About one in three employees in Singapore report feeling burnt out—one of the highest rates globally. Burnout and chronic fatigue carry a substantial economic cost and pose serious risks in professions where alertness is critical.
Yet diagnosing fatigue and related mental health conditions today relies largely on self-reported questionnaires. They are subjective, intermittent and poorly suited to real-time evaluation. In other words, by the time problems are detected, a dangerous window could already have opened.
The limitations of wearables
Wearable devices could fill the gap. They are designed to track heart signals and other markers which are linked to stress and fatigue. But there is a catch: their readings become significantly worse during movement. Every time you walk, type, or shift in your seat, it creates noise—motion artefacts—interference that can drown out the signals these devices are trying to capture. The fixes available today typically address only one type of noise or a narrow frequency band.
A research team led by Professor Ho Ghim Wei from the Department of Electrical and Computer Engineering under the College of Design and Engineering at the National University of Singapore, with Research Fellow Dr Tian Guo as first author, has developed a metahydrogel platform integrated with AI-driven signal processing that suppresses multiple sources of motion noise simultaneously.
Powered by artificial intelligence, the soft and skin-like hydrogel sensor demonstrates superior performance, especially during movement, when reducing signal noise is critical // Credit: NUSTheir findings—published in Nature Sensors on 24 March 2026—have been striking. The system delivers an electrocardiograph (ECG) signal-to-noise ratio (SNR) of 37.36 dB and blood pressure deviation as low as 3 mmHg during movement—think of it like hearing a whisper clearly in a crowded room. That accuracy that meets ISO clinical-grade standards and outperforms commercial trackers currently available in the market.
Combined with machine learning, the platform classifies fatigue levels with 92 per cent accuracy, pointing towards objective, continuous mental health monitoring in real-world settings.
Filtering noise at the source
Most wearables rely solely on software to clean up noisy data. The team tackled the problem at the sensor-body interface itself. The metahydrogel artefact-mitigating platform (MAP) combines two filtering methods in one material.
Nanoparticles self-assembled into periodic bands within the hydrogel act like a soundproofing panel, scattering and absorbing mechanical vibrations to block movement noise within targeted frequency ranges.
At the same time, by controlling how quickly ions travel through the gel, a biocompatible glycerol-water electrolyte only lets low-frequency heart signals (below 30 Hz) pass through while suppressing higher-frequency muscle electrical noise. A machine-learning denoising algorithm then removes any remaining noise.
The result? Combining improved hardware with smart algorithms, the system boosts signal quality from 5.19 dB to 37.36 dB, raising ECG peak-detection accuracy from 52 per cent to 93 per cent and making it easier to tell fatigue-related patterns from normal heart rhythms.
The platform is also soft enough to match the mechanical properties of biological tissue, breathable with a water vapour transmission rate exceeding that of human skin and durable under repeated stretching.
“Compared with current commercial devices, our metahydrogel platform demonstrates superior performance, particularly under motion conditions where artefact suppression is critical. Current smartwatches typically achieve ECG signal-to-noise ratios of 10-20 dB, which can decrease by approximately 40 per cent under motion due to artefacts and unstable contact. Our system achieves around 37 dB during daily activities,” said Tian.
From stable signals to mental-state decoding
Fatigue is not invisible. It disrupts the autonomic nervous system, leaving measurable traces in your body—in your heart rate variability, blood pressure patterns and ECG waveform features. However, these traces can only be seen if the sensor can capture them cleanly during everyday activity.
The team built a fully integrated, flexible wearable MAP system with wireless transmission and used it to monitor participants over multiple days, including simulated driving tasks designed to induce fatigue.