{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T15:19:18Z","timestamp":1783610358798,"version":"3.55.0"},"reference-count":57,"publisher":"Association for Computing Machinery (ACM)","issue":"1","license":[{"start":{"date-parts":[[2022,10,29]],"date-time":"2022-10-29T00:00:00Z","timestamp":1667001600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100004608","name":"Natural Science Foundation of Jiangsu Province","doi-asserted-by":"crossref","award":["BK20191371"],"award-info":[{"award-number":["BK20191371"]}],"id":[{"id":"10.13039\/501100004608","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Nature Science Foundation of China","doi-asserted-by":"crossref","award":["61962061"],"award-info":[{"award-number":["61962061"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Industry Academia Cooperation Innovation Fund Projection of Jiangsu Province","award":["BY2016001-02"],"award-info":[{"award-number":["BY2016001-02"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Embed. Comput. Syst."],"published-print":{"date-parts":[[2023,1,31]]},"abstract":"<jats:p>\n            During the past decade, human activity recognition\u00a0(\n            <jats:italic>HAR<\/jats:italic>\n            ) using wearable sensors has become a new research hot spot due to its extensive use in various application domains such as healthcare, fitness, smart homes, and eldercare. Deep neural networks, especially convolutional neural networks (\n            <jats:italic>CNNs<\/jats:italic>\n            ), have gained a lot of attention in\n            <jats:italic>HAR<\/jats:italic>\n            scenario. Despite exceptional performance,\n            <jats:italic>CNNs<\/jats:italic>\n            with heavy overhead is not the best option for\n            <jats:italic>HAR<\/jats:italic>\n            task due to the limitation of computing resource on embedded devices. As far as we know, there are many invalid filters in\n            <jats:italic>CNN<\/jats:italic>\n            that contribute very little to output. Simply pruning these invalid filters could effectively accelerate\n            <jats:italic>CNNs<\/jats:italic>\n            , but it inevitably hurts performance. In this article, we first propose a novel\n            <jats:italic>CNN<\/jats:italic>\n            for\n            <jats:italic>HAR<\/jats:italic>\n            that uses filter activation. In comparison with filter pruning that is motivated for efficient consideration, filter activation aims to activate these invalid filters from an accuracy boosting perspective. We perform extensive experiments on several public\n            <jats:italic>HAR<\/jats:italic>\n            datasets, namely, UCI-HAR\u00a0(\n            <jats:italic>UCI<\/jats:italic>\n            ), OPPORTUNITY\u00a0(\n            <jats:italic>OPPO<\/jats:italic>\n            ), UniMiB-SHAR\u00a0(\n            <jats:italic>Uni<\/jats:italic>\n            ), PAMAP2\u00a0(\n            <jats:italic>PAM2<\/jats:italic>\n            ), WISDM\u00a0(\n            <jats:italic>WIS<\/jats:italic>\n            ), and USC-HAD\u00a0(\n            <jats:italic>USC<\/jats:italic>\n            ), which show the superiority of the proposed method against existing state-of-the-art\u00a0(\n            <jats:italic>SOTA<\/jats:italic>\n            ) approaches. Ablation studies are conducted to analyze its internal mechanism. Finally, the inference speed and power consumption are evaluated on an embedded\n            <jats:italic>Raspberry Pi Model 3 B plus<\/jats:italic>\n            platform.\n          <\/jats:p>","DOI":"10.1145\/3551486","type":"journal-article","created":{"date-parts":[[2022,7,26]],"date-time":"2022-07-26T11:06:59Z","timestamp":1658833619000},"page":"1-23","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":41,"title":["Deep Ensemble Learning for Human Activity Recognition Using Wearable Sensors via Filter Activation"],"prefix":"10.1145","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6664-1172","authenticated-orcid":false,"given":"Wenbo","family":"Huang","sequence":"first","affiliation":[{"name":"Nanjing Normal University, Nanjing, Jiangsu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8749-7459","authenticated-orcid":false,"given":"Lei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Nanjing Normal University, Nanjing, Jiangsu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1795-4161","authenticated-orcid":false,"given":"Shuoyuan","family":"Wang","sequence":"additional","affiliation":[{"name":"Nanjing