激活函数与模型优化器对使用不同深度学习模型的人体活动识别系统性能的影响
Effect of Activation Function and Model Optimizer on the Performance of Human Activity Recognition System Using Various Deep Learning Models
AI总结:
本研究探讨了激活函数与优化器对不同深度学习模型在人体活动识别中的影响,发现ConvLSTM结合Adam或RMSprop可达到99%的准确率,优于BiLSTM在不同数据集上的表现。
摘要:
人体活动识别(HAR)在医疗、监控和创新环境中发挥着重要作用,可靠的行动识别支持及时的决策和自动化。尽管基于深度学习的HAR系统被广泛采用,但激活函数(AFs)和模型优化器(MOs)对性能的影响尚未得到充分分析,特别是它们的组合如何影响模型在实际场景中的行为。大多数现有研究集中在架构设计上,而AF和MO选择之间的相互作用仍相对未被探索。在本工作中,我们研究了三种常用的激活函数(ReLU、Sigmoid和Tanh)与四种优化算法(SGD、Adam、RMSprop和Adagrad)结合使用,采用两种递归深度学习架构,即BiLSTM和ConvLSTM。实验在HMDB51和UCF101数据集中的六个医疗相关活动类别上进行,考虑了它们在医疗导向的HAR应用中的适用性。我们的实验结果表明,ConvLSTM在两个数据集上均优于BiLSTM。ConvLSTM结合Adam或RMSprop,达到高达99.00%的准确率,展示了强大的时空学习能力和稳定的性能。虽然BiLSTM在UCF101上表现良好,准确率接近98.00%,但在HMDB51上性能下降到约60.00%,表明其在不同数据集上的鲁棒性有限,对AF和MO的变化敏感性较弱。本研究为优化HAR系统提供了实用见解,特别是对于实时医疗环境中需要快速和精确活动检测的应用至关重要。
英文摘要:
Human Activity Recognition (HAR) plays a vital role in healthcare, surveillance, and innovative environments, where reliable action recognition supports timely decision-making and automation. Although deep learning-based HAR systems are widely adopted, the impact of Activation Functions (AFs) and Model Optimizers (MOs) on performance has not been sufficiently analyzed, particularly regarding how their combinations influence model behavior in practical scenarios. Most existing studies focus on architecture design, while the interaction between AF and MO choices remains relatively unexplored. In this work, we investigate the effect of three commonly used activation functions (ReLU, Sigmoid, and Tanh) combined with four optimization algorithms (SGD, Adam, RMSprop, and Adagrad) using two recurrent deep learning architectures, namely BiLSTM and ConvLSTM. Experiments are conducted on six medically relevant activity classes selected from the HMDB51 and UCF101 datasets, considering their suitability for healthcare-oriented HAR applications. Our experimental results show that ConvLSTM consistently outperforms BiLSTM across both datasets. ConvLSTM, combined with Adam or RMSprop, achieves an accuracy of up to 99.00%, demonstrating strong spatio-temporal learning capabilities and stable performance. While BiLSTM performs reasonably well on UCF101, with accuracy approaching 98.00%, its performance drops to approximately 60.00% on HMDB51, indicating limited robustness across datasets and weaker sensitivity to AF and MO variations. This study provides practical insights for optimizing HAR systems, particularly for real-world healthcare environments where fast and precise activity detection is critical.
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。