{"type":"ScholarlyArticle","title":"Energy-Efficient Missing Data Imputation in Wearable Health Applications: A Classifier-aware Statistical Approach","authors":[{"name":"Dina Hussein","slug":"dina-hussein","given":"Dina","family":"Hussein","affiliation":"Washington State University"},{"name":"Taha Belkhouja","slug":"taha-belkhouja","given":"Taha","family":"Belkhouja","affiliation":"Washington State University"},{"name":"Ganapati Bhat","slug":"ganapati-bhat","given":"Ganapati","family":"Bhat","affiliation":"Washington State University"},{"name":"Janardhan Rao Doppa","slug":"janardhan-rao-doppa","given":"Janardhan Rao","family":"Doppa","affiliation":"Washington State University"}],"abstract":"Wearable devices are being increasingly used in high-impact health applications including vital sign monitoring, rehabilitation, and movement disorders. Wearable health monitoring can aid in the United Nations social development goal of healthy lives by enabling early warning, risk reduction, and management of health risks. Health tasks on wearable devices employ multiple sensors to collect relevant parameters of user’s health and make decisions using machine learning (ML) algorithms. The ML algorithms assume that data from all sensors are available for the health monitoring tasks. However, the applications may encounter missing or incomplete data due to user error, energy limitations, or sensor malfunction. Missing data results in significant loss of accuracy and quality of service. This paper presents a novel Classifier-Aware iMputation (CAM) approach to impute missing data such that classifier accuracy for health tasks is not affected. Specifically, CAM employs unsupervised clustering followed by a principled search algorithm to uncover imputation patterns that maintain high accuracy. Evaluations on seven diverse health tasks show that CAM achieves accuracy within 5% of the baseline with no missing data when one sensor is missing. CAM also achieves significantly higher accuracy compared to generative approaches with negligible energy overhead, making it suitable for wide range of wearable applications.","doi":"10.24963/ijcai.2024/807","url":"https://ijcai.org/proceedings/2024/807","pdf":"https://ijcai.org/proceedings/2024/0807.pdf","markdown":"https://ijcai.org/proceedings/2024/807.md","bibtex":"https://ijcai.org/proceedings/2024/bibtex/807","volume":{"slug":"2024","title":"Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2024","url":"https://ijcai.org/proceedings/2024/","year":2024,"location":"Jeju, Korea","dates":"3-9 August 2024","editors":"Kate Larson","isbn":"978-1-956792-04-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2024"},"section":"AI for Good","track":"AI for Good","number":807,"pages":{"first":7296,"last":7304},"keywords":["Machine Learning: General","Humans and AI: General","Multidisciplinary Topics and Applications: General","Search: General"],"videos":[],"references":[{"position":1,"raw":"[Alam and Ben Hamida, 2014] Muhammad Mahtab Alam and Elyes Ben Hamida. Surveying Wearable Human As- sistive Technology for Life and Safety Critical Applica- tions: Standards, Challenges and Opportunities. Sensors, 14(5):9153-9209, 2014.","title":"Surveying Wearable Human Assistive Technology for Life and Safety Critical Applications: Standards, Challenges and Opportunities","authors":"Ben Alam, ; Hamida, Mahtab Muhammad, Elyes Alam, Hamida Ben","year":"2014","venue":"Sensors","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Belkhouja and Doppa, 2020] Taha Belkhouja and Janard- han Rao Doppa. Analyzing Deep Learning for Time- Series Data Through Adversarial Lens in Mobile and IoT Applications. IEEE Trans. on Comput.-Aided Design of Integr. Circuits and Syst., 39(11):3190-3201, 2020.","title":"Analyzing Deep Learning for Time-Series Data Through Adversarial Lens in Mobile and IoT Applications","authors":"Taha Belkhouja, Janardhan Rao, Doppa","year":"2020","venue":"IEEE Trans. on Comput.