physical-activity

Python-based open source package for actigraphy data analysis

Package for analyzing human motion data (e.g. PA, gait)

This github repository contains the code for the chatbot Jody that is created for the thesis project: Goal setting dialogue for physical activity with a virtual coach.

"UBIWEAR: An end-to-end, data-driven framework for intelligent physical activity prediction to empower mHealth interventions" @ IEEE HealthCom 2022

The repository for the source code of the Motus system

Rasa chatbot to gather data for and test a personalized reinforcement learning algorithm to persuade people to do preparatory activities for smoking cessation and increasing physical activity.

A simple and light-weight feature extractor for wearable accelerometer data.

To solve the issues arising from modern-day lifestyle with remote working culture, mental wellness, and physical fitness.

A tool for estimating physical activity levels using accelerometric data and scientifically validated indices.

Frailty classification using machine learning on behavioural and physical health data

The goal of this project is to develop a predictive model that analyzes children's physical activity and fitness data to identify early signs of problematic internet use. Identifying these patterns can help trigger interventions to encourage healthier digital habits.

Web-based tool for visualizing and annotating accelerometry data. Supports collaborative labeling of activity segments in large time-series recordings. Built with Panel and Bokeh. Docs: https://tavoloperuno.github.io/py_visualize_accelerometry/ | Demo: https://tavoloperuno-accelerometry-viewer-demo.hf.space/

Virtual coach Mel that proposes preparatory activities for quitting smoking and becoming more physically active as well as activities that are meant to persuade people of the usefulness of certain competencies for quitting smoking.

The code in this repository draws on results from the Global Healthy and Sustainable Cities Indicator Collaboration Study to generate policy 'scorecard' reports.

Wingerson, MJ - Dissertation research

Chatbot for persuading smokers to use physical activity as an aid for quitting smoking.

Analysis code for: Associations Between Physical Activity Intensity and Experience, Self-Regulation, and Self-Reported Interoceptive Accuracy and Attention

Compliance monitoring dashboard for MotionPI — a secure smartphone + BLE-wristband health-sensing platform streaming ~7.7M records/day (EAI SmartSP 2025)

Virtual coach Jamie for setting physical activity plans with users that users are committed to.

This github repository contains the code for the chatbot Steph that is created for the thesis project: Using Reinforcement Learning to Personalize Daily Step Goals for a Collaborative Dialogue with a Virtual Coach.