{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T15:48:07Z","timestamp":1781797687428,"version":"3.54.5"},"reference-count":63,"publisher":"Association for Computing Machinery (ACM)","issue":"6","license":[{"start":{"date-parts":[[2022,11,30]],"date-time":"2022-11-30T00:00:00Z","timestamp":1669766400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Embed. Comput. Syst."],"published-print":{"date-parts":[[2022,11,30]]},"abstract":"<jats:p>Mental health problems impact the quality of life of millions of people around the world. However, diagnosis of mental health disorders is a challenging problem that often relies on self-reporting by patients about their behavioral patterns and social interactions. Therefore, there is a need for new strategies for diagnosis and daily monitoring of mental health conditions. The recent introduction of body-area networks consisting of a plethora of accurate sensors embedded in smartwatches and smartphones and edge-compatible deep neural networks (DNNs) points toward a possible solution. Such wearable medical sensors (WMSs) enable continuous monitoring of physiological signals in a passive and non-invasive manner. However, disease diagnosis based on WMSs and DNNs, and their deployment on edge devices, such as smartphones, remains a challenging problem. These challenges stem from the difficulty of feature engineering and knowledge distillation from the raw sensor data, as well as the computational and memory constraints of battery-operated edge devices. To this end, we propose a framework called MHDeep that utilizes commercially available WMSs and efficient DNN models to diagnose three important mental health disorders: schizoaffective, major depressive, and bipolar. MHDeep uses eight different categories of data obtained from sensors integrated in a smartwatch and smartphone. These categories include various physiological signals and additional information on motion patterns and environmental variables related to the wearer. MHDeep eliminates the need for manual feature engineering by directly operating on the data streams obtained from participants. Because the amount of data is limited, MHDeep uses a synthetic data generation module to augment real data with synthetic data drawn from the same probability distribution. We use the synthetic dataset to pre-train the weights of the DNN models, thus imposing a prior on the weights. We use a grow-and-prune DNN synthesis approach to learn both architecture and weights during the training process. We use three different data partitions to evaluate the MHDeep models trained with data collected from 74 individuals. We conduct two types of evaluations: at the data instance level and at the patient level. MHDeep achieves an average test accuracy, across the three data partitions, of 90.4%, 87.3%, and 82.4%, respectively, for classifications between healthy and schizoaffective disorder instances, healthy and major depressive disorder instances, and healthy and bipolar disorder instances. At the patient level, MHDeep DNN models achieve an accuracy of 100%, 100%, and 90.0% for the three mental health disorders, respectively, based on inference that uses 40, 16, and 22 minutes of sensor data collection from each patient.<\/jats:p>","DOI":"10.1145\/3527170","type":"journal-article","created":{"date-parts":[[2022,3,26]],"date-time":"2022-03-26T11:20:19Z","timestamp":1648293619000},"page":"1-22","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":55,"title":["MHDeep: Mental Health Disorder Detection System Based on Wearable Sensors and Artificial Neural Networks"],"prefix":"10.1145","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4297-2097","authenticated-orcid":false,"given":"Shayan","family":"Hassantabar","sequence":"first","affiliation":[{"name":"Princeton University, Princeton, NJ, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4145-1126","authenticated-orcid":false,"given":"Joe","family":"Zhang","sequence":"additional","affiliation":[{"name":"Princeton