Search

This paper presents a simultaneous pickup and delivery route designing model, which considers the use of express lockers. Unlike the traditional traveling salesman problem (TSP), this model analyzes the scenario that a courier serves a neighborhood with multiple trips. Considering the locker and vehicle capacity, the total cost is constituted of back order, lost sale, and traveling time. We aim to minimize the total cost when satisfying all requests. A modified deep Q-learning network is designed to get the optimal results from our model, leveraging masked multi-head attention to select the courier paths. Our algorithm outperforms other stochastic optimization methods with better optimal solutions and O(n) computational time in evaluation processes. The experiment has shown that reinforcement learning is a better choice than traditional stochastic optimization methods, consuming less power and time during evaluation processes, which indicates that this approach fits better for large-scale data and broad deployment.

With the advent of the Internet era, deep learning technology is developing rapidly in a wide range of application scenarios. As one of the main research methods of deep learning, convolutional neural network is widely used in the field of image recognition [5]. This paper hopes to build a modern intelligent tea image recognition system by combining in-depth learning technology, so as to help inherit traditional Chinese culture. The main work of this paper is as follows:(1)Making a sample data set containing about 49000 pictures;(2)Constructing convolution neural network;(3)The correct rate of training image recognition model is 96%;(4)Realize tea picture recognition;(5)Build the web page.Under the framework of tensorflow, the program of this subject realizes the tea picture recognition function by training convolution neural network [5][6], and builds it in the beautiful web page, so that the tea culture can be presented and spread in a more modern form, which is conducive to the inheritance and development of Chinese traditional culture.

The special grammar and abstruse rhetoric of Tang and Song poetry doomed the diversity of poetry research. In order to help scholars explore the information space of poetry, we took into account the breadth and depth of learning, combined with heterogeneous data sources such as poetry, videos, textbooks, knowledge graph and other media sources, and carried out visual modeling. We provide a visual and informative platform to demonstrate the potential power of visualization. It supports comprehensive search capabilities for multiple types of data, online generation of poets' knowledge graphs. Relationship diagram, word cloud diagram, pie chart and other visual charts are displayed on the platform, so that users can complete exploratory visual analysis by dragging, clicking and typing.

Vulnerability is one of the main causes of network intrusion. An effective way to mitigate security threats is to find and repair vulnerabilities as soon as possible. Traditional vulnerability detection methods are limited by expert knowledge. Existing deep learning-based methods neglect the connection between semantic graphs and cannot effectively deal with the structure information. Graph neural network brings new insight into vulnerability detection. However, benign nodes on the graph account for a large proportion, resulting in vulnerability information could be disturbed by them. To address the limitations of existing vulnerability detection approaches, in this paper, we propose ACGVD, a vulnerability detection method by constructing a graph network with attention. We first combine multiple semantic graphs together to form a more comprehensive graph. We then adopt the Graph neural network instead of the sequence-based model to automatically analyze the comprehensive graph. In order to solve the problem that the vulnerability information could be covered up, we add a double-level attention mechanism to the graph model. We also add a novel classification layer to extract the high-level features of the code. To make the experiment more realistic, the model is trained over the latest published real-world dataset. The experiment results demonstrate that compared with state-of-the-art methods, our model ACGVD achieves 5.01%, 13.89%, and 8.27% improvement in accuracy, recall and F1-score, respectively.

Web 3D was initially realized by installing plug-ins on the browser, and WebGL can render interactive 3D graphics on web pages without using plug-ins. Three.js is the open-source framework of WebGL, a small amount of JavaScript code can create complex 3D scenes. This article uses Three.js to realize 3D data visualization, including 3D histograms, pie charts, maps, earth, and force-oriented graphs, and uses them for a visualized display of film data.

This application, Color Dust, extracts and filters the color of image pixels online through Canvas, then performs clustering analysis and statistics based on the K-Means algorithm. With the help of front-end libraries such as D3.js, Vue.js, and Vuetify, the data visualization of image color is realized. The color extracted by the K-Means algorithm is the average of several tones that frequently appear in the image, and it is a good reference for harmonizing colors. After the extraction is completed, various methods of data visualization are used to display the information about colors in the picture in real time with D3.js and Vue’s responsiveness, and the color of the website can be changed according to different images in real time. In addition, this project encapsulated the algorithm steps of extraction process into npm packages, which can be quickly transplanted to Node.js or front-end of website.

