In the practical application scenario, the wheat kernel image background is single, and the imperfect characteristics of wheat imperfect grains are mostly local features while most of the image features are not different from normal grains. In order to solve the problems, an imperfect wheat kernel recognition method based on detail Image Enhancement (IE) was proposed. Firstly, the alternate minimization algorithm was used to constrain the L0 norms of the original image in the horizontal and vertical directions to smooth the original image as the base layer, and the original image was subtracted from the base layer to obtain the detail layer of the image. Then, the detail layer was delighted and superimposed with the base layer to enhance the image. Finally, the enhanced image was used as the input of the Convolutional Neural Network (CNN), and the CNN with Batch Normalization (BN) layer was used for recognition of the image. The classic classification networks LeNet-5, ResNet-34, VGG-16 and these networks with the BN layer were used as classification networks, and the images before and after enhancement were used as input to carry out classification experiments, and the accuracy of the test set was used to evaluate the performance. Experimental results show that by adding the BN layer and using the same input, all three classic classification networks have the accuracy of the test set increased by 5 percentage points, and when using the images with enhanced detail as input, the three networks have the accuracy of the test set increased by 1 percentage point, and when the above two are used together, all the three networks obtain the accuracy of the test set improved by more than 7 percentage points.

In order to generate a three-dimensional virtual human animation with rich expression and smooth movement, a method for generating three-dimensional virtual human animation based on synchronous capture of facial expression and human pose with two cameras was proposed. Firstly, the Transmission Control Protocol (TCP) network timestamp method was used to realize the time synchronization of the two cameras, and the ZHANG Zhengyou's calibration method was used to realize the spatial synchronization of the two cameras. Then, the two cameras were used to collect facial expressions and human poses respectively. When collecting facial expressions, the 2D feature points of the image were extracted and the regression of these 2D points was used to calculate the Facial Action Coding System (FACS) facial action unit in order to prepare for the realization of expression animation. Based on the standard head 3D coordinate, according to the camera internal parameters, the Efficient Perspective- n-Point (EP nP) algorithm was used to realize the head pose estimation. After that, the facial expression information was matched with the head pose estimation information. When collecting human poses, the Occlusion-Robust Pose-Map (ORPM) method was used to calculate the human poses and output data such as the position and rotation angle of each bone point. Finally, the established 3D virtual human model was used to show the effect of data-driven animation in the Unreal Engine 4 (UE4). Experimental results show that this method can simultaneously capture facial expressions and human poses and has the frame rate reached 20 fps in the experimental test, so it can generate natural and realistic three-dimensional animation in real time.

In view of the difficulties in real-time monitoring of component contents in rare earth extraction process and the high time consumption and memory consumption of existing component content detection methods, a dynamic monitoring system for element component content based on time sequence characteristics of solution images was designed. Firstly, the image acquisition device was used to obtain the time sequence image of the extraction tank solution. Considering the color characteristics of the extracted liquid and the incompleteness of single color space, the time sequence characteristics of the image were extracted in the color space of the fusion of HSI (Hue, Saturation, Intensity) and YUV (Luminance-Bandwidth-Chrominance) by using Principal Component Analysis (PCA) method, and combined with the production index, the Whale Optimization Algorithm (WOA) based Least Squares Support Vector Machine (LSSVM) classifier was constructed to judge the status of the working condition. Secondly, when the working condition was not optimal, the color histogram and color moment features of the image were extracted in HSV (Hue, Saturation, Value) color space, and an image retrieval system was developed with the linear weighted value of the mixed feature difference between solution images as the similarity measurement to obtain the value of component content. Finally, the test of the mixed solution of the praseodymium/neodymium extraction tank was carried out, and the results show that this system can realize the dynamic monitoring of element component content.

For Diabetic Retinopathy (DR), the image resolution is too high, the lesion features are too scattered to obtain, and the positive, negative, hard and easy samples are imbalanced, thus the DR staging accuracy cannot be effectively improved. Therefore, a DR staging method based on the combination of improved Faster Region-based Convolutional Neural Network (Faster R-CNN) and subgraph segmentation was proposed. First, subgraph segmentation was used to solve the interference problem of the optic disc region to lesion recognition. Second, a deep residual network was used in the feature extraction process to solve the problem of difficulty of obtaining features due to the small proportion of the lesions in the high-resolution fundus image. Finally, the Online Hard Example Mining (OHEM) method was used to solve the problem of imbalance between positive, negative, hard and easy samples during the generation of Region of Interest (ROI). In the DR staging experiments on EyePACS, an internationally open dataset, the accuracy of the proposed method in DR staging reached 94.83% in stage 0, 86.84% in stage 1, 94.00% in stage 2, 87.21% in stage 3 and 82.96% in phase 4. Experimental results show that the improved Faster R-CNN can efficiently stage DR images and automatically label the lesions.

