At present, in the field of video-based human action recognition, deep neural networks are mainly divided into two branches: the 2D convolutional neural network (CNN) and 3D CNN. However, 2D CNN’s temporal and spatial feature extraction processes are independent of each other, which means that it is easy to ignore the internal connection, affecting the performance of recognition. Although 3D CNN can extract the temporal and spatial features of the video sequence at the same time, the parameters of the 3D model increase exponentially, resulting in the model being difficult to train and transfer. To solve this problem, this article is based on 3D CNN combined with a residual structure and attention mechanism to improve the existing 3D CNN model, and we propose two types of human action recognition models (the Residual 3D Network (R3D) and Attention Residual 3D Network (AR3D)). Firstly, in this article, we propose a shallow feature extraction module and improve the ordinary 3D residual structure, which reduces the parameters and strengthens the extraction of temporal features. Secondly, we explore the application of the attention mechanism in human action recognition and design a 3D spatio-temporal attention mechanism module to strengthen the extraction of global features of human action. Finally, in order to make full use of the residual structure and attention mechanism, an Attention Residual 3D Network (AR3D) is proposed, and its two fusion strategies and corresponding model structure (AR3D_V1, AR3D_V2) are introduced in detail. Experiments show that the fused structure shows different degrees of performance improvement compared to a single structure.

With the popularity of the internet, the expression of emotions and methods of communication are becoming increasingly abundant, and most of these emotions are transmitted in text form. Text sentiment classification research mainly includes three methods based on sentiment dictionaries, machine learning and deep learning. In recent years, many deep learning-based works have used TextCNN (text convolution neural network) to extract text semantic information for text sentiment analysis. However, TextCNN only considers the length of the sentence when extracting semantic information. It ignores the semantic features between word vectors and only considers the maximum feature value of the feature image in the pooling layer without considering other information. Therefore, in this paper, we propose a convolutional neural network based on multiple convolutions and pooling for text sentiment classification (variable convolution and pooling convolution neural network, VCPCNN). There are three contributions in this paper. First, a multiconvolution and pooling neural network is proposed for the TextCNN network structure. Second, four convolution operations are introduced in the word embedding dimension or direction, which are helpful for mining the local features on the semantic dimensions of word vectors. Finally, average pooling is introduced in the pooling layer, which is beneficial for saving the important feature information of the extracted features. The verification test was carried out on four emotional datasets, including English emotional polarity, Chinese emotional polarity, Chinese subjective and objective emotion and Chinese multicategory. Our apporach is effective in that its result was up to 1.97% higher than that of the TextCNN network.

In practice, IOT (Internet of things) gateways are often used between sensor networks and the Internet to provide advanced services such as device monitoring and control. Sensor networks are connected to the Internet via these gateways based on various transmission protocols. In particular, the main features of IOT gateways are reliability, high real-time, security and so on. This paper proposes a heterogeneous IOT gateway based on dynamic priority scheduling algorithm. This gateway realizes data conversion and transformation between the Internet and sensor networks as well as several kinds of communication protocol: RS485, Bluetooth, CAN, Zigbee and GSM. To ensure the data security and reliability for IOT gateway, some higher-level protocols are designed and implemented on the gateway. A dynamic priority scheduling algorithm of a real-time system is also used in the gateway to address the problem of data concurrency and improve real-time performance by efficiently scheduling tasks. Simulation results reveal that the gateway realizes the data transmission between sensor networks and the Internet using specific higher-level protocols and response within a very short delay, achieving the goal of addressing the problem of data concurrency.

With the rapid development of deep convolutional neural networks, more and more computer vision tasks have been well resolved. These convolutional neural network solutions rely heavily on the performance of the hardware. However, due to privacy issues or the network instability, we need to run convolutional neural networks on embedded platforms. Critical challenges will be raised by limited hardware resources on the embedded platform. In this paper, we design and implement an embedded inference framework to accelerate the inference of the convolutional neural network on the embedded platform. For this, we first analyzed the time-consuming layers in the inference process of the network, and then we design optimization methods for these layers. Also, we design a memory pool specifically for neural networks. Our experimental results show that our embedded inference framework can run a classification model MobileNet in 80ms and a detection model MobileNet-SSD in 155ms on Firefly-RK3399 development board.

With rapid advances in wireless sensor networks and embedded computing technologies, various behaviour detection devices have arose and been applied in practical use for monitoring the situations of the elderly in order to ensure the safety of them. This paper aims to propose a behaviour detection system with a sensor board (iNEMO™ V2) and the iNEMO SDK (software development kit), which utilizes the accelerometer, micro-sensors, digital data processing as well as wireless technologies. The system practically simulates a real environment for the intended case.