International Journal of Information and Communication Technology (79 papers in press)
Stargan Based Camera Style Transfer for Person Retrieval
by Yuanyuan Wang, Zhijian Wang, Mingxin Jiang
Abstract: Person retrieval is also known as person re-identification (ReID) aiming to match person among cross cameras. Although the results of the person ReID have performed well in small datasets, the issues of the large number of identities in real scenarios or with more cameras have not been fully investigated. Being an image retrieval task under cross multi-cameras of intelligent video security, person ReID is influenced by the image style change caused by different camera illumination and view angles. The number of cameras in the latest datasets is increasing and more camera transfer models need to be trained. Traditional methods of generative adversarial network (GAN) can only handle transfer of two domains. To facilitate the research towards solving these problems, we use star generative adversarial networks (StarGAN) to transfer the image from one camera to another camera in the latest large benchmark datasets. We train multiple transfer models simultaneously, minimizing the bias among different cameras. Label smooth regularization (LSR) algorithm is utilized to mitigate the effects of noise in the model. We learn part-based descriptors from pedestrian samples to generate robust feature representation. Our work is competitive compared to the state-of-the-art.
Keywords: StarGAN; Person retrieval; LSR.
Fuzzy judgment of edge features under dynamic constraints in pedestrian tracking
by Yaomin Hu
Abstract: Pedestrian tracking and recognition is influenced by the pedestrian environment and edge factors of dynamic features, which is easy to tracking errors, so in order to improve the pedestrian tracking and recognition ability, it is required to conduct fuzzy judgment to edge features. Therefore, a fuzzy judgment method of edge features under dynamic constraints in pedestrian tracking based on local motion planning and edge contour segmentation was proposed. In this method, a geometry mesh area model for pedestrian tracking and recognition was constructed, and the fuzzy dynamic feature segmentation method was adopted to reconstruct dynamic edge feature points in pedestrian tracking to extract the greyscale pixel set under dynamic constraints in pedestrian tracking; edge feature quantity was fused based on the distribution intensity of greyscale pixels to realise pedestrian tracking image fusion and information enhancement processing; the three-dimensional dynamic constraint method was adopted for local motion planning of pedestrian tracking, and then fuzzy judgment was carried out to edge features in pedestrian tracking based on the edge contour segmentation results. The simulation results show that in pedestrian tracking and recognition, this method has strong fuzzy judgment ability of edge features and can provide results with error below 10 mm and relatively stable fluctuation, so this method can provide relatively high recognition accuracy and good robustness.
Keywords: pedestrian tracking; dynamic constraint; edge feature; recognition; image fusion.
Design of Cloud Computing-based Foreign Language Teaching Management System Based on Parallel Computing
by Kanmanli Maimaiti
Abstract: In view of the long response time of the traditional foreign language teaching management system and the inability to guide students to improve their learning interest, a foreign language teaching management system based on parallel computing is proposed. In this method, the cloud architecture of the foreign language teaching system is given under the cloud computing environment, on which the parallel computing method is adopted to design the foreign language teaching management system hardware, which is scalable and flexible. The parallel algorithm is designed and the communication between the modules of the system is implemented with C# language. The experimental results show that response time for each of the four scores of Zhang is 1s in reference , the response time for each of them is only 0.6s in this paper. The system can shorten the response time for query and improve the development speed of web-based foreign language teaching, effectively promotes the development of web-based foreign language teaching and students interests in foreign language learning.
Keywords: parallel computing; cloud environment; foreign language teaching; management system.
Study on the Subway Transfer Recognition during Rush Hour Based on Big Data
by Shushen YAO, Xiaoxiong WENG
Abstract: With the development of the subway network, multipath coexistence becomes very common in big cities. Its followed that the tickets clearing problem is highly concerned by co-investors, which relies on accurate transfer paths identification. Different from the commonly used Logit models for subway transfer recognition problem, we adopted the Adaptive Gauss Cloud Transformation (A-GCT) model, which transformed the distribution of passengers trip time into multiple concepts of different granularity, and evaluated the maturity of the concept by the of parameter named Confusion Degree (CD). The case in this paper shows that, the A-GCT model has higher accuracy in dealing with uncertain problem such as subway transfer recognition.
Keywords: Gaussian Cloud Transformation(GTC); subway transfer recognition; big data.