University, Princeton, NJ, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6481-6389","authenticated-orcid":false,"given":"Hongxu","family":"Yin","sequence":"additional","affiliation":[{"name":"Princeton University, Princeton, NJ, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1539-0369","authenticated-orcid":false,"given":"Niraj K.","family":"Jha","sequence":"additional","affiliation":[{"name":"Princeton University, Princeton, NJ, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2022,12,12]]},"reference":[{"key":"e_1_3_1_2_2","unstructured":"2020. Empatica E4 connect portal. https:\/\/www.empatica.com\/connect."},{"key":"e_1_3_1_3_2","unstructured":"2020. Number of connected wearable devices worldwide from 2016 to 2022. https:\/\/www.statista.com\/statistics\/487291\/global-connected-wearable-devices\/."},{"key":"e_1_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2018.04.012"},{"key":"e_1_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/MCE.2017.2746096"},{"key":"e_1_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10916-012-9898-z"},{"key":"e_1_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1186\/1756-0500-3-149"},{"issue":"1","key":"e_1_3_1_8_2","first-page":"1","article-title":"Identifying signals associated with psychiatric illness utilizing language and images posted to Facebook","volume":"6","author":"Birnbaum Michael L.","year":"2020","unstructured":"Michael L. Birnbaum, Raquel Norel, Anna Van Meter, Asra F. Ali, Elizabeth Arenare, Elif Eyigoz, Carla Agurto, Nicole Germano, John M. Kane, and Guillermo A. Cecchi. 2020. Identifying signals associated with psychiatric illness utilizing language and images posted to Facebook. Nature Schizophrenia 6, 1 (2020), 1\u201310.","journal-title":"Nature Schizophrenia"},{"key":"e_1_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1111\/j.1559-1816.1986.tb01135.x"},{"key":"e_1_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1111\/pcn.12178"},{"key":"e_1_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.5555\/1622407.1622416"},{"key":"e_1_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1177\/1178222618792860"},{"key":"e_1_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1093\/clipsy.7.1.48"},{"key":"e_1_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.psychres.2014.04.028"},{"key":"e_1_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2019.2914438"},{"key":"e_1_3_1_16_2","volume-title":"Proc. IEEE Conf. Computer Vision and Pattern Recognition","author":"Dai Xiaoliang","year":"2019","unstructured":"Xiaoliang Dai, Peizhao Zhang, Bichen Wu, Hongxu Yin, Fei Sun, Yanghan Wang, Marat Dukhan, Yunqing Hu, Yiming Wu, Yangqing Jia, Peter Vajda, Matt Uyttendaele, and Niraj K. Jha. 2019. ChamNet: Towards efficient network design through platform-aware model adaptation. In Proc. IEEE Conf. Computer Vision and Pattern Recognition."},{"key":"e_1_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-clinpsy-032816-045037"},{"key":"e_1_3_1_18_2","first-page":"24","volume-title":"Proc. Data Science with Human in the Loop: Language Advances","author":"Enayati Saman","year":"2021","unstructured":"Saman Enayati, Ziyu Yang, Benjamin Lu, and Slobodan Vucetic. 2021. A visualization approach for rapid labeling of clinical notes for smoking status extraction. In Proc. Data Science with Human in the Loop: Language Advances. 24\u201330."},{"key":"e_1_3_1_19_2","volume-title":"Proc. Int. Conf. Computer Science and Mechanical Automation","author":"Geng Xiang-Fei","year":"2017","unstructured":"Xiang-Fei Geng and Jun-Hai Xu. 2017. Application of autoencoder in depression diagnosis. In Proc. Int. Conf. Computer Science and Mechanical Automation."},{"key":"e_1_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1136\/eb-2017-102688"},{"key":"e_1_3_1_21_2","first-page":"1","volume-title":"Proc. Augmented Human Int. Conf.","author":"Gruenerbl Agnes","year":"2014","unstructured":"Agnes Gruenerbl, Venet Osmani, Gernot Bahle, Jose C. Carrasco, Stefan Oehler, Oscar Mayora, Christian Haring, and Paul Lukowicz. 