{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T13:54:55Z","timestamp":1774965295506,"version":"3.50.1"},"reference-count":54,"publisher":"Association for Computing Machinery (ACM)","issue":"2","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["Proc. ACM Interact. Mob. Wearable Ubiquitous Technol."],"published-print":{"date-parts":[[2025,6,9]]},"abstract":"<jats:p>In-bed postures offer valuable information about an individual's sleep quality and overall health conditions, particularly for patients with sleep apnea. However, current in-bed posture classification systems lack privacy-friendly and easy-to-install options. Furthermore, existing solutions do not consider variations between patients and are typically trained only once, neglecting the utilization of time consistency and unlabeled data from new patients. To address these limitations, this paper builds on a seismic sensor to introduce a novel sleep posture framework, which comprises two main components, namely, the Multi-Granularity Supervised Contrastive Learning (MGSCL) module and the ensemble Online Adaptation (oa) module. Unlike most existing contrastive learning frameworks that operate at the sample level, MGSCL leverages multi-granular information, operating not only at the sample level but also at the group level. The oa module enables the model to adapt to new patient data while ensuring time consistency in sleep posture predictions. Additionally, it quantifies model uncertainty to generate weighted predictions, further enhancing performance. Evaluated on a dataset of 100 patients collected at a clinical research center, MGSCLoa achieved an average accuracy of 91.67% and an average F1 score of 91.53% with only 40 seconds of labeled data per posture. In a Phase 2 evaluation with 11 participants over 13 nights in home settings, the framework reached an average accuracy of 85.37% and a weighted F1 score of 83.59% using just 3 minutes of labeled data per common posture for each participant. These results underscore the potential of seismic sensor-based in-bed posture classification for assessing sleep quality and related health conditions.<\/jats:p>","DOI":"10.1145\/3729464","type":"journal-article","created":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T21:21:56Z","timestamp":1750281716000},"page":"1-32","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Multi-granularity Supervised Contrastive Learning with Online Adaptation for Contactless In-bed Posture Classification"],"prefix":"10.1145","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-5601-4465","authenticated-orcid":false,"given":"Yingjian","family":"Song","sequence":"first","affiliation":[{"name":"The University of Georgia, USA, Athens, Georgia"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-8273-8532","authenticated-orcid":false,"given":"Haotian","family":"Xiang","sequence":"additional","affiliation":[{"name":"The University of Georgia, USA, Athens, Georgia"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-7051-7421","authenticated-orcid":false,"given":"Zixuan","family":"Zeng","sequence":"additional","affiliation":[{"name":"The University of Georgia, USA, Athens, Georgia"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-0904-4114","authenticated-orcid":false,"given":"Jiayu","family":"Chen","sequence":"additional","affiliation":[{"name":"The University of Georgia, USA, Athens, Georgia"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-5555-3778","authenticated-orcid":false,"given":"Yida","family":"Zhang","sequence":"additional","affiliation":[{"name":"The University of Georgia, USA, Athens, Georgia"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-0126-9244","authenticated-orcid":false,"given":"Zaid Farooq","family":"Pitafi","sequence":"additional","affiliation":[{"name":"The University of Georgia, USA, Athens, Georgia"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-5413-669X","authenticated-orcid":false,"given":"He","family":"Yang","sequence":"additional","affiliation":[{"name":"The University of Georgia, USA, Athens, Georgia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4051-1396","authenticated-orcid":false,"given":"Qin","family":"Lu","sequence":"additional","affiliation":[{"name":"The