In the digital era, social media and the Internet have become the primary channels for information access. While these platforms accelerate the spread of information, they also contribute to the proliferation of fake news, misleading individuals and disrupting social order. Although existing multimodal fake news detection methods have shown some progress, they predominantly rely on raw image and text features extracted by models. This approach often fails to capture implicit in-formation, resulting in the loss of crucial details needed for accurate comparison. In this paper, we propose SEMFD, an innovative method that enhances multimodal fake news detection by incorporating summaries generated from news text using a multimodal pre-trained model. These summaries are encoded alongside text and image features, which are then processed through a fine-grained multimodal alignment module. In this module, the aligned features interact, their weights are computed, and multimodal feature fusion is performed before being passed to a classifier. Extensive testing on two real-world datasets demonstrates the effectiveness of the SEMFD model.

ABSTRACT Background With the increasing integration of Artificial Intelligence (AI) and Internet of Things (IoT), the dissemination of multimodal data is undergoing revolutionary changes. To mitigate the societal risks posed by the rapid spread of malicious multimodal data, such as hateful memes, it is crucial to develop effective detection methods for such data. Existing detection models often struggle with data quality issues and lack interpretability, limiting their effectiveness in content moderation tasks. Aims This paper aims to propose an explainable hateful meme detection model by uncertainty‐aware dynamic fusion. The goal is to enhance both generalization performance and interpretability, addressing the limitations of conventional static fusion methods and existing algorithms for hateful meme detection. Materials & Methods To mitigate the societal risks posed by the rapid spread of malicious multimodal data, such as hateful memes, it is crucial to develop effective detection methods for such data. However, existing algorithms for hateful meme detection frequently overlook the data quality and the interpretability of model. To adress these challenges, this paper proposes Hate‐UDF, an explainable hateful meme detection model with uncertainty‐aware dynamic fusion, providing both high generalization ability and interpretability. This method dynamically evaluates the uncertainty of different modalities, obtains dynamic weights, and utilizes them to weight the feature values for fusion, thereby obtaining a uncertainty‐aware dynamic fusion method with provable upper bounds on generalization error. Furthermore, an analysis of the dynamic weights can explain the modality on which the model primarily relies for detection, thereby providing a method that is both explainable and reliable. Results We compare the performance of Hate‐UDF with three general models and three State of the Art (SOTA) models in the field of hateful meme detection on the Facebook Hateful Memes (FHM) and the Multimedia Automatic Misogyny Identification (MAMI) datasets. Hate‐UDF achieved state‐of‐the‐art performance, surpassing existing models on both datasets. Specifically, it improved accuracy and AUC by 7.56% and 2.8% on FHM and by 3.34% and 0.17% on MAMI compared with the current SOTA model, respectively. Additionally, we demonstrate that the visual modality is more important than the textual modality in the hateful meme detection model, and we explain the primary reason behind this by visualization. Discussion The model dynamically adapts to modality quality, enhancing reliability and reducing the risk of misclassification. Its interpretability, achieved through visualizations of modality and feature attributions, provides valuable insights for content moderation systems and highlights the importance of image modality in detecting hateful meme. While Hate‐UDF provides an explainable and reliable method for detecting hateful memes, it may still learn biases from the training data, potentially leading to the over‐detection of content from certain groups or communities. Future research must focus on improving the fairness and ethical responsibilities of the model's decisions. Conclusion This paper introduces the model of Hate‐UDF, a dynamic fusion method based on uncertainty, designed to improve multimodal fusion issues in existing hateful meme detection models. The model determines the reliability of different modal information by assessing their uncertainty and generates dynamic weights accordingly. By comparing these weights, the model can identify which modality is most influential in detecting malicious content. Therefore, the Hate‐UDF model not only has interpretability but also its generalization performance has been validated.