2014. Using smart phone mobility traces for the diagnosis of depressive and manic episodes in bipolar patients. In Proc. Augmented Human Int. Conf.1\u20138."},{"key":"e_1_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2014.2343154"},{"key":"e_1_3_1_23_2","volume-title":"Proc. Int. Conf. Learning Representations","author":"Han Song","year":"2016","unstructured":"Song Han, Huizi Mao, and William J. Dally. 2016. Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman Coding. In Proc. Int. Conf. Learning Representations."},{"key":"e_1_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.chaos.2020.110170"},{"key":"e_1_3_1_25_2","article-title":"STEERAGE: Synthesis of neural networks using architecture search and grow-and-prune methods","author":"Hassantabar Shayan","year":"2019","unstructured":"Shayan Hassantabar, Xiaoliang Dai, and Niraj K. Jha. 2019. STEERAGE: Synthesis of neural networks using architecture search and grow-and-prune methods. arXiv preprint arXiv:1912.05831 (2019).","journal-title":"arXiv preprint arXiv:1912.05831"},{"key":"e_1_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2021.3130228"},{"key":"e_1_3_1_27_2","article-title":"TUTOR: Training neural networks using decision rules as model priors","author":"Hassantabar Shayan","year":"2020","unstructured":"Shayan Hassantabar, Prerit Terway, and Niraj K. Jha. 2020. TUTOR: Training neural networks using decision rules as model priors. arXiv preprint arXiv:2010.05429 (2020).","journal-title":"arXiv preprint arXiv:2010.05429"},{"key":"e_1_3_1_28_2","article-title":"SCANN: Synthesis of compact and accurate neural networks","author":"Hassantabar Shayan","year":"2021","unstructured":"Shayan Hassantabar, Zeyu Wang, and Niraj K. Jha. 2021. SCANN: Synthesis of compact and accurate neural networks. IEEE Trans. Computer-Aided Design of Integrated Circuits and Systems (2021).","journal-title":"IEEE Trans. Computer-Aided Design of Integrated Circuits and Systems"},{"key":"e_1_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.physbeh.2015.09.032"},{"key":"e_1_3_1_30_2","first-page":"225","volume-title":"Proc. Int. Conf. Intelligent Computing","author":"Kuang Deping","year":"2014","unstructured":"Deping Kuang, Xiaojiao Guo, Xiu An, Yilu Zhao, and Lianghua He. 2014. Discrimination of ADHD based on fMRI data with deep belief network. In Proc. Int. Conf. Intelligent Computing. 225\u2013232."},{"key":"e_1_3_1_31_2","first-page":"27","volume-title":"Proc. Int. Conf. Cloud Computing and Big Data","author":"Kuang Deping","year":"2014","unstructured":"Deping Kuang and Lianghua He. 2014. Classification on ADHD with deep learning. In Proc. Int. Conf. Cloud Computing and Big Data. 27\u201332."},{"key":"e_1_3_1_32_2","volume-title":"The Diagnostic and Statistical Manual of Mental Disorders","author":"Lehman Jill Fain","year":"2000","unstructured":"Jill Fain Lehman. 2000. The Diagnostic and Statistical Manual of Mental Disorders. Am. Psychiatric Assoc."},{"key":"e_1_3_1_33_2","first-page":"507","volume-title":"Proc. Int. Conf. Multimedia","author":"Lin Huijie","year":"2014","unstructured":"Huijie Lin, Jia Jia, Quan Guo, Yuanyuan Xue, Qi Li, Jie Huang, Lianhong Cai, and Ling Feng. 2014. User-level psychological stress detection from social media using deep neural network. In Proc. Int. Conf. Multimedia. 507\u2013516."},{"key":"e_1_3_1_34_2","volume-title":"Proc. Int. Workshop Wearable and Implantable Body Sensor Networks","author":"Malan David J.","year":"2004","unstructured":"David J. Malan, Thaddeus Fulford-Jones, Matt Welsh, and Steve Moulton. 2004. CodeBlue: An ad hoc sensor network infrastructure for emergency medical care. In Proc. Int. Workshop Wearable and Implantable Body Sensor Networks."