ABSTRACT
Stress is a common problem in modern life that can bring both psychological and physical disorder. Wearable sensors are commonly used to study the relationship between physical records and mental status. Although sensor data generated by wearable devices provides an opportunity to identify stress in people for predictive medicine, in practice, the data are typically complicated and vague and also often fragmented. In this paper, we propose DataCompletion with Diurnal Regularizers (DCDR) and TemporallyHierarchical Attention Network (THAN) to address the fragmented data issue and predict human stress level with recovered sensor data. We model fragmentation as a sparsity issue. The nuclear norm minimization method based on the low-rank assumption is first applied to derive unobserved sensor data with diurnal patterns of human behaviors. A hierarchical recurrent neural network with the attention mechanism then models temporally structural information in the reconstructed sensor data, thereby inferring the predicted stress level. Data for this study were from 75 undergraduate students (taken from a sample of a larger study) who provided sensor data from smart wristbands. They also completed weekly stress surveys as ground-truth labels about their stress levels. This survey lasted 12 weeks and the sensor records are also in this period. The experimental results demonstrate that our approach significantly outperforms conventional methods in both data completion and stress level prediction. Moreover, an in-depth analysis further shows the effectiveness and robustness of our approach.
- Mart'in Abadi, Paul Barham, Jianmin Chen, Zhifeng Chen, Andy Davis, Jeffrey Dean, Matthieu Devin, Sanjay Ghemawat, Geoffrey Irving, Michael Isard, et almbox. 2016. Tensorflow: A system for large-scale machine learning. In 12th $$USENIX$$ Symposium on Operating Systems Design and Implementation ($$OSDI$$ 16) . 265--283.Google ScholarDigital Library
- Eirik Årsand, Miroslav Muzny, Meghan Bradway, Jan Muzik, and Gunnar Hartvigsen. 2015. Performance of the first combined smartwatch and smartphone diabetes diary application study. Journal of diabetes science and technology , Vol. 9, 3 (2015), 556--563.Google ScholarCross Ref
- American Psychological Association et almbox. 2017. Stress in America: The state of our nation. Stress in AmericaTM Survey (2017).Google Scholar
- Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio. 2014. Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 (2014).Google Scholar
- Jorn Bakker, Mykola Pechenizkiy, and Natalia Sidorova. 2011. What's your current stress level? Detection of stress patterns from GSR sensor data. In 2011 IEEE 11th international conference on data mining workshops. IEEE, 573--580.Google ScholarDigital Library
- Andrey Bogomolov, Bruno Lepri, Michela Ferron, Fabio Pianesi, and Alex Sandy Pentland. 2014. Daily stress recognition from mobile phone data, weather conditions and individual traits. In Proceedings of the 22nd ACM international conference on Multimedia. ACM, 477--486.Google ScholarDigital Library
- Aeron M Buchanan and Andrew W Fitzgibbon. 2005. Damped newton algorithms for matrix factorization with missing data. In 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) , Vol. 2. IEEE, 316--322.Google ScholarDigital Library
- Jian-Feng Cai, Emmanuel J Candès, and Zuowei Shen. 2010. A singular value thresholding algorithm for matrix completion. SIAM Journal on Optimization , Vol. 20, 4 (2010), 1956--1982.Google ScholarCross Ref
- Emmanuel J Candes and Yaniv Plan. 2010. Matrix completion with noise. Proc. IEEE , Vol. 98, 6 (2010), 925--936.Google ScholarCross Ref
- Emmanuel J Candès and Terence Tao. 2009. The power of convex relaxation: Near-optimal matrix completion. arXiv preprint arXiv:0903.1476 (2009).Google Scholar
- Luca Canzian and Mirco Musolesi. 2015. Trajectories of depression: unobtrusive monitoring of depressive states by means of smartphone mobility traces analysis. In Proceedings of the 2015 ACM international joint conference on pervasive and ubiquitous computing. ACM, 1293--1304.Google ScholarDigital Library
- Jinhui Chen and Jian Yang. 2013. Low-Rank Matrix Completion Based on Maximum Likelihood Estimation. In 2013 2nd IAPR Asian Conference on Pattern Recognition. IEEE, 261--265.Google Scholar
- Kemeng Chen, Wolfgang Fink, Janet Roveda, Richard D Lane, John Allen, and Johnny Vanuk. 2015. Wearable sensor based stress management using integrated respiratory and ECG waveforms. In 2015 IEEE 12th International Conference on Wearable and Implantable Body Sensor Networks (BSN). IEEE, 1--6.Google ScholarCross Ref
- Bo Cheng. 2011. Emotion recognition from physiological signals using AdaBoost. In International Conference on Applied Informatics and Communication. Springer, 412--417.Google ScholarCross Ref
