ABSTRACT
Recent advances in mobile health have produced several new models for inferring stress from wearable sensors. But, the lack of a gold standard is a major hurdle in making clinical use of continuous stress measurements derived from wearable sensors. In this paper, we present a stress model (called cStress) that has been carefully developed with attention to every step of computational modeling including data collection, screening, cleaning, filtering, feature computation, normalization, and model training. More importantly, cStress was trained using data collected from a rigorous lab study with 21 participants and validated on two independently collected data sets --- in a lab study on 26 participants and in a week-long field study with 20 participants. In testing, the model obtains a recall of 89% and a false positive rate of 5% on lab data. On field data, the model is able to predict each instantaneous self-report with an accuracy of 72%.
- Zephyr Bioharness. http://www.zephyr-technology.com/bioharness-bt, Accessed: September 2013.Google Scholar
- Adams, P., Rabbi, M., Rahman, T., Matthews, M., Voida, A., Gay, G., Choudhury, T., and Voida, S. Towards personal stress informatics: Comparing minimally invasive techniques for measuring daily stress in the wild. In Pervasive Health (2014), 72--79. Google ScholarDigital Library
- al'Absi, M. Stress and addiction: Biological and psychological mechanisms. Academic Press/Elsevier, 2007.Google Scholar
- al'Absi, M., and Arnett, D. Adrenocortical responses to psychological stress and risk for hypertension. Biomedecine & Pharmacotherapy 54, 5 (2000), 234--244.Google Scholar
- al'Absi, M., Bongard, S., Buchanan, T., Pincomb, G., J, L., and Lovallo, W. Cardiovascular and neuroendocrine adjustment to public speaking and mental arithmetic stressors. Psychophysiology 34 (1997), 266--75.Google ScholarCross Ref
- al'Absi, M., Hatsukami, D., Davis, G., and Wittmers, L. Prospective examination of effects of smoking abstinence on cortisol and withdrawal symptoms as predictors of early smoking relapse. Drug Alcohol Dependence 73, 3 (2004), 267--78.Google Scholar
- Berntson, G., Quigley, K., Jang, J., and Boysen, S. An approach to artifact identification: Application to heart period data. Psychophysiology 27, 5 (1990), 586--598.Google ScholarCross Ref
- Boser, B. E., Guyon, I. M., and Vapnik, V. N. A training algorithm for optimal margin classifiers. In Fifth Annual Workshop on Computational Learning Theory (1992), 144--152. Google ScholarDigital Library
- Chang, C.-C., and Lin, C.-J. LIBSVM: A library for support vector machines. ACM Transactions on Intelligent Systems and Technology 2 (2011), 27:1--27:27. Software available at http://www.csie.ntu.edu.tw/~cjlin/libsvm. Google ScholarDigital Library
- Choi, J., Ahmed, B., and Gutierrez-Osuna, R. Development and evaluation of an ambulatory stress monitor based on wearable sensors. IEEE Transactions on Information Technology in Biomedicine 16, 2 (2012), 279--286. Google ScholarDigital Library
- Chrousos, G., and Gold, P. The concepts of stress and stress system disorders: overview of physical and behavioral homeostasis. JAMA 267, 9 (1992), 1244.Google ScholarCross Ref
- Cohen, S., Kamarck, T., and Mermelstein, R. A global measure of perceived stress. Journal of Health and Social Behavior 24, 4 (1983), 385--396.Google ScholarCross Ref
- Enoch, M. Pharmacogenomics of alcohol response and addiction. American Journal of Pharmacogenomics 3, 4 (2003), 217--232.Google ScholarCross Ref
- Enoch, M. Genetic and environmental influences on the development of alcoholism. Ann NY Acad Sci 1094 (2007), 193--201.Google ScholarCross Ref
- Ertin, E., Stohs, N., Kumar, S., Raij, A., al'Absi, M., T. Kwon, Mitra, S., Shah, S., and Jeong, J. AutoSense: Unobtrusively Wearable Sensor Suite for Inferencing of Onset, Causality, and Consequences of Stress in the Field. In ACM SenSys (2011). Google ScholarDigital Library
- Healey, J., Nachman, L., Subramanian, S., Shahabdeen, J., and Morris, M. Out of the lab and into the fray: Towards modeling emotion in everyday life. Pervasive Computing 6030 (2010), 156--173. Google ScholarDigital Library
