发表机构
RPTU, DFKI（RPTU，DFKI）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对可穿戴HAR现有轻量循环模型的局限，提出全卷积框架LITEWAY，在16个HAR数据集上实现具竞争力性能，同时大幅缩减模型体积与能耗。
AI 中文摘要
可穿戴设备上的人体活动识别（HAR）因深度学习模型受限于资源受限设备的计算与能量约束，仍具挑战性。现有轻量方法常依赖循环架构（如GRU、LSTM），限制并行性并增加推理延迟。本文提出LITEWAY，一种适用于多通道传感器时间序列的模态无关全卷积框架，用结构化卷积分解替代循环时序建模。LITEWAY结合轻量卷积块、步长时序处理及卷积注意力池化，在高效捕获时序依赖的同时降低计算复杂度。我们在16个HAR数据集上对比TinyHAR、TinierHAR与MLP-HAR评估LITEWAY，其达到具竞争力的宏F1值，且模型体积较TinyHAR与TinierHAR分别减少4.06倍-9.52倍（轻量版）、3.87倍-9.07倍（完整版）；部署实验显示，其能量消耗较TinierHAR与MLP-HAR分别降低2.29倍-3.14倍（轻量版）、1.46倍-2.01倍（完整版），凸显全卷积时序建模在可穿戴HAR中的高效性，源代码公开于指定网址。
英文摘要
Wearable human activity recognition (HAR) remains challenging due to the computational and energy constraints of deep learning models on resource-limited devices. Existing lightweight approaches often rely on recurrent architectures (e.g., GRU and LSTM), limiting parallelism and increasing inference latency. We propose LITEWAY, a modality-agnostic, fully convolutional framework for multichannel sensor time series that replaces recurrent temporal modeling with structured convolutional decomposition. LITEWAY combines lightweight convolutional blocks, strided temporal processing, and convolution-attention pooling to efficiently capture temporal dependencies while reducing computational complexity. We evaluate LITEWAY on 16 HAR datasets against TinyHAR, TinierHAR, and MLP-HAR. LITEWAY achieves competitive macro F1 while reducing model size by 4.06x-9.52x (Light) and 3.87x-9.07x (Full) compared with TinyHAR and TinierHAR. Deployment experiments further show energy reductions of 2.29x-3.14x (Light) and 1.46x-2.01x (Full) compared with TinierHAR and MLP-HAR, highlighting efficient fully convolutional temporal modeling for wearable HAR. The source code is publicly available at https://github.com/dominique-nshimyimana/liteway.
Commentsaccepted at UbiComp / ISWC 2026
