Distributed Machine Learning for Psychology Monitoring

Project Description

Distributed Machine Learning (DML) for psychology monitoring represents a significant breakthrough in mental health care by decentralizing data processing, which enhances privacy and security for sensitive mental health information. One of the primary benefits of DML is its ability to protect user privacy by minimizing data aggregation, thus reducing the risk of data breaches. However, DML also introduces challenges, such as ensuring the accuracy and reliability of models trained on distributed data, effectively integrating multimodal data from various sources, and maintaining real-time processing capabilities. Critical research questions include balancing privacy with computational efficiency, standardizing diverse data sources, and developing robust algorithms for personalized mental health interventions. Addressing these challenges will be essential for the successful implementation of DML in psychology monitoring, ultimately improving mental health care.

 

In this project, we investigate DML implementations for psychology monitoring by leveraging mobile-sensed data. Collaborating closely with psychologists, we have developed Mobisense, an app that collects mobile phone usage data from participants in psychology studies. This initiative aims to explore how real-time, privacy-preserving data analysis can enhance the accuracy and effectiveness of mental health monitoring and interventions.

 

References:

[1] B. McMahan, E. Moore, D. Ramage, S. Hampson, and B. A. y Arcas, “Communication-efficient learning of deep networks from decentralized data,” in Artificial Intelligence and Statistics, pp. 1273–1282, PMLR, 2017. 

[2] M. Bauer, T. Glenn, J. Geddes, M. Gitlin, P. Grof, L. V. Kessing, S. Monteith, M. Faurholt-Jepsen, E. Severus, and P. C. Whybrow, “Smartphones in mental health: a critical review of background issues, current status and future concerns,” International journal of bipolar disorders, vol. 8, pp. 1–19, 2020. 

[3] R. Wang, F. Chen, Z. Chen, T. Li, G. Harari, S. Tignor, X. Zhou, D. Ben-Zeev, and A. T. Campbell, “Studentlife: assessing mental health, academic performance and behavioral trends of college students using smartphones,” in Proceedings of the 2014 ACM international joint conference on pervasive and ubiquitous computing, pp. 3–14, 2014. 

[4] D. Xenakis, E. Samikwa, J. Ajayi, A. D. Maio, T. Braun, and K. Schlegel, “Towards personality detection and prediction using smartphone sensor data,” in 2023 21st Mediterranean Communication and Computer Networking Conference (MedComNet), pp. 121–130, 2023. 

[5] R. Wang, F. Chen, Z. Chen, T. Li, G. Harari, S. Tignor, X. Zhou, D. Ben-Zeev, and A. T. Campbell, “Studentlife: Using smartphones to assess mental health and academic performance of college students,” Mobile Health: Sensors, Analytic Methods, and Applications, pp. 7–33, 2017. 

[6] X. Wang, Y. Han, V. C. Leung, D. Niyato, X. Yan, and X. Chen, “Convergence of edge computing and deep learning: A comprehensive survey,” IEEE Communications Surveys & Tutorials, vol. 22, no. 2, pp. 869–904, 2020.

 

 

 

Contact