Search

With the rapid development of internet technology and the increasing popularity of e-commerce, data encryption technology plays a very important role in data security. Information security has two aspects: security protocol and cryptographic algorithm and the latter is the foundation and core technology of information security. Advanced Encryption Standard (AES) encryption algorithm is one of the most commonly used algorithms in symmetric encryption algorithms. Such algorithms face issues when used in the context of key management and security functions. This paper focuses on the systematic analysis of these issues and summarizes AES algorithm implementation, comprehensive application and algorithm comparison with other existing methods. To analyze the performance of the proposed algorithm and to make full use of the advantages of AES encryption algorithm, one needs to reduce round key and improve the key schedule, as well as organically integrate with RSA algorithm. Java language is used to implement the algorithm due to its large library, then to show the efficiency of the proposed method we compare different parameters, such as encryption/decryption speed, entropies and memory consumption...) with a classic algorithm. Based on the results of the comparison between AES and the hybrid AES algorithm, the proposed algorithm shows good performance and high security. It therefore can be used for key management and security functions, particularly for sharing sensitive files through insecure channel. This analysis provides a reference useful for selecting different encryption algorithms according to different business needs.

Plagiarism source retrieval is the core task of plagiarism detection. It has become the standard for plagiarism detection to use the queries extracted from suspicious documents to retrieve the plagiarism sources. Generating queries from a suspicious document is one of the most important steps in plagiarism source retrieval. Heuristic-based query generation methods are widely used in the current research. Each heuristic-based method has its own advantages, and no one statistically outperforms the others on all suspicious document segments when generating queries for source retrieval. Further improvements on heuristic methods for source retrieval rely mainly on the experience of experts. This leads to difficulties in putting forward new heuristic methods that can overcome the shortcomings of the existing ones. This paper paves the way for a new statistical machine learning approach to select the best queries from the candidates. The statistical machine learning approach to query generation for source retrieval is formulated as a ranking framework. Specifically, it aims to achieve the optimal source retrieval performance for each suspicious document segment. The proposed method exploits learning to rank to generate queries from the candidates. To our knowledge, our work is the first research to apply machine learning methods to resolve the problem of query generation for source retrieval. To solve the essential problem of an absence of training data for learning to rank, the building of training samples for source retrieval is also conducted. We rigorously evaluate various aspects of the proposed method on the publicly available PAN source retrieval corpus. With respect to the established baselines, the experimental results show that applying our proposed query generation method based on machine learning yields statistically significant improvements over baselines in source retrieval effectiveness.

The problem of text plagiarism has increased because of the digital resources available on the World Wide Web. Source Retrieval and Text Alignment are two core tasks of plagiarism detection. A plagiarism source retrieval and text alignment system based on relevance ranking model is described in this paper. Not only the source retrieval task but also the text alignment task is all regarded as a process of information retrieval, and the relevance ranking is used to search the plagiarism sources and obtain the candidate plagiarism seeds. For source retrieval, BM25 model is used, while for text alignment, Vector Space Model is exploited. Furthermore, a plagiarism detection system named HawkEyes is developed based on the proposed methods and some demonstrations of HawkEyes are given.

Providing effective methods of identification of high-obfuscation plagiarism seeds presents a significant research problem in the field of plagiarism detection. The conventional methods of plagiarism detection are based on single type of features to capture plagiarism seeds. But for high-obfuscation plagiarism detection, these single type features are not sufficient for identifying the plagiarism seeds effectively because of the varied plagiarism methods used in high-obfuscation plagiarism. This paper presents a multi-features fusion method for the highobfuscation plagiarism seeds identification. This method exploits Logical Regression model to integrate lexicon features, syntax features, semantics features and structure features which extracted from suspicious document and source document. A multi-feature fusion classifier based on Logical Regression model is proposed to decide whether a text fragment pair can be regarded as plagiarism seeds or not. Experimental results on the PAN@CLEF2013 summary-obfuscation corpus show that the fusion of different types of features produces more accurate results.

