wearable-data

Local-first MCP server for Google Health API v4 (Fitbit + Pixel Watch) — Claude/Cursor/Hermes

Hermes Health Apollo: local-first wearable, calendar, and daily-context intelligence for Hermes Agent

Can wearables warn us when we're getting sick? A community citsci project – open source & open data!

Local-first MCP server for WHOOP recovery, HRV & sleep — Claude, Cursor, ChatGPT ready

Local-first MCP server for Garmin Body Battery, HRV, sleep & training data — Claude/Cursor ready

Local-first MCP server for Oura Ring readiness, sleep, HRV — Claude/Cursor/ChatGPT ready

71 位使用者、2.7 年 Garmin 穿戴資料的多變量分析專案：清理→EDA→PCA/聚類/ANOVA/迴歸→因子分析，含互動式報告與資料保護設計

Exploratory ML research comparing models on synthetic wearable cardiovascular data. Reproducible pipeline, model card, tests. Not a medical device.

Local-first AI health assistant using wearable metrics, anomaly detection, and an Ollama LLM backend.

Wearable-based endurance performance case study using Garmin data and 29 official FIDAL races.

Local-first persistent memory layer for AI agents. SQLite-backed, MCP-compatible, cross-agent. Privacy: secret-blocking writes, file-only storage.

Sync Oura, calendar, and email data to provide local-first health insights for the Hermes agent.

AI-powered wearable health check-in agent for Galaxy Fit / Samsung Health data. Uses Health Connect + Life Dashboard Companion to send health metrics into a Google Apps Script webhook, analyzes steps, sleep, heart rate, blood oxygen, and activity with the OpenAI API, then sends casual wellness check-ins to Telegram with optional bot support.

An Analysis on Depression using Actigraphy data

My role-focused case study of the wearable health telemetry project: AI model training, ML pipeline, and backend. Source public at Rhythm360/telemetry-healthcare.

Personal website of Soha Niroumandi — PhD candidate at USC specializing in AI and biomechanics.

LSTM neural network for predicting health metrics from wearable sensor data. Full ML pipeline with data preprocessing, model training, and performance evaluation in R and Python.

The AI-Powered Health Monitoring System is designed to monitor users' health in real-time by leveraging data from wearable devices such as smartwatches and fitness trackers.

A simple actigraphy processing pipeline for converting GENEActiv device files into CSV outputs for research analysis. The project includes device reading, preprocessing, epoch generation, sleep report export, and CSV comparison utilities.

End-to-end ML pipeline for wearable stress detection using HRV and sleep data, featuring multimodal feature engineering, outlier detection, SMOTE balancing, ensemble learning, cross-validation, and predictive analytics.