentage of participants who reported a score improvement of at least 4 points on the RMDQ was 52% in the intervention group vs 39% in the control group (adjusted odds ratio, 1.76; 95% CI, 1.15-2.70; P = .01).
Conclusions and Relevance Among adults who sought care for LBP in a primary care or an outpatient spine clinic, those who used the selfBACK system as an adjunct to usual care had reduced pain-related disability at 3 months. The improvement in pain-related disability was small and of uncertain clinical significance. Process evaluation may provide insights into refining the selfBACK app to increase its effectiveness.
Arne Munch-Ellingsen Tiago Veiga, Christoforos Papastergiopoulos
From a Low-Cost Air Quality Sensor Network to Decision Support Services: Steps towards Data Calibration and Service Development Journal Article
In: Sensors, vol. 21, no. 9, pp. 3190, 2021.
@article{VeigaEtAl21a,
title = {From a Low-Cost Air Quality Sensor Network to Decision Support Services: Steps towards Data Calibration and Service Development},
author = {Tiago Veiga, Arne Munch-Ellingsen, Christoforos Papastergiopoulos, Dimitrios Tzovaras, Ilias Kalamaras, Kerstin Bach, Konstantinos Votis, Sigmund Akselsen},
editor = {Hsi-Jen James Yeh},
url = {https://www.mdpi.com/1424-8220/21/9/3190},
doi = {10.3390/s21093190},
year = {2021},
date = {2021-05-05},
journal = {Sensors},
volume = {21},
number = {9},
pages = {3190},
abstract = {Air pollution is a widespread problem due to its impact on both humans and the environment. Providing decision makers with artificial intelligence based solutions requires to monitor the ambient air quality accurately and in a timely manner, as AI models highly depend on the underlying data used to justify the predictions. Unfortunately, in urban contexts, the hyper-locality of air quality, varying from street to street, makes it difficult to monitor using high-end sensors, as the cost of the amount of sensors needed for such local measurements is too high. In addition, the development of pollution dispersion models is challenging. The deployment of a low-cost sensor network allows a more dense cover of a region but at the cost of noisier sensing. This paper describes the development and deployment of a low-cost sensor network, discussing its challenges and applications, and is highly motivated by talks with the local municipality and the exploration of new technologies to improve air quality related services. However, before using data from these sources, calibration procedures are needed to ensure that the quality of the data is at a good level. We describe our steps towards developing calibration models and how they benefit the applications identified as important in the talks with the municipality.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Air pollution is a widespread problem due to its impact on both humans and the environment. Providing decision makers with artificial intelligence based solutions requires to monitor the ambient air quality accurately and in a timely manner, as AI models highly depend on the underlying data used to justify the predictions. Unfortunately, in urban contexts, the hyper-locality of air quality, varying from street to street, makes it difficult to monitor using high-end sensors, as the cost of the amount of sensors needed for such local measurements is too high. In addition, the development of pollution dispersion models is challenging. The deployment of a low-cost sensor network allows a more dense cover of a region but at the cost of noisier sensing. This paper describes the development and deployment of a low-cost sensor network, discussing its challenges and applications, and is highly motivated by talks with the local municipality and the exploration of new technologies to improve air quality related services. However, before using data from these sources, calibration procedures are needed to ensure that the quality of the data is at a good level. We describe our steps towards developing calibration models and how they benefit the applications identified as important in the talks with the municipality.
Kerstin Bach Bjørn Magnus Mathisen, Agnar Aamodt
Using extended siamese networks to provide decision support in aquaculture operations Journal Article
In: Applied Intelligence, pp. 1-12, 2021.
@article{MathisenEtAl21,
title = {Using extended siamese networks to provide decision support in aquaculture operations},
author = {Bjørn Magnus Mathisen, Kerstin Bach, Agnar Aamodt},
url = {https://link.springer.com/article/10.1007/s10489-021-02251-3#article-info},
doi = {10.1007/s10489-021-02251-3},
year = {2021},
date = {2021-03-26},
journal = {Applied Intelligence},
pages = {1-12},
abstract = {Aquaculture as an industry is quickly expanding. As a result, new aquaculture sites are being established at more exposed locations previously deemed unfit because they are more difficult and resource demanding to safely operate than are traditional sites. To help the industry deal with these challenges, we have developed a decision support system to support decision makers in establishing better plans and make decisions that facilitate operating these sites in an optimal manner. We propose a case-based reasoning system called aquaculture case-based reasoning (AQCBR), which is able to predict the success of an aquaculture operation at a specific site, based on previously applied and recorded cases. In particular, AQCBR is trained to learn a similarity function between recorded operational situations/cases and use the most similar case to provide explanation-by-example information for its predictions. The novelty of AQCBR is that it uses extended Siamese neural networks to learn the similarity between cases. Our extensive experimental evaluation shows that extended Siamese neural networks outperform state-of-the-art methods for similarity learning in this task, demonstrating the effectiveness and the feasibility of our approach.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Aquaculture as an industry is quickly expanding. As a result, new aquaculture sites are being established at more exposed locations previously deemed unfit because they are more difficult and resource demanding to safely operate than are traditional sites. To help the industry deal with these challenges, we have developed a decision support system to support decision makers in establishing better plans and make decisions that facilitate operating these sites in an optimal manner. We propose a case-based reasoning system called aquaculture case-based reasoning (AQCBR), which is able to predict the success of an aquaculture operation at a specific site, based on previously applied and recorded cases. In particular, AQCBR is trained to learn a similarity function between recorded operational situations/cases and use the most similar case to provide explanation-by-example information for its predictions. The novelty of AQCBR is that it uses extended Siamese neural networks to learn the similarity between cases. Our extensive experimental evaluation shows that extended Siamese neural networks outperform state-of-the-art methods for similarity learning in this task, demonstrating the effectiveness and the feasibility of our approach.
Marcuzzi, Anna; Bach, Kerstin; Nordstoga, Anne Lovise; Bertheussen, Gro Falkener; Ashikhmin, Ilya; Boldermo, Nora Østbø; Kvarner, Else-Norun; Nilsen, Tom Ivar Lund; Marchand, Gunn Hege; Ose, Solveig Osborg; Aasdahl, Lene; Kaspersen, Silje Lill; Bardal, Ellen Marie; Børke, Janne-Birgitte; Mork, Paul Jarle; Gismervik, Sigmund
In: BMJ Open, vol. 11, no. 9, 2021, ISSN: 2044-6055.
@article{Marcuzzi2021,
title = {Individually tailored self-management app-based intervention (selfBACK) versus a self-management web-based intervention (e-Help) or usual care in people with low back and neck pain referred to secondary care: protocol for a multiarm randomised clinical trial},
author = {Anna Marcuzzi and Kerstin Bach and Anne Lovise Nordstoga and Gro Falkener Bertheussen and Ilya Ashikhmin and Nora Østbø Boldermo and Else-Norun Kvarner and Tom Ivar Lund Nilsen and Gunn Hege Marchand and Solveig Osborg Ose and Lene Aasdahl and Silje Lill Kaspersen and Ellen Marie Bardal and Janne-Birgitte Børke and Paul Jarle Mork and Sigmund Gismervik},
url = {https://bmjopen.bmj.com/content/11/9/e047921},
doi = {10.1136/bmjopen-2020-047921},
issn = {2044-6055},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
journal = {BMJ Open},
volume = {11},
number = {9},
publisher = {British Medical Journal Publishing Group},
abstract = {Introduction Low back pain (LBP) and neck pain (NP) are common and costly conditions. Self-management is a key element in the care of persistent LBP and NP. Artificial intelligence can be used to support and tailor self-management interventions, but their effectiveness needs to be ascertained. The aims of this trial are (1) to evaluate the effectiveness of an individually tailored app-based self-management intervention (selfBACK) adjunct to usual care in people with LBP and/or NP in secondary care compared with usual care only, and (2) to compare the effectiveness of selfBACK with a web-based self-management intervention without individual tailoring (e-Help).Methods and analysis This is a randomised, assessor-blind clinical trial with three parallel arms: (1) selfBACK app adjunct to usual care; (2) e-Help website adjunct to usual care and (3) usual care only. Patients referred to St Olavs Hospital, Trondheim (Norway) with LBP and/or NP and accepted for assessment/treatment at the multidisciplinary outpatient clinic for back or neck rehabilitation are invited to the study. Eligible and consenting participants are randomised to one of the three arms with equal allocation ratio. We aim to include 279 participants (93 in each arm). Outcome variables are assessed at baseline (before randomisation) and at 6-week, 3-month and 6-month follow-up. The primary outcome is musculoskeletal health measured by the Musculoskeletal Health Questionnaire at 3 months. A mixed-methods process evaluation will document patients’ and clinicians’ experiences with the interventions. A health economic evaluation will estimate the cost-effectiveness of both interventions’ adjunct to usual care. Ethics and dissemination The trial is approved by the Regional Committee for Medical and Health Research Ethics in Central Norway (Ref. 2019/64084). The results of the trial will be published in peer-review journals and presentations at national and international conferences relevant to this topic. Trial registration number NCT04463043.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Introduction Low back pain (LBP) and neck pain (NP) are common and costly conditions. Self-management is a key element in the care of persistent LBP and NP. Artificial intelligence can be used to support and tailor self-management interventions, but their effectiveness needs to be ascertained. The aims of this trial are (1) to evaluate the effectiveness of an individually tailored app-based self-management intervention (selfBACK) adjunct to usual care in people with LBP and/or NP in secondary care compared with usual care only, and (2) to compare the effectiveness of selfBACK with a web-based self-management intervention without individual tailoring (e-Help).Methods and analysis This is a randomised, assessor-blind clinical trial with three parallel arms: (1) selfBACK app adjunct to usual care; (2) e-Help website adjunct to usual care and (3) usual care only. Patients referred to St Olavs Hospital, Trondheim (Norway) with LBP and/or NP and accepted for assessment/treatment at the multidisciplinary outpatient clinic for back or neck rehabilitation are invited to the study. Eligible and consenting participants are randomised to one of the three arms with equal allocation ratio. We aim to include 279 participants (93 in each arm). Outcome variables are assessed at baseline (before randomisation) and at 6-week, 3-month and 6-month follow-up. The primary outcome is musculoskeletal health measured by the Musculoskeletal Health Questionnaire at 3 months. A mixed-methods process evaluation will document patients’ and clinicians’ experiences with the interventions. A health economic evaluation will estimate the cost-effectiveness of both interventions’ adjunct to usual care. Ethics and dissemination The trial is approved by the Regional Committee for Medical and Health Research Ethics in Central Norway (Ref. 2019/64084). The results of the trial will be published in peer-review journals and presentations at national and international conferences relevant to this topic. Trial registration number NCT04463043.