- Mohamed Amine Chikh, Meryem Saidi, and Nesma Settouti. 2012. Diagnosis of diabetes diseases using an artificial immune recognition system2 (AIRS2) with fuzzy k-nearest neighbor. Journal of medical systems , Vol. 36, 5 (2012), 2721--2729.Google ScholarDigital Library
- Kyunghyun Cho, Bart Van Merriënboer, Caglar Gulcehre, Dzmitry Bahdanau, Fethi Bougares, Holger Schwenk, and Yoshua Bengio. 2014. Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv preprint arXiv:1406.1078 (2014).Google Scholar
- Mostafa Dehghani, Sascha Rothe, Enrique Alfonseca, and Pascal Fleury. 2017. Learning to attend, copy, and generate for session-based query suggestion. In Proceedings of the 2017 ACM on Conference on Information and Knowledge Management. ACM, 1747--1756.Google ScholarDigital Library
- Susan Folkman. 2013. Stress: appraisal and coping .Springer.Google Scholar
- Renee Garett, Sam Liu, and Sean D Young. 2017. A longitudinal analysis of stress among incoming college freshmen. Journal of American college health , Vol. 65, 5 (2017), 331--338.Google ScholarCross Ref
- Ian Goodfellow, Yoshua Bengio, and Aaron Courville. 2016. Deep learning .MIT press.Google ScholarDigital Library
- Gábor Gosztolya, Róbert Busa-Fekete, and László Tóth. 2013. Detecting autism, emotions and social signals using AdaBoost. Interspeech.Google Scholar
- Nils Y Hammerla, Shane Halloran, and Thomas Plötz. 2016. Deep, convolutional, and recurrent models for human activity recognition using wearables. In Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence. AAAI Press, 1533--1540.Google Scholar
- Xu Han, Jiasong Wu, Lu Wang, Yang Chen, Lotfi Senhadji, and Huazhong Shu. 2014. Linear total variation approximate regularized nuclear norm optimization for matrix completion. In Abstract and Applied Analysis , Vol. 2014. Hindawi.Google Scholar
- John HL Hansen and Brian D Womack. 1996. Feature analysis and neural network-based classification of speech under stress. IEEE Transactions on Speech and Audio Processing , Vol. 4, 4 (1996), 307--313.Google ScholarCross Ref
- Sepp Hochreiter and Jürgen Schmidhuber. 1997. Long short-term memory. Neural Computation , Vol. 9, 8 (1997), 1735--1780.Google ScholarDigital Library
- Natasha Jaques, Sara Taylor, Akane Sano, Rosalind Picard, et almbox. 2017. Predicting tomorrow's mood, health, and stress level using personalized multitask learning and domain adaptation. In IJCAI 2017 Workshop on Artificial Intelligence in Affective Computing. 17--33.Google Scholar
- Hayeon Jeong, Heepyung Kim, Rihun Kim, Uichin Lee, and Yong Jeong. 2017. Smartwatch wearing behavior analysis: a longitudinal study. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies , Vol. 1, 3 (2017), 60.Google ScholarDigital Library
- He Jiang, Xin Chen, Shuwei Zhang, Xin Zhang, Weiqiang Kong, and Tao Zhang. 2015. Software for wearable devices: Challenges and opportunities. In 2015 IEEE 39th Annual Computer Software and Applications Conference, Vol. 3. IEEE, 592--597.Google ScholarDigital Library
- Jyun-Yu Jiang and Wei Wang. 2018. RIN: Reformulation Inference Network for Context-Aware Query Suggestion. In Proceedings of the 27th ACM International Conference on Information and Knowledge Management. ACM, 197--206.Google ScholarDigital Library
- Jyun-Yu Jiang, Mingyang Zhang, Cheng Li, Michael Bendersky, Nadav Golbandi, and Marc Najork. 2019. Semantic Text Matching for Long-Form Documents. In The World Wide Web Conference. ACM, 795--806.Google Scholar
- Rafal Jozefowicz, Wojciech Zaremba, and Ilya Sutskever. 2015. An empirical exploration of recurrent network architectures. In Proceedings of the 32nd International Conference on Machine Learning (ICML '15). 2342--2350.Google Scholar
- Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014).Google Scholar
- Anil C Kokaram, Robin D Morris, William J Fitzgerald, and Peter JW Rayner. 1995. Interpolation of missing data in image sequences. IEEE Transactions on Image Processing , Vol. 4, 11 (1995), 1509--1519.Google ScholarDigital Library
- Yehuda Koren, Robert Bell, and Chris Volinsky. 2009. Matrix factorization techniques for recommender systems. Computer 8 (2009), 30--37.Google ScholarDigital Library
- Guokun Lai, Wei-Cheng Chang, Yiming Yang, and Hanxiao Liu. 2018. Modeling long-and short-term temporal patterns with deep neural networks. In The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval . ACM, 95--104.Google ScholarDigital Library
- Richard S Lazarus. 2006. Stress and emotion: A new synthesis .Springer Publishing Company.Google Scholar
- Robert LiKamWa, Yunxin Liu, Nicholas D Lane, and Lin Zhong. 2013. Moodscope: Building a mood sensor from smartphone usage patterns. In Proceeding of the 11th annual international conference on Mobile systems, applications, and services . ACM, 389--402.Google Scholar