This paper presents a new blockchain scheme using a linkable ring signature algorithm based on lattice cryptography. This scheme counters quantum attacks on blockchain transaction signatures. The signature algorithm ensures correctness, anonymity, and unforgeability using trap generation and rejection sampling. It’s resilient to quantum attacks due to lattice cryptography’s hardness. Compared to other lattice-based algorithms, it offers reduced signature generation and verification time, minimized signature length, lower storage requirements, and better scalability. Implementing this scheme supports blockchain transaction security and privacy, promoting blockchain’s sustainable development and widespread application. This research enhances blockchain security against quantum attacks, paving the way for more secure and efficient blockchain-based apps.

Aspect term extraction is an important subtask in aspect sentiment analysis, and it is a necessary step to complete other subtasks. Existing studies focus on complex and changeable models and only use single dataset for training, which is not conducive to the research and has no good to the application of aspect term extraction task. Therefore, this paper seeks for a simple and effective model to complete the task. We transformed the aspect term extraction task into sequence tagging task, and applied the BiLSTM-CRF model to extract the aspect terms. Experiment results and case studies showed that the F1 score of proposed model on the laptop dataset is 80.13, which is 6.35 higher than the best baseline model. On the restaurant dataset, the F1 score reached 85.2, 1.19 higher than the best baseline model. It proved that the BiLSTM-CRF has better performance than the baseline, and had greater advantages on multiple aspect words recognition. In addition, we applied BiLSTM-CRF model to our practical task, and constructed an aspect-level Yelp dataset in a semi-supervised method. The parameter setting of the method was discussed.

With the development of information technology, machine translation technologies play a crucial role in cross-language communication. However, there is a problem of information loss in machine translation. In view of the common problem, this paper proposes three Transform-Information Combination (Transformer-IC) models based on information combination method. The models are based on the Transformer and select different middle-layer information to compensate the output through arithmetic mean combination method, linear transformation method and multi-layer information combination method respectively. Experimental results based on Linguistic Data Consortium (LDC) Chinese-to-English corpus and International Workshop on Spoken Language Translation (IWSLT) English-to-German corpus show that the BLEU values of all kinds of Transformer-IC model are higher than that of the reference model, in particular the arithmetic mean combination method improves the BLEU value by 1.9. Compared with the Bert model, the results show that even though the Bert model has a good performance, the Transformer-IC models are better than the Bert model. Transformer-IC models can make full use of the middle-layer information and effectively avoid the problem of information loss.

The cloud computing, as a more distributed and more efficient paradigm with better performance, has played an important role in many fields. The cloud environment under the IoT has also assumed many roles such as the storage, the processor, the service provider and so on. However, the complex deployment and usage environment of the IoT brings new security risks to cloud computing. In response to this situation, this poster preliminarily designed a security scheme for the cloud environment of IoT. Based on the identity verification algorithms and blockchain technology, the credibility of data stored in the cloud can be ensured, while the security of data transmission from the cloud to data consumers is achieved.

There are lots of different sample points in a single trace, the each sample point containing some leakage information is useful to obtain the key when a chip encrypt plaintext with the key, these points of interest in a trace could be extracted and a new trace is formed sequentially. If using this shorter trace could improve the performance of classification in neural networks during side-channel attacks and to reduce the amount of traces required in the classification, and it means that these sample points are indeed useful and contain lots of information needed for side-channel attacks. In this paper, different amount of points of interest extracted from traces in ASCAD to form a new kind of traces as input data feed into neural networks including Multi-Layer Perceptron, Convolutional Neural Networks. In order to compare with the result of POI-traces, Principal Components Analysis was also used to shorter the length of the original trace in ASCAD, so that its length is the same as POI-traces'. About the results, the classification results with ASCAD traces are the worst using MLP or CNN, the results of PCA-traces which contain only 100 sample points using MLP are the best, and the results of POI-traces containing 300 sample points are the best result using CNN. So when using neural networks to assist side-channel attacks, the transformation of traces or the reduction of its length is advantageous to a certain extent.

