{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,14]],"date-time":"2025-10-14T07:16:08Z","timestamp":1760426168298,"version":"3.41.0"},"reference-count":45,"publisher":"Association for Computing Machinery (ACM)","issue":"5s","license":[{"start":{"date-parts":[[2023,9,9]],"date-time":"2023-09-09T00:00:00Z","timestamp":1694217600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"NSF CAREER","award":["CNS-2238257"],"award-info":[{"award-number":["CNS-2238257"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Embed. Comput. Syst."],"published-print":{"date-parts":[[2023,10,31]]},"abstract":"<jats:p>Human activity recognition\u00a0(HAR) is an important component in a number of health applications, including rehabilitation, Parkinson\u2019s disease, daily activity monitoring, and fitness monitoring. State-of-the-art HAR approaches use multiple sensors on the body to accurately identify activities at runtime. These approaches typically assume that data from all sensors are available for runtime activity recognition. However, data from one or more sensors may be unavailable due to malfunction, energy constraints, or communication challenges between the sensors. Missing data can lead to significant degradation in the accuracy, thus affecting quality of service to users. A common approach for handling missing data is to train classifiers or sensor data recovery algorithms for each combination of missing sensors. However, this results in significant memory and energy overhead on resource-constrained wearable devices. In strong contrast to prior approaches, this paper presents a clustering-based approach\u00a0(CIM) to impute missing data at runtime. We first define a set of possible clusters and representative data patterns for each sensor in HAR. Then, we create and store a mapping between clusters across sensors. At runtime, when data from a sensor are missing, we utilize the stored mapping table to obtain most likely cluster for the missing sensor. The representative window for the identified cluster is then used as imputation to perform activity classification. We also provide a method to obtain imputation-aware activity prediction sets to handle uncertainty in data when using imputation. Experiments on three HAR datasets show that CIM achieves accuracy within 10% of a baseline without missing data for one missing sensor when providing single activity labels. The accuracy gap drops to less than 1% with imputation-aware classification. Measurements on a low-power processor show that CIM achieves close to 100% energy savings compared to state-of-the-art generative approaches.<\/jats:p>","DOI":"10.1145\/3609111","type":"journal-article","created":{"date-parts":[[2023,9,9]],"date-time":"2023-09-09T13:33:18Z","timestamp":1694266398000},"page":"1-26","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["CIM: A Novel Clustering-based Energy-Efficient Data Imputation Method for Human Activity Recognition"],"prefix":"10.1145","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1914-7526","authenticated-orcid":false,"given":"Dina","family":"Hussein","sequence":"first","affiliation":[{"name":"Washington State University, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1085-2189","authenticated-orcid":false,"given":"Ganapati","family":"Bhat","sequence":"additional","affiliation":[{"name":"Washington State University, USA"}]}],"member":"320","published-online":{"date-parts":[[2023,9,9]]},"reference":[{"key":"e_1_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.3390\/s19173808"},{"issue":"9","key":"e_1_3_1_3_2","doi-asserted-by":"crossref","first-page":"95","DOI":"10.1007\/s10916-014-0095-0","article-title":"Better physical activity classification using smartphone acceleration sensor","volume":"38","author":"Arif Muhammad","year":"2014","unstructured":"Muhammad Arif, Mohsin Bilal, Ahmed Kattan, and S. Iqbal Ahamed. 2014. Better physical activity classification using smartphone acceleration sensor. J. of Med. Syst. 38, 9 (2014), 95.","journal-title":"J. of Med. Syst."