Search

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.

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.

Missing data is a major challenge in activity recognition and becomes an increasingly important study. Most current research on activity recognition is based on multiple sensors, which may bring the problem of missing data for one or more sensors. This paper presents Multi-source Denoising AutoEncoder (MSDA) for filling missing sensor data in walking recognition system based on previously proposed Hierarchical AdaBoost. The recovery method uses Denoising AutoEncoder to build a neural network which output is the embedding of features that include missing sensors, so that it can predict the features for missing sensor data. The experimental results show that MSDA can not only improve the recognition accuracy, but has higher performance comparing with other missing data processing method such as EM-PCA and filling missing data with a special value.

When design lines in complex topography are a such as mountain areas, the selection of route schemes are usually restricted by the geological conditions because of complex terrain. According to the characters of line-selection design in complex topography areas of mountain areas, from the perspective of geological line selection, built the evaluation model of route schemes in complex geological area using the analytic hierarchy process and fuzzy optimization algorithm to solve the comprehensive evaluation problem having multilevel indices of line- selection multi-scheme from bottom to top and realized selection and decision of line schemes based on virtual geographic environments. Examples show that the established evaluation model reduced decision makers subjective influence on the results, made human-computer interaction content reduce to a minimum, and improved the accuracy and reliability of the decision.