Figure - available via license: Creative Commons Attribution 4.0 International
Content may be subject to copyright.
Source publication
Research on the human activity recognition could be utilized for the monitoring of elderly people living alone to reduce the cost of home care. Video sensors can be easily deployed in the different zones of houses to achieve monitoring. The goal of this study is to employ a linear-map convolutional neural network (CNN) to perform action recognition...
Contexts in source publication
Context 1
... last, we used the two-stream concept, class score fusion for Fspatial and Fmotion, to evaluate the performance of the proposed method with cross-subject and cross-view sources. Table 5 shows the results without the DAG transfer. The best feature is Fspatial under the cross-subject source, which resulted in an accuracy and F1-score of 99.3% and 82.8%, respectively. ...Context 2
... Lie Group [25] 50.1 52.8 HBRNN [19] 59.1 64.0 Deep RNN [26] 59.29 64.09 Deep LSTM [26] 60.7 67.3 Part-aware LSTM [26] 62.9 70.3 ST-LSTM + Trust Gate [27] 69.2 77.7 Two-stream RNN [28] 71.3 79.5 Clips + CNN + MTLN [29] 79.6 84.8 ST-GCN [30] 81.5 88.3 SR-TSL [31] 84.8 92.4 Proposed DAG + linear-map CNN 86.1 94.7 We analyzed the actions with lower recall rates in the cross-subject and cross-view sources in Table 5-7. The four actions that often had lower recall rates were A10 (reading), A11 (writing), A28 (phone call), and A29 (playing with laptop). ...Similar publications
Gene expression datasets consist of thousand of genes with relatively small samplesizes (i.e. are large-$p$-small-$n$). Moreover, dependencies of various orders co-exist in the datasets. In the Undirected probabilistic Graphical Model (UGM) framework the Glasso algorithm has been proposed to deal with high dimensional micro-array datasets forcing s...
Citations
... Image-based and sensor-based methods are two commonly used data sensing methods [8]. The image-based methods usually use visual sensing devices, such as video cameras and photo cameras [9,10], to monitor human activities. However, their major disadvantages obtain the features of micro-Doppler spectrograms. ...
Human activity recognition (HAR) can monitor persons at risk of COVID-19 virus infection to manage their activity status. Currently, many people are isolated at home or quarantined in some specified places due to the spread of COVID-19 virus all over the world. This situation raises the requirement of using the HAR to observe physical activity levels to assess physical and mental health. This study proposes an ensemble learning algorithm (ELA) to perform activity recognition using the signals recorded by smartphone sensors. The proposed ELA combines a gated recurrent unit (GRU), a convolutional neural network (CNN) stacked on the GRU and a deep neural network (DNN). The input samples of DNN were an extra feature vector consisting of 561 time-domain and frequency-domain parameters. The full connected DNN was used to fuse three models for the activity classification. The experimental results show that the precision, recall, F1-score and accuracy achieved by the ELA are 96.8%, 96.8%, 96.8%, and 96.7%, respectively, which are superior to the existing schemes.
... When people learn yoga, the mainstream learning method is still to enroll in offline yoga training courses, but the practice time and venue are not fully free, and the learning content and progress are usually mastered by the teacher, which brings many inconveniences to the workplace people's exercise in [15]. At the same time, the current level of instructors varies, and the professional quality of teachers is more difficult to guarantee when full understanding is not conducted, so many people choose to find resources from the Internet for self-learning. is way is very convenient, but the accuracy and scientific nature of the exercise cannot be guaranteed, and unreasonable exercise habits and wrong postures can cause physical injury, which is contrary to the original purpose of exercising [16][17][18]. ...
The use of computer vision for target detection and recognition has been an interesting and challenging area of research for the past three decades. Professional athletes and sports enthusiasts in general can be trained with appropriate systems for corrective training and assistive training. Such a need has motivated researchers to combine artificial intelligence with the field of sports to conduct research. In this paper, we propose a Mask Region-Convolutional Neural Network (MR-CNN)- based method for yoga movement recognition based on the image task of yoga movement recognition. The improved MR-CNN model is based on the framework and structure of the region-convolutional network, which proposes a certain number of candidate regions for the image by feature extraction and classifies them, then outputs these regions as detected bounding boxes, and does mask prediction for the candidate regions using segmentation branches. The improved MR-CNN model uses an improved deep residual network as the backbone network for feature extraction, bilinear interpolation of the extracted candidate regions using Region of Interest (RoI) Align, followed by target classification and detection, and segmentation of the image using the segmentation branch. The model improves the convolution part in the segmentation branch by replacing the original standard convolution with a depth-separable convolution to improve the network efficiency. Experimentally constructed polygon-labeled datasets are simulated using the algorithm. The deepening of the network and the use of depth-separable network improve the accuracy of detection while maintaining the reliability of the network and validate the effectiveness of the improved MR-CNN.
Information networks organized according to Internet of Things (IoT) mesh topology have received great recognition over the past one and a half to two decades of years. The scale of projects grows from millions of users connected to hundreds of thousands of access points. IoT mesh nodes offer more fascinating regulations linking a variety of networks and radio technologies and therefore fully meet the ever-growing requirements of subscribers as mobility, quality of service (QoS) and the security. The possibility of organizing local or metropolitan networks using a mesh network topology, desegregating into wide area networks without any difficulty or effort, is considered a tempting condition for urban and individual users. This article, introduces optimal routing protocol for IoT Wireless Mesh Network (WMN) by optimizing the channel and frequency resources of the network based on mathematical calculations for resource allocation. We propose an approach to the synthesis of mesh networks, which allows determining the required number of connections between network nodes, as well as their channel width for a given frequency range while ensuring the minimum data transmission delay time. Optimization results show that the function value is improved for more than 16% and the proposed algorithm provides the most rational use of the allocated frequency range.