},{"key":"e_1_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.3390\/s20185356"},{"key":"e_1_3_1_5_2","article-title":"Generative adversarial networks in time series: A survey and taxonomy","author":"Brophy Eoin","year":"2021","unstructured":"Eoin Brophy, Zhengwei Wang, Qi She, and Tomas Ward. 2021. Generative adversarial networks in time series: A survey and taxonomy. arXiv preprint arXiv:2107.11098 (2021), 25.","journal-title":"arXiv preprint arXiv:2107.11098"},{"key":"e_1_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.3390\/s19071716"},{"key":"e_1_3_1_7_2","doi-asserted-by":"crossref","DOI":"10.1002\/9780470904848","volume-title":"Handbook of Statistical Data Editing and Imputation","author":"Waal Ton De","year":"2011","unstructured":"Ton De Waal, Jeroen Pannekoek, and Sander Scholtus. 2011. Handbook of Statistical Data Editing and Imputation. Vol. 563. John Wiley & Sons."},{"key":"e_1_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1049\/et.2015.0661"},{"key":"e_1_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1002\/mds.26642"},{"key":"e_1_3_1_10_2","volume-title":"The Elements of Statistical Learning","author":"Friedman Jerome","year":"2001","unstructured":"Jerome Friedman, Trevor Hastie, and Robert Tibshirani. 2001. The Elements of Statistical Learning, Vol. 1. Springer."},{"key":"e_1_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.06.007"},{"key":"e_1_3_1_12_2","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1007\/978-3-319-09259-1_2","article-title":"Accelerating Lloyd\u2019s algorithm for k-means clustering","author":"Hamerly Greg","year":"2015","unstructured":"Greg Hamerly and Jonathan Drake. 2015. Accelerating Lloyd\u2019s algorithm for k-means clustering. Partitional Clustering Algorithms (2015), 41\u201378.","journal-title":"Partitional Clustering Algorithms"},{"key":"e_1_3_1_13_2","article-title":"ODROID-XU3","year":"2014","unstructured":"Hardkernel. 2014. ODROID-XU3. https:\/\/www.hardkernel.com\/shop\/odroid-xu3\/ Accessed 11\/20\/2020. (2014).","journal-title":"https:\/\/www.hardkernel.com\/shop\/odroid-xu3\/ Accessed 11\/20\/2020"},{"issue":"1","key":"e_1_3_1_14_2","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1159\/000475801","article-title":"Telehealth management of parkinson\u2019s disease using wearable sensors: An exploratory study","volume":"1","author":"Heldman Dustin A.","year":"2017","unstructured":"Dustin A. Heldman, Denzil A. Harris, Timothy Felong, Kelly L. Andrzejewski, E. Ray Dorsey, Joseph P. Giuffrida, Barry Goldberg, and Michelle A. Burack. 2017. Telehealth management of parkinson\u2019s disease using wearable sensors: An exploratory study. Digital Biomarkers 1, 1 (2017), 43\u201351.","journal-title":"Digital Biomarkers"},{"key":"e_1_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.3390\/s20143811"},{"key":"e_1_3_1_16_2","first-page":"124","volume-title":"2019 Joint 8th Int. Conf. on Informatics, Electron.& Vision (ICIEV) and 2019 3rd Int. Conf. on Imaging, Vision & Pattern Recognition (icIVPR)","author":"Hossain Tahera","year":"2019","unstructured":"Tahera Hossain and Sozo Inoue. 2019. A comparative study on missing data handling using machine learning for human activity recognition. In 2019 Joint 8th Int. Conf. on Informatics, Electron.& Vision (ICIEV) and 2019 3rd Int. Conf. on Imaging, Vision & Pattern Recognition (icIVPR). 124\u2013129."},{"issue":"8","key":"e_1_3_1_17_2","first-page":"1185","article-title":"Analysis of impairments influencing gait velocity and asymmetry of hemiplegic patients after mild to moderate stroke","volume":"84","author":"Hsu An-Lun","year":"2003","unstructured":"An-Lun Hsu, Pei-Fang Tang, and Mei-Hwa Jan. 2003. Analysis of impairments influencing gait velocity and asymmetry of hemiplegic patients after mild to moderate stroke. Arch. Phys. Med. Rehabil. 84, 8 (2003), 1185\u20131193.","journal-title":"Arch. Phys. Med. Rehabil."},{"key":"e_1_3_1_18_2","first-page":"1","volume-title":"Proc. Int. Conf. on Comput.-Aided Des. (ICCAD\u201922)","author":"Hussein Dina","year":"2022","unstructured":"Dina Hussein, Taha Belkhouja, Ganapati Bhat, and Janardhan Rao Doppa. 2022. Reliable machine learning for wearable activity monitoring: Novel algorithms and theoretical guarantees. In Proc. Int. Conf. on Comput.-Aided Des. (ICCAD\u201922). 1\u20139."