Flogard, Eirik Lund; Mengshoel, Ole Jakob; Bach, Kerstin
Bayesian feature construction for case-based reasoning: Generating good checklists Inproceedings
In: Sánchez-Ruiz, Antonio A.; Floyd, Michael W. (Ed.): International Conference on Case-Based Reasoning, pp. 94–109, Springer Springer, Cham, 2021, ISBN: 978-3-030-86956-4.
@inproceedings{flogard2021bayesian,
title = {Bayesian feature construction for case-based reasoning: Generating good checklists},
author = {Eirik Lund Flogard and Ole Jakob Mengshoel and Kerstin Bach},
editor = {Antonio A. Sánchez-Ruiz and Michael W. Floyd},
url = {https://link.springer.com/chapter/10.1007/978-3-030-86957-1_7},
doi = {10.1007/978-3-030-86957-1_7},
isbn = {978-3-030-86956-4},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
booktitle = {International Conference on Case-Based Reasoning},
volume = {12877},
pages = {94--109},
publisher = {Springer, Cham},
organization = {Springer},
series = {LNCS},
abstract = {Checklists are used to aid the fulfillment of safety critical activities in a variety of different applications, such as aviation, health care or labour inspections. However, optimizing a checklist for a specific purpose can be challenging. Checklists also need to be trustworthy and user friendly to promote user compliance. With labour inspections as a starting point, we introduce the Checklist Construction Problem. To address the problem, we seek to optimize the content of labour inspection checklists in order to improve the working conditions in every organisation targeted for inspections. To do so, we introduce a hybrid framework called BCBR to construct trustworthy checklists. BCBR is based on case-based reasoning (CBR) and Bayesian inference (BI) and constructs new checklists based on past cases. A key novelty of BCBR is the use of BI for constructing new features in past cases. The augmented past cases are retrieved via CBR to construct new checklists, which ensures justification for the content of the checklists and promotes trust. Experiments suggest that BCBR is more effective than any other baseline we tested, in terms of constructing trustworthy checklists.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Checklists are used to aid the fulfillment of safety critical activities in a variety of different applications, such as aviation, health care or labour inspections. However, optimizing a checklist for a specific purpose can be challenging. Checklists also need to be trustworthy and user friendly to promote user compliance. With labour inspections as a starting point, we introduce the Checklist Construction Problem. To address the problem, we seek to optimize the content of labour inspection checklists in order to improve the working conditions in every organisation targeted for inspections. To do so, we introduce a hybrid framework called BCBR to construct trustworthy checklists. BCBR is based on case-based reasoning (CBR) and Bayesian inference (BI) and constructs new checklists based on past cases. A key novelty of BCBR is the use of BI for constructing new features in past cases. The augmented past cases are retrieved via CBR to construct new checklists, which ensures justification for the content of the checklists and promotes trust. Experiments suggest that BCBR is more effective than any other baseline we tested, in terms of constructing trustworthy checklists.
Verma, Deepika; Bach, Kerstin; Mork, Paul Jarle
In: Bramer, Max; Ellis, Richard (Ed.): Artificial Intelligence XXXVIII: 41st SGAI International Conference on Artificial Intelligence, pp. 282–295, Springer, Cham, 2021, ISBN: 978-3-030-91099-0.
@inproceedings{verma2021ukai,
title = {Using Automated Feature Selection for Building Case-Based Reasoning Systems: An Example from Patient-Reported Outcome Measurements},
author = {Deepika Verma and Kerstin Bach and Paul Jarle Mork},
editor = { Max Bramer and Richard Ellis},
url = {https://link.springer.com/chapter/10.1007/978-3-030-91100-3_23},
doi = {10.1007/978-3-030-91100-3_23},
isbn = {978-3-030-91099-0},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
booktitle = {Artificial Intelligence XXXVIII: 41st SGAI International Conference on Artificial Intelligence},
volume = {13101},
pages = {282--295},
publisher = {Springer, Cham},
series = {LNCS},
abstract = {Feature selection for case representation is an essential phase of Case-Based Reasoning (CBR) system development. To (semi-)automate the feature selection process can ease the knowledge engineering process. This paper explores the feature importance provided for XGBoost models as basis for creating CBR systems. We use Patient-Reported Outcome Measurements (PROMs) on low back pain from the SELFBACK project in our experiments. PROMs are a valuable source of information that capture physical, emotional as well as social aspects of well-being from the perspective of the patients. Leveraging the analytical capabilities of machine learning methods and data science techniques for exploiting PROMs have the potential of improving decision making. This paper presents a two-fold approach employed on our dataset for feature selection that combines statistical strength with data-driven knowledge modelling in CBR and compares it with permutation feature selection using XGBoost regressor. Furthermore, we compare the performance of the CBR models, built with the selected features, with two machine learning algorithms for predicting different PROMs.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Feature selection for case representation is an essential phase of Case-Based Reasoning (CBR) system development. To (semi-)automate the feature selection process can ease the knowledge engineering process. This paper explores the feature importance provided for XGBoost models as basis for creating CBR systems. We use Patient-Reported Outcome Measurements (PROMs) on low back pain from the SELFBACK project in our experiments. PROMs are a valuable source of information that capture physical, emotional as well as social aspects of well-being from the perspective of the patients. Leveraging the analytical capabilities of machine learning methods and data science techniques for exploiting PROMs have the potential of improving decision making. This paper presents a two-fold approach employed on our dataset for feature selection that combines statistical strength with data-driven knowledge modelling in CBR and compares it with permutation feature selection using XGBoost regressor. Furthermore, we compare the performance of the CBR models, built with the selected features, with two machine learning algorithms for predicting different PROMs.
2020
Bergmann, Ralph; Minor, Mirjam; Bach, Kerstin; Althoff, Klaus-Dieter; Muñoz-Avila, Héctor
Fallbasiertes Schließen Book Chapter
In: Ute Schmid Günter Görz, Tanya Braun (Ed.): pp. 343-394, De Gruyter, 2020.
@inbook{BergmannKIH2021,
title = {Fallbasiertes Schließen},
author = {Ralph Bergmann and Mirjam Minor and Kerstin Bach and Klaus-Dieter Althoff and Héctor Muñoz-Avila},
editor = {Günter Görz, Ute Schmid, Tanya Braun},
url = {https://www.degruyter.com/document/doi/10.1515/9783110659948-009/html},
doi = {10.1515/9783110659948},
year = {2020},
date = {2020-12-16},
urldate = {2020-12-16},
pages = {343-394},
publisher = {De Gruyter},
keywords = {},
pubstate = {published},
tppubtype = {inbook}
}
Vonstad, Elise Klæbo; Su, Xiaomeng; Vereijken, Beatrix; Bach, Kerstin; Nilsen, Jan Harald
Comparison of a Deep Learning-Based Pose Estimation System to Marker-Based and Kinect Systems in Exergaming for Balance Training Journal Article
In: Sensors, vol. 20, no. 23, pp. 6940, 2020.
