Author(s):
- Richa Sharma
- Shalli Rani
Abstract:
Quantified self (QS) is a term that exemplifies self-knowledge through self-tracking. The exponential rise in the number and variation of wearables and applications for personal use has facilitated smart-health concepts. It has now become effortless for a user to monitor himself and track his routine activities to gain more in-depth insight into his health. However, to study and analyze the massive amount of data gathered by such devices, machine learning needs to be integrated into the decision-making process. In this work, we propose a quantified self-based hybrid model that considers user-health from multiple perspectives to provide relevant recommendations. We further analyze the performance of support vector machine, Naïve Bayes, and a metalevel hybrid model of SVM and Naïve Bayes for the intended work. Based on the results, it is observed that the hybrid model enhances the accuracy by 6% of the weak performing classifier.
Documentation:
https://doi.org/10.1109/MITP.2021.3059485
References:
1.M. Hoogendoorn and B. Funk, Machine Learning for the Quantified Self. On the Art of Learning From Sensory Data, New York, NY, USA:Springer, 2018.Show in Context CrossRef Google Scholar
2.D. Nafus and J. Sherman, “Big data big questions| this one does not go up to 11: The quantified self-movement as an alternative big data practice”, Int. J. Commun., vol. 8, 2014.Show in Context Google Scholar
3.M. Swan, “Emerging patient-driven health care models: An examination of health social networks consumer personalized medicine and quantified self-tracking”, Int. J. Environ. Res. Public Health, vol. 6, no. 2, pp. 492-525, 2009.Show in Context CrossRef Google Scholar
4.K. Lorincz et al., “Sensor networks for emergency response: Challenges and opportunities”, IEEE Pervasive Comput., vol. 3, no. 4, pp. 16-23, Oct.–Dec. 2004.Show in Context View Article Full Text: PDF (1465KB) Google Scholar
5.M. Z. Shafiq, L. Ji, A. X. Liu, J. Pang and J. Wang, “A first look at cellular machine-to-machine traffic: Large scale measurement and characterization”, ACM SIGMETRICS Perform. Eval. Rev., vol. 40, no. 1, pp. 65-76, 2012.Show in Context Google Scholar
6.S. Yang, P. Zhou, K. Duan, M. S. Hossain and M. F. Alhamid, “emHealth: Towards emotion health through depression prediction and intelligent health recommender system”, Mobile Netw. Appl., vol. 23, no. 2, pp. 1-11, 2017.Show in Context Google Scholar
7.A. Felfernig and T. Ngoc, “Recommender systems for IoT enabled m-Health Appli-cations”, Artif. Intell. Appl. Innovations, vol. 520, pp. 227-237, 2018.Show in Context Google Scholar
8.F. Jabeen et al., “An IoT based efficient hybrid recommender system for cardiovascular disease”, Peer-to-Peer Netw. Appl., vol. 12, pp. 1-14, 2019. CrossRef Google Scholar
9.T. Sharon, “Self-tracking for health and the quantified self: Re-articulating autonomy solidarity and authenticity in an age of personalized healthcare”, Philosophy Technol., vol. 30, no. 1, pp. 93-121, 2017.Show in Context CrossRef Google Scholar
10.P. Sundaravadivel, E. Kougianos, S. P. Mohanty and M. K. Ganapathiraju, “Everything you wanted to know about smart health care: Evaluating the different technologies and components of the internet of things for better health”, IEEE Consum. Electron. Mag., vol. 7, no. 1, pp. 18-28, Jan. 2018.Show in Context View Article Full Text: PDF (2661KB) Google Scholar
11.T. Saheb and M. Saheb, “Analyzing and visualizing knowledge structures of health informatics from 1974 to 2018: A bibliometric and social network analysis”, Healthcare Inform. Res., vol. 25, no. 2, pp. 61-72, 2019.Show in Context CrossRef Google Scholar
12.D. Chousiadas, A. Menychtas, P. Tsanakas and I. Maglogiannis, “Advancing quantified-self applications utilizing visual data analytics and the internet of things”, Proc. IFIP Int. Conf. Artif. Intell. Appl. Innovations, pp. 263-274, 2018.Show in Context CrossRef Google Scholar
13.T. Parshakova and D. Saakes, “UMorph: Self-change tracker to reflect yourself to the future and past”, Proc. ACM Conf. Companion Publication Designing Interactive Syst., pp. 307-310, 2018.Show in Context Google Scholar
14.B. Fu, D. V. Gangatharan, A. Kuijper, F. Kirchbuchner and A. Braun, “Exercise monitoring on consumer smart phones using ultrasonic sensing”, Proc. 4th Int. Workshop Sensor Activity Recognit. Interact., pp. 9, 2017.Show in Context Google Scholar
15.B. Yong et al., “IoT-based intelligent fitness system”, J. Parallel Distrib. Comput., vol. 118, pp. 14-21, 2017.Show in Context CrossRef Google Scholar
16.R. Varatharajan, G. Manogaran, M. K. Priyan and R. Sundarasekar, “Wearable sensor devices for early detection of Alzheimer disease using dynamic time warping algorithm”, Cluster Comput., vol. 21, no. 1, pp. 681-690, 2018.Show in Context CrossRef Google Scholar
17.T. de Quadros, A. E. Lazzaretti and F. K. Schneider, “A movement decomposition and machine learning-based fall detection system using wrist wearable device”, IEEE Sensors J., vol. 18, no. 12, pp. 5082-5089, Jun. 2018.Show in Context View Article Full Text: PDF (958KB) Google Scholar
18.H. Buchele Harris and W. Chen, “Technology-enhanced classroom activity breaks impacting children’s physical activity and fitness”, J. Clin. Med., vol. 7, no. 7, 2018.Show in Context CrossRef Google Scholar
19.R. Burke, “Hybrid recommender systems: Survey and experiments”, User Model. User-Adapted Interaction, vol. 12, no. 4, pp. 331-370, 2002.Show in Context CrossRef Google Scholar
20.C. B. C. Latha and S. C. Jeeva, “Improving the accuracy of prediction of heart disease risk based on ensemble classification techniques”, Inform. Med. Unlocked, vol. 16, 2019.Show in Context CrossRef Google Scholar
21.M. Chen, Z. Yang, W. Saad, C. Yin, H. V. Poor and S. Cui, “A joint learning and communications framework for federated learning over wireless networks”, IEEE Trans. Wireless Commun., vol. 20, no. 1, pp. 269-283, Jan. 2021.Show in Context View Article Full Text: PDF (1940KB) Google Scholar