Nowadays, media from various countries have published a large number of report tweets on international hot topics. The rapid spread of news events on twitter has become increasingly popular. For hotspot mining of news events, topic division and sentiment analysis are two indispensable factors. In this Paper, we use topic segmentation and sentiment analysis to conduct hot mining of social media news for the US media and Chinese media tweets in Huawei-related news in 2019. First, we apply LDA to media tweets to divide topics and obtain related topic words. Then we devised improved methods for effective sentiment analysis on media tweets and influencer comments respectively. What's more, we draw some valid conclusions about news hotspot mining in social media tweets.

The traditional digitization method of electronic textbooks is limited by text data and illustration layout, and the data processing effect is poor. In order to adapt to the complex and changeable data formats, this paper proposes an adaptive data partitioning technique. We divide all the texts and illustrations in the textbooks into independent data blocks, locate and cut them, and use OCR technology to identify the information of each area to make the processing goals more clear. Experiments were conducted on the junior middle school history textbooks in terms of data recognition rate. The experimental results show that the method proposed in this paper has a good effect on the digitalization of electronic textbooks.

The research of complex network is a hot spot in current scientific research, such as the Internet network, neural network and social network. Main contents of this paper are about visualization and structural analysis of the political network of the Northern Song Dynasty in China, to show and dig objective information about history of this period. Firstly, we use community-structure to measure complexity of relationship network, besides, we fit plots to find rules of degree distribution and its scale-free property, finally, we use small-world model to verify its small-world phenomenon.

This paper presents the modeling, optimization, and validation of a hollow plunger type solenoid for high speed On/Off valve. In the preliminary design, an accurate equivalent magnetic circuit model of the proposed solenoid is carried out, and the magnetic circuit is arranged in Kirchhoffs voltage law matrix form for the convenience of computer calculation. An iterative method is applied to obtain accurate permeability of the nonlinear magnetic material. To optimize the design parameters, a multiobjective optimization process is developed, and the multiobjective particle swarm optimization method is used to obtain the Pareto front of the desired objectives. An approved solution in Pareto front is selected by analytic hierarchy process and validated by the finite element analysis (FEA) method. A prototype based on the final optimized design is manufactured and tested. The experiment results verified the validation proposed design and optimization process.

With the sustained development of social networks, increasing attention has been paid to social recommender systems. Current studies usually focus on indirect factors such as the similarity between users, but multiple direct interactions, such as mentions, reposts, and comments, are seldom considered. This paper addresses direct connections between users in social recommender systems. We analyze direct interactions to investigate the connection strength between users, and then, user preferences and item characteristics can be better described. Based on the analysis of social influence between users and users’ influence over the whole social network, we propose a recommendation method with social influence, which makes full use of information among users in social networks and introduces the mechanisms of macroscopic and microscopic influences. Direct interactions between users are incorporated into a matrix factorization objective function. Real-world microblog data are applied to verify our model, and the results show that the proposed recommendation method outperforms other state-of-the-art recommendation algorithms.

With the rapid development of film and television industry, it is necessary to find suitable stand-ins for actors, select appropriate actors for different periods of roles, and calculate the acting time of actors. The system detects the actor's face, extracts feature points, calculates face feature vectors, and then obtains the actor's identity information. Based on Dlib, this paper designed and implemented a film actor face recognition system, and designed experiments to verify the effectiveness of the face recognition system. The system has a high recognition rate for relatively clear faces, but the face recognition effect with occlusion needs to be improved.

Traditional text classification methods are based on statistics and feature selection. It does not perform well in processing large - scale corpus. In recent years, with the rapid development of deep learning and artificial neural networks, many scholars use them to solve text classification problems and achieve good results. Common text classification neural network models include textCNN, LSTM, and C-LSTM. Using a specific model can obtain more accurate features but ignore the context information. This paper proposes a C-LSTM with word embedding model to deal with this problem. Experiments show that the model proposed in this paper has great advantages in Chinese news text classification.

Nowadays, The network is developing rapidly and spreading all over the world, so a lot of data was generated, and we also felt the power of public opinion analysis. It can be said that every good or poorly-spoken movie will produce a wave of consensus for a period of time after release, and people are paying more and more attention to it. Our requirements for works and actors are becoming more and more strict. Therefore, whenever a good movie appears, the directors of various countries will remake, because there is already a mass foundation. This article mainly introduces the remake comparison between Chinese and foreign films and conducts a series of data visualization analysis, sorting, and comparison. In this paper, the data is visualized through analysis, and it is presented through three-dimensional word cloud, Nightingale rose diagram and force-Directed graph, so it is more convenient for observation. For the specific analysis of each film, this article has made a knowledge graph, which can be used to specifically view movies or characters.