@article{Vonstad21a,
title = {Comparison of a Deep Learning-Based Pose Estimation System to Marker-Based and Kinect Systems in Exergaming for Balance Training},
author = {Elise Klæbo Vonstad and Xiaomeng Su and Beatrix Vereijken and Kerstin Bach and Jan Harald Nilsen},
url = {https://www.mdpi.com/1424-8220/20/23/6940},
doi = {10.3390/s20236940},
year = {2020},
date = {2020-12-04},
urldate = {2020-12-04},
journal = {Sensors},
volume = {20},
number = {23},
pages = {6940},
abstract = {Using standard digital cameras in combination with deep learning (DL) for pose estimation is promising for the in-home and independent use of exercise games (exergames). We need to investigate to what extent such DL-based systems can provide satisfying accuracy on exergame relevant measures. Our study assesses temporal variation (ie, variability) in body segment lengths, while using a Deep Learning image processing tool (DeepLabCut, DLC) on two-dimensional (2D) video. This variability is then compared with a gold-standard, marker-based three-dimensional Motion Capturing system (3DMoCap, Qualisys AB), and a 3D RGB-depth camera system (Kinect V2, Microsoft Inc). Simultaneous data were collected from all three systems, while participants (N= 12) played a custom balance training exergame. The pose estimation DLC-model is pre-trained on a large-scale dataset (ImageNet) and optimized with context-specific pose annotated images. Wilcoxon’s signed-rank test was performed in order to assess the statistical significance of the differences in variability between systems. The results showed that the DLC method performs comparably to the Kinect and, in some segments, even to the 3DMoCap gold standard system with regard to variability. These results are promising for making exergames more accessible and easier to use, thereby increasing their availability for in-home exercise.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Using standard digital cameras in combination with deep learning (DL) for pose estimation is promising for the in-home and independent use of exercise games (exergames). We need to investigate to what extent such DL-based systems can provide satisfying accuracy on exergame relevant measures. Our study assesses temporal variation (ie, variability) in body segment lengths, while using a Deep Learning image processing tool (DeepLabCut, DLC) on two-dimensional (2D) video. This variability is then compared with a gold-standard, marker-based three-dimensional Motion Capturing system (3DMoCap, Qualisys AB), and a 3D RGB-depth camera system (Kinect V2, Microsoft Inc). Simultaneous data were collected from all three systems, while participants (N= 12) played a custom balance training exergame. The pose estimation DLC-model is pre-trained on a large-scale dataset (ImageNet) and optimized with context-specific pose annotated images. Wilcoxon’s signed-rank test was performed in order to assess the statistical significance of the differences in variability between systems. The results showed that the DLC method performs comparably to the Kinect and, in some segments, even to the 3DMoCap gold standard system with regard to variability. These results are promising for making exergames more accessible and easier to use, thereby increasing their availability for in-home exercise.
Bach, Kerstin; Akselsen, Sigmund; Tiago Veiga, Ilias Kalamaras
On the Use of Air Quality Microsensors for Supporting Decision Makers Conference
IoT '20 Companion: 10th International Conference on the Internet of Things Companion, ACM, New York, NY, United States, 2020, ISBN: 978-1-4503-8820-7.
@conference{BachEtAl21a,
title = {On the Use of Air Quality Microsensors for Supporting Decision Makers},
author = {Kerstin Bach and Sigmund Akselsen and Tiago Veiga, Ilias Kalamaras},
editor = { Paul Davidsson, Marc Langheinrich, Per Linde, Simon Mayer, Diego Casado-Mansilla, Daniel Spikol, Frank Alexander Kraemer, Nancy Russo },
url = {https://dl.acm.org/doi/abs/10.1145/3423423.3423463},
doi = {10.1145/3423423.3423463},
isbn = {978-1-4503-8820-7},
year = {2020},
date = {2020-10-06},
urldate = {2020-10-06},
booktitle = {IoT '20 Companion: 10th International Conference on the Internet of Things Companion},
publisher = {ACM},
address = {New York, NY, United States},
abstract = {In this poster, we present how a network of Internet-of-things (IoT) devices facilitated through machine learning can improve decision making. Our application domain is air quality in the municipality of Trondheim. Ambient air pollution poses a major threat to both health and climate with millions of premature deaths occurring every year. To enable solutions to this problem, accurate measurements of the phenomenon are required and tools for decision-makers need to be in place to quickly understand situations as well as suggest actions that lead to the best possible outcome.},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
In this poster, we present how a network of Internet-of-things (IoT) devices facilitated through machine learning can improve decision making. Our application domain is air quality in the municipality of Trondheim. Ambient air pollution poses a major threat to both health and climate with millions of premature deaths occurring every year. To enable solutions to this problem, accurate measurements of the phenomenon are required and tools for decision-makers need to be in place to quickly understand situations as well as suggest actions that lead to the best possible outcome.
Rasmussen, Charlotte Diana Nørregaard; Svendsen, Malene Jagd; Wood, Karen; Nicholl, Barbara I; Mair, Frances S; Sandal, Louise Fleng; Mork, Paul Jarle; Søgaard, Karen; Bach, Kerstin; Stochkendahl, Mette Jensen
App-Delivered Self-Management Intervention Trial selfBACK for People With Low Back Pain: Protocol for Implementation and Process Evaluation Journal Article
In: JMIR Research Protocols, vol. 9, no. 10, pp. e20308, 2020.
@article{Rasmussen2021,
title = {App-Delivered Self-Management Intervention Trial selfBACK for People With Low Back Pain: Protocol for Implementation and Process Evaluation},
author = {Charlotte Diana Nørregaard Rasmussen and Malene Jagd Svendsen and Karen Wood and Barbara I Nicholl and Frances S Mair and Louise Fleng Sandal and Paul Jarle Mork and Karen Søgaard and Kerstin Bach and Mette Jensen Stochkendahl},
url = {https://pubmed.ncbi.nlm.nih.gov/33118959/},
doi = {10.2196/20308},
year = {2020},
date = {2020-09-29},
urldate = {2020-09-29},
journal = {JMIR Research Protocols},
volume = {9},
number = {10},
pages = {e20308},
abstract = {Background: Implementation and process evaluation is vital for understanding how interventions function in different settings, including if and why interventions have different effects or do not work at all.
Objective: This paper presents the protocol for an implementation and process evaluation embedded in a multicenter randomized controlled trial conducted in Denmark and Norway (the selfBACK project). selfBACK is a data-driven decision support system that provides participants with weekly self-management plans for low back pain. These plans are delivered through a smartphone app and tailored to individual participants by using case-based reasoning methodology. In the trial, we compare selfBACK in addition to usual care with usual care alone.
Methods: The aim of this study is to conduct a convergent mixed-methods implementation and process evaluation of the selfBACK app by following the reach, effectiveness, adoption, implementation, and maintenance framework. We will evaluate the process of implementing selfBACK and investigate how participants use the intervention in daily life. The evaluation will also cover the reach of the intervention, health care provider willingness to adopt it, and participant satisfaction with the intervention. We will gather quantitative measures by questionnaires and measures of data analytics on app use and perform a qualitative exploration of the implementation using semistructured interviews theoretically informed by normalization process theory. Data collection will be conducted between March 2019 and October 2020.
Results: The trial opened for recruitment in February 2019. This mixed-methods implementation and evaluation study is embedded in the randomized controlled trial and will be collecting data from March 2019 to October 2020; dissemination of trial results is planned thereafter. The results from the process evaluation are expected 2021-2022.
Conclusions: This study will provide a detailed understanding of how self-management of low back pain can be improved and how a digital health intervention can be used as an add-on to usual care to support patients to self-manage their low back pain. We will provide knowledge that can be used to explore the possibilities of extending the generic components of the selfBACK system and key drivers that could be of use in other conditions and diseases where self-management is an essential prevention or treatment strategy.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Background: Implementation and process evaluation is vital for understanding how interventions function in different settings, including if and why interventions have different effects or do not work at all.
Objective: This paper presents the protocol for an implementation and process evaluation embedded in a multicenter randomized controlled trial conducted in Denmark and Norway (the selfBACK project). selfBACK is a data-driven decision support system that provides participants with weekly self-management plans for low back pain. These plans are delivered through a smartphone app and tailored to individual participants by using case-based reasoning methodology. In the trial, we compare selfBACK in addition to usual care with usual care alone.