Clustering analysis is an unsupervised method to find hidden structures in datasets and has been widely used in various fields. However, it is always difficult for users to understand, evaluate, and explain the clustering results in the spaces with dimension greater than three. Although high-dimensional visualization of clustering technology can express clustering results well, it still has significant limitations. In this paper, a visualization cluster analysis method based on the minimum distance spectrum (MinDS) is proposed, aimed at reducing the problems of clustering multidimensional datasets. First, the concept of MinDS is defined based on the distance between high-dimensional data. MinDS can map any dataset from high-dimensional space to a lower dimension to determine whether the data set is separable. Next, a clustering method which can automatically determine the number of categories is designed based on MinDS. This method is not only able to cluster a dataset with clear boundaries, but can also cluster the dataset with fuzzy boundaries through the edge corrosion strategy based on the energy of each data point. In addition, strategies for removing noise and identifying outliers are designed to clean datasets according to the characteristics of MinDS. The experimental results presented validate the feasibility and effectiveness of the proposed schemes and show that the proposed approach is simple, stable, and efficient, and can achieve multidimensional visualization cluster analysis of complex datasets.

In recent years, robot technology has been rapidly developed and applied to every walk of life. With the promotion and popularization of the robot technology, requirement of using robot is becoming high and the demand of intelligent robots is particularly urgent. Machine vision is an important research direction in the field of intelligent robotics. In the robot vision system, the core problem is the targets extraction, and the image segmentation is the key technique of extracting targets accurately, rapidly and in real-time. Since the environment is complex and the targets are diverse, the amount of images data perceived by robots is large and the images are unpredictable. Thus, it is very important to extract and segment targets accurately. Aimed at the segmentation processing of high-resolution images, a novel clustering algorithm is proposed in this paper. According to the sum of the energy of data and their sizes, it recognizes the clustering representatives and members, and identifies the most probability members by the competition among data points. Then we apply the algorithm by combining the novel clustering algorithm into Mean Shift clustering algorithm in color image segmentation problem. The algorithm can quickly and efficiently achieve the targets segmentation of high-resolution images, and has good segmentation effect. The experiments show that the proposed approach has better clustering quality and is faster than the traditional clustering algorithm.

Clustering analysis is an unsupervised method to find out hidden structures in datasets. Most partitional clustering algorithms are sensitive to the selection of initial exemplars, the outliers and noise. In this paper, a novel technique called data competition algorithm is proposed to solve the problems. First the concept of aggregation field model is defined to describe the partitional clustering problem. Next, the exemplars are identified according to the data competition. Then, the members will be assigned to the suitable clusters. Data competition algorithm is able to avoid poor solutions caused by unlucky initializations, outliers and noise, and can be used to detect the coexpression gene, cluster the image, diagnose the disease, distinguish the variety, etc. The provided experimental results validate the feasibility and effectiveness of the proposed schemes and show that the proposed approach of data competition algorithm is simple, stable and efficient. The experimental results also show that the proposed approach of data competition clustering outperforms three of the most well known clustering algorithms K-means clustering, affinity propagation clustering, hierarchical clustering.

Psychological counseling Q&A system is enjoying a remarkable and increasing popularity in recent years. Knowledge base is the important component for such kind of systems, but it is difficult and time-consuming to construct the knowledge base manually. Fortunately, there emerges large number of Q&A pairs in many psychological counseling websites, which can provide good source enriching the knowledge base. This paper presents the method of knowledge extraction from psychological consulting Q&A pairs of on-line psychological counseling websites, which include keywords, semantic extension and word sequence. P-XML, which is the knowledge template based on XML, is also designed to store the knowledge. The extracted knowledge has been successfully used in our non-obstructive psychologycal counseling system, called P.A.L., and the experimental results also demonstrated the feasibility and effectiveness of our approach.

Word Sense Disambiguation (WSD) is to decide the sense of an ambiguous word on particular context. Most of current studies on WSD only use several ambiguous words as test samples, thus leads to some limitation in practical application. In this paper, we perform WSD study based on large scale real-world corpus using two unsupervised learning algorithms based on ±n-improved Bayesian model and Dependency Grammar (DG)-improved Bayesian model. ±n-improved classifiers reduce the window size of context of ambiguous words with close-distance feature extraction method, and decrease the jamming of useless features, thus obviously improve the accuracy, reaching 83.18% (in open test). DG-improved classifier can more effectively conquer the noise effect existing in Naive-Bayesian classifier. Experimental results show that this approach does better on Chinese WSD, and the open test achieved an accuracy of 86.27%.