In the thousands of years Chinese history, countless important figures have emerged. Some of their life experience, works and research results are data that can be processed by programs and visualized. China Biographical Database (CBDB) is a relational database on Chinese historical figures started by Harvard University. This paper using the above database, taking the literati of Song Dynasty as an example, constructed and visualized a social network based on the social relations and correspondence between the characters. PageRank algorithm is used to evaluate the importance of people in the social network.

Nowadays, complex networks are widely used in various fields. As a hosting platform for open source and proprietary software projects, GitHub is used by many Internet companies and programmers. With the popularity of the Internet and the rapid development of the Internet, the number of users has exploded, and GitHub is not only a code hosting platform, but also a social networking platform for Internet practitioners to obtain information and knowledge, and even make friends. The sheer volume of users and the number of code repositories have also made it increasingly difficult for users to find code libraries that match their interests and users who share their interests. In order to effectively solve the above problems, based on the theory of ternary closure relations in the theory of social relations, according to the HITS algorithm, the repositories that may be interested and the like-minded friends are respectively recommended to the users. Another aspect of the system is data visualization, where users can intuitively get recommendations.

Using the complex network theory to analyze the character social network in literatures provides a perspective in literary analysis. This paper proves that the character social networks of Harry Potter and The Lord of the Rings are small-world and scale-free and not only preferential attachment but also some specific plots affect the development of The Lord of the Rings trilogy. That means the social networks from two literatures obey the complex network theories that the social networks in real word follow. Hence, these above properties make the two fictional novels’ networks more like networks in the real world and make people accept them well.

Entity relationship extraction is an important research topic in the field of NLP, which is to extract the relationship between two entities from natural language texts. Research shows that deep neural networks are feasible in the task of entity relation extraction and are superior to traditional relation extraction methods. In this paper, we compare the performance of the BLSTM model and the Bidirectional LSTM model with Attention under the entity relationship extraction task. The comparison includes the different performance of the model after adding additional NLP features and modifying embedding size. Compared with the BLSTM model, the Bidirectional LSTM model with Attention can achieve similar accuracy under the condition of simpler and less preprocessing. In addition, the larger size of dimension of word embedding and additional features acquired by NLP tools can improve the accuracy of relationship extraction. This article provides a reference standard for engineers to select the optimal model under different conditions.

With the development of social networks, we are more interested in every aspect of the relationship. We conducted a visualization analysis of the papers published on two journals of Communication University of China in five years. In addition, we combine the academic social network of three art universities in Beijing based on CNKI and use complex network-related knowledge to analyze the collaboration of these universities. In this paper, we apply the knowledge of visualization tools and complex networks to analyze the authors who have high productivity, the keywords of these papers and the academic partnerships of the three universities. In experiments, each college is regarded as a social network model. From the perspective of academic social networks and collaborative networks, we extract some features of each of the three art universities and make some conclusions.

With the development of information technology, the application began to show two levels of differentiation. The one, based on high-performance processors, graphics cards, and hardware with high read/write speed hard drives, such as tens of gigabytes of games. The other one, a lightweight program similar to WeChat mini program, based on the mobile terminal, can be used without downloading and installing, and can realize the function of the original ecological APP. The WeChat mini program can also be used in the field of education. This paper introduces the development framework of WeChat mini program and a language education platform based on WeChat mini program. This language education platform provides students with language teaching resources, such as text reading audio and video, text analysis, and extended reading. The system framework of the language education platform and the implementation of key technologies are highlighted.