Methods: The aim of this study is to conduct a convergent mixed-methods implementation and process evaluation of the selfBACK app by following the reach, effectiveness, adoption, implementation, and maintenance framework. We will evaluate the process of implementing selfBACK and investigate how participants use the intervention in daily life. The evaluation will also cover the reach of the intervention, health care provider willingness to adopt it, and participant satisfaction with the intervention. We will gather quantitative measures by questionnaires and measures of data analytics on app use and perform a qualitative exploration of the implementation using semistructured interviews theoretically informed by normalization process theory. Data collection will be conducted between March 2019 and October 2020.
Results: The trial opened for recruitment in February 2019. This mixed-methods implementation and evaluation study is embedded in the randomized controlled trial and will be collecting data from March 2019 to October 2020; dissemination of trial results is planned thereafter. The results from the process evaluation are expected 2021-2022.
Conclusions: This study will provide a detailed understanding of how self-management of low back pain can be improved and how a digital health intervention can be used as an add-on to usual care to support patients to self-manage their low back pain. We will provide knowledge that can be used to explore the possibilities of extending the generic components of the selfBACK system and key drivers that could be of use in other conditions and diseases where self-management is an essential prevention or treatment strategy.
Objective: This paper presents the protocol for an implementation and process evaluation embedded in a multicenter randomized controlled trial conducted in Denmark and Norway (the selfBACK project). selfBACK is a data-driven decision support system that provides participants with weekly self-management plans for low back pain. These plans are delivered through a smartphone app and tailored to individual participants by using case-based reasoning methodology. In the trial, we compare selfBACK in addition to usual care with usual care alone.
Methods: The aim of this study is to conduct a convergent mixed-methods implementation and process evaluation of the selfBACK app by following the reach, effectiveness, adoption, implementation, and maintenance framework. We will evaluate the process of implementing selfBACK and investigate how participants use the intervention in daily life. The evaluation will also cover the reach of the intervention, health care provider willingness to adopt it, and participant satisfaction with the intervention. We will gather quantitative measures by questionnaires and measures of data analytics on app use and perform a qualitative exploration of the implementation using semistructured interviews theoretically informed by normalization process theory. Data collection will be conducted between March 2019 and October 2020.
Results: The trial opened for recruitment in February 2019. This mixed-methods implementation and evaluation study is embedded in the randomized controlled trial and will be collecting data from March 2019 to October 2020; dissemination of trial results is planned thereafter. The results from the process evaluation are expected 2021-2022.
Conclusions: This study will provide a detailed understanding of how self-management of low back pain can be improved and how a digital health intervention can be used as an add-on to usual care to support patients to self-manage their low back pain. We will provide knowledge that can be used to explore the possibilities of extending the generic components of the selfBACK system and key drivers that could be of use in other conditions and diseases where self-management is an essential prevention or treatment strategy.
Nordstoga, Anne Lovise; Bach, Kerstin; Sani, Sadiq; Wiratunga, Nirmalie; Mork, Paul Jarle; Willumsen, Morten; Cooper, Kay
Usability and acceptability of an app (SELFBACK) to support self-management of low back pain: a mixed methods study. Journal Article
In: JMIR Rehabilitation and Assistive Technologies, vol. 7, no. 2, pp. e18729, 2020.
@article{Nordstoga2020,
title = {Usability and acceptability of an app (SELFBACK) to support self-management of low back pain: a mixed methods study.},
author = {Anne Lovise Nordstoga and Kerstin Bach and Sadiq Sani and Nirmalie Wiratunga and Paul Jarle Mork and Morten Willumsen and Kay Cooper},
url = {https://preprints.jmir.org/preprint/18729/accepted},
doi = {10.2196/18729},
year = {2020},
date = {2020-09-15},
journal = { JMIR Rehabilitation and Assistive Technologies},
volume = {7},
number = {2},
pages = {e18729},
publisher = {JMIR Publications},
abstract = {Self-management is the key recommendation for managing non-specific low back pain (LBP). However, there are well-documented barriers to self-management, therefore methods of facilitating adherence are required. Smartphone apps are increasingly being used to provide feedback and reinforcement to support self-management of long-term conditions such as LBP. The aim of this study was to assess the usability and acceptability of the selfBACK smartphone app, designed to support and facilitate self-management of non-specific LBP. The app provides weekly self-management plans, comprising physical activity, strength/flexibility exercises, and patient education. The plans are tailored to the patient's characteristics and symptom progress by using case-based reasoning methodology. The study was carried out in two stages, using a mixed-methods approach. All participants undertook surveys and semi-structured telephone interviews were conducted with a subgroup of participants. Stage 1 assessed an app version with only the physical activity component and a web-questionnaire that collects information necessary for tailoring the self-management plans. The physical activity component included monitoring of steps recorded by a wristband, goal-setting, and a scheme for sending personalised, timely and motivational notifications to the user's smartphone. Findings from stage 1 were used to refine the app and inform further development. Stage 2 investigated an app version that incorporated three self-management components (physical activity, exercises and education). A total of sixteen participants (age range 23-71 years) with ongoing or chronic non-specific LBP were included in stage 1, and eleven participants (age range 32-56) were included in stage 2. In stage 1, 94% of participants reported that the baseline questionnaire was easy to answer and 84% found completion time to be acceptable. Overall, participants were positive about the usability of the physical activity component but only 31% found the app functions to be well integrated. 90% of the participants were satisfied with the notifications and 80% perceived the notifications to be personalised. In stage 2, all participants reported that the web-questionnaire was easy to answer and the completion time acceptable. The physical activity and exercise components were rated useful by 80%, while 60% rated the educational component useful. Overall, participants were satisfied with the usability of the app; however, only 50% found the functions to be well integrated and 20% found them to be inconsistent. Overall, 80% of participants reported it to be useful for self-management. The interviews largely reinforced the survey findings in both stages. This study has demonstrated that participants considered the selfBACK app to be acceptable and usable, and that they thought it would be useful for supporting self-management of LBP. However, we identified some limitations and suggestions, which will be useful in guiding further development of the selfBACK app and other mHealth interventions.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Self-management is the key recommendation for managing non-specific low back pain (LBP). However, there are well-documented barriers to self-management, therefore methods of facilitating adherence are required. Smartphone apps are increasingly being used to provide feedback and reinforcement to support self-management of long-term conditions such as LBP. The aim of this study was to assess the usability and acceptability of the selfBACK smartphone app, designed to support and facilitate self-management of non-specific LBP. The app provides weekly self-management plans, comprising physical activity, strength/flexibility exercises, and patient education. The plans are tailored to the patient's characteristics and symptom progress by using case-based reasoning methodology. The study was carried out in two stages, using a mixed-methods approach. All participants undertook surveys and semi-structured telephone interviews were conducted with a subgroup of participants. Stage 1 assessed an app version with only the physical activity component and a web-questionnaire that collects information necessary for tailoring the self-management plans. The physical activity component included monitoring of steps recorded by a wristband, goal-setting, and a scheme for sending personalised, timely and motivational notifications to the user's smartphone. Findings from stage 1 were used to refine the app and inform further development. Stage 2 investigated an app version that incorporated three self-management components (physical activity, exercises and education). A total of sixteen participants (age range 23-71 years) with ongoing or chronic non-specific LBP were included in stage 1, and eleven participants (age range 32-56) were included in stage 2. In stage 1, 94% of participants reported that the baseline questionnaire was easy to answer and 84% found completion time to be acceptable. Overall, participants were positive about the usability of the physical activity component but only 31% found the app functions to be well integrated. 90% of the participants were satisfied with the notifications and 80% perceived the notifications to be personalised. In stage 2, all participants reported that the web-questionnaire was easy to answer and the completion time acceptable. The physical activity and exercise components were rated useful by 80%, while 60% rated the educational component useful. Overall, participants were satisfied with the usability of the app; however, only 50% found the functions to be well integrated and 20% found them to be inconsistent. Overall, 80% of participants reported it to be useful for self-management. The interviews largely reinforced the survey findings in both stages. This study has demonstrated that participants considered the selfBACK app to be acceptable and usable, and that they thought it would be useful for supporting self-management of LBP. However, we identified some limitations and suggestions, which will be useful in guiding further development of the selfBACK app and other mHealth interventions.
Sandal, Louise Fleng; Øverås, Cecilie K; Nordstoga, Anne Lovise; Wood, Karen; Bach, Kerstin; Hartvigsen, Jan; Søgaard, Karen; Mork, Paul Jarle
A digital decision support system (selfBACK) for improved self-management of low back pain: a pilot study with 6-week follow-up Journal Article
In: Pilot and Feasibility Studies volume, vol. 6, no. 72, 2020, ISSN: 2055-5784.
