Case study - Healthcare
Multi-room sensor monitoring for elderly care
Watch the story
See it in action.
Multi-room sensor monitoring with AI activity detection, voice control and a companion app to keep elderly people safe and independent.
What we built
Key capabilities.
Capture sensor data
Capture temperature, humidity, light, radar, smell and pressure across the house.
Plug-in hardware
A smart device that fits like a three-pin plug and enables sensor data capture.
AI activity detection
Activity detection using clustering and pattern recognition.
Voice control
Voice control makes reporting quick and easy.
Mobile app
An app to configure accounts and devices and view detailed analysis.
Analytics
Detailed, visual reporting makes decision-making easy.
Product
Inside the platform.
The journey
From challenge to results.
Challenges
- Health Risks of Independent Living: Seniors living alone are vulnerable to falls, health issues, and cognitive decline.
- Lack of Real-Time Awareness: Caregivers often hear about changes late and miss important health signs.
- Intrusive Monitoring Concerns: Traditional cameras and wearables may compromise privacy or cause discomfort.
- Unstructured Data Processing: Large volumes of raw sensor data are hard to turn into useful information.
Goals
- Improve Elderly Safety: Detect falls, routine deviations, and emergencies in real-time.
- Improve Health Monitoring: Identify patterns that indicate deteriorating health or cognitive decline.
- Reduce Caregiver Burden: Give caregivers automatic updates so they don’t have to watch constantly.
- Ensure Privacy and Comfort: Use non-intrusive sensors instead of invasive monitoring.
Actions
- Sensor Deployment Across Multiple Rooms: Temperature, humidity, and pressure sensors track environmental comfort.
- Light sensors detect activity during night and day.
- Radar sensors monitor movement, inactivity, and potential falls.
- Smell sensors identify hygiene issues, gas leaks, or spoiled food.
- Data Processing & AI-Based Classification: Cleaned and standardised the raw sensor data.
- Applied DBSCAN clustering to categorise activities.
- Detected anomalies such as extended inactivity or unusual movement patterns.
- Visualisation & Alerts: Heatmaps to track movement intensity across rooms.
- Time-series graphs to highlight routine changes.
- Caregiver alerts are triggered based on activity deviations.
Results
- Early Detection of Health Issues: Routine deviations helped detect early flu symptoms in an elderly individual.
- Identified prolonged inactivity in bed, prompting timely medical intervention.
- Emergency Response & Fall Detection: Radar sensors detected a fall in the bathroom, leading to immediate assistance.
- Caregivers received alerts when an individual remained motionless for too long.
- Cognitive Decline Insights: Identified nighttime wandering, an early sign of dementia.
- Detected increased forgetfulness (e.g., turning on appliances but not using them).
- Improved Caregiver Efficiency: Automated reports reduced the need for constant manual checks.
- Caregivers could deal with issues early instead of reacting to emergencies.
Let’s talk
Have a similar challenge?
Share a few details about your project and our team will get back to you with next steps.
- We reply within one business dayA senior engineer reads every message, not a sales bot.
- 30-minute discovery callWe map your goals, data and constraints together.
- A clear plan and estimateScope, architecture and timeline, usually within a week.