-Aided Design of Integr. Circuits and Syst","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Belkhouja and Doppa, 2022] Taha Belkhouja and Janard- han Rao Doppa. Adversarial Framework with Certified Robustness for Time-Series Domain via Statistical Fea- tures. Journal of Artificial Intelligence Research, 2022.","title":"Adversarial Framework with Certified Robustness for Time-Series Domain via Statistical Features","authors":"Taha Belkhouja, Janardhan Rao, Doppa","year":"2022","venue":"Journal of Artificial Intelligence Research","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Belkhouja et al., 2023] Taha Belkhouja, Yan Yan, and Ja- nardhan Rao Doppa. Dynamic Time Warping Based Adversarial Framework for Time-Series Domain. IEEE Trans. Pattern Anal. Mach. Intell., 45(6):7353-7366, 2023.","title":"Dynamic Time Warping Based Adversarial Framework for Time-Series Domain","authors":"Taha Belkhouja, Yan Yan, Janardhan Rao, Doppa","year":"2023","venue":"IEEE Trans. Pattern Anal. Mach. Intell","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Bhat et al., 2019] Ganapati Bhat, Ranadeep Deb, and Umit Y Ogras. OpenHealth: Open-Source Platform for Wearable Health Monitoring. IEEE Design & Test, 36(5):27-34, 2019.","title":"OpenHealth: Open-Source Platform for Wearable Health Monitoring","authors":"Ganapati Bhat, Ranadeep Deb, Umit Y Ogras","year":"2019","venue":"IEEE Design & Test","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Bhat et al., 2020] Ganapati Bhat, Nicholas Tran, Holly Shill, and Umit Y Ogras. w-HAR: An Activity Recogni- tion Dataset and Framework using Low-Power Wearable Devices. Sensors, 20(18):5356, 2020.","title":"w-HAR: An Activity Recognition Dataset and Framework using Low-Power Wearable Devices","authors":"Ganapati Bhat, Nicholas Tran, Holly Shill, Umit Y Ogras","year":"2020","venue":"Sensors","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Birbaumer et al., 2001] N Birbaumer, H Flor, N Ghanayim, T Hinterberger, I Iverson, E Taub, B Kotchoubey, A Kbler, and J Perelmouter. A Brain-Controlled Spelling Device for the Completely Paralyzed. Nature, pages 297-298, 2001.","title":"A Brain-Controlled Spelling Device for the Completely Paralyzed","authors":"H Birbaumer, N Flor, T Ghanayim, I Hinterberger, E Iverson, B Taub, Kotchoubey, Kbler, Perelmouter","year":"2001","venue":"Nature","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Creswell et al., 2018] Antonia Creswell, Tom White, Vin- cent Dumoulin, Kai Arulkumaran, Biswa Sengupta, and Anil A Bharath. Generative Adversarial Networks: An Overview. IEEE Signal Processing Magazine, 35(1):53- 65, 2018.","title":"Generative Adversarial Networks: An Overview","authors":"Antonia Creswell, Tom White, Vincent Dumoulin, Kai Arulkumaran, Biswa Sengupta, Anil A Bharath","year":"2018","venue":"IEEE Signal Processing Magazine","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[De Waal et al., 2011] Ton De Waal, Jeroen Pannekoek, and Sander Scholtus. Handbook of Statistical Data Editing and Imputation, volume 563.","title":"Handbook of Statistical Data Editing and Imputation","authors":"De Waal","year":"2011","venue":null,"doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Espay et al., 2016] Alberto J Espay, Paolo Bonato, Fatta B Nahab, Walter Maetzler, John M Dean, Jochen Klucken, Bjoern M Eskofier, Aristide Merola, Fay Horak, An- thony E Lang, et al. Technology in Parkinson's Dis- ease: Challenges and Opportunities. Movt. Disorders, 31(9):1272-1282, 2016.","title":"Technology in Parkinson's Disease: Challenges and Opportunities","authors":"Alberto J Espay, Paolo Bonato, B Fatta, Walter Nahab, Maetzler, Jochen John M Dean, Klucken, M Bjoern, Aristide Eskofier, Fay Merola, Anthony E Horak, Lang","year":"2016","venue":"Movt. Disorders","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Falchetta et al., 2020] Giacomo Falchetta, Ahmed T Ham- mad, and Soheil Shayegh. Planning Universal Accessibil- ity to Public Health Care in Sub-Saharan Africa. Proceed- ings of the National Academy of Sciences, 117(50):31760- 31769, 2020.","title":"Planning Universal Accessibility to Public Health Care in Sub-Saharan Africa","authors":"Giacomo Falchetta, Ahmed T Hammad, Soheil Shayegh","year":"2020","venue":"Proceedings of the National Academy of Sciences","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Guo et al., 2019] Zijian Guo, Yiming Wan, and Hao Ye. A Data Imputation Method for Multivariate