In order to cooperate with the formulation of the "People's Republic of China Radio and Television Industry Standards-- Technical specification of digital rights management for video audio content distribution", a fusion media copyright protection product and system test evaluation platform supporting domestic passwords was constructed, and the end-to-end multimedia copyright protection system was implemented. Test evaluation requires compatibility testing of the DRM (Digital Rights Management) system. This paper captures and filters the HTTP protocol packets in the 4K-DRM system, and then analyzes the compliance of the HTTP packet protocol such as key synchronization, key query, and content authorization to determine whether the system passes the compatibility test.

As an organization that develops DRM (digital right management) standards in China, ChinaDRM proposed a set of solutions for the DRM application. This paper mainly focuses on the rights expression and the content authorization mechanism of ChinaDRM. We built a basic model for ChinaDRM's rights expression, introduced the format of ChinaDRM license and gave a license instance for analysis. At the end of this paper, we introduced the content authorization mechanism of ChinaDRM.

Medical insurance management is the core content of social security management. In recent years, there are many events about medical insurance illegal behaviors cause a large number of medical insurance fund losses. How to effectively supervise the medical insurance fund to protect the legal rights of the insured person has become an urgent problem. Due to the low efficiency of audit work and the hidden illegal behavior, traditional medical insurance supervision systems often waste massive resources, but still cannot play an effective role. Based on analyzing the status of medical insurance supervision and the importance of transforming supervision mode, this paper mainly studies the design and implementation of an intelligent medical insurance supervision system.

Big data is increasingly becoming a hot research topic, applied to all walks of life. And the film and television big data makes big data science and film and television industry blend together, making far-reaching impact on the film and television works of creation, dissemination, acceptance and other aspects. With the hit of different types of films and TV plays, the screenwriter directing industry has become a lot of people dream career, they eager to show talent in this area. The significance of this paper is to use the online writing mode of the script to draw the figure of character relationship. It can clearly grasp the characters in the script by visualization, and make the decision support of the characters and balance the role relation to ensure the scriptwriter's layout is reasonable. Based on the current situation of script creation and the actual needs of users, so that different levels of users can freely create character relationship map, and give the role of quantitative analysis of the results, so as to achieve the purpose of supporting the creation.

Stacking model Fusion is a combination classification method for natural language processing and text categorization. Compared to a single weak classifier, model Fusion has the advantage of combining the classification strengths of multiple classifiers, so the combination classifier is often more accurate than a single classifier, and the research of this field has been developed rapidly in recent years, and the combination classifier has been applied in various natural language processing tasks. But only by using the prediction results of the first layer weak classifier to train the second layer classifier, it has a strong limitation, only considers the training of the classification result and ignores the semantic information. We think that the method of training the weak classifier by TFIDF to the document, the expression of the document is not enough, only the information about the frequency of the document and the document is lack of the semantic information of the word2vector. In this paper, a new combination classification method is proposed, which combines the various weak classifiers trained by TFIDF and Word2vector to express the documents in many aspects, and the feature expression can fully utilize the information provided by the document. It has better classification effect than individual word2vector expression and classification and simple weak classifier combination classification.

With the rapid development of the Internet, there are more and more ways of spreading news, and it's spreading faster and faster. This creates a lot of fake news that confuses the reader's vision. In order to construct a healthy news communication environment, it is necessary to suppress fake news and to crack down on the source of fake news, so it is necessary to trace the source of news. This paper tracks the news based on the distributed storage, decentralization and other features of the blockchain, with the technology of consensus algorithm and intelligent contract.

In 1976, S. Even and Cooper proved that Course Timetabling Problem (CTP) is a nondeterministic polynomial time-complete problem which is hard to be solved. Though many intelligent methods have been applied to solve the Course Timetabling Problem in recent years, there is still a lot of room for improvement. This paper proposed a Greedy and Genetic Fusion Algorithm (GGFA) to solve Course Timetabling Problem efficiently, which can obtain the local optimal solution by using Greedy Algorithm and provide a high-quality initial population for Genetic Algorithm. Simulation results prove that Greedy and Genetic Fusion Algorithm proposed in this paper has the stronger optimal ability and faster convergence speed than standard Genetic Algorithm, which could solve the CTP effectively and achieved good results.

