面向人类活动识别的经典模型、深度模型与生成式模型基准测试
Benchmarking Classical, Deep, and Generative Models for Human Activity Recognition
AI总结：
该研究针对人类活动识别任务，在五个基准数据集上对比了经典机器学习、深度学习、受限玻尔兹曼机三类模型的性能，发现CNN模型表现最优，为HAR任务的模型选型提供了参考依据。
摘要：
随着搭载传感器的设备与大型数据集的应用日益广泛，人类活动识别（Human Activity Recognition，HAR）的重要性显著提升。本文评估了三类模型在HAR任务上的性能：经典机器学习模型、深度学习架构以及受限玻尔兹曼机（Restricted Boltzmann Machines，RBMs），实验采用五个核心HAR基准数据集：UCI-HAR、OPPORTUNITY、PAMAP2、WISDM和Berkeley MHAD。本文评估了决策树、随机森林、卷积神经网络（Convolutional Neural Networks，CNN）、深度信念网络（Deep Belief Networks，DBNs）等多种模型，采用准确率、精确率、召回率、F1值等指标开展全面对比。结果显示，CNN模型在所有数据集上均表现最优，在Berkeley MHAD数据集上优势尤为突出；随机森林等经典模型在小型数据集上表现良好，但在处理更大、更复杂的数据时存在局限；基于RBM的模型也展现出可观潜力，尤其在特征学习方面。本文提供了详细的对比分析，可帮助研究人员为HAR任务选择最合适的模型。
英文摘要：
Human Activity Recognition (HAR) has gained significant importance with the growing use of sensor-equipped devices and large datasets. This paper evaluates the performance of three categories of models : classical machine learning, deep learning architectures, and Restricted Boltzmann Machines (RBMs) using five key benchmark datasets of HAR (UCI-HAR, OPPORTUNITY, PAMAP2, WISDM, and Berkeley MHAD). We assess various models, including Decision Trees, Random Forests, Convolutional Neural Networks (CNN), and Deep Belief Networks (DBNs), using metrics such as accuracy, precision, recall, and F1-score for a comprehensive comparison. The results show that CNN models offer superior performance across all datasets, especially on the Berkeley MHAD. Classical models like Random Forest do well on smaller datasets but face challenges with larger, more complex data. RBM-based models also show notable potential, particularly for feature learning. This paper offers a detailed comparison to help researchers choose the most suitable model for HAR tasks.
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。