Time Series Based on Generative Adversarial Network. Neurocomput- ing, 360:185-197, 2019.","title":"A Data Imputation Method for Multivariate Time Series Based on Generative Adversarial Network","authors":"Zijian Guo, Yiming Wan, Hao Ye","year":"2019","venue":"Neurocomputing","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Hardkernel, 2014] Hardkernel. Odroid-xu3. https://www. hardkernel.com/shop/odroid-xu3/ Accessed 5/29/2024, 2014.","title":"Hardkernel. Odroid-xu3","authors":"Hardkernel","year":"2014","venue":null,"doi":null,"url":"https://www.hardkernel.com/shop/odroid-xu3/Accessed5/29","internal_url":null},{"position":14,"raw":"[Hossain et al., 2020] Tahera Hossain, Md Ahad, Atiqur Rahman, and Sozo Inoue. A Method for Sensor-Based Activity Recognition in Missing Data scenario. Sensors, 20(14):3811, 2020.","title":"A Method for Sensor-Based Activity Recognition in Missing Data scenario","authors":"Tahera Hossain, Md Ahad, Atiqur Rahman, Sozo Inoue","year":"2020","venue":"Sensors","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Hussein and Bhat, 2023] Dina Hussein and Ganapati Bhat. CIM: A Novel Clustering-Based Energy-Efficient Data Imputation Method for Human Activity Recog- nition. ACM Transactions on Embedded Computing Systems (TECS), 22(5s):1-26, 2023.","title":"CIM: A Novel Clustering-Based Energy-Efficient Data Imputation Method for Human Activity Recognition","authors":"Dina Hussein, Ganapati Bhat","year":"2023","venue":"ACM Transactions on Embedded Computing Systems (TECS)","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Hussein et al., 2022a] Dina Hussein, Taha Belkhouja, Ganapati Bhat, and Janardhan Rao Doppa. Reliable Machine Learning for Wearable Activity Monitoring: Novel Algorithms and Theoretical Guarantees. In Proc. Int. Conf. Comput-Aided Des., pages 1-9, 2022.","title":"Reliable Machine Learning for Wearable Activity Monitoring: Novel Algorithms and Theoretical Guarantees","authors":"Hussein","year":"2022","venue":"Proc. Int. Conf. Comput-Aided Des","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Hussein et al., 2022b] Dina Hussein, Ganapati Bhat, and Ja- nardhan Rao Doppa. Adaptive Energy Management for Self-Sustainable Wearables in Mobile Health. In Proceed- ings of AAAI, pages 11935-11944. AAAI Press, 2022.","title":"Adaptive Energy Management for Self-Sustainable Wearables in Mobile Health","authors":"Hussein","year":"2022","venue":"Proceedings of AAAI","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Hussein et al., 2022c] Dina Hussein, Aaryan Jain, and Ganapati Bhat. Robust Human Activity Recognition Us- ing Generative Adversarial Imputation Networks. In 2022 Design, Automation & Test in Europe Conference & Exhi- bition (DATE), pages 84-87, 2022.","title":"Robust Human Activity Recognition Using Generative Adversarial Imputation Networks","authors":"Hussein","year":"2022","venue":"2022 Design, Automation & Test in Europe Conference & Exhibition (DATE)","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Hussein et al., 2023] Dina Hussein, Taha Belkhouja, Gana- pati Bhat, and Janardhan Rao Doppa. Energy-Efficient Missing Data Recovery in Wearable Devices: A Novel Search-Based Approach. In 2023 IEEE/ACM Interna- tional Symposium on Low Power Electronics and Design (ISLPED), pages 1-6, 2023.","title":"Energy-Efficient Missing Data Recovery in Wearable Devices: A Novel Search-Based Approach","authors":"Dina Hussein, Taha Belkhouja, Ganapati Bhat, Janardhan Rao, Doppa","year":"2023","venue":"IEEE/ACM International Symposium on Low Power Electronics and Design (ISLPED)","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Kingma and Ba, 2015] Diederik P Kingma and Jimmy Ba. Adam: A Method for Stochastic Optimization. In The Int. Conf. on Learning Representations (Poster), 2015.","title":"Adam: A Method for Stochastic Optimization","authors":"P Diederik, Jimmy Kingma, Ba","year":"2015","venue":"The Int. Conf. on Learning Representations (Poster)","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Lara and Labrador, 2012] Oscar D Lara and Miguel A Labrador. A Survey on Human Activity Recognition Us- ing Wearable Sensors. IEEE Commun. Surveys & Tut., 15(3):1192-1209, 