@article{SandalEtAl2020,
title = {A digital decision support system (selfBACK) for improved self-management of low back pain: a pilot study with 6-week follow-up},
author = {Louise Fleng Sandal and Cecilie K Øverås and Anne Lovise Nordstoga and Karen Wood and Kerstin Bach and Jan Hartvigsen and Karen Søgaard and Paul Jarle Mork},
editor = {Gillian Lancaster and Lehana Thabane},
url = {https://pilotfeasibilitystudies.biomedcentral.com/articles/10.1186/s40814-020-00604-2#citeas},
doi = {https://doi.org/10.1186/s40814-020-00604-2},
issn = {2055-5784},
year = {2020},
date = {2020-05-23},
journal = {Pilot and Feasibility Studies volume},
volume = {6},
number = {72},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Althoff, Klaus-Dieter; Bach, Kerstin; Bergmann, Ralph; Marling, Cindy
The 27th International Conference on Case-Based Reasoning Journal Article
In: AI Mag., vol. 41, no. 1, pp. 101–102, 2020.
@article{DBLP:journals/aim/AlthoffBBM20,
title = {The 27th International Conference on Case-Based Reasoning},
author = {Klaus-Dieter Althoff and Kerstin Bach and Ralph Bergmann and Cindy Marling},
url = {https://doi.org/10.1609/aimag.v41i1.5288},
doi = {10.1609/aimag.v41i1.5288},
year = {2020},
date = {2020-01-01},
journal = {AI Mag.},
volume = {41},
number = {1},
pages = {101--102},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Mathisen, Bjørn Magnus; Aamodt, Agnar; Bach, Kerstin; Langseth, Helge
Learning similarity measures from data Journal Article
In: Prog. Artif. Intell., vol. 9, no. 2, pp. 129–143, 2020.
@article{DBLP:journals/pai/MathisenABL20,
title = {Learning similarity measures from data},
author = {Bjørn Magnus Mathisen and Agnar Aamodt and Kerstin Bach and Helge Langseth},
url = {https://doi.org/10.1007/s13748-019-00201-2},
doi = {10.1007/s13748-019-00201-2},
year = {2020},
date = {2020-01-01},
journal = {Prog. Artif. Intell.},
volume = {9},
number = {2},
pages = {129--143},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Wijekoon, Anjana; Wiratunga, Nirmalie; Cooper, Kay; Bach, Kerstin
Learning to Recognise Exercises in the Self-Management of Low Back Pain Inproceedings
In: á, Roman Bart; Bell, Eric (Ed.): Proceedings of the Thirty-Third International Florida Artificial Intelligence Research Society Conference, Originally to be held in North Miami Beach, Florida, USA, May 17-20, 2020, pp. 347–352, AAAI Press, 2020.
@inproceedings{DBLP:conf/flairs/WijekoonWCB20,
title = {Learning to Recognise Exercises in the Self-Management of Low Back
Pain},
author = {Anjana Wijekoon and Nirmalie Wiratunga and Kay Cooper and Kerstin Bach},
editor = {Roman Bart á and Eric Bell},
url = {https://aaai.org/ocs/index.php/FLAIRS/FLAIRS20/paper/view/18460},
year = {2020},
date = {2020-01-01},
booktitle = {Proceedings of the Thirty-Third International Florida Artificial Intelligence
Research Society Conference, Originally to be held in North Miami
Beach, Florida, USA, May 17-20, 2020},
pages = {347--352},
publisher = {AAAI Press},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Bach, Kerstin; Mork, Paul Jarle
On the Explanation of Similarity for Developing and Deploying CBR Systems Inproceedings
In: á, Roman Bart; Bell, Eric (Ed.): Proceedings of the Thirty-Third International Florida Artificial Intelligence Research Society Conference, Originally to be held in North Miami Beach, Florida, USA, May 17-20, 2020, pp. 413–416, AAAI Press, 2020.
@inproceedings{DBLP:conf/flairs/BachM20,
title = {On the Explanation of Similarity for Developing and Deploying CBR
Systems},
author = {Kerstin Bach and Paul Jarle Mork},
editor = {Roman Bart á and Eric Bell},
url = {https://aaai.org/ocs/index.php/FLAIRS/FLAIRS20/paper/view/18472},
year = {2020},
date = {2020-01-01},
booktitle = {Proceedings of the Thirty-Third International Florida Artificial Intelligence
Research Society Conference, Originally to be held in North Miami
Beach, Florida, USA, May 17-20, 2020},
pages = {413--416},
publisher = {AAAI Press},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Verma, Deepika; Bach, Kerstin; Mork, Paul Jarle
Clustering of Physical Behaviour Profiles using Knowledge-intensive Similarity Measures Inproceedings
In: Rocha, Ana Paula; Steels, Luc; van den Herik, Jaap H (Ed.): Proceedings of the 12th International Conference on Agents and Artificial Intelligence, ICAART 2020, Volume 2, Valletta, Malta, February 22-24, 2020, pp. 660–667, SCITEPRESS, 2020.
@inproceedings{DBLP:conf/icaart/VermaBM20,
title = {Clustering of Physical Behaviour Profiles using Knowledge-intensive
Similarity Measures},
author = {Deepika Verma and Kerstin Bach and Paul Jarle Mork},
editor = {Ana Paula Rocha and Luc Steels and Jaap H van den Herik},
url = {https://doi.org/10.5220/0008980406600667},
doi = {10.5220/0008980406600667},
year = {2020},
date = {2020-01-01},
booktitle = {Proceedings of the 12th International Conference on Agents and Artificial
Intelligence, ICAART 2020, Volume 2, Valletta, Malta, February 22-24,
2020},
pages = {660--667},
publisher = {SCITEPRESS},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Bach, Kerstin; Akselsen, Sigmund; Veiga, Tiago; Kalamaras, Ilias
On the Use of Air Quality Microsensors for Supporting Decision Makers Inproceedings
In: 10th International Conference on the Internet of Things Companion, Association for Computing Machinery, Malmö, Sweden, 2020, ISBN: 9781450388207.
@inproceedings{10.1145/3423423.3423463,
title = {On the Use of Air Quality Microsensors for Supporting Decision Makers},
author = {Kerstin Bach and Sigmund Akselsen and Tiago Veiga and Ilias Kalamaras},
url = {https://doi.org/10.1145/3423423.3423463},
doi = {10.1145/3423423.3423463},
isbn = {9781450388207},
year = {2020},
date = {2020-01-01},
booktitle = {10th International Conference on the Internet of Things Companion},
publisher = {Association for Computing Machinery},
address = {Malmö, Sweden},
series = {IoT '20 Companion},
abstract = {In this poster we present how a network of Internet-of-things (IoT) devices facilitated through machine learning can improve decision making. Our application domain is air quality in the municipality of Trondheim. Ambient air pollution poses a major threat to both health and climate with millions of premature deaths occurring every year. To enable solutions to this problem, accurate measurements of the phenomenon are required and tools for decision makers need to be in place to quickly understand situations as well as suggest actions that lead to the best possible outcome.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
In this poster we present how a network of Internet-of-things (IoT) devices facilitated through machine learning can improve decision making. Our application domain is air quality in the municipality of Trondheim. Ambient air pollution poses a major threat to both health and climate with millions of premature deaths occurring every year. To enable solutions to this problem, accurate measurements of the phenomenon are required and tools for decision makers need to be in place to quickly understand situations as well as suggest actions that lead to the best possible outcome.
Murad, Abdulmajid; Kraemer, Frank Alexander; Bach, Kerstin; Taylor, Gavin
Information-Driven Adaptive Sensing Based on Deep Reinforcement Learning Inproceedings
In: Proceedings of the 10th International Conference on the Internet of Things, Association for Computing Machinery, Malmö, Sweden, 2020, ISBN: 9781450387583.
