More and more studies begin to focus on emotional conversation generation. However, the existing studies tend to focus only on emotional factors and ignore the relevance and diversity of topics in dialogues, as well as the emotional tendency closely related to topics, which may lead to the quality decline of generated responses. Therefore, a topic-expanded emotional conversation generation model that integrated topic information and emotional factors was proposed. Firstly, the conversation context was globally-encoded, the topic model was introduced to obtain the global topic words, and the external affective dictionary was used to obtain the global affective words in this model. Secondly, the topic words were expanded by semantic similarity and the topic-related affective words were extracted by dependency syntax analysis in the fusion module. Finally, the context, topic words and affective words were input into a decoder based on the attention mechanism to prompt the decoder to generate topic-related emotional responses. Experimental results show that the model can generate rich and emotion-related responses. Compared with the model Topic-Enhanced Emotional Conversation Generation(TE-ECG), the proposed model has an average increase of 16.3% and 15.4% in unigram diversity(distinct-1) and bigram diversity(distinct-2); and compared with Seq2SeqA(Sequence to Sequence model with Attention), the proposed model has an average increase of 26.7% and 28.7% in unigram diversity(distinct-1) and bigram diversity(distinct-2).

Low-poly is a popular style in the art design field recently. In order to improve the quality of image and video low-poly stylization, an image and video low-poly rendering method based on edge features and superpixel segmentation was proposed. Firstly, the intersection points of adjacent superpixels and the uniform sampling points of the difference set between feature edges and superpixel boundaries were extracted as the vertices of the triangle mesh, and Delaunay triangulation was performed to generate the initial triangle mesh. Then, the constrained quadric error metric method was used to simplify the generated mesh in order to generate the final triangle mesh. Finally, the triangle mesh was filled with color to obtain the image with low-poly style. For video low-poly rendering, the temporally consistent superpixels were used to track the same part of the object across frames to establish associations between the video frames, reducing the jitter after video rendering. In addition, the video segmentation method was used to segment the moving objects in the video, so as to obtain sampling points with different densities between the moving objects and the background, and the local stylized effect of the video was obtained by rendering the moving objects. Experimental results show that the proposed method can generate low-poly rendering results with better visual effects.

Pedestrian Re-IDentification (Re-ID) is a hot issue in the field of computer vision and mainly focuses on “how to relate to specific person captured by different cameras in different physical locations”. Traditional methods of Re-ID were mainly based on the extraction of low-level features, such as local descriptors, color histograms and human poses. In recent years, in view of the problems in traditional methods such as pedestrian occlusion and posture disalignment, pedestrian Re-ID methods based on deep learning such as region, attention mechanism, posture and Generative Adversarial Network (GAN) were proposed and the experimental results became significantly better than before. Therefore, the researches of deep learning in pedestrian Re-ID were summarized and classified, and different from the previous reviews, the pedestrian Re-ID methods were divided into four categories to discuss in this review. Firstly, the pedestrian Re-ID methods based on deep learning were summarized by following four methods region, attention, posture, and GAN. Then the performances of mAP (mean Average Precision) and Rank-1 indicators of these methods on the mainstream datasets were analyzed. The results show that the deep learning-based methods can reduce the model overfitting by enhancing the connection between local features and narrowing domain gaps. Finally, the development direction of pedestrian Re-ID method research was forecasted.

Aiming at the difficulty of constructing real tour routes from sparse refueling trajectories of self-driving tourists,a sparse trajectory clustering algorithm based on semantic representation was proposed to mine popular self-driving tour routes. Different from traditional trajectory clustering algorithms based on trajectory point matching,in this algorithm, the semantic relationships between different trajectory points were considered and the low-dimensional vector representation of the trajectory was learned. Firstly,the neural network language model was used to learn the distributed vector representation of the gas stations. Then,the average value of all the station vectors in each trajectory was taken as the vector representation of this trajectory. Finally,the classical k-means algorithm was used to cluster the trajectory vectors. The final visualization results show that the proposed algorithm mines two popular self-driving tour routes effectively.

