Precise rotational speed measurement is vital for performance, safety, and predictive maintenance in industrial, automotive, and consumer systems. Magnetic tachometers offer key advantages—non-intrusive operation, robustness to dust and liquids, and sensing through occlusions—making them effective where optical and RF methods fail. However, their range is widely believed to be limited to a few centimeters, restricting real-world use. This paper presents MagTach, a magnetic tachometry system that overturns this long-accepted range limitation. Our key observation is that higher-order harmonics in many motors’ magnetic emissions remain detectable far beyond the range where the fundamental falls below the noise floor. Building on this insight, we develop a harmonic-aware multi-task learning framework (HarmoNet-MTL) that jointly detects harmonic structures and estimates the rotation frequency under low signal-to-noise ratio. To support long-range harmonic sensing, we co-design hardware and algorithms, including inductive sensors optimized for harmonic responsiveness, a spatial–frequency filtering pipeline that suppresses power-line interference, and harmonic product spectrum processing to amplify harmonic patterns. Collectively, MagTach extends the effective range from only a few centimeters to around one meter, enabling meter-scale, hand-held, and through-obstacle operation. Across diverse motors, orientations, and environmental conditions, MagTach achieves state-of-the-art accuracy, with mean estimation errors of 0.27% at 50 cm, 0.43% at 70 cm, and 0.51% at 100 cm, while preserving the core benefits of magnetic sensing.

Distracted driving is a major cause of road accidents. Multiple targets, including the driver’s head and two hands, need to be monitored to detect unsafe driving behaviors. Previous driving monitoring systems rely on cameras or wearable sensors, yet these solutions have multiple limitations, including insufficient monitoring or requiring multiple wearable components. This paper proposes a new driving behavior monitoring system for improving road safety, which achieves unsafe driving behavior monitoring using only one pair of unobtrusive Commercial-Off-The-Shelf (COTS) smart glasses. The proposed system monitors the two hand movements using the front-facing camera, and detects head movements using the onboard sensors. A proof-of-concept system was implemented on a pair of Android-powered smart glasses, and a small-scale emulation study was conducted in the lab environment. Experiments show our system can monitor steering wheel control techniques and common head turn motions with f1 scores of 93.1% and 99%, respectively.