With the rapid development of neural network and face recognition, the image processing and recognition is more and more important. RCNN and OverFeat represent two early competing ways to do object recognition. In this paper, we review the development of image processing and recognition at the first stage, and then we introduce two methods used to recognize verification code. Finally, we design an experiment to compare the differences between BP and CNN in this field and propose some ways to improve the performance.

The development of computer's application changes our daily life. Online maps application and popularization provide us a more convenience life. As individual users, we usually search for single or several map markers on the Internet. For the existing online map, whether from the positioning accuracy, reaction speed, and operating convenience aspects, it is an advanced system. But for the abundant makers, due to the positions of the searched makers are so close, there is a problem of overlapping coverage between markers and markers at a certain zoom level, which requires the maker clustering algorithm to optimize the geographic information display. Through the aided optimize of interaction design in the process of maker clustering, it can help us to enhance the study of geographic data mining and analysis.

How to effectively utilize the computing resource remains a longstanding challenge in MapReduce application, and MapReduce system productivity has become a major issue in research field. In the paper, we explored the productivity mathematical models for MapReduce system, defining the productivity as the ratio of the workload and energy consumption per unit time, and proposed the measurement approach for MapReduce system productivity. Based on the measurement model and approach, this paper selected CPU intensive and I/O intensive computing in MapReduce to measure and evaluate MapReduce system productivity. Finally the measurement and evaluation result showed that productivity model and approach in the paper is reasonable and valid for architecture design of MapReduce system in production environment.

This paper discusses the necessity and importance of the establishment of big data from the current predicament of cable TV industry, and introduces the current situation of the development of big data of Internet and telecommunication industry,and expounds that the cable industry how to deal with and develop big data from many aspects,which ensure that cable industry can have the dominant position in the fierce competition.

With the development of Internet technology and the arrival of the era of big data, it is necessary to analyze and excavate the micro video data. It can help micro video creators to create better to analysis micro video data. This paper mainly introduces the structure design, key technical points and specific implementation steps of the micro video topic recommendation system.

Aiming at the functional requirements of the Express Supervision System, This paper discusses the advantages of using AngularJS to build the front-end framework, the advantages of using NodeJS to construct the back-end Web server, and the performance advantages of storing data based on MongoDB. This paper focuses on the storage solutions of using MongoDB to store large data and the statistical analysis solutions based on MapReduce. This paper argues on how to build Web services that meet the requirements of large data visualization based on NodeJs.

Although DOTA2 is a popular game around the world, no clear algorithm or software are designed to forecast the winning probability by analyzing the lineups. However, the author finds that Naive Bayes classifier, one of the most common classification algorithm, can analyze the lineups and predict the outcome according to the lineups and gives an improved Naive Bayes classifier. Using the DOTA2 data set published in the UCI Machine Learning Repository, we test Naive Bayes classifier's prediction of respective winning probability of both sides in the game. The results show that Naive Bayes classifier is a practical tool to analyze the lineups and predict the outcome based on players' choices.

The design of 3D scene should follow the rules of architecture's organization.At present,the 3D scene design are usually carried out by art designer who lack the knowledge of architecture.A method is proposed in this paper to solve the problem.We improved the interactive genetic algorithm to obtain the best adaptive features,and combined the ART1 network to simulate the behavior of users to evaluate the individuals. This method can solve the problem that manual evaluation operation may cause errors by the user's fatigue during the evaluation process ,and it can increase the number of generations to obtain more information.We improved the ART1 network based on the principle of experimental psychology to simulate the hierarchical structure of human brain's memory mode,and increased the memory capacity and compute efficiency.In this way,we can obtain the more accuracy adaptive values of 3D facade's features and improved the 3D architecture facade's evolution process.This method can reduce the tedious work in art design,and effectively guide the design of 3D scene scheme.The disadvantage of this method is that it is not do enough works to deeply explore the relationship between some kinds of implicit aesthetic indexes in aesthetic personality,and lack of successful exploring in establishing a reasonable approximate model to express the implicit aesthetic characteristics.In future we should study more deeply and solve the problems above.This method is suitable for batching optimizing the 3D architecture facade,and has a positive meaning for 3D architectural design,landsape design,3D game scene design and virtual reality.

