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.

When DC ground electrode of a high-voltage direct current (HVDC) transmission system is in the stage of early operation or in the case of failures and maintenance, an instantaneous large current will be generated and bring great potential safety hazards to the nearby buried oil/gas pipelines and facilities and operators. In order to ensure the safety of persons near the buried pipelines, we investigated the current interference of the HVDC ground electrode to buried pipelines and its personal safety distance (hereinafter referred to as a safety distance). Firstly, the model simulating the electromagnetic interference to buried pipelines was established by means of the numerical simulation technology. Then, the model was used to calculate the safety distance corresponding to eddy current interference of HVDC ground electrode to buried pipelines under different soil resistivities, pipeline lengths, pipeline anti-corrosion insulations, earth currents of ground electrode and pipeline sizes. Finally, the influence laws of above-mentioned factors on the interference degree of HVDC ground electrode were analyzed. And the following research results were obtained. First, the influence of pipeline length on the interference degree of interference of the HVDC ground electrode is great. The longer the pipeline, the greater the safety distance. When the pipeline is equal to or longer than 600 km, however, the safety distance is basically the same. Second, the effect of pipeline coating on the interference degree of HVDC ground electrode is great. As the coating surface resistivity increases, the safety distance increases gradually. Third, for multi-layer soil structures, the maximum single-layer resistivity can be taken as the overall resistivity. And correspondingly, the calculated safety distance obtained is the longest, and the evaluation result is more conservative. In conclusion, the safety distance diagrams of the pipelines with 4 lengths which are obtained based on the calculation results can be used as reference in the design of HVDC ground electrodes and pipelines, as well as the basis for selecting the safety distance of HVDC ground electrode or buried pipeline to be constructed. Keywords: HVDC ground electrode, Personal safety distance, Buried pipeline, Numerical simulation, Electromagnetic interference, Pipeline length, Soil resistivity, Coating surface resistivity

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.

The display of three dimensional geological body can visually describe the complex subsurface geological structure, effectively improve the engineer's space imagination and intuitively understand the geological spatial relationship. Through analysis of commonly used three dimensional geological data model and considered the impact of faults. The paper establishes a generalized triangular prism (GTP) element model, and achieves a three dimensional geological modeling method based on GTP. The paper proposes the error correction technology based on virtual drilling, which allows designers combine their experience to appropriately amend the unknown region of stratum, it contributes to improve the accuracy of 3D geological model. Finally, the paper achieves a 3D geological drilling, borehole cross section, visual information query and geological visualization technology such as virtual drilling, cutting, layering display based on 3D spatial analysis techniques and graphics.

Fluid&ndash, structure interaction (FSI) is a frequent and unstable inherent phenomenon in water conveyance systems. Especially in a system with a surge chamber, valve closing and the subsequent water level oscillation in the surge chamber are the excitation source of the hydraulic transient process. Water-hammer-induced FSI has not been considered in preceding research, and the results without FSI justify further investigations. In this study, an FSI eight-equation model is presented to capture its influence. Both the elbow pipe and surge chamber are treated as boundary conditions, and solved using the finite volume method (FVM). After verifying the feasibility of using FVM to solve FSI, friction, Poisson, and junction couplings are discussed in detail to separately reveal the influence of a surge chamber, tow elbows, and a valve on FSI. Results indicated that the major mechanisms of coupling are junction coupling and Poisson coupling. The former occurs in the surge chamber and elbows. Meanwhile, a stronger pressure pulsation is produced at the valve, resulting in a more complex FSI response in the water conveyance system. Poisson coupling and junction coupling are the main factors contributing to a large amount of local transilience emerging on the dynamic pressure curves. Moreover, frictional coupling leads to the lower amplitudes of transilience. These results indicate that the transilience is induced by the water hammer&ndash, structure interaction and plays important roles in the orifice optimization in the surge chamber.

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.

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.