HARMamba：基于双向Mamba的高效轻量可穿戴传感器人体活动识别
HARMamba: Efficient and Lightweight Wearable Sensor Human Activity Recognition Based on Bidirectional Mamba
AI总结：
本文提出HARMamba，一种结合选择性双向状态空间模型与硬件感知设计的轻量级可穿戴传感器人体活动识别架构，在四个公开数据集上以显著降低的计算和内存需求取得了领先的识别精度。
摘要：
基于可穿戴传感器的人体活动识别（HAR）是活动感知中的一个关键研究领域。然而，实现高效率和长序列识别仍然是一项挑战。尽管时序深度学习模型（如CNN、RNN和Transformer）得到了广泛研究，但它们庞大的参数量往往带来显著的计算和内存限制，使其不太适合资源受限的移动健康应用。本研究提出了HARMamba，一种创新的轻量级且多功能的HAR架构，它结合了选择性双向状态空间模型（State Spaces Model）和硬件感知设计。为了在实际场景中优化实时资源消耗，HARMamba采用线性递归机制和参数离散化，使其能够选择性地关注相关输入序列，同时高效地融合扫描和重计算操作。该模型使用独立通道处理传感器数据流，将每个通道划分为图像块（patch），并在序列末尾附加分类令牌。它利用位置嵌入来表示序列顺序。图像块序列随后由HARMamba Block处理，分类头最终输出活动类别。HARMamba Block是HARMamba架构的基本组成部分，能够有效捕获更具判别力的活动序列特征。HARMamba优于当代最先进的框架，在显著降低计算和内存需求的同时，提供了相当或更好的准确率。其有效性已在4个公开可用的数据集上得到广泛验证，即PAMAP2、WISDM、UNIMIB SHAR和UCI。HARMamba在这四个数据集上的F1分数分别为99.74%、99.20%、88.23%和97.01%。
英文摘要：
Wearable sensor-based human activity recognition (HAR) is a critical research domain in activity perception. However, achieving high efficiency and long sequence recognition remains a challenge. Despite the extensive investigation of temporal deep learning models, such as CNNs, RNNs, and transformers, their extensive parameters often pose significant computational and memory constraints, rendering them less suitable for resource-constrained mobile health applications. This study introduces HARMamba, an innovative light-weight and versatile HAR architecture that combines selective bidirectional State Spaces Model and hardware-aware design. To optimize real-time resource consumption in practical scenarios, HARMamba employs linear recursive mechanisms and parameter discretization, allowing it to selectively focus on relevant input sequences while efficiently fusing scan and recompute operations. The model employs independent channels to process sensor data streams, dividing each channel into patches and appending classification tokens to the end of the sequence. It utilizes position embedding to represent the sequence order. The patch sequence is subsequently processed by HARMamba Block, and the classification head finally outputs the activity category. The HARMamba Block serves as the fundamental component of the HARMamba architecture, enabling the effective capture of more discriminative activity sequence features. HARMamba outperforms contemporary state-of-the-art frameworks, delivering comparable or better accuracy with significantly reducing computational and memory demands. It's effectiveness has been extensively validated on 4 publically available datasets namely PAMAP2, WISDM, UNIMIB SHAR and UCI. The F1 scores of HARMamba on the four datasets are 99.74%, 99.20%, 88.23% and 97.01%, respectively.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
