Skip to content
#federated learning Book Open access

Demo: Multimodal Stress Monitoring with Split Federated Fine-Tuning on Mobile Devices

Nov 2026 · Proceedings of the Twenty-seventh International Symposium on Theory, Algorithmic Foundations, and Protocol Design for Mobile Networks and Mobile Computing · 0 citations · 2 references

TL;DR

An end-to-end mobile system for proactive stress monitoring from wearable signals supported by an extensible split federated learning system that enables on-device LoRA fine-tuning of large language models.

Abstract

We present an end-to-end mobile system for proactive stress monitoring from wearable signals. The framework is supported by an extensible split federated learning system that enables on-device LoRA fine-tuning of large language models. By analyzing physiological data, the application distinguishes emotional states, summarizes recent trends, and provides brief, actionable suggestions. Upon detecting a negative emotional state, the paired smartwatch or smartphone proactively delivers notifications to users to encourage mindfulness. The on-site demonstration will showcase real-time sensing-inference on smartwatch-phone pairs, alongside a recorded split federated learning process that continuously learns from user private data. Our code has been open-sourced at: https://github.com/HKU-WILL-Lab/Multimodal-Stress-Monitoring-with-Split-Federated-Fine-Tuning-on-Mobile-Devices.

Read PDF

Similar papers

Open access Oct 2026

Quantifying Smartphone Overuse: A Machine Learning Analysis of Severity and Lifestyle Effects

Smartphone use has become an important part of communication, education, entertainment and social interaction. At the same time, excessive or uncontrolled usage may be associated with reduced productivity, disturbed routines, social difficulties and other lifestyle concerns. This paper presents a machine-learning-based...

Y. S. Madhuri, D. P. Reddy · 0 citations
#reinforcement learning Review Open access Oct 2026

Smart Education Platform: Based on Emotions Content Delivery Using ML

This project proposes a Smart Education Platform that dynamically adapts online learning content based on students’ real-time emotions to improve engagement and outcomes. Leveraging multimodal inputs—facial expressions detected via webcam using ResNet, speech sentiment analysis through Wav2Vec, and contextual surveys t...

N. R. Reddy, G. N., G. N et al. · 0 citations
Open access Sep 2026

StressNet: Neuromorphic multimodal stress recognition from wearable physiological signals

Continuous, real-time monitoring of psychological stress is becoming increasingly important in digital health and remote patient-monitoring systems. However, deploying always-on stress-monitoring models on consumer wearable devices remains challenging because of their limited computational resources and microjoule-...

M. Sajid, N. Aburaed, R. Maskeliūnas · 0 citations
Conference Open access Sep 2026

ChillMate Real Time Wrist Based Stress Detection with Motion Aware Personalization on Smartwatches

Results show that heart rate variability and motion based stress detection can run end-to-end on unmodified consumer hardware, while the cross-dataset analysis makes explicit the limits of such models under domain shift.

Simge Çevik, Ela Bilgisu, Cansu Abay et al. · 0 citations
Open access Oct 2026

Artificial Intelligence Driven Assessment of Daoist Meditation and Breathing Practices Using Wearable IoT Devices

The proliferation of wearable Internet of Things (IoT) devices has introduced novel opportunities for continuous and objective monitoring of individuals engaged in meditation and controlled breathing practices. This study presents an artificial intelligence (AI)-driven framework for assessing the physiological and psyc...

D. Rao, S. Gobinath, K.Tamilarasi et al. · 0 citations
Open access 2026

Short-Term Emotion Change Prediction With Compact and Informative Mobile Sensing Inputs

Emotional change prediction can help characterize affective dynamics from real-world behavioral data and may inform future non-clinical affective-state estimation systems. This study investigates short-term emotion change prediction using only objective mobile sensing features. Based on the StudentLife dataset, emotion...

Wei Zhao, K. Go · 0 citations

Related blog posts

Microsoft Research Blog Nov 16, 2026

TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient

AI coding agents are increasingly help developers fix bugs and build features largely on their own, but every interaction with their models consumes tokens. In each session, an agent sends instructions, tool descriptions, and session history to its model. Most efforts to reduce this cost focus on individual tasks. Yet developers return to the same […] The post TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient appeared first on Microsoft Research.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.