<p>Human Activity Recognition (HAR) is the task of automatically identifying and characterizing human behaviors from sensor or video observations. HAR is a vibrant field with significant practical importance. Recent advances in artificial intelligence and multimodal sensing have led to a surge in data scale and complexity, imposing higher demands on models’ discriminability and generalizability. Traditional machine learning relies on hand-crafted features and struggles to handle complex scenarios. Although deep learning enables automatic representation learning, it still faces bottlenecks in cross-scenario transfer as well as inference and storage overheads. To address these issues, we propose the Hash-MMDC method, which adopts a ResNet backbone and integrates attention-based feature selection to produce efficient, discriminative representations; in the hash embedding stage, we approximate the non-differentiable <InlineEquation ID="IEq1"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="44443_2025_297_Article_IEq1.gif" Format="GIF" Height="12" Rendition="HTML" Resolution="72" Type="Linedraw" Width="30" /> </InlineMediaObject> <EquationSource Format="TEX">$sgn$</EquationSource> <EquationSource Format="MATHML"><math> <mrow> <mi mathvariant="italic">sgn</mi> </mrow> </math></EquationSource> </InlineEquation> with a differentiable <InlineEquation ID="IEq2"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="44443_2025_297_Article_IEq2.gif" Format="GIF" Height="14" Rendition="HTML" Resolution="72" Type="Linedraw" Width="39" /> </InlineMediaObject> <EquationSource Format="TEX">$tanh$</EquationSource> <EquationSource Format="MATHML"><math> <mrow> <mi mathvariant="italic">tanh</mi> </mrow> </math></EquationSource> </InlineEquation> to obtain near-binary hash codes (e.g., <InlineEquation ID="IEq3"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="44443_2025_297_Article_IEq3.gif" Format="GIF" Height="16" Rendition="HTML" Resolution="72" Type="Linedraw" Width="51" /> </InlineMediaObject> <EquationSource Format="TEX">$+1, -1$</EquationSource> <EquationSource Format="MATHML"><math> <mrow> <mo>+</mo> <mn>1</mn> <mo>,</mo> <mo>-</mo> <mn>1</mn> </mrow> </math></EquationSource> </InlineEquation>); furthermore, we maximize class-wise Maximum Mean Discrepancy (MMD) in the hash space to enhance inter-class separability and employ a self-updating center loss to reduce intra-class dispersion. We evaluate the proposed method on multiple benchmark HAR datasets (OPPORTUNITY, PAMAP2, WISDM, UniMiB_SHAR), and the results show that our approach outperforms mainstream baseline models in accuracy and exhibits robust generalization, demonstrating its potential for deployment in real-world IoT scenarios.</p>

Hash-MMDC: Enhancing human activity recognition with hash-based optimization

期刊论文
出版模式：

开放获取
发表日期：

2025年10月20日

查看全文

Shi Cheng,
Qiang Liu,
Jie Wan

摘要

Human Activity Recognition (HAR) is the task of automatically identifying and characterizing human behaviors from sensor or video observations. HAR is a vibrant field with significant practical importance. Recent advances in artificial intelligence and multimodal sensing have led to a surge in data scale and complexity, imposing higher demands on models’ discriminability and generalizability. Traditional machine learning relies on hand-crafted features and struggles to handle complex scenarios. Although deep learning enables automatic representation learning, it still faces bottlenecks in cross-scenario transfer as well as inference and storage overheads. To address these issues, we propose the Hash-MMDC method, which adopts a ResNet backbone and integrates attention-based feature selection to produce efficient, discriminative representations; in the hash embedding stage, we approximate the non-differentiable $sgn$ $sgn$ with a differentiable $tanh$ $\tanh$ to obtain near-binary hash codes (e.g., $+1, -1$ $+ 1, - 1$ ); furthermore, we maximize class-wise Maximum Mean Discrepancy (MMD) in the hash space to enhance inter-class separability and employ a self-updating center loss to reduce intra-class dispersion. We evaluate the proposed method on multiple benchmark HAR datasets (OPPORTUNITY, PAMAP2, WISDM, UniMiB_SHAR), and the results show that our approach outperforms mainstream baseline models in accuracy and exhibits robust generalization, demonstrating its potential for deployment in real-world IoT scenarios.