Technology will affect the learning experience in many ways in the next few years, Internet of Things (IOT) continues to confirm an important position in the development of the environment and the society of information and communication technology. Through the Internet support of things, institutions provide a richer learning experience, improve operational efficiency, real-time student performance. By obtaining practical insight, improve learning outcomes. This research aims to maximize how the benefits and higher education are to find the possibility of the Internet of things to reduce the risks associated with it. There is a need to make further efforts to release the full potential of IoT systems and technology. Therefore, proposes research on the impact of the Internet of Things in higher education, especially in universities. The Internet of Things stands out in many areas and, at any level, significantly changes the way colleges work and improves student learning. This has great potential for universities and other educational institutions. If prepared early, a wide range of leaders, staff, and students will ensure successful implementation. The development of the Internet of Things can lead to the development of local universities. Scholars, researchers, and students show the discovery and development of IoT systems, devices, applications, and services in unique locations. In the following year, will be provided by many scientific research institutes and companies to provide some evidence of the future of the Internet of Things in higher education. The Internet of Things, on the other hand, also poses a significant challenge to higher education.

The (n, k)-star graph S_n, k is a generalization of the star graph. The structure connectivity and substructure connectivity are two generalizations of the classical connectivity, which can be used to measure the fault tolerance of the network whose faults must be some subgraphs with a special structure. In this paper, we will determined the structure connectivity and substructure connectivity of (n, k)-star graphs with respect to the complete graph structures.

With the deepening of convolutional neural networks, training a delicate network may be more difficult. This article explores which training strategies on a limited set of training data will make the network perform better, and demonstrated a terse hierarchy training strategy. We only need to do a small-scale data processing, add a priori class label for each piece based on the original dataset, the network will learn functions to classify the priori class and final class simultaneously and end to end. The knowledge learned by hierarchy A network part could guide the classification task at the hierarchy B network part. Experiments on CIFAR-10 show that network trained by this strategy will perform better and robust. Finally, the classification accuracy on the test set also has a certain improvement compared with the ordinary training strategy.

This paper presents a new multi-DOF flexible micro-displacement manipulator based on ferrofluid for high precision micro-displacement manipulation. It is aimed at achieving a flexible, smooth and precise control of multiple degrees of freedom micro-displacement by utilizing controlled ferrofluid. The mover of the proposed manipulator is suspended on the ferrofluid affected by the combined magnetic field coupled by a permanent magnetic field and a controlled electromagnetic field. Then the proposed manipulator can be manipulated by changing the strength of the combined magnetic field, which is adjusted by the input current. In addition, the proposed manipulator also can effectively eliminate the disturbance to the micro-operation caused by vibration during operation since the mover is totally supported by ferrofluid. The finite element analysis is also performed to observe the magnetic field intensity changes in ferrofluid with different excitation current, which verifies the rationality and feasibility of the proposed manipulators. Consequently, the proposed manipulator has a significant potential for applications where the high precision micro-displacement manipulation, such as microinjection system.

With the rapid development of neural network and face recognition, the Convolution Neural Networks(CNN) is more and more widely applied. Considering the shortcomings of traditional clustering methods, spectral clustering and self-organizing feature mapping neural network (SOM), a variety of new clustering methods based on deep learning are constantly created. In this paper, firstly a convolutional neural network is used in automatically feature extraction. After extracting features with CNN, S-SOM, an integrated algorithm of SOM and spectral clustering, is proposed to cluster face image data. Finally, to verify the effectiveness of the method, an experiment is employed. Meanwhile, we also analyze the effect of some related parameters of S-SOM on face clustering for further research.

The SALSA algorithm combines the main features of the PageRank and the HITS, which achieves better results than PageRank and HITS algorithm. The SALSA divides the nodes into two types of authority and hub as the HITS algorithm and adopts the random walk mode like the PageRank. Here tries applying the SALSA algorithm to the scene that recommends actors for films and TV dramas. The basic data is crawled by web crawler from douban.com, and it contains 500 films and 500 TV dramas with their chief four actors and scores. In this experiment, the films and TV dramas are seen as hub nodes, and the actors are seen as authority node. After hundred interactions of SALSA algorithm, a network index of each node is calculated. The higher the value is, the more worthy of recommendation.

This paper describes the importance of film and TV production projects management, the management solutions of TV network projects are provided by using contemporary computer technology. The shooting notice management is a sub module of the big data intelligent drama script system. It focuses on realizing automation and intelligent shooting notice management through improving the traditional way of writing and announcing shooting notices by using Excel spreadsheets. Be able to automatically supplement the other information of the field according to the completed field and avoid repeatedly finding the fill. Automatically query and fill out various personnel information. Determining the repeat of scene and the completion level of filming. Automatically judging expiration shooting notices. Archiving shooting notices for subsequent inspection. The announcement and management of the shooting notice is greatly facilitated.