2012.","title":"Oscar D Lara and Miguel A Labrador. A Survey on Human Activity Recognition Using Wearable Sensors","authors":"Labrador Lara","year":"2012","venue":"IEEE Commun. Surveys & Tut","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Limaye and Adegbija, 2018] Ankur Limaye and Tosiron Adegbija. HERMIT: A Benchmark Suite for the Internet of Medical Things. IEEE Internet of Things Journal, 5(5), 2018.","title":"HERMIT: A Benchmark Suite for the Internet of Medical Things","authors":"Ankur Limaye, Tosiron Adegbija","year":"2018","venue":"IEEE Internet of Things Journal","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Liu et al., 2020] Shengzhong Liu, Shuochao Yao, Yifei Huang, Dongxin Liu, Huajie Shao, Yiran Zhao, Jinyang Li, Tianshi Wang, Ruijie Wang, Chaoqi Yang, and Tarek Abdelzaher. Handling Missing Sensors in Topology- Aware IoT Applications with Gated Graph Neural Net- work. Proc. of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, 4(3):1-31, 2020.","title":"Handling Missing Sensors in Topology-Aware IoT Applications with Gated Graph Neural Network","authors":"Shengzhong Liu, Shuochao Yao, Yifei Huang, Dongxin Liu, Huajie Shao, Yiran Zhao, Jinyang Li, Tianshi Wang, Ruijie Wang, Chaoqi Yang, Tarek Abdelzaher","year":"2020","venue":"Proc. of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Maetzler et al., 2013] Walter Maetzler, Josefa Domingos, Karin Srulijes, Joaquim J Ferreira, and Bastiaan R Bloem. Quantitative Wearable Sensors for Objective As- sessment of Parkinson's Disease. Movement Disorders, 28(12):1628-1637, 2013.","title":"Quantitative Wearable Sensors for Objective Assessment of Parkinson's Disease","authors":"Walter Maetzler, Josefa Domingos, Karin Srulijes, Joaquim J Ferreira, Bastiaan R Bloem","year":"2013","venue":"Movement Disorders","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Maetzler et al., 2016] Walter Maetzler, Jochen Klucken, and Malcolm Horne. A Clinical View on the Development of Technology-Based Tools in Managing Parkinson's Dis- ease. Movement Disorders, 31(9):1263-1271, 2016.","title":"A Clinical View on the Development of Technology-Based Tools in Managing Parkinson's Disease","authors":"Maetzler","year":"2016","venue":"Movement Disorders","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Mosenia et al., 2017] Arsalan Mosenia, Susmita Sur-Kolay, Anand Raghunathan, and Niraj K Jha. Wearable Medi- cal Sensor-Based System Design: A Survey. IEEE Trans- actions on Multi-Scale Computing Systems, 3(2):124-138, 2017.","title":"Wearable Medical Sensor-Based System Design: A Survey","authors":"Arsalan Mosenia, Susmita Sur-Kolay, Anand Raghunathan, Niraj K Jha","year":"2017","venue":"IEEE Transactions on Multi-Scale Computing Systems","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Pires et al., 2020] Ivan Miguel Pires, Faisal Hussain, Nuno M Garcia, and Eftim Zdravevski. Improving Human Activity Monitoring by Imputation of Missing Sensory Data: Experimental Study. Future Internet, 12(9):155, 2020.","title":"Improving Human Activity Monitoring by Imputation of Missing Sensory Data: Experimental Study","authors":"Ivan Miguel Pires, Faisal Hussain, Nuno M Garcia, Eftim Zdravevski","year":"2020","venue":"Future Internet","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Reiss and Stricker, 2012] Attila Reiss and Didier Stricker. Introducing a New Benchmarked Dataset for Activity Monitoring. In International Symposium on Wearable Computers, pages 108-109, 2012.","title":"Introducing a New Benchmarked Dataset for Activity Monitoring","authors":"Stricker Reiss, Attila Reiss, Didier Stricker","year":"2012","venue":"International Symposium on Wearable Computers","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Sachs et al., 2022] Jeffrey D Sachs, Christian Kroll, Guil- lame Lafortune, Grayson Fuller, and Finn Woelm. Sus- tainable Development Report 2022. Cambridge University Press, 2022.","title":"Sustainable Development Report 2022","authors":"Christian Jeffrey D Sachs, Guillame Kroll, Grayson Lafortune, Finn Fuller, Woelm","year":"2022","venue":null,"doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Schmidt et al., 2018] Philip Schmidt, Attila Reiss, Robert Duerichen, Claus