University of Georgia, USA, Athens, Georgia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5097-2113","authenticated-orcid":false,"given":"Xiang","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of North Carolina at Charlotte, USA, Athens, Georgia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1627-6549","authenticated-orcid":false,"given":"Bradley G.","family":"Phillips","sequence":"additional","affiliation":[{"name":"The University of Georgia, USA, Athens, Georgia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4246-8616","authenticated-orcid":false,"given":"Fei","family":"Dou","sequence":"additional","affiliation":[{"name":"The University of Georgia, USA, Athens, Georgia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8174-1772","authenticated-orcid":false,"given":"WenZhan","family":"Song","sequence":"additional","affiliation":[{"name":"The University of Georgia, USA, Athens, Georgia"}]}],"member":"320","published-online":{"date-parts":[[2025,6,18]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11325-022-02576-4"},{"key":"e_1_2_1_2_1","volume-title":"Monitoring cloud-native applications: Lead agile operations confidently using open source software","author":"Chakraborty Mainak","unstructured":"Mainak Chakraborty and Ajit Pratap Kundan. 2021. Grafana. In Monitoring cloud-native applications: Lead agile operations confidently using open source software. Springer, 187--240."},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/PerCom45495.2020.9127369"},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3671127.3698170"},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3604806"},{"key":"e_1_2_1_6_1","volume-title":"Xiaoli Li, and Cuntai Guan.","author":"Eldele Emadeldeen","year":"2021","unstructured":"Emadeldeen Eldele, Mohamed Ragab, Zhenghua Chen, Min Wu, Chee Keong Kwoh, Xiaoli Li, and Cuntai Guan. 2021. Time-series representation learning via temporal and contextual contrasting. arXiv preprint arXiv:2106.14112 (2021)."},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3308189"},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/EMBC.2018.8512436"},{"key":"e_1_2_1_9_1","volume-title":"Proc. Intl. Conf. Mach. Learn.","author":"Gal Yarin","year":"2016","unstructured":"Yarin Gal and Zoubin Ghahramani. 2016. Dropout as a Bayesian approximation: Representing model uncertainty in deep learning. Proc. Intl. Conf. Mach. Learn. (2016), 1050--1059."},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.3390\/biology11071030"},{"key":"e_1_2_1_11_1","volume-title":"Mengjiao Hu, Gang Chuai, and Rong Huang.","author":"Hu Dikun","year":"2024","unstructured":"Dikun Hu, Weidong Gao, Kai Keng Ang, Mengjiao Hu, Gang Chuai, and Rong Huang. 2024. Smart Sleep Monitoring: Sparse Sensor-Based Spatiotemporal CNN for Sleep Posture Detection. Sensors (Basel, Switzerland) 24, 15 (2024)."},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/LSENS.2022.3148378"},{"key":"e_1_2_1_13_1","first-page":"2427","article-title":"Test-time classifier adjustment module for model-agnostic domain generalization","volume":"34","author":"Iwasawa Yusuke","year":"2021","unstructured":"Yusuke Iwasawa and Yutaka Matsuo. 2021. Test-time classifier adjustment module for model-agnostic domain generalization. Proc. of Adv. Neural Inf. Process. Syst. 34 (2021), 2427--2440.","journal-title":"Proc. of Adv. Neural Inf. Process. Syst."},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.3390\/s21010258"},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPSN.2016.7460676"},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3131672.3131679"},{"key":"e_1_2_1_17_1","volume-title":"Side Sleeper: Benefits, Drawbacks, How to Do it, Which Side Is Best. https:\/\/www.healthline.com\/health\/side-sleeper","author":"Cherney","year":"2019","unstructured":"Cherney K. 2019. Side Sleeper: Benefits, Drawbacks, How to Do it, Which Side Is Best. https:\/\/www.healthline.com\/health\/side-sleeper"},{"key":"e_1_2_1_18_1","first-page":"18661","article-title":"Supervised contrastive learning","volume":"33","author":"Khosla Prannay","year":"2020","unstructured":"Prannay Khosla, Piotr Teterwak, Chen Wang, Aaron Sarna, Yonglong Tian, Phillip Isola, Aaron Maschinot, Ce Liu, and Dilip Krishnan. 