Adaptive Smart Homes for the Elderly: AI, VR, and IoT for Independent Living
PI: Dhananjay Singh (IST)
Based on pilot work, we will submit a large-scale proposal to NSF, create dataset and open-source platform for in class engagement and learning, fund graduate student tuition, and support a postdoc.
Project Description:
Aiming to facilitate the ageing in place project seeks to create an AI-powered smart home system to meet the increasing demand for safe, autonomous living among the elderly. Non-invasive health monitoring, privacypreserving artificial intelligence analytics, and immersive Virtual Reality (VR) experiences will all be included in the system. AI will continuously monitor vital signs, mobility patterns, and behavioural changes using ambient sensors, therefore identifying abnormalities such as falls or irregular health events in real time. Customised care and timely alerts to carers will be guaranteed by machine learning models adjusting to particular routines. By means of voiceactivated discussions, reminders, and companionship to lower loneliness, AI-driven virtual assistants will improve cognitive health and social engagement. Edge artificial intelligence, federated learning, and safe data pipelines will all help to guard privacy. While VR simulations will let stakeholders see and assess usability, healthcare impact, and residential comfort, Building Information Modelling (BIM) will help smart house design. The project will present a functional prototype evaluated in a simulated environment by the end of the year, proving how artificial intelligence may improve aged care, lower healthcare costs, and advance well-being. Results will support open-source tools and guide the next major smart ageing projects anchored in human-centred artificial intelligence design.
Desired Skills/Expertise:
Knowledge of artificial intelligence and machine learning for IoT sensor integration, NLP for virtual assistants, and privacy-preserving methods, including federated learning for health surveillance. Essential skills are those in VR development, BIM, HCI, and Python programming.
Other Requirements or Expectations:
Availability for weekly meetings; post-comp’s graduate student status, Knowledge of user-centred design, healthcare data, and elder care technology can help to enable effective system development and stakeholder involvement.
Specific Objectives:
• Develop an AI-based system for real-time, non-invasive health monitoring of elderly individuals.
• Personalize care using machine learning models that adapt to individual routines and detect anomalies.
• Implement privacy-preserving data processing using federated learning.
• Design AI-driven virtual assistants for cognitive and social support.
• Simulate and evaluate smart home functionality using VR environments.
Medium/Long-Term Goal:
Based on pilot work, submit a large-scale external research proposal such as NIH’s Smart Health program and NSF’s Smart and Connected Health initiative. Establish a publicly available dataset and open-source platform to support broader community research on aging-in-place.
Connection to ICDS Mission:
This project aligns with ICDS’s mission by integrating data science, AI, and IoT technologies to address the critical societal challenge of aging-in-place through a privacy-conscious digital twin framework. It supports interdisciplinary research, real-world impact, and the development of AI-enabled solutions to improve health and quality of life.
Engagement with ICDS:
This project will actively participate in ICDS activities, including talks, symposiums, and collaborative forums.