@inproceedings{10.1145/3410992.3411001,
title = {Information-Driven Adaptive Sensing Based on Deep Reinforcement Learning},
author = {Abdulmajid Murad and Frank Alexander Kraemer and Kerstin Bach and Gavin Taylor},
url = {https://doi.org/10.1145/3410992.3411001},
doi = {10.1145/3410992.3411001},
isbn = {9781450387583},
year = {2020},
date = {2020-01-01},
booktitle = {Proceedings of the 10th International Conference on the Internet of Things},
publisher = {Association for Computing Machinery},
address = {Malmö, Sweden},
series = {IoT '20},
abstract = {In order to make better use of deep reinforcement learning in the creation of sensing policies for resource-constrained IoT devices, we present and study a novel reward function based on the Fisher information value. This reward function enables IoT sensor devices to learn to spend available energy on measurements at otherwise unpredictable moments, while conserving energy at times when measurements would provide little new information. This is a highly general approach, which allows for a wide range of use cases without significant human design effort or hyperparameter tuning. We illustrate the approach in a scenario of workplace noise monitoring, where results show that the learned behavior outperforms a uniform sampling strategy and comes close to a near-optimal oracle solution.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
In order to make better use of deep reinforcement learning in the creation of sensing policies for resource-constrained IoT devices, we present and study a novel reward function based on the Fisher information value. This reward function enables IoT sensor devices to learn to spend available energy on measurements at otherwise unpredictable moments, while conserving energy at times when measurements would provide little new information. This is a highly general approach, which allows for a wide range of use cases without significant human design effort or hyperparameter tuning. We illustrate the approach in a scenario of workplace noise monitoring, where results show that the learned behavior outperforms a uniform sampling strategy and comes close to a near-optimal oracle solution.
Mathisen, Bjørn Magnus; Bach, Kerstin; Meidell, Espen; Måløy, Håkon; Sjøblom, Edvard Schreiner
FishNet: A Unified Embeddiung for Salmon Recognition Inproceedings
In: Proceedings of the Twenty-fourth European Conference on Artificial Intelligence, pp. 3001–3008, 2020.
@inproceedings{mathisen2020fishnet,
title = {FishNet: A Unified Embeddiung for Salmon Recognition},
author = {Bjørn Magnus Mathisen and Kerstin Bach and Espen Meidell and Håkon Måløy and Edvard Schreiner Sjøblom},
year = {2020},
date = {2020-01-01},
booktitle = {Proceedings of the Twenty-fourth European Conference on Artificial Intelligence},
pages = {3001--3008},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
2019
Sandal, Louise Fleng; Stochkendahl, Mette Jensen; Svendsen, Malene Jagd; Wood, Karen; Øverås, Cecilie K; Nordstoga, Anne Lovise; Villumsen, Morten; Rasmussen, Charlotte Diana Nørregaard; Nicholl, Barbara; Cooper, Kay; Kjaer, Per; Mair, Frances S; Sjøgaard, Gisela; Nilsen, Tom Ivar Lund; Hartvigsen, Jan; Bach, Kerstin; Mork, Paul Jarle; Søgaard, Karen
An app-delivered self-management program for people with low back pain: protocol for the selfBACK randomized controlled trial Journal Article
In: JMIR Research Protocols, vol. 8, no. 12, 2019.
@article{SandalEtAl2019,
title = {An app-delivered self-management program for people with low back pain: protocol for the selfBACK randomized controlled trial},
author = {Louise Fleng Sandal and Mette Jensen Stochkendahl and Malene Jagd Svendsen and Karen Wood and Cecilie K Øverås and Anne Lovise Nordstoga and Morten Villumsen and Charlotte Diana Nørregaard Rasmussen and Barbara Nicholl and Kay Cooper and Per Kjaer and Frances S Mair and Gisela Sjøgaard and Tom Ivar Lund Nilsen and Jan Hartvigsen and Kerstin Bach and Paul Jarle Mork and Karen Søgaard},
editor = {Muhammad Abid Azam and Vered Valeria Latman and Joel Katz},
url = {https://www.researchprotocols.org/2019/12/e14720/},
doi = {10.2196/14720},
year = {2019},
date = {2019-12-03},
journal = {JMIR Research Protocols},
volume = {8},
number = {12},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Bach, Kerstin; Ruocco, Massimiliano (Ed.)
Nordic Artificial Intelligence Research and Development Collection
Springer, Cham, 2019, ISBN: 978-3-030-35663-7.
@collection{NAIS2019,
title = {Nordic Artificial Intelligence Research and Development},
editor = {Kerstin Bach and Massimiliano Ruocco},
url = {https://link.springer.com/book/10.1007/978-3-030-35664-4},
doi = {10.1007/978-3-030-35664-4},
isbn = {978-3-030-35663-7},
year = {2019},
date = {2019-11-30},
volume = {1056},
publisher = {Springer, Cham},
series = {Communications in Computer and Information Science book series (CCIS)},
keywords = {},
pubstate = {published},
tppubtype = {collection}
}
Svendsen, Malene Jagd; Rasmussen, Charlotte Diana Nørregaard; Sandal, Louise Fleng; Stochkendahl, Mette Jensen; Hartvigsen, Jan; Cooper, Kay; Kjaer, Per; Bach, Kerstin; Mork, Paul Jarle
15th WFC Biennial Congress and 78th ECU Convention, 2019.
@conference{Svendsen2019,
title = {Designing a digital support intervention for the Self-Management of Low Back Pain (SelfBACK)-an intervention mapping approach},
author = {Malene Jagd Svendsen and Charlotte Diana Nørregaard Rasmussen and Louise Fleng Sandal and Mette Jensen Stochkendahl and Jan Hartvigsen and Kay Cooper and Per Kjaer and Kerstin Bach and Paul Jarle Mork},
editor = {Valerie A Ubbes},
url = {https://wfc-ecu-berlin-2019.exordo.com/programme/presentation/21},
year = {2019},
date = {2019-03-22},
booktitle = {15th WFC Biennial Congress and 78th ECU Convention},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
Bach, Kerstin; Marling, Cindy; Mork, Paul Jarle; Aamodt, Agnar; Mair, Frances S; Nicholl, Barbara I
Design of a clinician dashboard to facilitate co-decision making in the management of non-specific low back pain Journal Article
In: J. Intell. Inf. Syst., vol. 52, no. 2, pp. 269–284, 2019.
@article{DBLP:journals/jiis/BachMMAMN19,
title = {Design of a clinician dashboard to facilitate co-decision making in the management of non-specific low back pain},
author = {Kerstin Bach and Cindy Marling and Paul Jarle Mork and Agnar Aamodt and Frances S Mair and Barbara I Nicholl},
url = {https://doi.org/10.1007/s10844-018-0539-y},
doi = {10.1007/s10844-018-0539-y},
year = {2019},
date = {2019-01-01},
journal = {J. Intell. Inf. Syst.},
volume = {52},
number = {2},
pages = {269--284},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Jaiswal, Amar; Bach, Kerstin; Meisingset, Ingebrigt; Vasseljen, Ottar
Case Representation and Similarity Modeling for Non-Specific Musculoskeletal Disorders - a Case-Based Reasoning Approach Inproceedings
In: á, Roman Bart; Brawner, Keith W (Ed.): Proceedings of the Thirty-Second International Florida Artificial Intelligence Research Society Conference, Sarasota, Florida, USA, May 19-22 2019, pp. 359–363, AAAI Press, 2019.
@inproceedings{DBLP:conf/flairs/JaiswalBMV19,
title = {Case Representation and Similarity Modeling for Non-Specific Musculoskeletal
Disorders - a Case-Based Reasoning Approach},
author = {Amar Jaiswal and Kerstin Bach and Ingebrigt Meisingset and Ottar Vasseljen},
editor = {Roman Bart á and Keith W Brawner},
url = {https://aaai.org/ocs/index.php/FLAIRS/FLAIRS19/paper/view/18194},
year = {2019},
date = {2019-01-01},
booktitle = {Proceedings of the Thirty-Second International Florida Artificial
Intelligence Research Society Conference, Sarasota, Florida, USA,
May 19-22 2019},
pages = {359--363},
publisher = {AAAI Press},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Jaiswal, Amar; Bach, Kerstin
A Data-Driven Approach for Determining Weights in Global Similarity Functions Inproceedings
In: Bach, Kerstin; Marling, Cindy (Ed.): Case-Based Reasoning Research and Development - 27th International Conference, ICCBR 2019, Otzenhausen, Germany, September 8-12, 2019, Proceedings, pp. 125–139, Springer, 2019.
@inproceedings{DBLP:conf/iccbr/JaiswalB19,
title = {A Data-Driven Approach for Determining Weights in Global Similarity
Functions},
author = {Amar Jaiswal and Kerstin Bach},
editor = {Kerstin Bach and Cindy Marling},
url = {https://doi.org/10.1007/978-3-030-29249-2_9},
doi = {10.1007/978-3-030-29249-2_9},
year = {2019},
date = {2019-01-01},
booktitle = {Case-Based Reasoning Research and Development - 27th International
Conference, ICCBR 2019, Otzenhausen, Germany, September 8-12, 2019,
Proceedings},
volume = {11680},
pages = {125--139},
publisher = {Springer},
series = {Lecture Notes in Computer Science},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Bach, Kerstin
Workshop preface Inproceedings
In: Kapetanakis, Stelios; Borck, Hayley (Ed.): Workshops Proceedings for the Twenty-seventh International Conference on Case-Based Reasoning co-located with the Twenty-seventh International Conference on Case-Based Reasoning (ICCBR 2019), Otzenhausen, Germany, September 8-12, 2019, pp. 143, CEUR-WS.org, 2019.