Intelligent Monitoring System for Thermal Energy Consumption of Buildings under the IoT Technology
by Lu Wang, Difei Jiang
Abstract: In view of the poor accuracy of single value of heat energy consumption and the weak real-time monitoring of energy consumption in buildings, an intelligent monitoring system for thermal energy consumption of buildings under the Internet of Things (IoT) technology is designed. The overall structure of the intelligent monitoring system for thermal energy consumption of buildings is constructed. The DSP integrated signal processor is used for data acquisition and real-time information processing of thermal energy of buildings. A wireless intelligent gateway for building thermal energy consumption monitoring is designed by using Internet of things technology, a wireless sensor network model is constructed. The VME bus is used as information transmission channel to realize intelligent monitoring for thermal energy consumption. The test results show that the real-time monitoring accuracy of the system is better than that of the traditional method, and it has a good application prospect in all aspects.
Keywords: Internet of Things (IoT) technology; thermal energy of buildings; energy consumption monitoring; system design.
An Algorithm of Decomposition and Combinatorial Optimization Based on 3-Otsu
by Liejun Wang, Junhui Wu, Ji-Wei Qin
Abstract: Recently, the 3-Otsu(three-dimensional maximum between-class variance algorithm) have drawn great attention in image segmentation. However the time consumption and calculation amount of 3-Otsu is large, so this paper provide a compositing 3-Otsu decomposed algorithm. Firstly, the histogram of 3-Otsu is resolved into three two-dimensional histogram by projecting, and the projection plane is three coordinate plane of its own space. Secondly, the two-dimensional histogram formed after segmented by using 2-Otsu, then three segmentation results are obtained. Finally, three segmentation results are combined in linear manner, and combination result is the output of segmentation result, under the ideal noise-free, gaussian noise, salt noise, pepper noise and salt and pepper mixture noise, respectively. The results show that the proposed algorithm is nearly 30 times smaller in time consumption than 3-Otsu, although slightly more than 2-otsu,its value is still small. Meanwhile the anti-noise performance, especially for mixed noise, is better than two other algorithms.
Keywords: three-dimensional Otsu; decomposition and reduction; linear combination.
Video Encryption Based on Chaotic Array System: Working with Image Directly
by Hongyan Zang, Jing Yang, Guodong Li
Abstract: A new three-dimensional discrete chaotic system is proposed according to the Marotto theorem in this paper. On this basis, a coupled array chaotic system is given as the drive system. Moreover, with the help of the bidirectional generalized synchronization theorem, the response system is constructed and proved to be chaotic. According to the chaotic matrix generated by the above systems, a special video encryption scheme was proposed. While the experiment shows that the encryption scheme occupies a large key space and enjoys an approximately uniform distribution of the ciphertext entropy already, the main contribution of the new constructed system is the higher speed than the vector system since once the encryption starts, the chaotic matrix generated by the array systems and the image with the same size to the matrix can be operated directly.
Keywords: generalized synchronization; video encryption; coupled array chaotic system; computing simulation.
User Information Intrusion Prediction Method Based on Empirical Mode Decomposition and Spectrum Feature Detection
by Zheng Ma, Yan Ma, Xiaohong Huang, Manjun Zhang, Bo Su
Abstract: In distributed intelligent computing environment, user information is vulnerable to plaintext intrusion, resulting in information leakage. In order to ensure the security of user information, a user information intrusion prediction method based on empirical mode decomposition and spectrum feature detection in distributed intelligent computing is proposed in this paper. Firstly, a model of user information and intrusion signal in distributed intelligent computing is established; then an intrusion detection model is established with signal processing method; finally, time-frequency analysis and feature decomposition are conducted for intrusion information in distributed intelligent computing with empirical mode decomposition method, and accurate prediction of user intrusion information is achieved based on joint probability density distribution of spectrum feature, so as to improve the algorithm design. The simulation results show that when the signal to noise ratio is 12.4dB, the detection probability of the method proposed in this paper is 1, and then the false alarm probability can be 0, which indicates that this method can provide good intrusion detection probability and low false alarm probability even at relatively low signal to noise ratio. Therefore, the method proposed in this paper has good intrusion interception and prediction ability.
Keywords: distributed intelligent computing; user information; intrusion prediction; feature extraction; empirical mode decomposition.