In order to solve the problems of high abstraction degree of network warfare and insufficient means of simulation and effectiveness evaluation of network warfare under the condition of informationization, a method of network warfare simulation and effectiveness evaluation integrating multiple indexes of both attack and defense sides was proposed. Firstly, for the network warfare attacker, four kinds of attack methods were introduced to attack the network; and for the network defender, the network node structure, content importance and emergency response ability were introduced as the defense indicators of the network. Then, the network warfare effectiveness evaluation model was established by integrating PageRank algorithm and fuzzy comprehensive evaluation method into Light Gradient Boosting Machine (LightGBM) algorithm. Finally, by defining the node damage effectiveness curve, the evaluation results of residual effectiveness and damage effectiveness in the whole network warfare attack and defense system were obtained. The simulation results show that the effectiveness evaluation model of network warfare can effectively evaluate the operational effectiveness of both attack and defense sides of network warfare, which verifies the rationality and feasibility of the effectiveness evaluation method of network warfare.

In order to prolong the lifespan of heterogeneous directional sensor network, a node scheduling algorithm based on Enhanced Coral Reef Optimization algorithm (ECRO) and with different monitoring requirements for different monitoring targets was proposed. ECRO was utilized to divide the sensor set into multiple sets satisfying the coverage requirements, so that the network lifespan was able to be prolonged by the scheduling among sets. The improvement of Coral Reef Optimization algorithm (CRO) was reflected in four aspects. Firstly, the migration operation in biogeography-based optimization algorithm was introduced into the brooding of coral reef to preserve the excellent solutions of the original population. Secondly, the differential mutation operator with chaotic parameter was adopted in brooding to enhance the optimization ability of the offspring. Thirdly, a random reverse learning strategy were performed on the worst individual of population in order to improve the diversity of population. Forthly, by combining CRO and simulated annealing algorithm, the local searching capability of algorithm was increased. Extensive simulation experiments on both numerical benchmark functions and node scheduling were conducted. The results of numerical test show that, compared with genetic algorithm, simulated annealing algorithm, differential evolution algorithm and the improved differential evolution algorithm, ECRO has better optimization ability. The results of sensor network node scheduling show that, compared with greedy algorithm, the Learning Automata Differential Evolution (LADE) algorithm, the original CRO, ECRO has the network lifespan improved by 53.8%, 19.0% and 26.6% respectively, which demonstrates the effectiveness of the proposed algorithm.

To address the problem of bandwidth resource management in Web applications, a prediction method for bandwidth requirement and Quality of Service (QoS) of Web applications based on network simulation was proposed. A modeling framework and formal specification were presented for Web services, a simplified parallel workload model was adopted, the model parameters were extracted from Web application access logs by means of automated data mining, and the complex network transmission process was simulated by using network simulation tool. As a result, the bandwidth requirement and changes on QoS were able to be predicted under different workload intensities. A classic benchmark system named TPC-W was used to evaluate the accuracy of prediction results. Theoretical analysis and simulation results show that compared with traditional linear regression prediction, network simulation can stably simulate real system, the predicted average relative error for total request number and total byte number is 4.6% and 3.3% respectively. Finally, with different bandwidth scaling schemes simulated and evaluated based on the TPC-W benchmark system, the results can provide decision support for resource management of Web applications.

Concerning the problem that the posture is not correct and even endangers the health of body builder caused by the lack of supervision and guidance in the process of bodybuilding, a new method of real-time detection of deep squat posture was proposed. The most common deep squat behavior in bodybuilding was abstracted and modeled by three-dimensional information of human joints extracted through Kinect camera, solving the problem that computer vision technology is difficult to detect small movements. Firstly, Kinect camera was used to capture the depth images to obtain three-dimensional coordinates of human body joints in real time. Then, the deep squat posture was abstracted as torso angle, hip angle, knee angle and ankle angle, and the digital modeling was carried out to record the angle changes frame by frame. Finally, after completing the deep squat, a threshold comparison method was used to calculate the non-standard frame ratio in a certain period of time. If the calculated ratio was greater than the given threshold, the deep squat was judged as non-standard, otherwise judged as standard. The experiment results of six different types of deep squat show that the proposed method can detect different types of non-standard deep squat, and the average recognition rate is more than 90% of the six different types of deep squat, which can play a role in reminding and guiding bodybuilders.