To overcome the performance degradation of palm vein recognition system due to the small quantity and the uneven quality of palm vein images, a palm vein image recognition method based on side chain connected convolutional neural network was proposed. Firstly, palm vein features were extracted by convolution layer and pooling layer based on ResNet model. Secondly, the Exponential Linear Unit (ELU) activation function, Batch Normalization (BN) and Dropout technology were used to improve and optimize the model, so as to alleviate gradient disappear, prevent over fitting, speed up convergence and enhance the generalization ability of the model. Finally, Densely Connected Network (DenseNet) was introduced to make the extracted palm vein features more abundant and effective. Experimental results on two public databases and one self-built database show that, the recognition rates of the proposed method on the three databases are 99.98%, 97.95%, 97.96% respectively, indicating that the proposed method can effectively improve the performance of palm vein recognition system, and is more suitable for the practical applications of palm vein recognition.

To solve the degradation of recognition performance caused by unclear palm vein contour, low image contrast and brightness, a new palm vein enhancement method based on adaptive fusion was proposed. Firstly, based on Dark Channel Prior (DCP) defogging algorithm and adaptively selected defogging coefficient according to variation coefficient of the palm vein image, DCP enhanced image was obtained. And based on Partial Overlapped Sub-block Histogram Equalization (POSHE) algorithm, POSHE enhanced image was obtained. Secondly, the image was divided into 16 sub-blocks, and the weight of each sub-block was determined by the gray mean and the standard deviation. Finally, two kinds of enhanced images were fused adaptively according to the weight of each sub-block, obtaining the adaptive fused enhanced image. This method not only retains the advantages of DCP algorithm in enhancing image contrast and brightness without introducing significant noise, but also preserves the benefits of POSHE algorithm in enhancing image contrast and brightness without losing local details. Meanwhile, adaptive fusion of the two algorithms solves the problem of missing palm vein in shadow areas of DCP images and reduces the blocking artifacts produced by POSHE. Experimental results carried out on two public databases and a self-built database show that the equal error rates are 0.0004, 0.0472, 0.0579 and the correct recognition rates are 99.98%, 94.27%, 92.05% respectively, indicating that compared with existing image enhancement methods, the proposed method reduces the equal error rate and improves the recognition accuracy.

Aiming at the problem of the dependence between software system modules, a hybrid defect prediction model based on network representation learning was constructed by analyzing the network structure of software system. Firstly, the software system was converted into a software network on a module-by-module basis. Then, network representation technique was used to perform the unsupervised learning on the system structural feature of each module in software network. Finally, the system structural features and the semantic features learned by the convolutional neural network were combined to construct a hybrid defect prediction model. The experimental results show that the hybrid defect prediction model has better defect prediction effects in three open source softwares, poi, lucene and synapse of Apache, and its F1 index is respectively 3.8%, 1.0%, 4.1% higher than that of the optimal model based on Convolutional Neural Network (CNN). Software network structure feature analysis provides an effective research thought for the construction of defect prediction model.

Aiming at the problems of data sparseness and cold start in social network recommendation systems, a hybrid social network recommendation algorithm based on feature Transform and Probabilistic Matrix Factorization (TPMF) was proposed. Using Probability Matrix Factorization (PMF) method as recommendation framework, trust network, the relationship between the recommended items, user-item score matrix and adaptive weight were combined to balance the impact of individual and social potential characteristics on users. The trust feature transfer was introduced into the recommendation system as valid basis for recommendation. Compared to the User-Based Collaborative Filtering (UBCF), TidalTrust, PMF and SoRec, the experimental results show that the Mean Absolute Error (MAE) of TPMF was decreased by 4.1% to 20.8%, and the Root Mean Square Error (RMSE) of TPMF was decreased by 3.3% to 18.5%. Compared with the above four algorithms, for the cold start problem, the Mean Absolute Error was decreased by 1.6 to 14.7%, and the RMSE was decreased by 1.2% to 9.7%, which verifies TPMF effectively alleviates cold start problem and improves the robustness of the algorithm.

Since it is difficult to denoise and simplify a three dimensional point cloud data by a same parameter, a new unified algorithm based on the Extended Surface Variation based Local Outlier Factor (ESVLOF) for denoising and simplification of scattered point cloud was proposed. Through the analysis of the definition of ESVLOF, its properties were given. With the help of the surface variability computed in denoising process and the default similarity coefficient, the parameter γ which decreased with the increase of surface variation was constructed. Then the parameter γ was used as local threshold for denoising and simplifying point cloud. The simulation results show that this method can preserve the geometric characteristics of the original data. Compared with traditional 3D point-cloud preprocessing, the efficiency of this method is nearly doubled.