Normal University, Nanjing, Jiangsu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3696-9281","authenticated-orcid":false,"given":"Hao","family":"Wu","sequence":"additional","affiliation":[{"name":"Yunnan University, Kunming, Yunnan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1982-6780","authenticated-orcid":false,"given":"Aiguo","family":"Song","sequence":"additional","affiliation":[{"name":"Southeast University, Nanjing, Jiangsu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2022,10,29]]},"reference":[{"key":"e_1_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1145\/3358175"},{"key":"e_1_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i1.16103"},{"key":"e_1_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/3458750"},{"key":"e_1_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1145\/3431503"},{"key":"e_1_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1145\/3266142"},{"key":"e_1_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2022.3174816"},{"key":"e_1_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2022.3149337"},{"key":"e_1_3_1_9_2","article-title":"Semisupervised human activity recognition with radar micro-Doppler signatures","author":"Li Xinyu","year":"2021","unstructured":"Xinyu Li, Yuan He, Francesco Fioranelli, and Xiaojun Jing. 2021. Semisupervised human activity recognition with radar micro-Doppler signatures. IEEE Trans. Geosci. Rem. Sens. 60 (2021), 1\u201312.","journal-title":"IEEE Trans. Geosci. Rem. Sens."},{"key":"e_1_3_1_10_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TIM.2021.3091990","article-title":"Shallow convolutional neural networks for human activity recognition using wearable sensors","volume":"70","author":"Huang Wenbo","year":"2021","unstructured":"Wenbo Huang, Lei Zhang, Wenbin Gao, Fuhong Min, and Jun He. 2021. Shallow convolutional neural networks for human activity recognition using wearable sensors. IEEE Trans. Instrum. Measur. 70 (2021), 1\u201311.","journal-title":"IEEE Trans. Instrum. Measur."},{"key":"e_1_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"e_1_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3084827"},{"key":"e_1_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.10.013"},{"key":"e_1_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/3264947"},{"key":"e_1_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/3267242.3267286"},{"key":"e_1_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2016.04.032"},{"key":"e_1_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.5555\/2832747.2832806"},{"key":"e_1_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/BSN.2016.7516235"},{"key":"e_1_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806333"},{"key":"e_1_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2020.2972628"},{"key":"e_1_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2017.09.027"},{"key":"e_1_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2019.2911669"},{"key":"e_1_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.3390\/s16010115"},{"key":"e_1_3_1_24_2","article-title":"Pruning filters for efficient convNets","author":"Li Hao","year":"2016","unstructured":"Hao Li, Asim Kadav, Igor Durdanovic, Hanan Samet, and Hans Peter Graf. 2016. Pruning filters for efficient convNets. arXiv preprint arXiv:1608.08710 (2016).","journal-title":"arXiv preprint arXiv:1608.08710"},{"key":"e_1_3_1_25_2","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding","author":"Han Song","year":"2015","unstructured":"Song Han, Huizi Mao, and William J. Dally. 2015. Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding. arXiv preprint arXiv:1510.00149 (2015).","journal-title":"arXiv preprint arXiv:1510.00149"},{"key":"e_1_3_1_26_2","article-title":"Exploring linear relationship in feature map subspace for convNets compression","author":"Wang Dong","year":"2018","unstructured":"Dong Wang, Lei Zhou, Xueni Zhang, Xiao Bai, and Jun Zhou. 2018. Exploring linear relationship in feature map subspace for convNets compression. arXiv preprint arXiv:1803.05729 (2018).","journal-title":"arXiv preprint arXiv:1803.05729"},{"key":"e_1_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2017.08.002"},{"key":"e_1_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.107899"},{"key":"e_1_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2018.2869843"},{"key":"e_1_3_1_30_2","article-title":"SCSP: Spectral clustering filter pruning with soft self-adaption