Researchers at the National University of Singapore have built an AI-powered sensor platform that detects fatigue with 92% accuracy. The system uses a new material called metahydrogel combined with machine learning to track subtle changes in heart rate, blood pressure, and ECG signals that indicate mental exhaustion.
The breakthrough addresses a major gap in health monitoring. Unlike physical injuries, fatigue develops gradually without obvious symptoms. Current assessments rely mainly on questionnaires, which are subjective and only capture snapshots of how people feel. This new system provides continuous, objective monitoring of mental and physical states.
How does it work?
The sensor platform tackles the biggest challenge in wearable health tech: separating meaningful body signals from noise caused by movement. The metahydrogel material has two built-in filtering mechanisms:
- A nanoparticle structure that absorbs movement-related vibrations
- A liquid component that lets heart signals pass through while blocking unwanted noise
A machine learning algorithm then cleans up any remaining interference while preserving the important physiological signals.
The team trained their fatigue detection model by collecting continuous physiological data from participants during various activities, including simulated driving tasks. This data was paired with validated fatigue assessment scores to teach the system to recognize patterns associated with exhaustion.
Why does it matter?
The system achieved impressive technical specs that meet clinical-grade standards:
- 37 decibels ECG signal-to-noise ratio during movement
- Blood pressure deviation of around 3 millimeters of mercury
- 92% accuracy in fatigue detection (up from 64% without the special sensor material)
“Current smartwatches typically achieve ECG signal-to-noise ratios of 10-20 dB, which can decrease by approximately 40% under motion due to artefacts and unstable contact. Our system achieves around 37 dB during daily activities,” said Dr Tian Guo, the study’s first author.
Beyond fatigue tracking, the system also reduces noise in other body signals including heart and breathing sounds, voice, brain activity, and eye movements.
The context
Fatigue and mental health issues are increasingly serious public health concerns. They affect cognitive performance, decision-making, productivity, and safety in everyday settings. The problem is that these states often develop gradually before people become aware of them.
Previous approaches have tried to solve noisy sensor data with software fixes after the fact. But the Singapore team tackled the problem at the source – the sensor-body interface itself.
“Rather than relying solely on software to clean up noisy data, the team tackled the problem at the sensor-body interface itself,” NUS noted in a media release.
Dr Tian explained that software-based signal processing “typically works after noise has already entered the system,” making it difficult to remove motion artifacts without affecting the underlying physiological signals. Many existing algorithms also “lack sufficient selectivity,” often suppressing meaningful signals alongside noise.
The work builds on about four years of research, with the past two years focused on developing the metahydrogel approach. The team is now working with mental health specialists to identify the most relevant physiological signals for clinical use and seeking industry partners to turn the platform into a commercial product.
“While the platform is still at a research stage, our immediate efforts are directed towards manufacturability, clinical interpretability, and large-scale validation,” said study lead Prof Ho Ghim Wei.