In order to explore the topological changes of Normal Aging human Brain Functional Network (NABFN), a network evolution Model based on Naive Bayes (NBM) was proposed. Firstly, the probability of existing edges between nodes was defined based on link prediction algorithm of Naive Bayes (NB) and anatomical distance. Secondly, based on the brain functional networks of young people, a specific network evolution algorithm was used to obtain a simulation network of the corresponding middle-aged and old-aged gradually by constantly adding edges. Finally, a network Similarity Index (SI) was proposed to evaluate the similarity degree between the simulation network and the real network. In the comparison experiments with network evolution Model based on Common Neighbor (CNM), the SI values between the simulation networks constructed by NBM and the real networks (4.479 4, 3.402 1) are higher than those of CNM (4.100 4, 3.013 2). Moreover, the SI value of both simulation networks are significantly higher than those of simulation networks derived from random network evolution algorithm (1.892 0, 1.591 2). The experimental results confirm that NBM can predict the topological changing process of NABFN more accurately.

Intrusion Detection System (IDS) has become an essential part of network security system, the practicability and durability of the existing intrusion detection methods still have improvement space, like detecting intrusion threats earlier and improving the detection accuracy of intrusion detection systems. Therefore, an intrusion detection method based on Ensemble Transfer Learning (ETL) via weighted mutual information was proposed. Firstly, the transfer strategy was used to model multiple feature sets, then the mutual information was used to measure the data attribution of feature sets under the transfer models in different domains. Finally, the weighted ensemble was performed to the multiple transfer models according to the measures, obtaining the ensemble transfer model. The method was able to construct the intrusion detection model better than the traditional models without ensemble or transfer learning by learning the knowledge of little labeled samples in the new environment and many labeled samples in the prior environment. The benchmark NSL-KDD dataset was used to evaluate the proposed method and the results show that the proposed method has good convergence performance and improve the accuracy of intrusion detection.

With the development of large-scale network environments and big data-related technologies, traditional data fusion analysis technology faces new challenges. Focusing on poor flexibility and low processing efficiency in current multi-source data fusion analysis process, a multi-source data parallel preprocessing method based on similar connection was proposed, in which the idea of dividing and conquering and paralleling was adopted. Firstly, the preprocessing method was improved to increase the flexibility by unifying similar semantics in multi-source data and retaining personality semantics. Secondly, an improved parallel MapReduce framework was proposed to improve the efficiency of similar connections. The experimental results show that the proposed method reduces total data volume by 32% while ensuring data integrity. Compared with traditional MapReduce framework, the improved framework decreases 43.91% of time consumed; therefore, the proposed method can effectively improve the efficiency of multi-source data fusion analysis.

In cognitive radio networks, for the robust joint optimization problem of multiuser admission control and power beamforming, a joint optimization scheme based on smooth approximation of entropy function was proposed. Firstly, the two optimization problems of admission control and transmit power beams were converted into a joint optimization problem by L ₀-norm minimization. Secondly, the method of smoothing approximation based on entropy function was used to optimize the non-convexity and discontinuity of L ₀-norm. Finally, since the objective function was smooth, differentiable and unimodal function, the problem was transformed into the Lagrange function, and Armijo gradient descent method was used to get the optimal solution. The numerical results show that by using the proposed algorithm, the number of admitted uses is not significantly increased when the Signal-to-Interference-plus-Noise Ratio (SINR) is relatively low, but the transmission power consumption is decreased and the number of admitted uses is increased when SINR is relatively high. The uncertain Channel State Information (CSI) of model is analyzed, which can make the network better adapt to the changes of the outside world and improve the reliability of the network. The proposed algorithm can effectively realize the optimal allocation of the network resources and improve the network performance.

Aiming at the resource allocation problem for the uplink in cognitive radio networks, a game-theoretic algorithm for joint power control and rate allocation adapted to multi-cell cognitive radio networks was proposed. To control user's power and rate more reasonably and reduce interference among Secondary Users (SUs), firstly, the different cost factors for power and rate were set respectively, so as to control user more reasonably and avoid user excessively increasing transmission power. Then, the existence and uniqueness of the Nash Equilibrium (NE) for the proposed algorithm were proved, the convergence demonstration of the proposed algorithm was given. Finally, for solving the optimization problem of the transmission power and transmission rate, the iterative updating flowchart of the proposed algorithm for the joint power control and rate allocation was presented. The theoretical analysis and simulation results show that, compared with the similar game algorithms, on the premise of guaranteeing the quality of communication, the proposed algorithm can make user acquire higher transmission rate and higher Signal to Interference plus Noise Ratio (SINR) at lower transmission power, reduce the interference among users, and improve the system capacity of SUs.