Coming with the big data era, our traditional TV media is under the impact of new media, directly reflect in the loss of customers and a serious decline in advertising. This paper analyzes the main problem television media confronting in the big data era, calls the need for the big data platform of television media to solve these problems, and proposes the general idea of big data platform television media and the big data platform framework of television media.

Cloud computing is the product of a traditional classical computer technology, communications technology integration and development, also the key technology to lead information industry means to the future of innovation. This article describes the key technology of cloud computing, reviews cloud computing for industry development status and analyzes the applications of radio and television carrier services, researches how to build a legitimate broadcasting operators cloud computing architecture for supporting the corresponding business applications, how to improve user perception, reducing stress operator core system for enterprises and make cost efficiency.

Huang and Wu proposed a new network which is called balanced hypercube, the balanced hypercube is a variant of the hypercube network. As a crucial factor to evaluate the performance of the interconnection networks, fault tolerance of the interconnection networks has been widely studied in recent years. Hence, it is nature to consider the fault tolerance of the balanced hypercubes. Wu and Huang have proved that the balanced hypercube is bipartite graph. Hao has proved that there exists a fault-free Hamiltonian path between any two adjacent vertices in BHnwith (2n-2) faulty edges. This paper has proved one Hamiltonian property in BHnwith (n - 1) faulty edges.

Biogeography-based optimization (BBO) is a recently-developed algorithm that uses migration to share information among candidate solutions. We use differential evolution algorithm's mutation operator to improve the individual migration operator, and take an adaptive method in setting the value of the scaling factor. The new individual migration is combined with two traditional gene migrations, thus we get a new multiple migrations operator. The biogeography-based optimization with multiple migrations (HLBBO) is proposed based on this new operator. Experiments have been conducted on 25 benchmarks from the 2005 Congress on Evolutionary Computation. Compared with BBO algorithm and linearized BBO, the results show that the proposed algorithm HLBBO can improve the convergence speed and solution accuracy. And the boxplot of the best fitness value show the algorithm' s stability.

Nowadays, people pursuit of fast and convenient way of life, fast and convenient service of ATM is made for people to avoid waiting in line at the bank for a long time. In order to serve people conveniently, it is need to monitor the ATM equipment to guarantee its normal operation, and deal with the unexpected problems in time. Therefore, this paper builds a cloud platform for alarm service, does some alarm analysis, which appears at different times in different locations of the ATM machine. This can provide better service for ATM users. This system is called ATM Alarm Data Analysis System.

In the logistics industry, if every business know the flow and flow direction of different items and the type of items clearly, it will convenient for the business to make sales plan in time and improve the income. Based on the idea, this paper designs a method, which for carry out statistical analysis on the flow of items, and introduce the specific process. Face with the data which has large quantity, variety of item categories, the article design a program of data preprocessing at first, then calculate items' similarity by corpus-based approach, combined with the K-means cluster algorithm for the classification of items, and analysis of items' category. Analysis flow and flow direction by means of statistical analysis. At last, visualize the analysis result, output to foreground.

Nowadays, with the rapid progress of computer technology, some new words like big data, visualization emerge in endlessly. Meanwhile, research of these respects is still ongoing. By using data visualization technology, we can obtain an excellent data analysis result. By using Item Response Theory (IRT) and Computerized Adaptive Testing (CAT) system, this paper is to build a method of individual adaptive English learning and memory. It will also combines the method of English learning with data visualization, aims to create a modern, visual and attracting English learning method, and creates a new learning experience.