The high-obfuscation plagiarism detection in big data environment, such as the paraphrasing and cross-language plagiarism, is often difficult for anti-plagiarism system because the plagiarism skills are becoming more and more complex. This paper proposes HawkEyes, a plagiarism detection system implemented based on the source retrieval and text alignment algorithms which developed for the international competition on plagiarism detection organized by CLEF. The text alignment algorism in HawkEyes gained the first place in PAN@CLEF2012. In the demonstration, we will present our system implemented on PAN@CLEF2014 training data corpus.

Being as an important nonlinear component of block ciphers, Substitution box (S-box) directly affect the security of the cryptographic systems. It is important and difficult to design cryptographically strong S-box that simultaneously meet with multiple cryptographic criteria such as bijection, non-linearity, strict avalanche criterion (SAC), bits independence criterion (BIC), differential probability (DP) and linear probability (LP). To address the issue, an S-box generation approach based on L-L cascade Chaotic Map and Line Map (LLCMLM) is proposed in this paper. L-L cascade chaotic map is used to generate an integer sequence ranging 0–255, and line map is applied to scramble the position of the integer sequence. A series of experiments have been conducted to compare multiple cryptographic criteria of LLCMLM with other algorithms. Simulation results indicate that LLCMLM meets well with the design criteria of the S-box.

Being a measurable criterion of clustering quality for the classical K-means algorithm, the objective function always exists many local minimum values. The objective function may converge at some minimum values, when the initial clustering centers are dropped neighbor to the local minimum values, or the two data objects in the same cluster are regarded as two initial clustering centers which represent two clusters. Then, the problem of local optimal solution will happen. To this, a K-means clustering algorithm based on the maximum triangle rule (KMTR) is proposed in this paper. KMTR, which uses the rule of maximum triangle, selects appropriate initial clustering centers for the classical K-means algorithm. Experimental results on some UCI data sets show the validity of applying maximum triangle rule to the K-means algorithm.

A new color image segmentation method combining twice used watershed and Ncut of improved the weight matrix algorithm is presented in this paper. It preprocesses an image by the twice used watershed algorithm to form segmented regions that preserve the desirable discontinuity characteristics of image. The segmented regions, instead of the image pixels are then represented by using the graph structure and considered as the input image of Ncut algorithm. In addition a new weight matrix is designed in this paper according to the image color and space information. Then the Ncut method is applied to perform globally optimized clustering. Because the image clustering uses the segmented regions, instead of the image pixels, the new method can effectively reduce the computational complexity of traditional Ncut method by using secondary watershed algorithm. The new weight matrix also has certain self-adaptability. Through a large number of experiments using color natural scene images, the results show that the proposed method has superior performance and less computational costs compared to the traditional Ncut algorithm and the method combining the mean shift (MS) and Ncut.

The authors use opportunistic scheduling to improve the performance of wireless body area model. Previously the model of research is not much about of the model of wireless body area. The algorithm selects the best channel to transmit the data. So the throughput reaches the maximum. It increases the rate and saves the transmission time .It produces encouraging results when we apply the algorithm on the wireless body area networks with the introduction of simulation in the system setup.The effect is better than the former research result.The algorithm can also be used in other area of the wireless communication.

In this paper, methods of feature selection used in the spam filtering are studied, including CHI square (CHI), Expected Cross Entropy (ECE), the Weight of Evidence for Text (WET) and Information Gain (IG) and a novel modified CHI feature selection method is proposed in spam filtering. The spam filter combined Support Vector Machine (SVM) is selected to evaluate the CHI square, Expected Cross Entropy, the Weight of Evidence for Text, Information Gain and modified CHI. The experiment proved that the modified CHI could improve the precision, recall and F test measure of spam filter and the modified CHI feature selection method is effective.