Aiming at the problem of large amount of data and characteristics of surface in laser scattered point cloud, a K-Nearest Neighbors (KNN) searching algorithm for laser scattered point cloud was put forward to reduce memory usage and improve processing efficiency. Firstly, only the non-empty subspace numbers were stored by multistage classification and dynamic linked list storage. Adjacent subspace was coded in ternary, and the pointer connection between adjacent subspaces was established by dual relationship of code, a generalized table that contained all kinds of required information for KNN searching was constructed, then KNN were searched. In the process of KNN searching, the candidate points outside inscribed sphere of filtration cube were directly deleted when calculating the distance from measured point to candidate points, thus reducing the candidate points that participate in the sort by distance to half. Both dividing principles, whether it relies on K value or not, can be used to calculate different K neighborhoods. Experimental results prove that the proposed algorithm not only has low memory usage, but also has high efficiency.

Concerning that the original Surface Variation based Local Outlier Factor (SVLOF) cannot filter out the outliers on edges or corners of three-dimensional solid, a new near outlier detection algorithm of scattered point cloud was proposed. This algorithm firstly defined SVLOF on the k neighborhood-like region, and expanded the definition of SVLOF. The expanded SVLOF can not only filter outliers on smooth surface but also filter outliers on edges or corners of three-dimensional solid. At the same time, it still retains the space of threshold value enough of original SVLOF. The experimental results of the simulation data and measured data show that the new algorithm can detect the near outliers of scattered point cloud effectively without changing the efficiency obviously.

Concerning the proxy signcryption security problem in reality, motivated by Gus proxy signature scheme (GU K, JIA W J, JIANG C L. Efficient identity-based proxy signature in the standard model. The Computer Journal, 2013:bxt132), a new secure identity-based proxy signcyption scheme in the standard model was proposed. Proxy signcryption allowed that the original signcrypter delegated his authority of signcrption to the proxy signcrypter in such a way that the latter could generate ciphertext on behalf of the former. By combining the functionalities of identity-based signcryption and proxy signature scheme, the new scheme not only had the advantage of identity-based signcryption scheme, but also had the function of proxy signature scheme. Analysis results show that, under the assumption of Diffie-Hellman problem, the proposed scheme is confidential and unforgeable. Compared with the known scheme, the scheme requires 2 pairings computation in proxy key generation and 1 pairing computation in proxy signcryption. So it has higher computational efficiency.

This paper proposed a new best viewpoints selection approach that was capable of selecting best viewpoints for 3D models based on a feature points detection process. First, a new saliency measure was defined to compute the saliency of 3D meshes vertices, which assumed that the saliency of a given vertex on a 3D model could be described by its average difference of distances within a local space. Then, the effective feature points were promisingly able to be extracted based on vertices saliency. Finally, a simple selection strategy was adopted to determine the best viewpoints for 3D mesh models. The quality of viewpoints was a combination of the geometirc distribution and the saliency of visible feature points. The experimental results validate the effectiveness of the proposed approach, which can measure viewpoint quality objectively and obtain the best viewpoints of good visual effect.

With reference to network coding theory, a reliable data transmission policy,MGrowth Codes was proposed, for wireless sensor network environment. Through a gradientbased routing design, all data can converge to sink node (Sink). In addition, the data transmission policy can also use encoded packet to decode other encoded packets, which can further enhance the data recoverability. After the network simulation, MGrowth Codes can effectively increase the throughput of the wireless sensor network and improve the reliability of data transmission.

A new approach to finding the core point of fingerprint was given. Based on the location of core point, fingerprint images were classified by using structural classification and were matched by using graphical matching. The core point method was combined with neighborhood matching approach and a new compound matching approach based on fuzzy discrimination was presented. In this approach, core point seeking once more based on the characteristics of fingerprint images was presented. Experiments were done on 1000 fingerprint images (20 percent of the images of low quality). 100 percent of the images were classified rightly and 98.7 percent of the images were matched rightly.

Development of WLAN and its security protocols were presented. Then researches were made on some of the most important security standards formed in the development. Finally, based on the characteristics of these protocols the implementation was displayed.