In modern society, some famous news websites such as Sina and Times server to provide information every day for millions of users. But with the continuous development of information technology, the amount of disorder data is increasing. How to organize the text and make automatically text classification has become a challenge. The traditional manual classification of news text not only consumes a lot of human and financial resources, but also hardly achieved classification task quickly. In this paper, the paper mainly makes a research about the news text classification. It proposes a news text classification model based on Latent Dirichlet Allocation (LDA). Due to the dimension of the news texts is too high, this model uses topic model to make text dimension reduced and get features. At the same time, the paper also makes a research on Softmax regression algorithm to solve multi-class of text problems in our life and make it as model's classifier. The paper evaluates proposed model on a real news dataset and the result of the experiment shows the improved model performs relatively well. The model can effectively reduce the features dimension of the news text and get good classification results.

With the development of science and technology, it generates a large amount of data. Data visualization is an important branch to help people get a better understanding of the changing trend of data. Data visualization is a significant method to Big Data Analysis, which shows the importance of data in a visual form. By using data visualization, people can easily find the association between data. According to the requirement of ATM service, this paper designs and implements the information visualization system of ATM alarm data.

With the development of the Internet and social networking service, the micro-video is becoming more popular, especially for youngers. However, for many users, they spend a lot of time to get their favorite micro-videos from amounts videos on the Internet; for the micro-video producers, they do not know what kinds of viewers like their products. Therefore, this paper proposes a micro-video recommendation system. The recommendation algorithms are the core of this system. Traditional recommendation algorithms include content-based recommendation, collaboration recommendation algorithms, and so on. At the Bid Data times, the challenges what we meet are data scale, performance of computing, and other aspects. Thus, this paper improves the traditional recommendation algorithms, using the popular parallel computing framework to process the Big Data. Slope one recommendation algorithm is a parallel computing algorithm based on MapReduce and Hadoop framework which is a high performance parallel computing platform. The other aspect of this system is data visualization. Only an intuitive, accurate visualization interface, the viewers and producers can find what they need through the micro-video recommendation system.

With the development of Internet, shopping on the internet is becoming more and more popular. In the meantime, the massive commodity make the experience of online shopping bad. In order to solve this problem, commodity recommendation system is applied into e-commerce platform and the experience of online shopping has been promoted. Essentially, commodity recommendation is a kind of behavior prediction. So, research on user behavior prediction can also promote experience of online shopping. In this paper, the FMs algorithm is applied into prediction of user behavior. Based on real data of user behavior data, we take advantage of four kinds of behavior to make analysis and propose a good user behavior prediction model based on FMs algorithm.

The most direct access to evaluate what kinds of topics are valuable for video producers, and bring them inspiration is to seek subjects which specific groups concern currently. We can obtain massive user information from social networking platforms, large video sites and search engines, and then exploit the data to produce more practical works with the combination of business requirements. In views of the existing disadvantages of inferior scalability, sparsity problem and huge volume test data, the application of Singular Value Decomposition Method(SVD) actualize the unknown prediction score function of set of tests. The simulation results show that scalability, sparsity and omputational efficiency improved effectively.

Many available algorithms are structurally recursive and can invoke the typical algorithm itself once or even more times to solve tightly related sub-problems. All of these algorithms follow the major principle called Divided-and-Conquer method, which first divides initial problem into several items same in goals but have a smaller scale. The Merge Sort uses this ideology to compass complexity and accelerate processing time. The coordinate-recorded merge sort algorithm continues the main idea, lets the processing problems get larger gradually, but directly works out solutions of the smallest subproblems at the very start, in other words, the dividing process becomes useless.

With the rapid development of China universities, especially the expanding enrollment of higher occupation technical school in recent years promotes Chinese higher education into the popularization era. At the same time, it also leads to that college student employment situation is very serious. The employment pressure intensified. In the face of surplus resources situation, comprehensive quality requirements of graduate students are also getting higher in social workplace. So the college students' occupation literacy level has become a key factor in the employment competition, so the research of College Students' occupation quality system is very important. This paper makes full use of data mining and data analysis algorithm, which puts forward a novel multidimensional professionalism evaluation model based on Logistic regression and decision tree algorithm. The model considers common requirements and personalized recommendations of professionalism. This model can be as much as possible used to help students predict their occupation literacy and interest required key professionalism, which can improve and adjust themselves and increase the possibility of being employed.