},{"key":"e_1_3_1_19_2","doi-asserted-by":"crossref","first-page":"84","DOI":"10.23919\/DATE54114.2022.9774548","volume-title":"2022 Design, Automation & Test in Europe Conference & Exhibition (DATE\u201922)","author":"Hussein Dina","year":"2022","unstructured":"Dina Hussein, Aaryan Jain, and Ganapati Bhat. 2022. Robust human activity recognition using generative adversarial imputation networks. In 2022 Design, Automation & Test in Europe Conference & Exhibition (DATE\u201922). 84\u201387."},{"key":"e_1_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4614-7138-7"},{"key":"e_1_3_1_21_2","volume-title":"The Int. Conf. on Learning Representations (Poster\u201915)","author":"Kingma Diederik P.","year":"2015","unstructured":"Diederik P. Kingma and Jimmy Ba. 2015. Adam: A method for stochastic optimization. In The Int. Conf. on Learning Representations (Poster\u201915)."},{"key":"e_1_3_1_22_2","doi-asserted-by":"crossref","first-page":"1654","DOI":"10.1109\/INFCOM.2013.6566962","volume-title":"2013 Proceedings IEEE INFOCOM","author":"Kong Linghe","year":"2013","unstructured":"Linghe Kong, Mingyuan Xia, Xiao-Yang Liu, Min-You Wu, and Xue Liu. 2013. Data loss and reconstruction in sensor networks. In 2013 Proceedings IEEE INFOCOM. 1654\u20131662."},{"issue":"4","key":"e_1_3_1_23_2","article-title":"Sensor placement variations in wearable activity recognition","volume":"13","author":"Kunze Kai","year":"2014","unstructured":"Kai Kunze and Paul Lukowicz. 2014. Sensor placement variations in wearable activity recognition. IEEE Perv. Comput. 13, 4 (2014).","journal-title":"IEEE Perv. Comput."},{"key":"e_1_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/1964897.1964918"},{"key":"e_1_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/SURV.2012.110112.00192"},{"issue":"3","key":"e_1_3_1_26_2","first-page":"1","article-title":"Handling missing sensors in topology-aware IoT applications with gated graph neural network","volume":"4","author":"Liu Shengzhong","year":"2020","unstructured":"Shengzhong Liu et\u00a0al. 2020. Handling missing sensors in topology-aware IoT applications with gated graph neural network. Proc. Interactive, Mobile, Wearable and Ubiquitous Tech. 4, 3 (2020), 1\u201331.","journal-title":"Proc. Interactive, Mobile, Wearable and Ubiquitous Tech."},{"key":"e_1_3_1_27_2","first-page":"1603","volume-title":"Proc. Advances in Neural Information Processing Systems","author":"Luo Yonghong","year":"2018","unstructured":"Yonghong Luo, Xiangrui Cai, Ying Zhang, Jun Xu, and Xiaojie Yuan. 2018. Multivariate time series imputation with generative adversarial networks. In Proc. Advances in Neural Information Processing Systems. 1603\u20131614."},{"key":"e_1_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1002\/mds.26673"},{"key":"e_1_3_1_29_2","first-page":"2442","volume-title":"2022 44th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC\u201922)","author":"Mamun Abdullah","year":"2022","unstructured":"Abdullah Mamun, Seyed Iman Mirzadeh, and Hassan Ghasemzadeh. 2022. Designing deep neural networks robust to sensor failure in mobile health environments. In 2022 44th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC\u201922). 2442\u20132446."},{"key":"e_1_3_1_30_2","article-title":"Nvidia Tesla T4 GPU","year":"2022","unstructured":"Nvidia. 2022. Nvidia Tesla T4 GPU. [Online] https:\/\/www.nvidia.com\/en-in\/data-center\/tesla-t4\/, accessed May 28, 2023. (2022).","journal-title":"[Online] https:\/\/www.nvidia.com\/en-in\/data-center\/tesla-t4\/, accessed May 28, 2023"},{"key":"e_1_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/3224207.3224212"},{"key":"e_1_3_1_32_2","first-page":"621","volume-title":"Proc. 26th Asia and South Pacific Des. Autom. Conf.","author":"Odema Mohanad","year":"2021","unstructured":"Mohanad Odema, Nafiul Rashid, and Mohammad Abdullah Al Faruque. 2021. Energy-aware design methodology for myocardial infarction detection on low-power wearable devices. In Proc. 26th Asia and South Pacific Des. Autom. Conf.621\u2013626."},{"key":"e_1_3_1_33_2","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume":"32","author":"Paszke Adam","year":"2019","unstructured":"Adam Paszke et\u00a0al. 2019. Pytorch: An imperative style, high-performance deep learning library. Proc. Advances in Neural Information Processing Systems 32 (2019).","journal-title":"Proc. Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.3390\/fi12090155"},{"key":"e_1_3_1_35_2","first-page":"59","volume-title":"Proc. Int. Conf. on ICT for Smart Society","author":"Prabowo Okyza M.","year":"2016","unstructured":"Okyza M. Prabowo, Kusprasapta Mutijarsa, and Suhono Harso Supangkat. 2016. Missing data handling using machine learning for human activity recognition on mobile device. In Proc. Int. Conf. on ICT for Smart Society. 59\u201362."},{"key":"e_1_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2022.3140465"},{"key":"e_1_3_1_37_2","first-page":"108","volume-title":"Int. Symp. Wearable Comput.","author":"Reiss Attila","year":"2012","unstructured":"Attila Reiss and Didier Stricker. 2012. Introducing a new benchmarked dataset for activity monitoring. In Int. Symp. Wearable Comput.108\u2013109."},{"key":"e_1_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.3390\/s18092967"},{"key":"e_1_3_1_39_2","first-page":"1","volume-title":"Proc. Int. Conf. on Hardware\/Software Codesign and System Synthesis","author":"Samie Farzad","year":"2016","unstructured":"Farzad Samie, Lars Bauer, and J\u00f6rg Henkel. 2016. IoT technologies for embedded computing: A survey. In Proc. Int. Conf. on Hardware\/Software Codesign and System Synthesis. 1\u201310."},{"issue":"3","key":"e_1_3_1_40_2","article-title":"A tutorial on conformal prediction","volume":"9","author":"Shafer Glenn","year":"2008","unstructured":"Glenn Shafer and Vladimir Vovk. 2008. A tutorial on conformal prediction. J. Machine Learn. Research 9, 3 (2008).","journal-title":"J. Machine Learn. Research"},{"key":"e_1_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.3390\/s140610146"},{"key":"e_1_3_1_42_2","article-title":"Deep neural imputation: A framework for recovering incomplete brain recordings","author":"Talukder Sabera","year":"2022","unstructured":"Sabera Talukder, Jennifer J. Sun, Matthew Leonard, Bingni W. Brunton, and Yisong Yue. 2022. Deep neural imputation: A framework for recovering incomplete brain recordings. arXiv:2206.08094 (2022).","journal-title":"arXiv:2206.08094"},{"key":"e_1_3_1_43_2","article-title":"Conformal prediction for dynamic time-series","author":"Xu Chen","year":"2020","unstructured":"Chen Xu and Yao Xie. 2020. Conformal prediction for dynamic time-series. arXiv preprint arXiv:2010.09107 (2020).","journal-title":"arXiv preprint arXiv:2010.09107"},{"key":"e_1_3_1_44_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-013-1501-1"},{"key":"e_1_3_1_45_2","first-page":"5689","volume-title":"Proc. Int. Conf. on Machine Learn.","author":"Yoon Jinsung","year":"2018","unstructured":"Jinsung Yoon, James Jordon, and Mihaela Schaar. 2018. GAIN: Missing data imputation using generative adversarial nets. In Proc. Int. Conf. on Machine Learn.5689\u20135698."},{"key":"e_1_3_1_46_2","first-page":"233","volume-title":"Proc. Int. Symp. on Comput. Science in Sports","author":"Zhao Zhao","year":"2016","unstructured":"Zhao Zhao, S. Ali Etemad, and Ali Arya. 2016. Gamification of exercise and fitness using wearable activity trackers. In Proc. Int. Symp. on Comput. Science in Sports. 233\u2013240."}],"container-title":["ACM Transactions on Embedded Computing Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3609111","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3609111","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T17:48:58Z","timestamp":1750182538000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3609111"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,9]]},"references-count":45,"journal-issue":{"issue":"5s","published-print":{"date-parts":[[2023,10,31]]}},"alternative-id":["10.1145\/3609111"],"URL":"https:\/\/doi.org\/10.1145\/3609111","relation":{},"ISSN":["1539-9087","1558-3465"],"issn-type":[{"type":"print","value":"1539-9087"},{"type":"electronic","value":"1558-3465"}],"subject":[],"published":{"date-parts":[[2023,9,9]]},"assertion":[{"value":"2023-03-23","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-07-13","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-09-09","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}