Concerning the problem that the Hidden Markov Model (HMM) parameters are difficult to configure, an improved method of situation assessment based on HMM was proposed to reflect the security of the network. The proposed method used the output of intrusion detection system as input, classified the alarm events by Snort manual to get the observation sequence, and established the HMM model, the improved Simulated Annealing (SA) algorithm combined with the Baum_Welch (BW) algorithm to optimize the HMM parameters, and used the method of quantitative analysis to get the security situational value of the network. The experimental results show that the proposed method can improve the accuracy and convergence speed of the model.

To reduce the time complexity of situational element acquisition and cope with the low detection accuracy of small class samples caused by imbalanced class distribution of attack samples in large-scale networks, a situation element extraction mechanism based on deep auto-encoder network was proposed. In this mechanism, the improved deep auto-encoder network was introduced as basic classifier to identify data type. On the one hand, in the training of the auto-encoder network, the training rule based on Cross Entropy (CE) function and Back Propagation (BP) algorithm was adopted to overcome the shortcoming of slow weights updating by the traditional variance cost function. On the other hand, in the stage of fine-tuning and classification of the deep network, an Active Online Sampling (AOS) algorithm was applied in the classifier to select the samples online for updating the network weights, so as to eliminate redundancy of the total samples, balance the amounts of all sample types, improve the classification accuracy of small class samples. Simulation and analysis results show that the proposed scheme has a good accuracy of situation element extraction and small communication overhead of data transmission.

To solve the problem that traditional image classification methods deal with the whole image in a non-hierarchical way, an image classification method based on visual saliency detection was proposed. Firstly, the visual attention model was employed to generate the salient region. Secondly, the texture feature and time signature feature of the image were extracted by Gabor filter and pulse coupled neural network, respectively. Finally, the support vector machine was adopted to accomplish image classification according to the features of the salient region. The experimental results show that the image classification precision rates of the proposed method in SIMPLIcity and Caltech are 94.26% and 95.43%, respectively. Obviously, saliency detection and efficient image feature extraction are significant to image classification.

Since Scale Invariant Local Ternary Pattern (SILTP) background modeling algorithm is of high complexity and slow computing speed, which is not suitable for real-time video processing, a new method named Uniform Scale Invariant Local Ternary Pattern (USILTP) background modeling algorithm was proposed. Firstly, the feature of USILTP was extracted by regulating the frequency of SILTP coding jump in order to reduce the feature dimension of SILTP. Secondly, a USILTP background modeling parallel algorithm based on Intel core graphics (Intel HD) and Open Computing Language technology (OpenCL) was designed and implemented to further accelerate USILTP background modeling algorithm. Finally, the foreground result of USILTP background modeling algorithm was optimized by combing multiple color channel models. The experimental result shows that the proposed algorithm can be applied to process 320×240 resolution video at a rate of 98 frame/s on the Intel HD 4600, which is 4 times faster than that of SILTP background modeling algorithm. In terms of foreground detection, the performance of the proposed algorithm is improved by 2.1% compared with SILTP background modeling algorithm on the public dataset.

Since the evaluation of Distributed Denial of Service (DDoS) is inaccurate and network security situational evaluation is not comprehensive, a new network security situational awareness model based on information fusion was proposed. Firstly, to improve the accuracy of evaluation, a situation assessment method of DDoS attack based on the information of data packet was proposed; Secondly, the original Common Vulnerability Scoring System (CVSS) was improved and the leak vulnerability was evaluated to make the assessment more comprehensive; Then, according to the combination of objective weight and subjective weight, the method of calculating the combined weights and optimizing the results by Sequence Quadratic Program (SQP) algorithm was raised to reduce the uncertainty of fusion; Finally, the network security situation was got by fusing three aspects evaluation. To verify the original evaluation of DDoS was inaccurate, a testing platform was built and the alarm of the same DDoS differed by 3 orders of magnitude. Compared to the original method based on alarm, the steady and accurate result of evaluation was obtained based on data packet. The experimental results show that the proposed method can improve the accuracy of evaluation results.