Deep Forest-based Hypertension and OSAHS Patient Screening Model
by Pingping Wang, Lei Ma, Yun-Hui Lv, Yang Xiang, Dang-guo Shao, Xin Xiong
Abstract: Incidence of OSAHS is high in hypertension patients. To make the OSAHS diagnosis more precise and simple, an OSAHS screening model is built hereof by deep forest algorithm with the collected information of hypertension and OSHAS patients from the Sleep and Respiration Center of a hospital. Firstly, variation in index and dimensions and inter-class imbalance in sample dataset is resolved by normalization and SMOTE method; and OSAHS screening model is built by deep forest method (gcForest) after redundant information in features is removed with modified chi-square test single feature selection. The results show that with modified chi-square test single feature selection method, the redundant features can be effectively removed and performance of classifier can be improved; Deep forest-based OSAHS screening model is superior to other classification models in classification performance and can effectively improve the precision of OSAHS patient screening, reduce the incidence of OSAHS missed diagnosis.
Keywords: Hypertension; OSAHS; Unbalanced data; Feature selection; Deep forest; Screening model.
Design of Automatic Detection System for Vehicle networking Communication Abnormal Data based on CAN Bus
by Qun Le, Kun Jiang, Feng Zhang
Abstract: Aiming at the problems of low detection rate and accuracy rate, high false detection rate and missed detection rate caused by the proportion of abnormal data in the current design system when detecting abnormal data in the process of vehicle networking communication, an automatic detection system of abnormal data in vehicle networking communication based on CAN bus is proposed and designed. The system mainly includes two parts: vehicle networking communication subsystem and vehicle networking communication data anomaly detection subsystem. The vehicle networking communication subsystem includes vehicle networking communication data acquisition unit and C/S structure. The real-time interaction process between client and server is given. The experimental results and discussions prove that the design system can automatically detect abnormal data in vehicle networking communication, and it is less affected by the proportion of abnormal data, which has the advantages of higher detection rate and accuracy, lower false detection rate and missed detection rate. At the same time, the preliminary conclusion is drawn that the sampling ratio will hardly affect the detection results.
Keywords: CAN Bus; Vehicle networking; Communication; Abnormal Data; Automatic Detection; System Design;rnrn.
Slices Reconstructing Algorithm for Single Image Dedusting
by Haiyan Zhang, Shangbing Gao, Mingxin Jiang
Abstract: For solving the image degradation in the non-uniform dusting environment with multiple scattering lights, the slices reconstructing algorithm for single image was proposed for dust elimination in the paper. Firstly, the slices along the depth orientation were produced based on McCartney model in dust environment. Secondly, the union algorithm of dust detection was used to detect dust patches in the slices where non-dust areas were reserved while the dust zones were marked as the candidate detecting areas of the next slice image. Then, the image was reconstructed by combining these non-dust areas of each slice and the dust zone of the last slice. Finally, the faster guided filter was applied to the reconstructed area. The experimental results had proved that the reconstruction algorithm could get rid of dust in object image not only effectively but also fast. The papers work had laid the foundation for object detection and recognition work had based on computer vision in dusts environment.
Keywords: Image Restoration; Dust Detection; Image Reconstruction; Multiple Scattering; Single Image.
A Magnetic Resonance Imaging Denoising Technique Using Non-Local Means and Unsupervised Learning
by Tao Wu, Lei Xie
Abstract: We propose a new non-local mean (NLM) algorithm using unsupervised learning and k-means clustering for denoising magnetic resonance (MR) images. Our technique improves image pro-cessing speeds with enhanced denoising performance on multiple types of images. The calculation of similarity weights at the cluster level improves computational efficiency. We conducted experiments with brain MR images of various sizes, including three T1- and T2-weighted images. Three quality metrics show that our algorithm achieves moderate improvements in denoising accuracy with significant reductions in execution time. The proposed method processed the sample data in one-fifth of the time of the original NLM method. Compared to several state-of-the-art methods, our method offers improved peak signal-to-noise ratios (PSNRs) for samples with large amounts of noise.
Keywords: Magnetic resonance imaging; Image denoising; Non-local mean; k-means; Unsupervised Learning.
Research on Equilibrium scheduling of Airborne Network Resource based on Load Gini Coefficient
by Jin Guo, Shengbing Zhang
Abstract: Aiming at the problems of long running time and serious data loss in traditional equilibrium scheduling method for airborne network resource, a new equilibrium scheduling method for airborne network resource based on load Gini coefficient is proposed. According to the related principle of Gini coefficient of income distribution in the field of economics, the Gini coefficient of network load distribution is monitored. Through genetic algorithm, an optimal allocation scheme which can satisfy the load change constraints and effectively avoid dynamic migration is found. The experimental results show that the data loss rate of this method is between 0 and 2, and the average running time is 6 milliseconds and 12.5 milliseconds shorter than that of the other two methods, which can effectively reduce the data loss rate and running time of the system, and improve the overall efficiency of the system.