@inproceedings{DBLP:conf/iccbr/Bach19,
title = {Workshop preface},
author = {Kerstin Bach},
editor = {Stelios Kapetanakis and Hayley Borck},
url = {http://ceur-ws.org/Vol-2567/demo_preface.pdf},
year = {2019},
date = {2019-01-01},
booktitle = {Workshops Proceedings for the Twenty-seventh International Conference
on Case-Based Reasoning co-located with the Twenty-seventh International
Conference on Case-Based Reasoning (ICCBR 2019), Otzenhausen, Germany,
September 8-12, 2019},
volume = {2567},
pages = {143},
publisher = {CEUR-WS.org},
series = {CEUR Workshop Proceedings},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Bach, Kerstin; Mathisen, Bjørn Magnus; Jaiswal, Amar
Demonstrating the myCBR Rest API Inproceedings
In: Kapetanakis, Stelios; Borck, Hayley (Ed.): Workshops Proceedings for the Twenty-seventh International Conference on Case-Based Reasoning co-located with the Twenty-seventh International Conference on Case-Based Reasoning (ICCBR 2019), Otzenhausen, Germany, September 8-12, 2019, pp. 144–155, CEUR-WS.org, 2019.
@inproceedings{DBLP:conf/iccbr/BachMJ19,
title = {Demonstrating the myCBR Rest API},
author = {Kerstin Bach and Bjørn Magnus Mathisen and Amar Jaiswal},
editor = {Stelios Kapetanakis and Hayley Borck},
url = {http://ceur-ws.org/Vol-2567/paper13.pdf},
year = {2019},
date = {2019-01-01},
booktitle = {Workshops Proceedings for the Twenty-seventh International Conference
on Case-Based Reasoning co-located with the Twenty-seventh International
Conference on Case-Based Reasoning (ICCBR 2019), Otzenhausen, Germany,
September 8-12, 2019},
volume = {2567},
pages = {144--155},
publisher = {CEUR-WS.org},
series = {CEUR Workshop Proceedings},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Murad, Abdulmajid; Bach, Kerstin; Kraemer, Frank Alexander; Taylor, Gavin
IoT Sensor Gym: Training Autonomous IoT Devices with Deep Reinforcement Learning Inproceedings
In: Proceedings of the 9th International Conference on the Internet of Things, IoT 2019, Bilbao, Spain, October 22-25, 2019, pp. 37:1–37:4, ACM, 2019.
@inproceedings{DBLP:conf/iot/MuradBKT19,
title = {IoT Sensor Gym: Training Autonomous IoT Devices with Deep Reinforcement
Learning},
author = {Abdulmajid Murad and Kerstin Bach and Frank Alexander Kraemer and Gavin Taylor},
url = {https://doi.org/10.1145/3365871.3365911},
doi = {10.1145/3365871.3365911},
year = {2019},
date = {2019-01-01},
booktitle = {Proceedings of the 9th International Conference on the Internet of
Things, IoT 2019, Bilbao, Spain, October 22-25, 2019},
pages = {37:1--37:4},
publisher = {ACM},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Kalamaras, Ilias; Xygonakis, Ioannis; Glykos, Konstantinos; Akselsen, Sigmund; Munch-Elligsen, Arne; Nguyen, Hai Thanh; Lepperod, Andreas Jacobsen; Bach, Kerstin; Votis, Konstantinos; Tzovaras, Dimitrios
Visual analytics for exploring air quality data in an AI-enhanced IoT environment Inproceedings
In: Chbeir, Richard; Manolopoulos, Yannis; Ilarri, Sergio; Papadopoulos, Apostolos (Ed.): 11th International Conference on Management of Digital EcoSystems, MEDES 2019, Limassol, Cyprus, November, 2019, pp. 103–110, ACM, 2019.
@inproceedings{DBLP:conf/medes/KalamarasXGAMNL19,
title = {Visual analytics for exploring air quality data in an AI-enhanced IoT environment},
author = {Ilias Kalamaras and Ioannis Xygonakis and Konstantinos Glykos and Sigmund Akselsen and Arne Munch-Elligsen and Hai Thanh Nguyen and Andreas Jacobsen Lepperod and Kerstin Bach and Konstantinos Votis and Dimitrios Tzovaras},
editor = {Richard Chbeir and Yannis Manolopoulos and Sergio Ilarri and Apostolos Papadopoulos},
url = {https://doi.org/10.1145/3297662.3365816},
doi = {10.1145/3297662.3365816},
year = {2019},
date = {2019-01-01},
booktitle = {11th International Conference on Management of Digital EcoSystems,
MEDES 2019, Limassol, Cyprus, November, 2019},
pages = {103--110},
publisher = {ACM},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Murad, Abdulmajid; Kraemer, Frank Alexander; Bach, Kerstin; Taylor, Gavin
Autonomous Management of Energy-Harvesting IoT Nodes Using Deep Reinforcement Learning Inproceedings
In: 13th IEEE International Conference on Self-Adaptive and Self-Organizing Systems, SASO 2019, Umea, Sweden, June 16-20, 2019, pp. 43–51, IEEE, 2019.
@inproceedings{DBLP:conf/saso/MuradKBT19,
title = {Autonomous Management of Energy-Harvesting IoT Nodes Using Deep Reinforcement Learning},
author = {Abdulmajid Murad and Frank Alexander Kraemer and Kerstin Bach and Gavin Taylor},
url = {https://doi.org/10.1109/SASO.2019.00015
http://arxiv.org/abs/1905.04181},
doi = {10.1109/SASO.2019.00015},
year = {2019},
date = {2019-01-01},
booktitle = {13th IEEE International Conference on Self-Adaptive and Self-Organizing
Systems, SASO 2019, Umea, Sweden, June 16-20, 2019},
pages = {43--51},
publisher = {IEEE},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Bach, Kerstin; Marling, Cindy (Ed.)
Springer, vol. 11680, 2019, ISBN: 978-3-030-29248-5.
@proceedings{DBLP:conf/iccbr/2019,
title = {Case-Based Reasoning Research and Development - 27th International
Conference, ICCBR 2019, Otzenhausen, Germany, September 8-12, 2019,
Proceedings},
editor = {Kerstin Bach and Cindy Marling},
url = {https://doi.org/10.1007/978-3-030-29249-2},
doi = {10.1007/978-3-030-29249-2},
isbn = {978-3-030-29248-5},
year = {2019},
date = {2019-01-01},
volume = {11680},
publisher = {Springer},
series = {Lecture Notes in Computer Science},
keywords = {},
pubstate = {published},
tppubtype = {proceedings}
}
Verma, Deepika; Bach, Kerstin; Mork, Paul Jarle
Similarity Measure Development for Case-Based Reasoning- A Data-driven Approach Journal Article
In: CoRR, vol. abs/1905.08581, 2019.
@article{DBLP:journals/corr/abs-1905-08581,
title = {Similarity Measure Development for Case-Based Reasoning- A Data-driven
Approach},
author = {Deepika Verma and Kerstin Bach and Paul Jarle Mork},
url = {http://arxiv.org/abs/1905.08581},
year = {2019},
date = {2019-01-01},
journal = {CoRR},
volume = {abs/1905.08581},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
2018
Aha, David W; Bach, Kerstin; Gundersen, Odd Erik; Lieber, Jean
The 25th International Conference on Case-Based Reasoning Journal Article
In: AI Mag., vol. 39, no. 2, pp. 79–80, 2018.
@article{DBLP:journals/aim/AhaBGL18,
title = {The 25th International Conference on Case-Based Reasoning},
author = {David W Aha and Kerstin Bach and Odd Erik Gundersen and Jean Lieber},
url = {https://doi.org/10.1609/aimag.v39i2.2797},
doi = {10.1609/aimag.v39i2.2797},
year = {2018},
date = {2018-01-01},
journal = {AI Mag.},
volume = {39},
number = {2},
pages = {79--80},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Bach, Kerstin
From Data to Context Aware Decision Making Challenges and Opportunities Inproceedings
In: Nalepa, Grzegorz J; á, Vicente Juli; é, José Tomás Palma M; Â,; Carrascosa, Carlos; Novais, Paulo (Ed.): Proceedings of the Workshop on Affective Computing and Context Awareness in Ambient Intelligence (AfCAI 2018), Valencia, Spain, April 19-20, 2018, CEUR-WS.org, 2018.
