Federated Learning Framework for Mobile Sensing Apps in Mental Health
Bibliographic record
Abstract
Mental health issues are negatively impacting people, the economy and life expectancy. Several mobile applications are developed to aid mental health treatment and mobile sensing applications help remotely monitor patients with mental illness, understand key factors like sleep and exercise, and deliver effective treatment methods. Though new smartphones are increasingly efficient, the majority of mental health applications transfer data to centralized servers for processing. In this paper, we propose a Federated Learning framework for Mental Health Monitoring Systems (MHMS) to preserve user data privacy, reduce network usage and improve performance. To detect depression using the Federated Learning framework we defined a mobile application architecture, and developed two versions of applications that collect three types of sensing information such as location, accelerometer and calls. We defined epochs and developed an anomaly detection algorithm that helps to label local data to train models. We conducted a preliminary study for 6 weeks using two app versions. The results from the study indicate the app implementing the Federated Learning framework is capable of continuously tracking data utilizing less power, storage space and internet data. It also preserved users' privacy. In future, we are planning to implement Federated Learning to run large-scale studies with improved server-side federated averaging methods.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.003 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".