- Healey, J. A., and Picard, R. W. Detecting stress during real-world driving tasks using physiological sensors. IEEE Transactions on Intelligent Transportation Systems 6, 2 (2005), 156--166. Google ScholarDigital Library
- Henry, J. Stress, neuroendocrine patterns, and emotional response. Stressors and the adjustment disorders (1990), 477--496.Google Scholar
- Hong, J.-H., Ramos, J., and Dey, A. K. Understanding physiological responses to stressors during physical activity. In ACM UbiComp (2012), 270--279. Google ScholarDigital Library
- Kreibig, S. D. Autonomic nervous system activity in emotion: A review. Biological Psychology 84, 3 (2010), 394--421.Google ScholarCross Ref
- Kreibig, S. D., Wilhelm, F. H., Roth, W. T., and Gross, J. J. Cardiovascular, electrodermal, and respiratory response patterns to fear- and sadness-inducing films. Psychophysiology 44, 5 (2007), 787--806.Google ScholarCross Ref
- Kusserow, M., Amft, O., and Troster, G. Monitoring stress arousal in the wild. IEEE Pervasive Computing 12, 2 (2013), 28--37. Google ScholarDigital Library
- Lu, H., Frauendorfer, D., Rabbi, M., Mast, M. S., Chittaranjan, G. T., Campbell, A. T., Gatica-Perez, D., and Choudhury, T. Stresssense: Detecting stress in unconstrained acoustic environments using smartphones. In ACM UbiComp (2012), 351--360. Google ScholarDigital Library
- Lu, W., Nystrom, M. M., Parikh, P. J., Fooshee, D. R., Hubenschmidt, J. P., Bradley, J. D., and Low, D. A. A semi-automatic method for peak and valley detection in free-breathing respiratory waveforms. Medical Physics 33, 10 (2006), 3634--3636.Google Scholar
- Mark, G., Wang, Y., and Niiya, M. Stress and multitasking in everyday college life: An empirical study of online activity. In ACM CHI (2014), 41--50. Google ScholarDigital Library
- McEwen, B. Protection and damage from acute and chronic stress. Ann NY Acad Sci 1032 (2004), 1--7.Google ScholarCross Ref
- McEwen, B., and Stellar, E. Stress and the individual: mechanisms leading to disease. Archives of Internal Medicine 153, 18 (1993), 2093.Google ScholarCross Ref
- Mcfarland, D. H. Respiratory Markers of Conversational Interaction. Journal of Speeh, Language and Hearing Research 44 (2001), 128--143.Google ScholarCross Ref
- Melillo, P., Formisano, C., Bracale, U., and Pecchia, L. Classification tree for real-life stress detection using linear heart rate variability analysis. case study: students under stress due to university examination. In World Congress on Medical Physics and Biomedical Engineering. Springer Berlin Heidelberg, 2013, 477--480.Google ScholarCross Ref
- Myrtek, M. Heart and emotion: Ambulatory monitoring studies in everyday life. Hogrefe & Huber Publishers, 2004.Google Scholar
- Neder, J., Dal Corso, S., Malaguti, C., Reis, S., De Fuccio, M., Schmidt, H., Fuld, J., and Nery, L. The pattern and timing of breathing during incremental exercise: a normative study. European Respiratory Journal 21, 3 (2003), 530--538.Google ScholarCross Ref
- Nielsen, P., Grice, I. L., Smaill, B., and Hunter, P. Mathematical model of geometry and fibrous structure of the heart. American Journal of Physiology-Heart and Circulatory Physiology 260, 4 (1991), H1365--H1378.Google ScholarCross Ref
- Nunnally, J. C. Psychometric Theory, 2 ed. McGraw-Hill, New York, 1978.Google Scholar
- Pan, J., and Tompkins, W. A real-time qrs detection algorithm. IEEE Transactions on Biomedical Engineering 32, 3 (1985), 230--236.Google Scholar
- Plarre, K., Raij, A., Guha, S., al'Absi, M., Ertin, E., and Kumar, S. Automated detection of sensor detachments for physiological sensing in the wild. In Wireless Health 2010 (2010), 216--217. Google ScholarDigital Library
- Plarre, K., Raij, A., Hossain, S., Ali, A., Nakajima, M., al'Absi, M., Ertin, E., Kamarck, T., Kumar, S., Scott, M., Siewiorek, D., Smailagic, A., and Wittmers, L. Continuous inference of psychological stress from sensory measurements collected in the natural environment. In ACM IPSN (2011), 97--108.Google Scholar
- Platt, J. C. Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods. In Advances in Large Margin Classifiers, MIT Press (1999), 61--74.Google Scholar