In recent years, the network dramas have been more and more popular, and many people have become the screenwriter and director. How to create a better script has become a hot topic. This paper introduces the play script management system and discusses the realistic significance of character’s biography and relationships for both screenwriters and directors. The system uses the online writing mode of the script to draw graphs of relationships and helps screenwriter and director better grasp the relationships among the characters and the plots of the story by visualization. Finally, the graph of relationships can not only help screenwriters create play scripts conveniently but also help directors understand dramas well.

Assessing the importance of a node in a network is often very important. It can show the core of a network and provide guidance to decision makers. This paper combines the relevant characteristics of social networks, and proposes to use related smoothing weight factors to balance the clustering coefficient of nodes in the network, and to measure the importance of nodes as an important index. Experiments show that the importance of the nodes evaluated by this method is closer to the real situation. The importance of all nodes in the entire network is more consistent with the power law distribution.

With the continuous development of Internet technology, there is a growing desire for greater breakthroughs in the field of artificial intelligence to promote social development and progress. However, artificial intelligence has developed slowly in the past due to the complexity of its theory and the constraints of the related software and hardware conditions. As a branch of the field of AI, deep learning can learn the essential features of data and promote the development of AI. Convolution neural network is a typical multi-layer supervised learning neural network, which is widely used in various fields, especially image processing and speech recognition. This paper first introduces the research significance of convolution neural network, and then introduces its structure. The following paper studies and analyzes the architecture of LeNet-5, and improves it. Finally, the Keras framework is used to carry out the experiment on the improved network structure.

Nowadays, complex networks are widely used in various fields. We combine the role network of TV dramas and use complex network-related knowledge to analyze the characteristics of different types of popular TV series. In this paper, we apply the knowledge of social networks in a clever manner to analyze three different types of TV series——Mr. Love, West World and the Dream of Red Mansions. We introduce some important complex networks and their practical significance reflected in complex networks, including three-dimensional closures, structural holes, enemy-friend networks and the balance of multi-node network. In experiments, each TV series is abstracted as a social network model. From the perspective of social networks, we extract the above-mentioned feature structures in each network to find out their own characteristics and determine the appropriate ways to measure them.

With the exponential growth of network information resource, distributed Web Crawler was introduced for fetching massive web pages. However, when many websites designed a series of Anti-crawlers tactics to disturb Web Crawlers, it is our first imperative to deal with these strategies. We first elaborated on Web-Crawlers and Anti-Crawlers strategies. At the same time, this paper mainly proposed some effective measures to guarantee efficient web-crawling when faced with Anti-crawler tactics. Then we designed a experiment to analyze possible influencing factors. Finally, the future direction about distributed Web Crawels which runs on Hadoop platform was proposed by this paper.

The current script system management mainly by human to complete the production process time-consuming and labor-intensive. This article analyzes the present situation of script writing, expounds the importance of standardizing script, and studies the layered modeling method of SAAS software. Using the system point of view the division of functional modules, the design of the system workflow, the use of big data for script writing, and in Python3.5 + Flask0.11 + MySQL5.6 environment to achieve a full range of film and television drama management system. The system has finished writing from the script writer to improve the process of shooting shots. Practice has proved that the use of SAAS software model management system is reasonable, the cloud online writing script can greatly improve the efficiency of script writing.

As the Chinese film industry flourishes, it is of great significance to assess the influence of film and film participants. Based on the theory of complex networks, this paper studies the ranking of influence in the film-participant heterogeneous network. Participants may have multiple identities such as directors, screenwriters, and actors. Referring to the PageRank algorithm of the page ranking algorithm and combining the features of the film industry, a new ranking algorithm, MovieRank, is proposed. The core three rules are as follows: (1) If the movie rank is high, the ranking of the participating players is also high; and if the participants have a high ranking. It also has a high ranking in participating movies; (2) the rankings of films and participating players are influenced by their social attributes; (3) the movie contributes more to their high-position participants, and the participants contribute more to the movie that they play an important role in it. Experimenting with Chinese movie information as experimental data, it is found that the new algorithm MovieRank actually performs better than the original PageRank algorithm. At the same time, through the analysis of the experimental results, it is found that the cooperation between actors from Hong Kong and Taiwanese is very close in the Chinese movie network, and that the directors and screenwriters have higher stability and less change than the actors.

