Dywave: Event-Aligned Dynamic Tokenization for Heterogeneous IoT Sensing Signal
This work addresses the challenge of tokenizing non-stationary, multi-scale IoT signals for downstream tasks like activity recognition and emotion monitoring, offering significant efficiency and accuracy gains.
Dywave proposes a dynamic tokenization framework for heterogeneous IoT sensing signals that aligns tokens with intrinsic temporal structures and physical events, achieving up to 12% higher accuracy and 75% reduction in token length across five real-world datasets.
Internet of Things (IoT) systems continuously collect heterogeneous sensing signals from ubiquitous sensors to support intelligent applications such as human activity analysis, emotion monitoring, and environmental perception. These signals are inherently non-stationary and multi-scale, posing unique challenges for standard tokenization techniques. This paper proposes Dywave, a dynamic tokenization framework for IoT sensing signals that constructs compact input representations aligned with intrinsic temporal structures and underlying physical events. Dywave leverages wavelet-based hierarchical decomposition, identifies meaningful temporal boundaries corresponding to underlying semantic events, and adaptively compresses redundant intervals while preserving temporal coherence. Extensive evaluations on five real-world IoT sensing datasets across activity recognition, stress assessment, and nearby object detection demonstrate that Dywave outperforms state-of-the-art methods by up to 12% in accuracy, while improving computational efficiency by reducing input token lengths by up to 75% across mainstream sequence models. Moreover, Dywave exhibits improved robustness to domain shifts and varying sequence lengths.