For stream cipher to implement effective fast discrete Fourier spectra attack, it is necessary to find a low spectral weight relation or a low spectral weight annihilator. By using discrete Fourier transform of periodic sequences, a necessary and sufficient condition of the sequences which meet product relation was achieved. And on this basis, by defining spectral cycle difference, a kind of low spectral weight relation and annihilator was derived. At the same time, the spectral properties of m sequences was researched, a method to calculate the spectral space quickly was proposed and an example was given.

To minimize damage from network security problem, an improved network security situation assessment model based on Fuzzy Analytic Hierarchy Process (FAHP) was proposed. First, a set of index system in conformity with actual environment which consists of index layer, criterion layer and decision layer was established in consideration of the large-scale network environment in the future. Aiming at the influence on evaluation by data distribution uncertainty and fuzziness in situation assessment, the proposed model used Fuzzy C-Means (FCM) clustering algorithm and the best clustering criterion for data preprocessing to get the optimal cluster number and cluster center. Finally, multi-factor secondary assessment model was established for situation assessment vector. The simulation results show that, compared with the present situation assessment method based on FAHP, the improved method takes the factors which have small weights into consideration better, so the standard deviation is smaller and evaluation results are more objective and accurate.

Classical regression algorithms for data set analysis of multiple models have the defects of long calculating time and low detecting accuracy of models. Therefore, a heuristic robust regression analysis method was proposed. This method mimicked the clustering principle of immune system. The B cell network was taken as classifier of data set and memory of model set. Conformity between data and model was used as the classification criteria, which improved the accuracy of the data classification. The extraction process of model set was divided into a parallel iterative trial including clustering, regressing and clustering again, by which the solution of model set was gradually approximated to. The simulation results show that the proposed algorithm needs obviously less calculating time and it has higher detecting accuracy of models than classical ones. According to the results of the eight-model data set analysis in this paper, among the classical algorithms, the best algorithm is the successive extraction algorithm based on Random Sample Consensus (RANSAC). Its mean model detecting accuracy is 90.37% and the calculating time is 53.3947s. The detecting accuracy of those classical algorithms which calculating time is below 0.5s is bellow 1%. By the contrary, the proposed algorithm needs only 0.5094s and its detecting accuracy is 98.25%.

Concerning the lackness of effective means in the feature evaluation of Advanced Radar Emitter Signals (ARES), and the excessive dependence on expert experience in Analytic Hierarchy Process (AHP), a new feature evaluation model of ARES named SPA-FAHP was proposed based on Set Pair Analysis (SPA) and Fuzzy Analytic Hierarchy Process (FAHP). In order to solve the uncertainty or fuzzy judgement of the judge people when they evaluate the large-capacity data of radar emitter signals, the traditional AHP was improved through the introduction of triangular fuzzy numbers, and the index weights of ARES feature evaluation system were analyzed by FAHP. Then, the expert decision matrix of traditional AHP was made improvement and identical degree analysis through the introduction of SPA theory to solve the problem that the decisions of AHP rely on experience of experts too much. Finally, ARES features were made comprehensive evaluation through the combination of index weights matrix and identical degree matrix of the decision. The calculation results show that the model is effective and feasible. It can achieve the characteristic analysis and evaluation of ARES features more objectively.

To solve the issue that, in wireless resource competition, the environment information which gamers get in power game is asymmetric, a power game mechanism based on hidden Markov prediction was proposed. By establishing a Hidden Markov Prediction Model (HMPM), the proposed mechanism estimated whether competitors would take part in the game to improve the information accuracy of the game. Then, the predicted information was used to calculate the best transmission power via the cost function. The simulation results show that, compared with MAP (Maximum A Posteriori) method and NP (No Predicting) method, the power game model based on hidden Markov prediction can not only meet the target capacity, but also improve the power efficiency of the unauthorized users.

Most of the variants of Graph Cut algorithm do not impose any shape constraints on the segmentations, rendering it difficult to obtain semantic valid segmentation results. As for pedestrian segmentation, this difficulty leads to the non-human shape of the segmented object. An improved Graph Cut algorithm combining shape priors and discriminatively learned appearance model was proposed in this paper to segment pedestrians in static images. In this approach, a large number of real pedestrian silhouettes were used to encode the a'priori shape of pedestrians, and a hierarchical model of pedestrian template was built to reduce the matching time, which would hopefully bias the segmentation results to be humanlike. A discriminative appearance model of the pedestrian was also proposed in this paper to better distinguish persons from the background. The experimental results verify the improved performance of this approach.