Most NLP tasks are based on large, well-organized corpus in general domain, while limited work has been done in specific domain due to the lack of qualified corpus and evaluation dataset. However domain-specific applications are widely needed nowadays. In this paper, we propose a fast and inexpensive, model-assisted method to train a high-quality distributional model from scattered, unconstructed web pages, which can capture knowledge from a specific domain. This approach does not require pre-organized corpus and much human help, and hence works on the specific domain which can’t afford the cost of artificially constructed corpus and complex training. We use Word2vec to assist in creating term set and evaluation dataset of embroidery domain. Next, we train a distributional model on filtered search results of term set, and conduct a task-specific tuning via two simple but practical evaluation metrics, word pairs similarity and in-domain terms’ coverage. Furthermore, our much-smaller models outperform the word embedding model trained on a large, general corpus in our task. In this work, we demonstrate the effectiveness of our method and hope it can serve as a reference for researchers who extract high-quality knowledge in specific domains.

Software complexity brings software developers and learners a series of challenges to face. Automatically analyzing large-scale software systems with complex network provides a new insight into software analysis, design, evolution, reuse, and iterative developing. Nowadays, extracting network models derived from software systems and making it easily comprehensible remains challengeable for software engineers. This paper focus on Python software. We propose a series of algorithms to extract python software networks, and a concept of visual information entropy to visualize network to an optimal statue by D3.js. Then we analyze python software networks in different perspectives by Pajek. A series experiments illustrate that software network can disclose the internal hidden associations to facilitate programmer and learner to understand the software complex structure and business logic through the simplified complexity. Finally we create a synthetic software tool integrated by above three functions, which can assist programmers to understand software macro structure and the hidden backbone associations.

The electro-hydrostatic actuator (EHA) is replacing the traditional hydraulic actuator to become an important part of the aircraft hydraulic system, because of its power by wire, easy maintenance and high reliability. But the application of EHA is limited by its disadvantage of heat dissipation. Therefore, it is necessary to establish the thermodynamic modeling and analysis of the thermal performance of EHA. In this paper, the EHA one-dimensional multi-discipline models are established by Modelica. A flexible model library of each component of EHA with thermodynamic characteristics is carried out. An EHA model based on this components are established and simulated to evaluate the correction of the model. The simulation results indicates that the models can be used to simulate the dynamic of electrical, mechanic and thermal in high accuracy. It lays a foundation for the heat control of EHA.

In order to explore the swarm behavior of Multi-agent systems further, this paper investigates the Vicsek and Boid simulation model. We researched on the Vicsek model in 3D space and rules of avoid collisions, velocity matching and flock centering in the Boid model. At the same time, we make some improvement of the original model and then simulate on Unity3d Engine and analysis the result. The simulation results show that the improved model works fine in 3d space and is better for the simulation of swarm behaviors.

with the continuous development of Internet technology, information overload is becoming more and more serious. It's getting harder to get useful information from the network. Although the search engine can help users find information they need from the vast amounts of information in a certain extent, but cannot completely solve the problem of information overload, when users cannot accurately describe the information they need, you need to recommend system to help users find valuable information for users. So recommender systems are becoming more and more important. The movie recommender system implemented in this paper is based on the traditional user-based collaborative filtering algorithm, and the user project scoring matrix is pre filled. At the same time, database technology of this system uses graph database which is good at dealing with complex relations. In data visualization, the degree of recommendation of a movie is expressed by the size of the node and the thickness of the edge, so as to improve the user experience.

With the continuous enrichment of film and television, the script management system came into being. At the same time, the arrival of the Web2.0 era has made people become stricter about the usability and interactive experience of the website. Well designed and well featured web sites can increase user experience and increase user retention, while poorly designed and slow acting sites make users feel bad and churn out a large number of users. Therefore, the front-end design and interaction of web applications is becoming more important. The first chapter introduces the background and significance of the development of art play library system, the second chapter introduces the three basic front-end technologies and the common framework, the third chapter introduces the overall structure of the system and the specific design and implementation of front end, the fourth chapter summarizes.

