Python API for Mentalab biosignal aquisition devices

[EMNLP 2025] Official implementation of "SensorLLM: Aligning Large Language Models with Motion Sensors for Human Activity Recognition"

[ECAI 2020] Tensorflow 2.x Implementation of "Human Activity Recognition from Wearable Sensor Data Using Self-Attention"

Attend and Discriminate: Beyond the State-of-the-Art for Human Activity Recognition Using Wearable Sensors

Insurance Recommendation System is to suggest best insurance to the users based on thier health. Every user is given a health score based on his/her vitals; of which data is measured by the the wearables data. Wearables data such as Cardiopulmonary and Vascular data and Glucose level. So basically suggesting the best insurance policy based on th…

Official implementation of "ZARA: Zero-shot Motion Time-Series Analysis via Knowledge and Retrieval Driven LLM Agents"

More to Less (M2L): Enhanced Health Recognition in the Wild with Reduced Modality of Wearable Sensors

Use python to extract and model your whoop data; you might just unlock a new level

The W4H Integrated Toolkit Repository provides a unified platform for managing, analyzing, and visualizing wearable health data using a suite of open-source tools and frameworks.

Arm mounted computer, which includes detection for bio signatures, accleration, gyroscope(Orientaion to Gravity well), and uploads to master control server.

Deep Learning models to fuse imu-based motion capture and first-person video data to improve the prediction of future knee and ankle joint kinematics, in complex real-world environments.

A test project to explore smartwatch data simulation and human activity recognition

[IJCAI 2024] Official TensorFlow implementation of "Wearable Sensor-Based Few-Shot Continual Learning on Hand Gestures for Motor-Impaired Individuals via Latent Embedding Exploitation".

Python tool for preprocessing and analyzing infant wearable sensor data (IMU) based on CHLA's INC Lab algorithm.

This project presents an innovative approach to how static hand gestures can be classified with wrist-worn barometric pressure sensors.

This repository presents the implementation of our collaborative project between UPenn/Orthopaedics, UDel/Physical Therapy, and CMU/Engineering on exercise prediction.