TL;DR
Get workout gear delivered free with Prime
- Fast, free delivery on millions of items
- Prime Video, Amazon Music and more included
- Member-only deals all year
Researchers at Nottingham Trent University and Integrated System Technologies developed and tested a home-monitoring prototype combining radar, thermal sensors and smart plugs. In a mock-home study, combining the sensor data improved performance, but the report does not establish real-world emergency detection accuracy or show that the system is ready for use in homes.
Researchers from Nottingham Trent University (NTU) and Integrated System Technologies Ltd have developed and tested a home sensor prototype that combines radar, thermal sensing and smart plugs to monitor activity without cameras or wearable devices. The study, published in Sensors in 2026, explores whether the system could identify possible emergencies and changes in daily routines, though it does not establish that the prototype is ready for routine use in people’s homes.
The prototype uses millimeter-wave radar to detect movement, with sensors placed at selected locations in a home. Smart plugs connected to household appliances track patterns associated with everyday activities, such as making tea or preparing food. Low-resolution thermal sensors identify broad postures, including sitting, standing, walking and lying down, while avoiding facial detail, the researchers said.
An AI system combines the sensor readings and learns a resident’s patterns over time. The researchers say departures from those patterns could indicate an event such as a fall or another serious health problem, or a gradual change in mobility or routine. If an emergency is detected, the intended system would alert care professionals or loved ones so they could check on the resident remotely or in person.
For the study, the team tested the sensors in a mock domestic setting with six room layouts, including bedrooms and living areas arranged with different furniture. Researchers recorded activities to assess how well the system recognized movement and posture. They reported that combining data from all three technologies improved performance compared with relying on sensor types separately. The source report does not give specific accuracy figures.
Monitoring Without Cameras or Wearables
The proposed approach addresses a practical tension in home monitoring: older people may want to remain at home, while families and care providers may worry about falls or other events going unnoticed. A system that detects unusual activity without recording conventional video could offer another option for checking on residents, particularly when in-person supervision is not continuous.
Its potential value is not limited to sudden incidents. The researchers say changes such as prolonged inactivity, altered sleep patterns or missed household routines might prompt an earlier welfare check. Those signals would not, by themselves, confirm illness or explain why a routine changed. The study presents them as possible indicators for follow-up, not as diagnoses.
Privacy protections are central to the design: the thermal output is kept at low resolution, and the system does not rely on wearable devices. Still, describing a system as privacy-preserving does not resolve every question about data handling or consent. Any practical use would need clear rules on what is collected, who receives alerts and how residents can control monitoring.
home emergency sensor system for elderly
As an affiliate, we earn on qualifying purchases.
As an affiliate, we earn on qualifying purchases.
How the Prototype Was Tested
The research, titled “Privacy-Preserving Ambient Sensing for Activities of Daily Living: Multimodal Radar-Thermal Human Activity Recognition and Smart Plug Appliance Recognition,” was published in the journal Sensors. The listed authors include NTU researchers and staff from Integrated System Technologies Ltd. The work was conducted in a mock home rather than reported as a trial with older residents living independently.
That distinction matters when interpreting the results. Testing whether sensors can recognize activities in arranged room layouts is an early step; it does not by itself show how reliably a system would work across occupied homes, different residents, or changing day-to-day conditions. The source report describes improved performance when sensor inputs were combined but does not provide results from a deployment in real homes.
Dr. Yangang Xing of NTU’s School of Architecture, Design and the Built Environment, the study’s lead researcher, said the project aims to support older adults who want to stay in their homes rather than move into residential care. Integrated System Technologies chief executive Geoff Archenhold described the concept as part of an ambient assisted living environment, with a home monitoring well-being in the background.
“By combining these three technologies, we can establish a complete picture of how someone is coping at home.”
— Dr. Yangang Xing, lead researcher at Nottingham Trent University
As an affiliate, we earn on qualifying purchases.
Real-Home Performance Is Unknown
The reported testing took place in a mock domestic environment. The source material does not say whether the system has been evaluated with older people in occupied homes, how often it correctly identifies emergencies, or how often it might generate false alarms. It also does not provide detailed performance metrics or a comparison with existing monitoring approaches.
It remains unclear when or whether the prototype could become a product, what it would cost to install and maintain, and how it would handle sensor failures, connectivity problems or changes in a resident’s routine. The report also does not specify what data would be stored, how long it would be retained, or the precise consent and access arrangements for residents and caregivers.
The described system is intended to notify people who can check on a resident; the report does not establish that it detects or treats medical conditions. Its usefulness and privacy protections in everyday care settings have yet to be demonstrated in the material provided.
As an affiliate, we earn on qualifying purchases.
Further Testing Needed at Home
The study establishes a prototype and reports that its combined sensors performed better in the mock-home tests, but the source material does not announce a schedule for the next research phase. A key next step would be testing with residents in real homes over time, measuring detection accuracy, false alerts and the system’s reliability under ordinary living conditions.
Further evaluation would also need to address setup and maintenance, resident consent, data access and how alerts fit into caregivers’ existing responsibilities. Until those results are available, the technology should be understood as a research system with a proposed use, rather than a proven service that can keep older people safe or help them remain at home longer.
As an affiliate, we earn on qualifying purchases.
Key Questions
What does the home sensor system use?
It combines millimeter-wave radar for movement, low-resolution thermal sensors for broad body posture, and smart plugs that track patterns in appliance use.
Has the system been tested in older people’s homes?
The report describes tests in a mock domestic environment with six room layouts. It does not report a trial in occupied homes with older residents.
Can the prototype diagnose a health problem?
No such capability is established in the report. The system is intended to flag possible emergencies or unusual changes for a caregiver to check; those alerts would not confirm a diagnosis.
How does the system aim to protect privacy?
The prototype does not use cameras or wearable devices. Its thermal sensors produce low-resolution output intended to identify posture without displaying facial features or personal identity, according to the researchers.
When could the system be available?
The source report gives no release date or commercialization plan. Real-home performance, costs and deployment arrangements remain unreported.
Source: rss
Fall Picks
fall essentials
As an affiliate, we earn on qualifying purchases.