With the rapid development of the Internet, people have a higher demand for the performance experience of the Web site. To improve page utilization and user interaction experience, web page capacity becomes bigger and bigger and use a lot of JavaScript code and its framework technology in web pages which makes web pages more expressive and richer.[1] However, it also affects the resolution efficiency of the Web page in the browser, and directly delays the loading time of the Web page. To improve the user experience, web optimization becomes extremely necessary. Web site optimization is divided into front-end optimization and back-end optimization of two ways. We found that only 10%∼20% of the time was used to get HTML documents from the Web server to the front-end browsers and the 80%∼90% of the time was used in response to the front end[2]. Front-end optimization requires less time and resources, and modifying a small number of programs can quickly improve the speed of your site[3]. This article focuses on the front-end, from five aspects of the reduction of HTTP requests, page element optimization, Client caching optimization, DNS optimization and compression technology to propose some optimization methods to achieve the performance of the Web site to improve without changing the database and background code[4].

Tariff recovery risks of electrical users are always big problems for electric power company, and the user portrait technology can realize tariff recovery risks assessment and defense by analyzing user power consumption, payment and arrears data from electricity information acquisition system and marketing system. This paper studies the multi-source data fusion and clean technology to handle power consumption, payment and arrears data. On this basis, the electrical user label system is established, the scene design of tariff recovery risks assessment is realized, and the C4.5 algorithm is used to evaluate the risks of tariff recovery. The analysis results of test case show that the model and algorithm proposed in this paper have high availability and accuracy, and can provide the references for electric power company to reduce the risk of tariff recovery.

The present paper concerns itself with a theoretical calculation study on implementation and optimization of protein sequence issue. Using ant colony optimization algorithm (ACO) to build the Two-Dimensional Hydrophobic-Hydrophilic (2DHP) model. There are three parts in this paper. Starting with a brief introduction of the ant colony optimization and 2DHP model, then we propose a method on how to construct such model based on ant colony optimization algorithm. We end the study with the conclusion that ant colony optimization algorithm for protein sequence theoretical calculation can be improved.

This paper mainly talks about the Recurrent Neural Network and introduces a more effective neural network model named LSTM. Then, the paper recommends a special language model based on Recurrent Neural Network. With the help of LSTM and RNN language models, program can predict the next character after a certain character. The main purpose of this paper is to compare the LSTM model with the standard RNN model and see their results in character prediction. So we can see the huge potential of Recurrent Neural Network Language Model in the field of character prediction.

Existing identity providing models are generally user-oriented or service provider-oriented, which can hardly meet the requirements of integration for heterogeneous resources of enterprise. This paper presents a unified identity providing model for accessing to heterogeneous resources: providing resource identity, identity mapping from heterogeneous resources identity to unified identity, and also providing identity providing interface for application software developing. Unified identity shields the differences of identity information among resources in heterogeneous environment, which makes users get the ability to access resources with one unified identity.

The score in art exam, part of College entrance examination, is very useful and helpful. Thanks to the exam management system we got the data easily, and there are huge amount of data accumulated. We analyzed the data and visualize the data through Cluster Analysis and Correlation Analysis. And get the relationship between number of students and age, subject, position. Finally we visualize the analyzed data.

The design of flight control actuation system is facing major challenge due to the development of more electrical aircraft. The task is to find the combinations of power sources, actuators and computers, which becomes more complex because of the new power sources and actuator types of more electrical aircraft. It is impossible to determine optimal architecture by traditional trial-and-error method within acceptable time. Therefore, the need for new methodology for actuation system architecture design emerges. This study proposes an intelligent design method which has steps of design space exploration of actuation system architectures by constraint satisfaction problem (CSP) method, safety assessment process to exclude unsafety solution, multi-objectives optimization to get Pareto optimal front and comprehensive decision for final architecture via analytic hierarchy process. And the design method is implemented in python and a software platform is developed. Furthermore, within the paper a case study for A350 flight control actuation system is presented to testify the application of this methodology. Compared to the traditional hydraulic architecture, the optimal architecture is more competitive in weight, power and cost. At the same time, the optimal architecture is found in less than 30 minutes among 1075 candidates, which greatly reduces the design cycle. This method deals with the problem in the design of flight control actuation system.

Optical CT is now expanding into reconstruction from few views or limited-view range projection considering the economy and practicality. To solve the conflict of velocity and precision, which are two main aims that image reconstruction algorithm pursued, an innovative complex image reconstruction algorithm for real-time measurement of transient field is proposed. This method reconstructs computerized tomography (CT) image firstly by frequency spectrum approach reconstruction technique (FSART) and then by modified simultaneous algebraic reconstruction technique (MSART) and can give a fast and precise reconstruction to complicated transient field.