Concerning the shopping information Web page constructed by template, and the large number of Web information and complex Web structure, this paper studied how to extract the shopping information from the Web page template by not using the complex learning rule. The paper defined the Web page template and the extraction template of Web page and designed template language that was used to construct the template. This paper also gave a model of extraction based on template. The experimental results show that the recall rate of the proposed method is 12% higher than the Extraction problem Algorithm (EXALG) by testing the standard 450 Web pages; the results also show that the recall rate of this method is 7.4% higher than Visual information and Tag structure based wrapper generator (ViNTs) method and 0.2% higher than Augmenting automatic information extraction with visual perceptions (ViPER) method and the accuracy rate of this method is 5.2% higher than ViNTs method and 0.2% higher than ViPER method by testing the standard 250 Web pages. The recall rate and the accuracy rate of the extraction method based on the rapid construction template are improved a lot which makes the accuracy of the Web page analysis and the recall rate of the information in the shopping information retrieval and the shopping comparison system improve a lot .

Based on the theory of Restless Multi-Armed Bandit (RMAB) model, a novel mechanism of dynamic spectrum access was proposed for the problem that how to coordinate multiple user access multiple idle channels. Firstly, concerning the channel sensing error of the cognitive user being existed in the practical network, the Whittle index policy which can deal with sensing error effectively was derived. In this policy, the users achieved one belief value for every channel based on the historical experience accumulation and chose the channel, which was needed to sense and access, by considering the immediate and future rewards based on the belief values. Secondly, this paper used the multi-bid auction algorithm to deal with the collision among secondary users when they selected the channels to improve the spectrum utilization. The simulation results demonstrate that, in the same environment, the cognitive users with the proposed mechanism have higher throughtput than the mechanism without dealing with sensing error or without multi-bid.

To solve the problem of transmission in wireless networks, a transmission and scheduling scheme based on W-learning algorithm in wireless networks was proposed in this paper. Building the system model based on Markov Decision Progress (MDP), with the help of W-learning algorithm, the goal of using this scheme was to transmit intelligently, namely, the package loss under the premise of energy saving by choosing which one to transmit and the transmit mode legitimately was reduced. The curse of dimensionality was overcome by state aggregate method, and the number of actions was reduced by action set reduction scheme. The storage space compression ratio of successive approximation was 41%; the storage space compression ratio of W-learning algorithm was 43%. Finally, the simulation results were given to evaluate the performances of the scheme, which showed that the proposed scheme can transport data as much as possible on the basis of energy saving, the state aggregation method and the action set reduction scheme can simplify the calculation with little influence on the performance of algorithms.

Cognitive network can improve the end-to-end performance of the network, and ensure QoS(Quality of Service) requirements. The existing routing algorithm does not have cognitive ability. To solve this problem, a multi-path routing algorithm of cognitiveload balancing was proposed, which combined the advantages of Q-learning algorithm and ant algorithm, to establish and maintain the route through ant algorithm, and to achieve congestion avoidance and load balancing by Q-learning algorithm. The simulation contrast with OPNET shows that the algorithm is valid and effective at controlling packet loss ratio, delay and bandwidth utilization.

Concerning the linear collusion attack problem in Combined Public Key (CPK) cryptosystem, on the basis of the nature of the linear collusion attack and according to the principle of key generation, a new equation set was constructed. Through the linear transformation to the coefficient matrix of the equation set, the rank of the equations can be solved, and it is less than the number of seeds of private key seed matrix. At the same time, the analysis of the private key's structure shows that the rank of the augmented matrix is not equal to the rank of coefficient matrix. Thus both sides above prove that the attacker never get the unique solution to the private key seed matrix even if he get all the private keys. Therefore, it demonstrates that there does not exist the threat of linear collusion attack in the CPK cryptosystem.

This survey summarized the studies on text sentiment analysis in the view of granularity from the following five aspects: sentiment word extraction, sentiment corpus and dictionary construction, entity and opinion holders analysis,document level sentiment analysis, and text sentiment analysis applications. It pointed out that the current sentiment analysis system cannot gain high precision. Further research should focus on: widely and appropriately applying study achievement of natural language processing to text sentiment analysis; finding and choosing suitable features and algorithms in text sentiment classifications; utilizing the existing language tools and relevant resources in fast building standard language tools and resources and applying them.