You Don't Need Attention: Gated Convolutional Modeling for Watch-Based Fall Detection

TL;DR

This paper introduces Gated-CNN, a lightweight convolutional model with sigmoid gating that improves fall detection accuracy on smartwatch data, outperforming attention-based methods in efficiency and localization.

Contribution

The paper proposes a novel Gated-CNN architecture that replaces attention with sigmoid gating for efficient, accurate fall detection on wearable devices.

Findings

Achieved over 90% F1-score across five datasets.

Real-time deployment on a smartwatch yielded 97% F1-score and 98% accuracy.

Outperformed Transformer-based baselines in accuracy and efficiency.

Abstract

Existing deep learning approaches for wearable fall detection systems rely on self-attention mechanisms that impose quadratic computational overhead, distributing weights across all time steps. This global weight distribution impairs the precise localization of the brief impact signatures that characterize falls within short, fixed-length windows. To overcome this challenge, we propose Gated-CNN, a lightweight dual-stream architecture that processes accelerometer and gyroscope streams through independent one-dimensional convolutional feature extractors, followed by (i) a sigmoid gating module that selectively suppresses uninformative background activations while amplifying fall-discriminative features, (ii) a global average pooling layer that compresses each stream into a compact fixed-length descriptor, and (iii) a shared classification head that fuses both descriptors for binary fall prediction. For offline evaluation, we evaluate the model across five wrist-mounted inertial measurement unit (IMU) datasets, achieving average F1-scores of 93%, 93%, 90%, 91%, and 90% on SmartFallMM, WEDA-Fall, FallAllD, UMAFall, and UP-Fall, outperforming Transformer baselines. For real-time evaluation, we deployed the model on a Google Pixel Watch 3 and tested across 12 participants. The model achieves an average F1-score of 97% and an accuracy of 98% with zero missed falls, showing that sigmoid gating offers a more structurally aligned and computationally efficient alternative to attention for commodity smartwatch-based fall detection.