In recent years, Deep Learning (DL) models, including Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and Long Short-Term Memory (LSTM), have been widely used for Human Activities Recognition (HAR). They have achieved considerable performance improvements over classical Machine Learning (ML) approaches due to their excellent feature representation capabilities. Simple human activities are performed in sequential order with no overlaps or concurrent actions. The paucity of labeled training activity samples, high computational cost, and system resource requirements of deep learning architectures compared to lightweight models are some of the research challenges confronting the HAR community. We framed the lightweight DL-based CNNs, RNNs, and LSTM model for HAR to tackle these research challenges. The RNNs and LSTM have single layers with softmax activation functions, whereas the one-dimensional CNNs have two convolutional and single max-pooling layers. To evaluate the performance of our models, we used the publicly available benchmark WISDM experimental dataset, which includes the reading of six activities (walking, jogging, upstairs, downstairs, sitting, and standing) performed by 36 participants using a single accelerometer sensor. The experimental result illustrates the efficacy of our models in activity recognition, demonstrating that they attain higher accuracy while being computationally efficient.

近年来，深度学习（DL）模型，包括卷积神经网络（CNN）、循环神经网络（RNN）和长短期记忆（LSTM），已广泛用于人类活动识别（HAR）。由于其出色的特征表示能力，它们比传统的机器学习（ML）方法取得了相当大的性能改进。简单的人类活动是按顺序执行的，没有重叠或并发的动作。与轻量级模型相比，深度学习架构缺乏标记的训练活动样本、高计算成本和系统资源需求是 HAR 社区面临的一些研究挑战。我们为 HAR 构建了基于深度学习的轻量级 CNN、RNN 和 LSTM 模型来应对这些研究挑战。RNN 和 LSTM 具有带有 softmax 激活函数的单层，而一维 CNN 具有两个卷积层和单个最大池化层。为了评估我们模型的性能，我们使用了公开的基准 WISDM 实验数据集，其中包括 36 名参与者使用单个加速度传感器执行的六种活动（步行、慢跑、上楼、下楼、坐着和站立）的读数。实验结果说明了我们的模型在活动识别方面的有效性，证明它们在计算效率较高的同时获得了更高的准确性。其中包括读取 36 名参与者使用单个加速度计传感器执行的六项活动（步行、慢跑、上楼、下楼、坐着和站立）。实验结果说明了我们的模型在活动识别方面的有效性，证明它们在计算效率较高的同时获得了更高的准确性。其中包括读取 36 名参与者使用单个加速度计传感器执行的六项活动（步行、慢跑、上楼、下楼、坐着和站立）。实验结果说明了我们的模型在活动识别方面的有效性，证明它们在计算效率较高的同时获得了更高的准确性。