manners","author":"Zhuo Huiyuan","year":"2018","unstructured":"Huiyuan Zhuo, Xuelin Qian, Yanwei Fu, Heng Yang, and Xiangyang Xue. 2018. SCSP: Spectral clustering filter pruning with soft self-adaption manners. arXiv preprint arXiv:1806.05320 (2018).","journal-title":"arXiv preprint arXiv:1806.05320"},{"key":"e_1_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00663"},{"key":"e_1_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/3267242.3267287"},{"key":"e_1_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2019.2917225"},{"key":"e_1_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/431"},{"key":"e_1_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00454"},{"issue":"1","key":"e_1_3_1_36_2","first-page":"1","article-title":"A systematic review of smartphone-based human activity recognition methods for health research","volume":"4","author":"Straczkiewicz Marcin","year":"2021","unstructured":"Marcin Straczkiewicz, Peter James, and Jukka-Pekka Onnela. 2021. A systematic review of smartphone-based human activity recognition methods for health research. Nat. Partn. J.: Digit. Med. 4, 1 (2021), 1\u201315.","journal-title":"Nat. Partn. J.: Digit. Med."},{"key":"e_1_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1145\/3090076"},{"key":"e_1_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-35395-6_30"},{"key":"e_1_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/INSS.2010.5573462"},{"key":"e_1_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.3390\/app7101101"},{"key":"e_1_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISWC.2012.13"},{"key":"e_1_3_1_42_2","doi-asserted-by":"publisher","DOI":"10.1145\/2003653.2003656"},{"key":"e_1_3_1_43_2","doi-asserted-by":"publisher","DOI":"10.1145\/2370216.2370438"},{"key":"e_1_3_1_44_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2021.107671"},{"key":"e_1_3_1_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2020.2978772"},{"key":"e_1_3_1_46_2","doi-asserted-by":"publisher","DOI":"10.1145\/3448083"},{"key":"e_1_3_1_47_2","doi-asserted-by":"publisher","DOI":"10.1109\/THMS.2021.3086008"},{"key":"e_1_3_1_48_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i13.17416"},{"key":"e_1_3_1_49_2","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2022.3165875"},{"key":"e_1_3_1_50_2","first-page":"1","article-title":"Learning disentangled representation for mixed-reality human activity recognition with a single IMU sensor","volume":"70","author":"Xia Songpengcheng","year":"2021","unstructured":"Songpengcheng Xia, Lei Chu, Ling Pei, Zixuan Zhang, Wenxian Yu, and Robert C. Qiu. 2021. Learning disentangled representation for mixed-reality human activity recognition with a single IMU sensor. IEEE Trans. Instrum. Measur. 70 (2021), 1\u201314.","journal-title":"IEEE Trans. Instrum. Measur."},{"key":"e_1_3_1_51_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2020.114093"},{"key":"e_1_3_1_52_2","doi-asserted-by":"publisher","DOI":"10.1109\/PerComWorkshops48775.2020.9156264"},{"key":"e_1_3_1_53_2","doi-asserted-by":"publisher","DOI":"10.1109\/MSN48538.2019.00092"},{"key":"e_1_3_1_54_2","doi-asserted-by":"publisher","DOI":"10.1109\/JSYST.2022.3153503"},{"key":"e_1_3_1_55_2","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3450006"},{"key":"e_1_3_1_56_2","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2020.3013403"},{"key":"e_1_3_1_57_2","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2020.3045135"},{"key":"e_1_3_1_58_2","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3449903"}],"container-title":["ACM Transactions on Embedded Computing Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3551486","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3551486","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:00:25Z","timestamp":1750186825000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3551486"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,29]]},"references-count":57,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2023,1,31]]}},"alternative-id":["10.1145\/3551486"],"URL":"https:\/\/doi.org\/10.1145\/3551486","relation":{},"ISSN":["1539-9087","1558-3465"],"issn-type":[{"value":"1539-9087","type":"print"},{"value":"1558-3465","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,10,29]]},"assertion":[{"value":"2022-01-10","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-07-22","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-10-29","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}