The problem of ambiguous word sense poses lots of difficulties for language automatic understanding. And the research of word sense discrimination is applied to the resolution of this problem. Statistics are booming in researching this problem. While due to limitation of the scale of training corpus, the method of Statistical word sense discrimination can not attain satisfying results yet. Therefore, under condition that only limit scale corpus is available, how to improve the efficiency and effectiveness of statistical learning method is a hotspot in supervised word sense recognition research. On the basis of the concept of word sense Category, a new word sense discrimination method using word sense Category Extending is proposed. Experiment results show that the proposed method can effectively improve the accuracy of word sense discrimination as the training corpus is not enlarged..

Feature selection is a key step in automatic text categorization system and it has a significant impact on classification result. In this paper we do research on mutual information (MI) which is one basic method of feature selection. Firstly, we found out three main problems of MI by analyzing the formula of MI theoretically and systematically - the MI loss, the information difference among categories, and the excessive emphasis on low-frequency terms. Then, to solve these three questions, we proposed an improved feature selection method by calculating the absolute values of MI and calculating the differential values between maximum and average of MI. At last, we tested our method using K-Nearest Neighbor (KNN) classifier and Support Vector Machine (SVM) classifier respectively, and we also compared it with the original method on Chinese corpus. The results demonstrate the effectiveness and feasibility of the proposed method.

Speech endpoint detection in strong noise environment plays an important role in speech signal processing. Hilbert-Huang Transform (HHT) is based on the local characteristics of signals, which is an adaptive and efficient transformation method. It is particularly suitable for analyzing the non-linear and non-stationary signals such as speech signal. In this paper, we chose the noisy speech signal when the signal-to-noise ratio is negative. A novel algorithm for speech endpoint detection based on Hilbert-Huang transform is provided after analyzing the noisy speech signal. The signal is first decomposed by Empirical Mode Decomposition (EMD), and partial decomposition results are processed by Hilbert transform. The threshold of noise is estimated by analyzing the front of signal's Hilbert amplitude spectrum. The speech segments and non-speech segments can be distinguished by the threshold and the whole signal's Hilbert amplitude spectrum. Simulation results show that the speech signal can be effective detected by this algorithm at low signal-to-noise ratio.

Cluster ensemble techniques have been recently shown to be effective in improving the accuracy and stability of single clustering algorithms. A critical problem in cluster ensemble is how to combine multiple clusterers to yield a final superior clustering result. In this paper, we present an efficient spectral graph theory-based ensemble clustering method feasible for large scale applications such as document clustering. Since the EigenValue Decomposition (EVD) of Laplacian is formidable for large document sets, we first transform it to a Singular Value Decomposition (SVD) problem, and then an equivalent EVD is performed. Experiments show that our spectral algorithm yields better clustering results than other cluster ensemble techniques without high computational cost.

The critical problem in cluster ensemble is how to combine clusterers to yield a final superior clustering result. In this paper, we introduce a spectral method to solve document cluster ensemble problem. Since spectral clustering inevitably needs to compute the eigenvalues and eigenvectors of a matrix, for large scale document datasets, itpsilas computationally intractable. By using algebraic transformation to similarity matrix we get a feasible algorithm. Experiments on TREC and Reuters document sets show that our spectral algorithm yields better clustering results than other typical cluster ensemble techniques without high computational cost.

The input of network is the key problem for Chinese word sense discrimination utilizing the neural network. This paper presents an input model of neural network that calculates the mutual information between contextual words and ambiguous word by using statistical method and taking the contextual words to certain number beside the ambiguous word according to (-M, +N). The experiment adopts triple-layer BP neural network model and proves how the size of training set and the value of M and N affect the performance of neural network model. The experimental objects are six pseudowords owning three word-senses constructed according to certain principles. Tested accuracy of our approach on a closed-corpus reaches 90.31%, and 89.62% on a open-corpus. The experiment proves that the neural network model has good performance on word sense Discrimination.

This paper presents a new approach based on Vicarious Words (VWs) to resolve Word Sense Discrimination (WSD) in Chinese language. VWs are particular artificial ambiguous words, which can be used to realize unsupervised WSD. A Bayesian classifier is implemented to test the efficacy of the VW solution on Senseval-3 Chinese test suite. The performance is better than state-of-the-art results with an average F-measure of 0.80. The experiment verifies the value of VW for unsupervised method in WSD.