With the development of network information technology, a lot of news comes into the view of Internet users. We have entered the “information overload” era. So how to find useful information becomes more and more important. Personalized news recommendation is a kind of technology to find the news that users want to get urgently. It is based on the browsing history of many users. Through analysis of their interests, we can realize the personalized news recommendation for different people. In our system, we propose an improved association rules. This method associates with collaborative filtering algorithm to form a hybrid recommendation algorithm. Through using this new algorithm, we can generate recommendation lists and realize the personalized news recommendation.

With the development of Internet technology, the main source of human access to news reporters changes from the original traditional print media to the Internet-based technology news portal. However, with the data technology incoming, the information is exploding on the Internet. If the company can provide some news that users are interested in from the data of ocean, the company can gain the favorites of users. This paper is based on links of web structure and Sequential Pattern by analyzing the user's click-stream behavior to obtain the browsing habits and preferences of users. Through using the recommendation technology, it can help predict the interests of users and reduce the users' searching time for news.

Public opinion is the people's response for social phenomena, issues, hot topics, attitudes, emotions, and so on. It reflects the focus problems of the current time of the society. By analyzing the public opinion, we can infer what will happen in the next time, and give better decision support for governments and businesses. Big Data technology is becoming a powerful data analyzing tools for massive data in recent years. Hadoop is an open source massive data processing platform based on Big Data. Mahout is a data mining algorithms' set based on Hadoop, which is designed for processing large-scale and complex data. In most instances, the public opinion information contains many text messages. For many traditional text mining algorithms, it is almost impossible to handle high dimensional data concerns large-volume and complex data sets. Hence, this paper uses Mahout text mining algorithms to process public opinion information.

The KNN is a classic text classification algorithm. In this paper, we propose a new text classification algorithm based on the KNN. We set a text similarity threshold to optimize the value of K. In this way, we can avoid the wrong result of classification led by the unbalance of sample size. In the meantime, we use the maximal operator to calculate the text similarity instead of cosine similarity. According to the experimental data, we have made a better classification result in this way.

This paper analyzes two existing protocols, points out that they cannot resist off-line dictionary attack. And considering most of protocols cannot meet the personalized requirements, this paper presents a personalized key exchange protocol, users can choose the number of generated session keys according to their own requirements. And through safety analysis, the protocol can resist various common attacks.

With the development of network music digitization, how to effectively integrate the massive music resources on the web and to provide service for user has became an urgent problem to be solved. This paper designs a system which combines cloud computing and music integration. This architecture will provide technical support to the effective integration of online music resources.

In recent years, kNN algorithm is paid attention by many researchers and is proved one of the best text categorization algorithms. Text categorization is according to training set, which is assigned class label to decide a new document, which is not assigned class label belongs to some kind of document. But for a classifier, text preprocessing is the bottleneck of categorization. In the original feature space, there are always thousands upon thousands words. The dimension of feature space is very high. So in this paper, we adopt a new feature weight method---- improved Gini index to reduce the dimension of feature space and improve the categorization precision. In addition, we discuss the improvement of decision rule and dimension selection. We design an adaptive fuzzy kNN text classifier. Here the adaptive indicate the adaptive of dimension selection. The experiment results show that our algorithm is effective and feasible.

With the development of WWW (World Wide Web), more and more people surf on the Web, more and more Web sites provide forum for people to publish their reviews, so there are many reviews on some special topic in many forums. Our system mainly aims at the reviews of customer for some product. The data set comes from forum data or emails or any other form of reviews. The mining result can guide the company's CEO to make science decision for company's products research and market development and the mining result can guide the customers to purchase more satisfying products. Our system mainly adopts data mining technology, natural language processing technology, Web text mining technology and so on. In the realization of our system, we adopt role based concepts and theory, this makes the realization more reasonable and more efficiency and this makes the system function more perfect and more science.