Abstract
Human Activity Recognition (HAR) on resource constrained wearables requires models that balance accuracy against strict memory and computational budgets. State of the art lightweight architectures such as TinierHAR (34K parameters) and TinyHAR (55K parameters) achieve strong accuracy, but exceed memory budgets of microcontrollers with limited SRAM once operating system overhead is considered. We present MicroBi-ConvLSTM, an ultra-lightweight convolutional-recurrent architecture achieving 11.4K parameters on average through two stage convolutional feature extraction with 4x temporal pooling and a single bidirectional LSTM layer. This represents 2.9x parameter reduction versus TinierHAR and 11.9x versus DeepConvLSTM while preserving linear O(N) complexity. Evaluation across eight diverse HAR benchmarks shows that MicroBi-ConvLSTM maintains competitive performance within the ultra-lightweight regime: 93.41% macro F1 on UCI-HAR, 94.46% on SKODA assembly gestures, and 88.98% on Daphnet gait freeze detection. Systematic ablation reveals task dependent component contributions where bidirectionality benefits episodic event detection, but provides marginal gains on periodic locomotion. INT8 post training quantization incurs only 0.21% average F1-score degradation, yielding a 23.0 KB average deployment footprint suitable for memory constrained edge devices.
Abstract (translated)
在资源有限的可穿戴设备上进行人体活动识别（HAR）需要能够平衡精度和严格内存及计算预算的模型。尽管像TinierHAR（含34K参数）和TinyHAR（含55K参数）这样的轻量级架构实现了强大的准确性，但一旦考虑了操作系统的开销后，这些模型还是超出了资源有限的微控制器的SRAM存储限制。 我们提出了一种名为MicroBi-ConvLSTM的超轻量化卷积递归架构，在两阶段卷积特征提取的基础上（其中时间池化比为4倍），配合一个单向双向LSTM层，平均参数量仅为11.4K。这相对于TinierHAR减少了2.9倍参数，并且相比DeepConvLSTM减少达11.9倍的参数数量，同时保持线性O(N)复杂度。 在八个不同的人体活动识别基准测试中，MicroBi-ConvLSTM展示了其在超轻量级模型下的竞争力：UCI-HAR基准上达到93.41%的宏F1分数，在SKODA装配手势检测上为94.46%，而Daphnet步态冻结检测则达到了88.98%。系统性消融实验揭示了任务依赖性的组件贡献，其中双向性在事件检测中表现出了明显的优势，但在周期性运动检测中的边际收益有限。 INT8后训练量化仅导致平均F1分数下降0.21%，但可以将模型的部署大小降至约23.0KB，这对于内存受限的边缘设备来说是理想的。
URL
https://arxiv.org/abs/2602.06523
