·
·
Friday, 9 October 2026dailybeirut.com
Tech & Science
New research from Nottingham Trent University details a privacy-focused, AI-driven home monitoring system using radar and heat sensors for older adults.
A new low-cost monitoring solution developed by researchers at Nottingham Trent University (NTU) enables safe health tracking for older adults in their own homes, eliminating the need for intrusive cameras or wearable devices. The system integrates radar, thermal sensors, and smart plugs to observe daily routines while strictly preserving user privacy.
The technology relies on artificial intelligence to synthesize data from three distinct sensor types, identifying potential critical health events such as falls, heart attacks, strokes, or other serious illnesses. Dr Yangang Xing, the lead researcher from NTU’s School of Architecture, Design and the Built Environment, explained that the primary goal is supporting the increasing number of seniors who prefer aging in place rather than moving into residential care facilities.
Xing noted that combining these technologies creates a comprehensive picture of an individual’s coping mechanisms at home. Beyond detecting immediate emergencies, the system offers early warnings if mobility declines or daily routines begin to deteriorate.
Movement detection within the property is handled by millimetre-wave radar, with multiple sensors discreetly positioned throughout the home. Behavioral patterns linked to everyday tasks—such as making tea, preparing food, or working at a desk—are monitored via smart plugs that connect standard household appliances to Wi-Fi.
Thermal sensors identify body posture, distinguishing between sitting, standing, walking, and lying down. To protect privacy, these sensors operate at high pixelation and low resolution, ensuring facial features and personal identities remain obscured while preventing the display of intricate movements or images.
The AI component learns an individual’s specific behavior patterns over time to detect anomalies, whether they are sudden emergency health events or gradual health declines. If an emergency is flagged, care professionals and family members receive notifications to conduct wellbeing checks, either remotely or in person.
To validate the system, the research team tested the sensors in a mock domestic environment featuring six different room layouts, including bedrooms and living areas with varying furniture arrangements. A series of activities was recorded to assess the accuracy of movement and posture identification.
Researchers determined that performance improved when information from all sensors was combined, indicating the technologies function best as an integrated network rather than standalone monitoring tools. The study, titled "Privacy-Preserving Ambient Sensing for Activities of Daily Living: Multimodal Radar-Thermal Human Activity Recognition and Smart Plug Appliance Recognition," has been published in the journal Sensors.
The project involved collaboration with Integrated System Technologies Ltd. The research team included Dr Geoff Archenhold, Bilal Mohammed, and Martin Harris from the company, alongside Dr Jordan J. Bird and Dr Isibor Kennedy Ihianle from NTU’s School of Science and Technology.
Dr Archenhold, chief executive officer of Integrated System Technologies Ltd, stated that the system could form part of an ambient assisted living environment where homes quietly monitor residents’ wellbeing in the background. He highlighted that changes in mobility, prolonged inactivity, altered sleep patterns, or the absence of normal household routines could potentially indicate emerging health concerns.
Archenhold added that the technology aims to give older people confidence to go about their daily business while feeling secure that their health is being monitored without infringing on their privacy, ultimately allowing them to stay in their own homes for longer.
