Human activity recognition (HAR) is one of the important research areas in pervasive computing. Among HAR, sensor-based activity recognition refers to acquiring a high-level knowledge about human activities from readings of many low-level sensors. In recent years, although the existing methods of deep learning (DL) have been widely used for sensor-based HAR with some good performance, they still face such challenges as feature extraction and characterization, continuous action segmentation in dealing with time series problems. In this study, a multichannel fusion model is proposed with the idea of dividing. In this proposed architecture, a multichannel convolutional neural network (CNN) is used to enhance the ability to extract features at different scales, and then the fused features are fed into the gated recurrent unit (GRU) for feature labeling and enhanced feature representation, through the learning of temporal relationships. Finally, the multichannel CNN-GRU model is designed using global average pooling (GAP) to connect the feature maps with the final classification. The model performance was conducted on three benchmark datasets of WISDM, UCI-HAR, and PAMAP2 with the accuracy of 96.41%, 96.67%, and 96.25% respectively. The results show that the proposed model demonstrates better activity detection capability than some of the reported results.

Human Activity Recognition (HAR) is an important research area in human–computer interaction and pervasive computing. In recent years, many deep learning (DL) methods have been widely used for HAR, and due to their powerful automatic feature extraction capabilities, they achieve better recognition performance than traditional methods and are applicable to more general scenarios. However, the problem is that DL methods increase the computational cost of the system and take up more system resources while achieving higher recognition accuracy, which is more challenging for its operation in small memory terminal devices such as smartphones. So, we need to reduce the model size as much as possible while taking into account the recognition accuracy. To address this problem, we propose a multi-scale feature extraction fusion model combining Convolutional Neural Network (CNN) and Gated Recurrent Unit (GRU). The model uses different convolutional kernel sizes combined with GRU to accomplish the automatic extraction of different local features and long-term dependencies of the original data to obtain a richer feature representation. In addition, the proposed model uses separable convolution instead of classical convolution to meet the requirement of reducing model parameters while improving recognition accuracy. The accuracy of the proposed model is 97.18%, 96.71%, and 96.28% on the WISDM, UCI-HAR, and PAMAP2 datasets respectively. The experimental results show that the proposed model not only obtains higher recognition accuracy but also costs lower computational resources compared with other methods.

The global health crisis due to the fast spread of coronavirus disease (Covid-19) has caused great danger to all aspects of healthcare, economy, and other aspects. The highly infectious and insidious nature of the new coronavirus greatly increases the difficulty of outbreak prevention and control. The early and rapid detection of Covid-19 is an effective way to reduce the spread of Covid-19. However, detecting Covid-19 accurately and quickly in large populations remains to be a major challenge worldwide. In this study, A CNN-transformer fusion framework is proposed for the automatic classification of pneumonia on chest X-ray. This framework includes two parts: data processing and image classification. The data processing stage is to eliminate the differences between data from different medical institutions so that they have the same storage format; in the image classification stage, we use a multi-branch network with a custom convolution module and a transformer module, including feature extraction, feature focus, and feature classification sub-networks. Feature extraction subnetworks extract the shallow features of the image and interact with the information through the convolution and transformer modules. Both the local and global features are extracted by the convolution module and transformer module of feature-focus subnetworks, and are classified by the feature classification subnetworks. The proposed network could decide whether or not a patient has pneumonia, and differentiate between Covid-19 and bacterial pneumonia. This network was implemented on the collected benchmark datasets and the result shows that accuracy, precision, recall, and F1 score are 97.09%, 97.16%, 96.93%, and 97.04%, respectively. Our network was compared with other researchers’ proposed methods and achieved better results in terms of accuracy, precision, and F1 score, proving that it is superior for Covid-19 detection. With further improvements to this network, we hope that it will provide doctors with an effective tool for diagnosing Covid-19.

Human activity recognition (HAR) is an important sub-field of pervasive computing and pattern recognition. While researchers have achieved remarkable results in feature extraction and classification for sensor-based HAR, they have encountered performance bottlenecks. Sensor signal denoising has emerged as an excellent approach to enhance the performance of sensor-based HAR architectures. In this study, we propose a novel self-supervised blind denoising method for sensor signals, which serves as a new module in the HAR task and significantly improves the overall system performance. Our method applies the idea of masking from image inpainting to temporal signal processing, and utilizes the neighboring signal to predict the signal at the center, leveraging independent noisy measurements and temporal relationships between real neighboring signals, without the need to understand the noise distribution. The denoising function is learned from samples, and the denoised signals are then fed into the classification model. Experimental results conducted on benchmark datasets WISDM, UCI-HAR, and PAMAP2 demonstrate the effectiveness of our denoising method. After denoising, the inner-class divergence of actions decreases, while the outer-class divergence increases. As a result, the recognition accuracy of the system significantly improves to 98.6%, 97.64%, and 97.12% on the respective datasets.