TL;DR
Researchers at Nottingham Trent University and Integrated System Technologies developed and tested a home-monitoring prototype that combines radar, thermal sensors and smart plugs. In a mock home study, using data from all three sensor types improved activity-recognition performance, but real-world effectiveness and readiness for routine use remain unclear.
Researchers at Nottingham Trent University and technology company Integrated System Technologies have developed and tested a home sensor system intended to identify changes in older adults’ daily activity and possible emergencies without using cameras or wearable devices. The prototype combines radar, low-resolution thermal sensors and smart plugs, with artificial intelligence analyzing their data; the reported testing took place in a mock domestic setting, not in residents’ homes.
Get health and wellness essentials delivered free with Prime
- Fast, free delivery on millions of items
- Prime Video, Amazon Music and more included
- Member-only deals all year
The system uses millimeter-wave radar to detect movement, thermal sensors to distinguish postures such as sitting, standing, walking and lying down, and smart plugs to track activity involving connected household appliances. The study says the thermal data are highly pixelated and designed not to show facial features or identify a person. Sensors can be placed discreetly at selected locations around a home.
The AI is intended to learn a resident’s usual patterns over time and flag activity that differs from them. Researchers describe possible signals including a fall, prolonged inactivity, changes in mobility or sleep, or a break in ordinary household routines. If the system detects a possible emergency, the proposed setup would notify care professionals or loved ones so they can check on the resident remotely or in person.
For the study, the team assessed the technologies in a mock domestic environment with six room layouts, including bedrooms and living areas with different furniture arrangements. Activities were recorded to test recognition of movement and posture. The researchers report that combining data from all three sensor types improved performance compared with using the technologies separately. The source does not provide a numerical accuracy result in its summary.
Monitoring Without Cameras or Wearables
The research addresses a practical tension in home care: some older people want to remain in their own homes, while families and care workers may want ways to notice a fall or a gradual change in routine. A system that can detect activity without recording ordinary camera images or requiring a wearable could offer another option for checking on someone who lives alone.
That potential should not be confused with demonstrated health outcomes. The reported work tests activity recognition in a controlled mock home; it does not establish that the system can reliably identify heart attacks, strokes or other illnesses in everyday use, or that it enables people to live independently for longer. Its value will depend on dependable alerts, clear consent and privacy safeguards, and appropriate responses from caregivers.
Products Worth Considering

Levoit Core 300S-P Smart WiFi Air Purifier for Home and Pets

Withings Body Smart Wi-Fi and Bluetooth Body Composition Scale

OMRON Complete 2-in-1 Upper Arm Blood Pressure Monitor with EKG
As an affiliate, we earn on qualifying purchases.
How the Three Sensors Work Together
The project is described in the paper Privacy-Preserving Ambient Sensing for Activities of Daily Living: Multimodal Radar-Thermal Human Activity Recognition and Smart Plug Appliance Recognition, published in the journal Sensors. The listed research team includes members of NTU’s School of Architecture, Design and the Built Environment and School of Science and Technology, alongside staff from Integrated System Technologies.
The three inputs capture different kinds of information: radar detects movement, thermal sensors estimate body posture, and smart plugs record appliance use associated with everyday tasks. The researchers’ reported finding that the combined system performed better in testing suggests that these signals may complement one another. It does not, on its own, show how the system would perform across a broader range of homes, residents or unexpected events.
“This technology aims to support the growing number of older adults who wish to remain in their own homes for longer, rather than moving into residential care.”
— Dr. Yangang Xing, lead researcher at Nottingham Trent University
Real-World Reliability Remains Untested
The source describes testing in a mock home with six layouts, but does not report trials in occupied homes or provide details about the number and characteristics of participants. It also does not give specific accuracy, false-alarm or missed-event rates, or explain how well the system distinguished a medical emergency from an ordinary change in routine.
It is not clear when the prototype might be tested in real households, whether it has regulatory approval, what it would cost to install and maintain, or how alerts would be managed at all hours. The reported work supports further investigation; it does not establish that the system can diagnose a condition or replace medical assessment, emergency services or direct care.
Further Testing Will Shape Deployment
The researchers’ next steps are not specified in the supplied report. Further evaluation would need to establish how the system performs in lived-in homes and varied routines, including how often it raises false alarms or misses important events. Assessment of residents’ consent, data handling, installation needs and caregiver response procedures would also help determine whether the approach is suitable for wider use.
Until those details are available, the system should be understood as a research prototype with potential applications, rather than an established home-care service. The paper is published in Sensors under the title given above, with DOI 10.3390/s26165066.
Key Questions
What does the home sensor system monitor?
It combines radar for movement, thermal sensors for posture and smart plugs for appliance-use patterns. The research describes using those signals to identify ordinary activity and possible changes from a person’s routine.
Does the system use cameras or wearable devices?
The reported prototype is designed to work without cameras or wearables. Its thermal output is described as low-resolution and pixelated to limit identification of facial features and personal identity.
Has it been shown to detect strokes or heart attacks reliably?
No such real-world reliability is established in the supplied report. Researchers describe these as possible events the system aims to flag, but the reported testing was in a mock domestic environment and the summary gives no clinical detection rates.
Has the system been tested in older people’s homes?
The report describes testing in a mock home with six room layouts. It does not say that the prototype has been evaluated in occupied homes or provide a schedule for household trials.
Is the system available to buy?
The source describes a research prototype and does not announce a commercial launch, price or availability date. Those details remain unspecified.
Source: rss