},{"key":"e_1_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.pmcj.2016.01.008"},{"issue":"12","key":"e_1_3_1_36_2","first-page":"2037","article-title":"Analyse power consumption by mobile applications using fuzzy clustering approach","volume":"31","author":"Mehrotra D.","year":"2018","unstructured":"D. Mehrotra, D. Nagpal, R. Srivastava, and R. Nagpal. 2018. Analyse power consumption by mobile applications using fuzzy clustering approach. Int. J. Engineering 31, 12 (2018), 2037\u20132043.","journal-title":"Int. J. Engineering"},{"key":"e_1_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbx044"},{"key":"e_1_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-clinpsy-032816-044949"},{"key":"e_1_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jhealeco.2019.102240"},{"key":"e_1_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.3390\/jcm3030959"},{"key":"e_1_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.1017\/S0033291716002166"},{"key":"e_1_3_1_42_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2017.04.001"},{"key":"e_1_3_1_43_2","doi-asserted-by":"publisher","DOI":"10.1038\/srep38897"},{"key":"e_1_3_1_44_2","doi-asserted-by":"publisher","DOI":"10.1111\/jcpp.12381"},{"key":"e_1_3_1_45_2","first-page":"1","article-title":"Instagram photos reveal predictive markers of depression","volume":"6","author":"Reece Andrew G.","year":"2017","unstructured":"Andrew G. Reece and Christopher M. Danforth. 2017. Instagram photos reveal predictive markers of depression. EPJ Data Science 6 (2017), 1\u201312.","journal-title":"EPJ Data Science"},{"key":"e_1_3_1_46_2","volume-title":"Proc. CEUR Workshop","author":"Sadeque Farig","year":"2017","unstructured":"Farig Sadeque, Dongfang Xu, and Steven Bethard. 2017. UArizona at the CLEF eRisk 2017 pilot task: Linear and recurrent models for early depression detection. In Proc. CEUR Workshop, Vol. 1866. NIH Public Access."},{"key":"e_1_3_1_47_2","first-page":"4510","volume-title":"Proc. IEEE\/CVF Conf. Computer Vision and Pattern Recognition","author":"Sandler Mark","year":"2018","unstructured":"Mark Sandler, Andrew Howard, Menglong Zhu, Andrey Zhmoginov, and Liang-Chieh Chen. 2018. MobileNet v2: Inverted residuals and linear bottlenecks. In Proc. IEEE\/CVF Conf. Computer Vision and Pattern Recognition. 4510\u20134520."},{"key":"e_1_3_1_48_2","doi-asserted-by":"publisher","DOI":"10.1186\/s12888-017-1551-4"},{"key":"e_1_3_1_49_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2013.08.053"},{"key":"e_1_3_1_50_2","doi-asserted-by":"publisher","DOI":"10.1162\/106365602320169811"},{"key":"e_1_3_1_51_2","doi-asserted-by":"publisher","DOI":"10.1093\/ije\/dyu038"},{"key":"e_1_3_1_52_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41398-020-0780-3"},{"key":"e_1_3_1_53_2","first-page":"2820","volume-title":"Proc. IEEE Conf. Computer Vision and Pattern Recognition","author":"Tan Mingxing","year":"2019","unstructured":"Mingxing Tan, Bo Chen, Ruoming Pang, Vijay Vasudevan, Mark Sandler, Andrew Howard, and Quoc V. Le. 2019. MnasNet: Platform-aware neural architecture search for mobile. In Proc. IEEE Conf. Computer Vision and Pattern Recognition. 2820\u20132828."},{"key":"e_1_3_1_54_2","first-page":"1924","volume-title":"Proc. Int. Conf. Move to Meaningful Internet Systems","author":"Wac Katarzyna","year":"2006","unstructured":"Katarzyna Wac, Aart Van Halteren, and Dimitri Konstantas. 2006. QoS-predictions service: Infrastructural support for proactive QoS-and context-aware mobile services (position paper). In Proc. Int. Conf. Move to Meaningful Internet Systems. Springer, 1924\u20131933."},{"key":"e_1_3_1_55_2","first-page":"10734","volume-title":"Proc. IEEE Conf. Computer Vision and Pattern Recognition","author":"Wu Bichen","year":"2019","unstructured":"Bichen Wu, Xiaoliang Dai, Peizhao Zhang, Yanghan Wang, Fei Sun, Yiming Wu, Yuandong Tian, Peter Vajda, Yangqing Jia, and Kurt Keutzer. 2019. FBNet: Hardware-aware efficient convnet design via differentiable neural architecture search. In Proc. IEEE Conf. Computer Vision and Pattern Recognition. 