- Rahman, M., Bari, R., Ali, A., Sharmin, M., Raij, A., Hovsepian, K., Hossain, S., Ertin, E., Kennedy, A., Epstein, D., et al. Are we there yet?: feasibility of continuous stress assessment via wireless physiological sensors. In ACM Conference on Bioinformatics, Computational Biology, and Health Informatics (BCB) (2014), 479--488. Google ScholarDigital Library
- Rahman, T., Zhang, M., Voida, S., and Choudhury, T. Towards accurate non-intrusive recollection of stress levels using mobile sensing and contextual recall. In Pervasive Health (2014), 166--169. Google ScholarDigital Library
- Rainville, P., Bechara, A., Naqvi, N., and Damasio, A. R. Basic emotions are associated with distinct patterns of cardiorespiratory activity. International journal of psychophysiology 61, 1 (2006), 5--18.Google ScholarCross Ref
- Rakotomamonjy, A., Bach, F. R., Canu, S., and Grandvalet, Y. Simplemkl. Journal of Machine Learning Research 9 (2008), 2491--2521.Google Scholar
- Rifkin, R. Everything Old is New Again: A Fresh Look at Historical Approaches in Machine Learning. PhD thesis, MIT, 2002. Google ScholarDigital Library
- Rosmond, R., and Björntorp, P. Endocrine and metabolic aberrations in men with abdominal obesity in relation to anxio-depressive infirmity. Metabolism 47, 10 (1998), 1187--1193.Google ScholarCross Ref
- Sapolsky, R. M. Why zebras don't get ulcers: The acclaimed guide to stress, stress-related diseases, and coping-now revised and updated. Macmillan, 2004.Google Scholar
- Sarker, H., Sharmin, M., Ali, A. A., Rahman, M. M., Bari, R., Hossain, S. M., and Kumar, S. Assessing the availability of users to engage in just-in-time intervention in the natural environment. In Proceedings of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing, UbiComp '14, ACM (New York, NY, USA, 2014), 909--920. Google ScholarDigital Library
- Sharma, N., and Gedeon, T. Computational models of stress in reading using physiological and physical sensor data. In Advances in Knowledge Discovery and Data Mining. Springer Berlin Heidelberg, 2013, 111--122.Google Scholar
- Sharmin, M., Raij, A., Epstein, D., Nahum-Shani, I., Beck, G., Vhaduri, S., Preston, K., and Kumar, S. Visualization of time-series sensor data to inform the design of just-in-time adaptive stress interventions. In ACM UbiComp (2015). Google ScholarDigital Library
- Stephens, C., Christie, I., and Friedman, B. Autonomic specificity of basic emotions: Evidence from pattern classification and cluster analysis. Biological psychology 84, 3 (2010), 463--473.Google Scholar
- Sun, F.-T., Kuo, C., Cheng, H.-T., Buthpitiya, S., Collins, P., and Griss, M. Activity-aware mental stress detection using physiological sensors. Mobile Computing, Applications, and Services 76 (2012), 211--230.Google Scholar
- Wu, M. Trimmed and Winsorized Eestimators. PhD thesis, Michigan State University, 2006.Google Scholar
- Zhai, J., and Barreto, A. Stress detection in computer users based on digital signal processing of noninvasive physiological variables. In IEEE EMBS (2006), 1355--1358.Google ScholarCross Ref
Index Terms
- cStress: towards a gold standard for continuous stress assessment in the mobile environment
Recommendations
Remote assistance for people with dementia at home using reminiscence systems and a schedule prompter
We developed a system that remotely supports the daily lives of people with dementia at home using reminiscence video and a reminiscence conversation system with a schedule prompter to produce relaxation and prevent behavioural disturbances. Quality ...
Elderly Assistance Using Wearable Sensors by Detecting Fall and Recognizing Fall Patterns
UbiComp '18: Proceedings of the 2018 ACM International Joint Conference and 2018 International Symposium on Pervasive and Ubiquitous Computing and Wearable ComputersFalling is a serious threat to the elderly people. One severe fall can cause hazardous problems like bone fracture or may lead to some permanent disability or even death. Thus, it has become the need of the hour to continuously monitor the activities of ...
A wearable point-of-care system for home use that incorporates plug-and-play and wireless standards
A point-of-care system for continuous health monitoring should be wearable, easy to use, and affordable to promote patient independence and facilitate acceptance of new home healthcare technology. Reconfigurability, interoperability, and scalability are ...
Comments