@inproceedings{DBLP:conf/afcai/Bach18,
title = {From Data to Context Aware Decision Making Challenges and Opportunities},
author = {Kerstin Bach},
editor = {Grzegorz J Nalepa and Vicente Juli á and José Tomás Palma M é and  and Carlos Carrascosa and Paulo Novais},
url = {http://ceur-ws.org/Vol-2166/afcai18-paper14.pdf},
year = {2018},
date = {2018-01-01},
booktitle = {Proceedings of the Workshop on Affective Computing and Context Awareness
in Ambient Intelligence (AfCAI 2018), Valencia, Spain, April 19-20,
2018},
volume = {2166},
publisher = {CEUR-WS.org},
series = {CEUR Workshop Proceedings},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Nikpour, Hoda; Aamodt, Agnar; Bach, Kerstin
Bayesian-Supported Retrieval in BNCreek: A Knowledge-Intensive Case-Based Reasoning System Inproceedings
In: Cox, Michael T; Funk, Peter; Begum, Shahina (Ed.): Case-Based Reasoning Research and Development - 26th International Conference, ICCBR 2018, Stockholm, Sweden, July 9-12, 2018, Proceedings, pp. 323–338, Springer, 2018.
@inproceedings{DBLP:conf/iccbr/NikpourAB18,
title = {Bayesian-Supported Retrieval in BNCreek: A Knowledge-Intensive Case-Based
Reasoning System},
author = {Hoda Nikpour and Agnar Aamodt and Kerstin Bach},
editor = {Michael T Cox and Peter Funk and Shahina Begum},
url = {https://doi.org/10.1007/978-3-030-01081-2_22},
doi = {10.1007/978-3-030-01081-2_22},
year = {2018},
date = {2018-01-01},
booktitle = {Case-Based Reasoning Research and Development - 26th International
Conference, ICCBR 2018, Stockholm, Sweden, July 9-12, 2018, Proceedings},
volume = {11156},
pages = {323--338},
publisher = {Springer},
series = {Lecture Notes in Computer Science},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Verma, Deepika; Bach, Kerstin; Mork, Paul Jarle
Modelling Similarity for Comparing Physical Activity Profiles - A Data-Driven Approach Inproceedings
In: Cox, Michael T; Funk, Peter; Begum, Shahina (Ed.): Case-Based Reasoning Research and Development - 26th International Conference, ICCBR 2018, Stockholm, Sweden, July 9-12, 2018, Proceedings, pp. 415–430, Springer, 2018.
@inproceedings{DBLP:conf/iccbr/VermaBM18,
title = {Modelling Similarity for Comparing Physical Activity Profiles - A
Data-Driven Approach},
author = {Deepika Verma and Kerstin Bach and Paul Jarle Mork},
editor = {Michael T Cox and Peter Funk and Shahina Begum},
url = {https://doi.org/10.1007/978-3-030-01081-2_28},
doi = {10.1007/978-3-030-01081-2_28},
year = {2018},
date = {2018-01-01},
booktitle = {Case-Based Reasoning Research and Development - 26th International
Conference, ICCBR 2018, Stockholm, Sweden, July 9-12, 2018, Proceedings},
volume = {11156},
pages = {415--430},
publisher = {Springer},
series = {Lecture Notes in Computer Science},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Vonstad, Elise Klaebo; Su, Xiaomeng; Vereijken, Beatrix; Nilsen, Jan Harald; Bach, Kerstin
Cassification of Movement Quality in A Weight-shifting Exercise Inproceedings
In: Bach, Kerstin; Bunescu, Razvan C; Farri, Oladimeji; Guo, Aili; Hasan, Sadid A; Ibrahim, Zina M; Marling, Cindy; Raffa, Jesse; Rubin, Jonathan; Wu, Honghan (Ed.): Proceedings of the 3rd International Workshop on Knowledge Discovery in Healthcare Data co-located with the 27th International Joint Conference on Artificial Intelligence and the 23rd European Conference on Artificial Intelligence (IJCAI-ECAI 2018), Stockholm, Schweden, July 13, 2018, pp. 27–32, CEUR-WS.org, 2018.
@inproceedings{DBLP:conf/ijcai/VonstadSVNB18,
title = {Cassification of Movement Quality in A Weight-shifting Exercise},
author = {Elise Klaebo Vonstad and Xiaomeng Su and Beatrix Vereijken and Jan Harald Nilsen and Kerstin Bach},
editor = {Kerstin Bach and Razvan C Bunescu and Oladimeji Farri and Aili Guo and Sadid A Hasan and Zina M Ibrahim and Cindy Marling and Jesse Raffa and Jonathan Rubin and Honghan Wu},
url = {http://ceur-ws.org/Vol-2148/paper04.pdf},
year = {2018},
date = {2018-01-01},
booktitle = {Proceedings of the 3rd International Workshop on Knowledge Discovery
in Healthcare Data co-located with the 27th International Joint Conference
on Artificial Intelligence and the 23rd European Conference on Artificial
Intelligence (IJCAI-ECAI 2018), Stockholm, Schweden, July 13, 2018},
volume = {2148},
pages = {27--32},
publisher = {CEUR-WS.org},
series = {CEUR Workshop Proceedings},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Bach, Kerstin
Knowledge Engineering for Distributed Case-Based Reasoning Systems Incollection
In: Nalepa, Grzegorz J; Baumeister, Joachim (Ed.): Synergies Between Knowledge Engineering and Software Engineering, vol. 626, pp. 129–147, Springer, 2018.
@incollection{DBLP:series/asc/Bach18,
title = {Knowledge Engineering for Distributed Case-Based Reasoning Systems},
author = {Kerstin Bach},
editor = {Grzegorz J Nalepa and Joachim Baumeister},
url = {https://doi.org/10.1007/978-3-319-64161-4_7},
doi = {10.1007/978-3-319-64161-4_7},
year = {2018},
date = {2018-01-01},
booktitle = {Synergies Between Knowledge Engineering and Software Engineering},
volume = {626},
pages = {129--147},
publisher = {Springer},
series = {Advances in Intelligent Systems and Computing},
keywords = {},
pubstate = {published},
tppubtype = {incollection}
}
Bach, Kerstin; Bunescu, Razvan C; Farri, Oladimeji; Guo, Aili; Hasan, Sadid A; Ibrahim, Zina M; Marling, Cindy; Raffa, Jesse; Rubin, Jonathan; Wu, Honghan (Ed.)
CEUR-WS.org, vol. 2148, 2018.
@proceedings{DBLP:conf/ijcai/2018khd,
title = {Proceedings of the 3rd International Workshop on Knowledge Discovery
in Healthcare Data co-located with the 27th International Joint Conference
on Artificial Intelligence and the 23rd European Conference on Artificial
Intelligence (IJCAI-ECAI 2018), Stockholm, Schweden, July 13, 2018},
editor = {Kerstin Bach and Razvan C Bunescu and Oladimeji Farri and Aili Guo and Sadid A Hasan and Zina M Ibrahim and Cindy Marling and Jesse Raffa and Jonathan Rubin and Honghan Wu},
url = {http://ceur-ws.org/Vol-2148},
year = {2018},
date = {2018-01-01},
volume = {2148},
publisher = {CEUR-WS.org},
series = {CEUR Workshop Proceedings},
keywords = {},
pubstate = {published},
tppubtype = {proceedings}
}
2017
Prestmo, Tale; Bach, Kerstin; Aamodt, Agnar; Mork, Paul Jarle
Evolutionary Inspired Adaptation of Exercise Plans for Increasing Solution Variety Inproceedings
In: Aha, David W; Lieber, Jean (Ed.): Case-Based Reasoning Research and Development - 25th International Conference, ICCBR 2017, Trondheim, Norway, June 26-28, 2017, Proceedings, pp. 272–286, Springer, 2017.
@inproceedings{DBLP:conf/iccbr/PrestmoBAM17,
title = {Evolutionary Inspired Adaptation of Exercise Plans for Increasing
Solution Variety},
author = {Tale Prestmo and Kerstin Bach and Agnar Aamodt and Paul Jarle Mork},
editor = {David W Aha and Jean Lieber},
url = {https://doi.org/10.1007/978-3-319-61030-6_19},
doi = {10.1007/978-3-319-61030-6_19},
year = {2017},
date = {2017-01-01},
booktitle = {Case-Based Reasoning Research and Development - 25th International
Conference, ICCBR 2017, Trondheim, Norway, June 26-28, 2017, Proceedings},
volume = {10339},
pages = {272--286},
publisher = {Springer},
series = {Lecture Notes in Computer Science},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}