10734\u201310742."},{"key":"e_1_3_1_56_2","first-page":"9127","volume-title":"Proc. IEEE Conf. Computer Vision and Pattern Recognition","author":"Wu Bichen","year":"2018","unstructured":"Bichen Wu, Alvin Wan, Xiangyu Yue, Peter Jin, Sicheng Zhao, Noah Golmant, Amir Gholaminejad, Joseph Gonzalez, and Kurt Keutzer. 2018. Shift: A zero flop, zero parameter alternative to spatial convolutions. In Proc. IEEE Conf. Computer Vision and Pattern Recognition. 9127\u20139135."},{"key":"e_1_3_1_57_2","first-page":"97","volume-title":"Proc. Int. Conf. Cyber-Physical Systems","author":"Xue Yuankun","year":"2017","unstructured":"Yuankun Xue and Paul Bogdan. 2017. Constructing compact causal mathematical models for complex dynamics. In Proc. Int. Conf. Cyber-Physical Systems. 97\u2013107."},{"key":"e_1_3_1_58_2","first-page":"1181","volume-title":"Proc. Allerton Conf. Communication, Control, and Computing","author":"Xue Yuankun","year":"2016","unstructured":"Yuankun Xue, Sergio Pequito, Joana R. Coelho, Paul Bogdan, and George J. Pappas. 2016. Minimum number of sensors to ensure observability of physiological systems: A case study. In Proc. Allerton Conf. Communication, Control, and Computing. 1181\u20131188."},{"key":"e_1_3_1_59_2","first-page":"642","volume-title":"Proc. Design, Automation & Test in Europe Conf. & Exhibition","author":"Xue Yuankun","year":"2016","unstructured":"Yuankun Xue, Saul Rodriguez, and Paul Bogdan. 2016. A spatio-temporal fractal model for a CPS approach to brain-machine-body interfaces. In Proc. Design, Automation & Test in Europe Conf. & Exhibition. 642\u2013647."},{"issue":"1","key":"e_1_3_1_60_2","first-page":"1","article-title":"An in silico deep learning approach to multi-epitope vaccine design: A SARS-CoV-2 case study","volume":"11","author":"Yang Zikun","year":"2021","unstructured":"Zikun Yang, Paul Bogdan, and Shahin Nazarian. 2021. An in silico deep learning approach to multi-epitope vaccine design: A SARS-CoV-2 case study. Scientific Reports 11, 1 (2021), 1\u201321.","journal-title":"Scientific Reports"},{"key":"e_1_3_1_61_2","doi-asserted-by":"publisher","DOI":"10.1561\/1000000054"},{"key":"e_1_3_1_62_2","article-title":"DiabDeep: Pervasive diabetes diagnosis based on wearable medical sensors and efficient neural networks","author":"Yin Hongxu","year":"2019","unstructured":"Hongxu Yin, Bilal Mukadam, Xiaoliang Dai, and Niraj K. Jha. 2019. DiabDeep: Pervasive diabetes diagnosis based on wearable medical sensors and efficient neural networks. IEEE Trans. Emerging Topics in Computing (2019).","journal-title":"IEEE Trans. Emerging Topics in Computing"},{"key":"e_1_3_1_63_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ebiom.2018.03.017"},{"key":"e_1_3_1_64_2","volume-title":"Proc. Int. Conf. Learning Representations","author":"Zoph Barret","year":"2017","unstructured":"Barret Zoph and Quoc V. Le. 2017. Neural architecture search with reinforcement learning. In Proc. Int. Conf. Learning Representations."}],"container-title":["ACM Transactions on Embedded Computing Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3527170","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3527170","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T17:51:01Z","timestamp":1750182661000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3527170"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,30]]},"references-count":63,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2022,11,30]]}},"alternative-id":["10.1145\/3527170"],"URL":"https:\/\/doi.org\/10.1145\/3527170","relation":{},"ISSN":["1539-9087","1558-3465"],"issn-type":[{"value":"1539-9087","type":"print"},{"value":"1558-3465","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,11,30]]},"assertion":[{"value":"2021-07-27","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-03-14","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-12-12","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}