UbiLab - Ubiquitous Health Technology Lab

📢 Calling all caregivers and seniors! 🌟 Participate in our study and help revolutionize the concept of self-sufficient living with intelligent home sensors! 🏠💡

🔬 We are creating an innovative platform that models and identifies individual daily activities, empowering caregivers to monitor their loved ones who live independently. 🧑‍🦳🏡

👥 Qualifications: Age 60 and above
⏰ Estimated duration: Approximately 3 hours
📝 Complete a brief pre-study questionnaire (10-12 minutes)
👣 Engage in everyday tasks in our lab while wearing wearable devices, following instructions (such as turning on lights, washing dishes, cleaning, reading books, and eating)

💰 Receive $15 per hour for your valuable involvement and contribute to the future of caregiving! 💙🤝

✅ Be part of this transformative research! Enroll today and make a lasting impact on the concept of independent living! 🌟📲

Meet Dr Shahabeddin Abhari!

Dr Abhari is a Post Doctoral Fellow at UbiLab and is currently working on a project to develop standards for smart homes and communities interested in implementing active assisted living (AAL) technologies.

If you would like to learn more about Dr Abhari, please visit his Linkedin: https://www.linkedin.com/in/shahabeddin-abhari-ba01a688/

Our Team 💙

AI-Powered Non-Contact In-Home Gait Monitoring and Activity Recognition System Based on mm-Wave FMCW Radar and Cloud Computing

This article presents a cloud-based system for non-contact, real-time recognition and monitoring of physical activities and walking periods within a domestic environment.

The proposed system employs standalone Internet of Things (IoT)-based millimeter wave radar devices and deep learning models to enable autonomous, free-living activity recognition and gait analysis. To train deep learning models, we utilize range-Doppler maps generated from a dataset of real-life in-home activities. The performance of several deep learning models is evaluated based on accuracy and prediction time, with the gated recurrent network (GRU) model selected for real-time deployment due to its balance of speed and accuracy compared to 2D Convolutional Neural Network Long Short-Term Memory (2D-CNNLSTM) and Long Short-Term Memory (LSTM) models. The overall accuracy of the GRU model for classifying in-home physical activities of trained subjects is 93%, with 86% accuracy for a new subject. In addition to recognizing and differentiating various activities and walking periods, the system also records the subject’s activity level over time, washroom use frequency, sleep/sedentary/active/out-of-home durations, current state, and gait parameters. Importantly, the system maintains privacy by not requiring the subject to wear or carry any additional devices.

Study by: Abedi, H., Ansariyan, A., Morita, P., Wong, A., Boger, J., and Shaker, G.
doi: 10.1109/JIOT.2023.3235268.