- Thang Luong, Hieu Pham, and Christopher D Manning. 2015. Effective Approaches to Attention-based Neural Machine Translation. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing . 1412--1421.Google ScholarCross Ref
- Denali Molitor and Deanna Needell. 2018. Matrix Completion for Structured Observations. arXiv preprint arXiv:1801.09657 (2018).Google Scholar
- Oscar Martinez Mozos, Virginia Sandulescu, Sally Andrews, David Ellis, Nicola Bellotto, Radu Dobrescu, and Jose Manuel Ferrandez. 2017. Stress detection using wearable physiological and sociometric sensors. International journal of neural systems , Vol. 27, 02 (2017), 1650041.Google ScholarCross Ref
- Pentti Paatero and Unto Tapper. 1994. Positive matrix factorization: A non-negative factor model with optimal utilization of error estimates of data values. Environmetrics , Vol. 5, 2 (1994), 111--126.Google ScholarCross Ref
- Emily A Pierceall and Marybelle C Keim. 2007. Stress and coping strategies among community college students. Community College Journal of Research and Practice , Vol. 31, 9 (2007), 703--712.Google ScholarCross Ref
- Benjamin Recht, Maryam Fazel, and Pablo A Parrilo. 2010. Guaranteed minimum-rank solutions of linear matrix equations via nuclear norm minimization. SIAM review , Vol. 52, 3 (2010), 471--501.Google Scholar
- Robert S Sandler, James E Everhart, Mark Donowitz, Elizabeth Adams, Kelly Cronin, Clifford Goodman, Eric Gemmen, Shefali Shah, Aida Avdic, and Robert Rubin. 2002. The burden of selected digestive diseases in the United States. Gastroenterology , Vol. 122, 5 (2002), 1500--1511.Google ScholarCross Ref
- Aarti Sathyanarayana, Shafiq Joty, Luis Fernandez-Luque, Ferda Ofli, Jaideep Srivastava, Ahmed Elmagarmid, Teresa Arora, and Shahrad Taheri. 2016. Sleep quality prediction from wearable data using deep learning. JMIR mHealth and uHealth , Vol. 4, 4 (2016), e125.Google Scholar
- Joseph L Schafer and John W Graham. 2002. Missing data: our view of the state of the art. Psychological methods , Vol. 7, 2 (2002), 147.Google Scholar
- Mai Shouman, Tim Turner, and Rob Stocker. 2012. Applying k-nearest neighbour in diagnosing heart disease patients. International Journal of Information and Education Technology , Vol. 2, 3 (2012), 220--223.Google ScholarCross Ref
- Feng-Tso Sun, Cynthia Kuo, Heng-Tze Cheng, Senaka Buthpitiya, Patricia Collins, and Martin Griss. 2010. Activity-aware mental stress detection using physiological sensors. In International conference on Mobile computing, applications, and services. Springer, 282--301.Google Scholar
- Lieven Vandenberghe and Stephen Boyd. 1996. Semidefinite programming. SIAM review , Vol. 38, 1 (1996), 49--95.Google Scholar
- Yuxi Wang, Kaishun Wu, and Lionel M Ni. 2016. Wifall: Device-free fall detection by wireless networks. IEEE Transactions on Mobile Computing , Vol. 16, 2 (2016), 581--594.Google ScholarDigital Library
- Junfeng Yang and Xiaoming Yuan. 2013. Linearized augmented Lagrangian and alternating direction methods for nuclear norm minimization. Mathematics of computation , Vol. 82, 281 (2013), 301--329.Google Scholar
- Zichao Yang, Diyi Yang, Chris Dyer, Xiaodong He, Alex Smola, and Eduard Hovy. 2016. Hierarchical attention networks for document classification. In Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 1480--1489.Google ScholarCross Ref
- Mi Zhang and Alexander A Sawchuk. 2013. Human daily activity recognition with sparse representation using wearable sensors. IEEE journal of Biomedical and Health Informatics , Vol. 17, 3 (2013), 553--560.Google ScholarCross Ref
- Tong Zhang, Jue Wang, Liang Xu, and Ping Liu. 2006. Using wearable sensor and NMF algorithm to realize ambulatory fall detection. In International conference on natural computation. Springer, 488--491.Google ScholarDigital Library
Recommendations
System-level calibration for data fusion in wireless sensor networks
Wireless sensor networks are typically composed of low-cost sensors that are deeply integrated in physical environments. As a result, the sensing performance of a wireless sensor network is inevitably undermined by biases in imperfect sensor hardware ...
Learning from sensor network data
SenSys '09: Proceedings of the 7th ACM Conference on Embedded Networked Sensor SystemsWithin the PermaSense project, two wireless sensor networks have been deployed for a long-term operation in the Swiss Alps. For enabling state-of-the-art permafrost research based on the collected data, highest possible data quality and yield have to be ...
Secure data aggregation in wireless sensor networks: A comprehensive overview
Wireless sensor networks often consists of a large number of low-cost sensor nodes that have strictly limited sensing, computation, and communication capabilities. Due to resource restricted sensor nodes, it is important to minimize the amount of data ...
Comments