This paper presents the concept of vicarious words and develops a new unsupervised Chinese word sense disambiguation method. This method, after statistical learning from the vicarious words, realizes unsupervised word sense disambiguation by calculating mutual information to measure the degree of collocation information between the ambiguous words and their context. In our experiment, we test ten real ambiguous words and get the highest accuracy of 97%. The mean accuracy was 88.52%. The experimental results have proved the feasibility of this method.

Word Sense Disambiguation (WSD) is usually considered to be a pattern classification to research and it has always being a key problem and one of difficult points in natural language processing. Statistical learning theory is a mainstream of the research method for WSD. The distribution of the word-senses of an ambiguous word is always not symmetrical and the distinction between word-senses' emergence frequency is great sometimes, so the judgment results are inclined to the maximum probability word-sense in the word-sense classification. The reflection of this phenomenon is obviously in the Bayesian model. When using the Bayesian model to carry on some research we find a new word-sense decision rule, which have a better precision than Bayesian model in WSD. In order to validate the credibility and stabilization of this method we carry through the experiment time and again, and acquire lots of experiment data. The results of the experiment indicate that new decision rule is more excellent than Bayesian decision rule. Furthermore this paper provides a theoretical foundation for this new decision rule.

Word sense disambiguation (WSD) has always being a key problem and one of difficult points in natural language processing. WSD is usually considered to be a pattern classification to be research. Feature selection is an important sector of WSD process. We review naive Bayes model (NBM) seriously, and the feature selection method adopted in this paper is directed at Bayesian Assumption to improve NBM. Positional information concealed in the context of ambiguous word is mined via information gain calculation, to increase the knowledge acquisition efficiency of Bayesian model and to improve the effect of word-sense classification. Eight ambiguous words are tested in our experiment; the experimental results of improved Bayesian model are higher 3.5 per cent than the ones of NBM. The accuracy rise is bigger and the improvement effect is outstanding; and these results prove also the method put forward in this paper is efficacious.

In this paper, a universal kinematics model has been presented to a robot with four caster-cambered wheels. The effect toward the robot kinematics performance based on caster and camber has been analyzed. Closed-chain space and Instantaneous Superposition Frame (ISR) is used to build a 3-D kinematics model about differential suspension mobile robot with caster-cambered wheels by independent propulsion and individual steering. An algorithm to estimate the wheel slippage is given. And the Jacobian of wheel with caster and camber has been presented. The results can be the extension of the research results of P.F. Muir and Rajagoplan.

The maneuver control strategy of mobile robot with four steered independently driven wheels (4WS4WD) in rough terrain is rarely discussed. In this paper a approach of projection is adopted to get the equivalent maneuver radii and equivalent steering angles of a 4WS4WD mobile robot based on a arbitrary equivalent Instantaneous Center of Rotation-EICR, and the EICR is a vertical line on the plane of the reference frame. Thus a generic maneuver algorithm in rough terrain with constraints has been investigated explicitly to limit the orientation scope of steering wheels by means of the data of the pitch, roll, azimuth, the angle of rocker and the relative position of EICR of robot from the feed back of Inertial Measurement Unit (EMU), angle sensors, latitudinal sensors and other sensors. A typical maneuver algorithm of robot on plane has been drawn from the generic maneuver algorithm. Then factors which may affect the errors of maneuver action of mobile robot have been analyzed. Finally the results from simulation and tests are implemented to validate the feasibility of the proposed algorithms.

Firstly an interval extending and merging technology is introduced and then an improved association rules mining method with temporal restraint is proposed. The association analysis which takes use of interval extending and merging technology is implemented based on the data with temporal restraint. Finally the corresponding algorithm is presented.

This paper presents a new approach based on Equivalent Pseudowords (EPs) to tackle Word Sense Disambiguation (WSD) in Chinese language. EPs are particular artificial ambiguous words, which can be used to realize unsupervised WSD. A Bayesian classifier is implemented to test the efficacy of the EP solution on Senseval-3 Chinese test set. The performance is better than state-of-the-art results with an average F-measure of 0.80. The experiment verifies the value of EP for unsupervised WSD.