2020. Supervised contrastive learning. Proc. of Adv. Neural Inf. Process. Syst. 33 (2020), 18661--18673.","journal-title":"Proc. of Adv. Neural Inf. Process. Syst."},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3062385"},{"key":"e_1_2_1_20_1","volume-title":"Proc. Intl. Conf. Mach. Learn. PMLR, 5606--5615","author":"Kiyasseh Dani","year":"2021","unstructured":"Dani Kiyasseh, Tingting Zhu, and David A Clifton. 2021. Clocs: Contrastive learning of cardiac signals across space, time, and patients. In Proc. Intl. Conf. Mach. Learn. PMLR, 5606--5615."},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.engreg.2022.11.003"},{"key":"e_1_2_1_22_1","volume-title":"Smart sleep monitoring system via passively sensing human vibration signals","author":"Li Fangyu","year":"2020","unstructured":"Fangyu Li, Maria Valero, Jose Clemente, Zion Tse, and Wenzhan Song. 2020. Smart sleep monitoring system via passively sensing human vibration signals. IEEE sensors journal 21, 13 (2020), 14466--14473."},{"key":"e_1_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2017.2737461"},{"key":"e_1_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2822818"},{"key":"e_1_2_1_25_1","unstructured":"A McCann. 2020. Best Sleeping Positions for Sleep Apnea. https:\/\/www.cpap.com\/blog\/best-sleeping-positions-sleep-apnea\/"},{"key":"e_1_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/EMBC.2018.8513009"},{"key":"e_1_2_1_27_1","first-page":"1","article-title":"Time series databases and influxdb","volume":"12","author":"Zehra Naqvi Syeda Noor","year":"2017","unstructured":"Syeda Noor Zehra Naqvi, Sofia Yfantidou, and Esteban Zim\u00e1nyi. 2017. Time series databases and influxdb. Studienarbeit, Universit\u00e9 Libre de Bruxelles 12 (2017), 1--44.","journal-title":"Studienarbeit, Universit\u00e9 Libre de Bruxelles"},{"key":"e_1_2_1_28_1","volume-title":"Towards stable test-time adaptation in dynamic wild world. arXiv preprint arXiv:2302.12400","author":"Niu Shuaicheng","year":"2023","unstructured":"Shuaicheng Niu, Jiaxiang Wu, Yifan Zhang, Zhiquan Wen, Yaofo Chen, Peilin Zhao, and Mingkui Tan. 2023. Towards stable test-time adaptation in dynamic wild world. arXiv preprint arXiv:2302.12400 (2023)."},{"key":"e_1_2_1_29_1","volume-title":"Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748","author":"van den Oord Aaron","year":"2018","unstructured":"Aaron van den Oord, Yazhe Li, and Oriol Vinyals. 2018. Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)."},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3055031.3055077"},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3411843"},{"key":"e_1_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2021.108397"},{"key":"e_1_2_1_33_1","unstructured":"Racotech. 2024. RGI-4.5Hz Geophone. http:\/\/www.racotech.biz\/parameter\/RGI-4.5Hz%20Geophone.pdf"},{"key":"e_1_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.5664\/jcsm.6802"},{"key":"e_1_2_1_35_1","unstructured":"Schuitenmaker. 2022. Sleeping on the left side reduces acid reflux. https:\/\/www.amsterdamumc.org\/en\/research\/news\/sleeping-on-the-left-side-reduces-acid-reflux.htm"},{"key":"e_1_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICC51166.2024.10622995"},{"key":"e_1_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2023.3316674"},{"key":"e_1_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3678514"},{"key":"e_1_2_1_39_1","volume-title":"Proc. Intl. Conf. Mach. Learn. PMLR, 9229--9248","author":"Sun Yu","year":"2020","unstructured":"Yu Sun, Xiaolong Wang, Zhuang Liu, John Miller, Alexei Efros, and Moritz Hardt. 2020. Test-time training with self-supervision for generalization under distribution shifts. In Proc. Intl. Conf. Mach. Learn. PMLR, 9229--9248."},{"key":"e_1_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICECTA.2017.8252020"},{"key":"e_1_2_1_41_1","volume-title":"Tent: Fully test-time adaptation by entropy minimization. arXiv preprint arXiv:2006.10726","author":"Wang Dequan","year":"2020","unstructured":"Dequan Wang, Evan Shelhamer, Shaoteng Liu, Bruno Olshausen, and Trevor Darrell. 2020. Tent: Fully test-time adaptation by entropy minimization. arXiv preprint arXiv:2006.10726 (2020)."