Marberger, and Kristof Van Laerhoven. Introducing WESAD, a Multimodal Dataset for Wearable Stress and Affect Detection. In Proc. of the 20th ACM Int. Conf. on Multimodal Interaction, pages 400-408, 2018.","title":"Introducing WESAD, a Multimodal Dataset for Wearable Stress and Affect Detection","authors":"Philip Schmidt, Attila Reiss, Robert Duerichen, Claus Marberger, Kristof Van Laerhoven","year":"2018","venue":"Proc. of the 20th ACM Int. Conf. on Multimodal Interaction","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Shoaib et al., 2014] Muhammad Shoaib, Stephan Bosch, Ozlem Durmaz Incel, Hans Scholten, and Paul JM Havinga. Fusion of Smartphone Motion Sensors for Phys- ical Activity Recognition. Sensors, 14(6):10146-10176, 2014.","title":"Fusion of Smartphone Motion Sensors for Physical Activity Recognition","authors":"Shoaib","year":"2014","venue":"Sensors","doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Talukder et al., 2022] Sabera Talukder, Jennifer J Sun, Matthew Leonard, Bingni W Brunton, and Yisong Yue. Deep Neural Imputation: A Framework for Recovering In- complete Brain Recordings. arXiv:2206.08094, 2022.","title":"Deep Neural Imputation: A Framework for Recovering Incomplete Brain Recordings","authors":"Sabera Talukder, Jennifer J Sun, Matthew Leonard, Bingni W Brunton, Yisong Yue","year":"2022","venue":null,"doi":null,"url":null,"internal_url":null},{"position":33,"raw":"[Theodoridis, 2011] Theo Theodoridis. EMG Physical Ac- tion Data Set. UCI Machine Learning Repository, 2011. DOI: https://doi.org/10.24432/C53W49.","title":"EMG Physical Action Data Set","authors":"Theo Theodoridis","year":"2011","venue":"UCI Machine Learning Repository","doi":"10.24432/c53w49","url":"https://doi.org/10.24432/C53W49","internal_url":null},{"position":34,"raw":"[Villar et al., 2016] Jose R Villar, Paula Vergara, Manuel Menéndez, Enrique de la Cal, Víctor M González, and Javier Sedano. Generalized Models for the Classification of Abnormal Movements in Daily Life and its Applica- bility to Epilepsy Convulsion Recognition. International Journal of Neural Systems, 26(06):1650037, 2016.","title":"Generalized Models for the Classification of Abnormal Movements in Daily Life and its Applicability to Epilepsy Convulsion Recognition","authors":"Paula Jose R Villar, Manuel Vergara, Enrique Menéndez, De La Cal, M Víctor, Javier González, Sedano","year":"2016","venue":"International Journal of Neural Systems","doi":null,"url":null,"internal_url":null},{"position":35,"raw":"[Wilhelm et al., 2015] Mathias Wilhelm, Daniel Krakowczyk, Frank Trollmann, and Sahin Albayrak. eRing: Multiple Finger Gesture Recognition with One Ring Using an Electric Field. In Proc. Int. Work. on Sensor-based Activity Recognition and Interaction, pages 1-6, 2015.","title":"eRing: Multiple Finger Gesture Recognition with One Ring Using an Electric Field","authors":"Mathias Wilhelm, Daniel Krakowczyk, Frank Trollmann, Sahin Albayrak","year":"2015","venue":"Proc. Int. Work. on Sensor-based Activity Recognition and Interaction","doi":null,"url":null,"internal_url":null},{"position":36,"raw":"[Xu et al., 2018] Tao Xu, Pengchuan Zhang, Qiuyuan Huang, Han Zhang, Zhe Gan, Xiaolei Huang, and Xi- aodong He. AttnGAN: Fine-Grained Text to Image Gener- ation With Attentional Generative Adversarial Networks. In Proc. of the IEEE Conf. on Computer Vision and Pat- tern Recognition (CVPR), pages 1316-1324, 2018.","title":"AttnGAN: Fine-Grained Text to Image Generation With Attentional Generative Adversarial Networks","authors":"Tao Xu, Pengchuan Zhang, Qiuyuan Huang, Han Zhang, Zhe Gan, Xiaolei Huang, Xiaodong He","year":"2018","venue":"Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition (CVPR)","doi":null,"url":null,"internal_url":null},{"position":37,"raw":"[Yoon et al., 2018] Jinsung Yoon, James Jordon, and Mi- haela Schaar. GAIN: Missing Data Imputation Using Gen- erative Adversarial Nets. In Proc. Int. Conf. on Machine Learning, pages 5689-5698, 2018.","title":"GAIN: Missing Data Imputation Using Generative Adversarial Nets","authors":"Yoon","year":"2018","venue":"Proc. Int. Conf. on Machine Learning","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}