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.

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.

In this paper, the problem of controller design for a class of T-S fuzzy systems with time-varying delay is considered. The stability condition with adjustable parameter is derived by introducing a parameter into the inequality which occurred in the proof. And then, the sufficient conditions with adjustable parameter for the existence of feedback gains are derived in the form of linear matrix inequalities. The feedback gain is different when the adjustable parameter take different values, therefore, the dynamic performance of the closed-loop systems is also different. Lastly, an illustrative example is given to show the effectiveness of the proposed method.