},{"key":"e_1_2_1_42_1","first-page":"1","article-title":"Optimization-Free Test-Time Adaptation for Cross-Person Activity Recognition. Proc. of ACM on Intera., Mobile","volume":"7","author":"Wang Shuoyuan","year":"2024","unstructured":"Shuoyuan Wang, Jindong Wang, Huajun Xi, Bob Zhang, Lei Zhang, and Hongxin Wei. 2024. Optimization-Free Test-Time Adaptation for Cross-Person Activity Recognition. Proc. of ACM on Intera., Mobile, Wearab. and Ubiqui. Technol. 7, 4 (2024), 1--27.","journal-title":"Wearab. and Ubiqui. Technol."},{"key":"e_1_2_1_43_1","volume-title":"Proc. of Adv. Neural Inf. Process. Syst. 36","author":"Wang Yihe","year":"2024","unstructured":"Yihe Wang, Yu Han, Haishuai Wang, and Xiang Zhang. 2024. Contrast everything: A hierarchical contrastive framework for medical time-series. Proc. of Adv. Neural Inf. Process. Syst. 36 (2024)."},{"key":"e_1_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3519302"},{"key":"e_1_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPECA53709.2022.9719095"},{"key":"e_1_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3051124"},{"key":"e_1_2_1_47_1","first-page":"1","article-title":"BodyCompass: Monitoring sleep posture with wireless signals. Proc. of ACM on Intera., Mobile","volume":"4","author":"Yue Shichao","year":"2020","unstructured":"Shichao Yue, Yuzhe Yang, Hao Wang, Hariharan Rahul, and Dina Katabi. 2020. BodyCompass: Monitoring sleep posture with wireless signals. Proc. of ACM on Intera., Mobile, Wearab. and Ubiqui. Technol. 4, 2 (2020), 1--25.","journal-title":"Wearab. and Ubiqui. Technol."},{"key":"e_1_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397311"},{"key":"e_1_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i8.20881"},{"key":"e_1_2_1_50_1","first-page":"3988","article-title":"Self-supervised contrastive pre-training for time series via time-frequency consistency","volume":"35","author":"Zhang Xiang","year":"2022","unstructured":"Xiang Zhang, Ziyuan Zhao, Theodoros Tsiligkaridis, and Marinka Zitnik. 2022. Self-supervised contrastive pre-training for time series via time-frequency consistency. Proc. of Adv. Neural Inf. Process. Syst. 35 (2022), 3988--4003.","journal-title":"Proc. of Adv. Neural Inf. Process. Syst."},{"key":"e_1_2_1_51_1","volume-title":"BIBE 2019; Intl. Conf. on Biolog. Inf. and Biomed. Eng. VDE, 1--4.","author":"Zhang Yichao","year":"2019","unstructured":"Yichao Zhang, Weize Song, Zhenming Yuan, and Xiaoyan Sun. 2019. A preliminary result on sleep posture identification with BCG signals. In BIBE 2019; Intl. Conf. on Biolog. Inf. and Biomed. Eng. VDE, 1--4."},{"key":"e_1_2_1_52_1","volume-title":"Proc. Intl. Conf. Mach. Learn. PMLR, 41647--41676","author":"Zhang Yifan","year":"2023","unstructured":"Yifan Zhang, Xue Wang, Kexin Jin, Kun Yuan, Zhang Zhang, Liang Wang, Rong Jin, and Tieniu Tan. 2023. Adanpc: Exploring non-parametric classifier for test-time adaptation. In Proc. Intl. Conf. Mach. Learn. PMLR, 41647--41676."},{"key":"e_1_2_1_53_1","volume-title":"Delta: degradation-free fully test-time adaptation. arXiv preprint arXiv:2301.13018","author":"Zhao Bowen","year":"2023","unstructured":"Bowen Zhao, Chen Chen, and Shu-Tao Xia. 2023. Delta: degradation-free fully test-time adaptation. arXiv preprint arXiv:2301.13018 (2023)."},{"key":"e_1_2_1_54_1","volume-title":"Proce. Symposium (SPSympo). IEEE, 316--321","author":"Zhou Tao","year":"2021","unstructured":"Tao Zhou, Zhaoyang Xia, Xiangfeng Wang, and Feng Xu. 2021. Human sleep posture recognition based on millimeter-wave radar. In 2021 Sign. Proce. Symposium (SPSympo). IEEE, 316--321."}],"container-title":["Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3729464","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T12:20:58Z","timestamp":1755865258000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3729464"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,9]]},"references-count":54,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,6,9]]}},"alternative-id":["10.1145\/3729464"],"URL":"https:\/\/doi.org\/10.1145\/3729464","relation":{},"ISSN":["2474-9567"],"issn-type":[{"value":"2474-9567","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,9]]},"assertion":[{"value":"2025-06-18","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}