Department of Electronics and Communication Engineering, Techno Main Salt Lake, Salt Lake City, EM-4/1, Sector-V, Kolkata 700091, West Bengal, India.
Department of Information Technology, Jadavpur University Second Campus, Jadavpur University, Plot No. 8, Salt Lake Bypass, LB Block, Sector III, Salt Lake City, Kolkata 700106, West Bengal, India.
Biosensors (Basel). 2022 Jun 7;12(6):393. doi: 10.3390/bios12060393.
Biomedical images contain a huge number of sensor measurements that can provide disease characteristics. Computer-assisted analysis of such parameters aids in the early detection of disease, and as a result aids medical professionals in quickly selecting appropriate medications. Human Activity Recognition, abbreviated as 'HAR', is the prediction of common human measurements, which consist of movements such as walking, running, drinking, cooking, etc. It is extremely advantageous for services in the sphere of medical care, such as fitness trackers, senior care, and archiving patient information for future use. The two types of data that can be fed to the HAR system as input are, first, video sequences or images of human activities, and second, time-series data of physical movements during different activities recorded through sensors such as accelerometers, gyroscopes, etc., that are present in smart gadgets. In this paper, we have decided to work with time-series kind of data as the input. Here, we propose an ensemble of four deep learning-based classification models, namely, 'CNN-net', 'CNNLSTM-net', 'ConvLSTM-net', and 'StackedLSTM-net', which is termed as 'Ensem-HAR'. Each of the classification models used in the ensemble is based on a typical 1D Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) network; however, they differ in terms of their architectural variations. Prediction through the proposed Ensem-HAR is carried out by stacking predictions from each of the four mentioned classification models, then training a Blender or Meta-learner on the stacked prediction, which provides the final prediction on test data. Our proposed model was evaluated over three benchmark datasets, WISDM, PAMAP2, and UCI-HAR; the proposed Ensem-HAR model for biomedical measurement achieved 98.70%, 97.45%, and 95.05% accuracy, respectively, on the mentioned datasets. The results from the experiments reveal that the suggested model performs better than the other multiple generated measurements to which it was compared.
生物医学图像包含大量可以提供疾病特征的传感器测量值。对这些参数进行计算机辅助分析有助于疾病的早期发现，从而帮助医务人员快速选择合适的药物。人体活动识别，简称“HAR”，是对常见人体测量值的预测，这些测量值包括行走、跑步、喝水、烹饪等动作。它对医疗保健服务领域非常有利，例如健身追踪器、老年人护理以及为将来使用而存档患者信息。可以作为输入提供给 HAR 系统的两种类型的数据是，第一，人类活动的视频序列或图像，第二，通过传感器记录的不同活动期间的物理运动的时间序列数据，例如智能小工具中的加速度计、陀螺仪等。在本文中，我们决定使用时间序列类型的数据作为输入。在这里，我们提出了一个由四个基于深度学习的分类模型组成的集成，即“CNN-net”、“CNNLSTM-net”、“ConvLSTM-net”和“StackedLSTM-net”，称为“Ensem-HAR”。集成中使用的每个分类模型都是基于典型的 1D 卷积神经网络（CNN）和长短时记忆（LSTM）网络构建的；但是，它们在架构上有所不同。通过提出的 Ensem-HAR 进行预测是通过堆叠来自上述四个分类模型的预测来完成的，然后在堆叠的预测上训练一个 Blender 或元学习者，这为测试数据提供最终预测。我们的建议模型在三个基准数据集 WISDM、PAMAP2 和 UCI-HAR 上进行了评估；在所述数据集上，用于生物医学测量的建议 Ensem-HAR 模型分别实现了 98.70%、97.45%和 95.05%的准确度。实验结果表明，所提出的模型比其他多个生成的测量值表现更好。