Keywords: load Gini coefficient; airborne network resources; equilibrium scheduling.
Fault Diagnosis of Fan Gearboxes Based on EEMD Energy Entropy and SOM Neural Networks
by Biao Ma, Gang Li, Guping ZHENG
Abstract: Aiming at the difficulty of feature extraction for gear fault diagnosis and the problem of traditional classification methods cannot diagnose the faults in wind turbine Gearboxes adaptively, a new fault diagnosis method based on Ensemble Empirical Mode Decomposition (EEMD) energy entropy and SOM Neural Networks (SOM-NN) is proposed. Firstly, the EEMD method is used to decompose the original vibration signal of the gear under all kinds of condition into several Intrinsic Mode Functions (IMF) and calculate the energy value of each IMF and the energy entropy of the signal. Then the IMF energy proportion and the signal energy entropy are selected to form a set of features which can reflect the fault vibration signal. The values of these features are inputted to SOM neural network for classification. The numerical simulation results show that the accuracy of the method is 100% in the fault diagnosis of wind turbine gearbox.
Keywords: ensemble empirical mode decomposition; energy entropy; self-organizing feature mapping (SOM); wind turbine; Gearboxes; fault diagnosis.
Design of Art Interactive Teaching System Based on Multiple Intelligence Theory
by Junliang Dong, Zhuomin Huang
Abstract: It is of great practical significance to study the interactive teaching system of art. The traditional art teaching system is used to analyze the information interaction model, which leads to the poor interaction performance of the system. Therefore, an art interactive teaching system based on multiple intelligence theory was proposed in this paper. The art interactive teaching system mainly consists of interactive teaching service information transmitter, student mark database and web page layering server. Based on hardware design, the entire art interactive teaching system was designed through the information interaction algorithm based on multiple intelligence theory. In order to verify the effectiveness of the designed system, a simulation experiment is performed, the results show that the system has high output signal-to-noise ratio (SNR) and the interaction efficiency is over 80%, which demonstrated the good information interaction performance and excellent application prospects of the system. The system has good application prospects.
Keywords: Multiple intelligence theory; art teaching; information interaction; teaching system.
Clustering based Word Segmentation from Off-line Handwritten Uyghur Text-line Images
by Askar Hamdulla, Aysadet Abliz, Abdusalam Dawut, Kamil Moydin, Palidan Tuerxun
Abstract: For the word segmentation of handwritten Uyghur text images, this paper proposes a segmentation method based on clustering algorithm. In this paper, firstly, the preprocessed text line images are projected to the vertical direction, which can get the initial probable segmentation points and record the blank spaces and text length between connected domains. By using clustering algorithm, the blank spaces are classified into two categories: within word gap and between words gap. Then the first mergence is completed according to the clustering results. For the existed phenomenon of over segmentation, one merging method based on threshold is proposed through the combination of text region length and blank space length so that the final segmentation points are obtained. And the experimental results show that this method can effectively solve the word segmentation problem in the handwritten text images.
Keywords: Uyghur handwritten text; Word segmentation; Clustering; Coloring process.
The Image Classification Algorithm Research using Class Information Loss and Joint Structural Similarity
by Shian Wang
Abstract: Aiming at the supervised training of Convolutional Neural Networks, the weighted joint structural similarity and class information supervised training method has been proposed. Firstly, for a small image, the Convolutional Neural Networks that can extract high-level information of images is designed. Secondly, a weighted joint structural similarity and class information loss function training convolutional neural network are established. Finally, handwritten numbers and Cifar10 images are obtained by Mnist dataset. The image classification experiments can validate the effectiveness of the proposed network. The experimental results can show that the image classification error rate of improved network on Mnist handwritten digits and Cifar10 dataset is 0.23% and 10% respectively. Under the premise that there is no dataset increase on the Mnist dataset, the performance of proposed network exceeds the performance. The performance of all single networks on the dataset, on the Cifar10 dataset, the proposed network can achieve higher image classification accuracy with less computational effort. At the same time, the supervision of joint structural similarity and class information loss can speed up the training process of proposed network.
Keywords: Convolutional Neural Network; Image Classification; Structure Similarity; Deep Learning; Metric Learning.
Color Image Encryption Algorithm Based on Hyperchaos and DNA Sequences
by Ji-xian Cui, Guodong Li, Le-le Wang, Cong Ma
Abstract: In order to overcome the shortcomings of the single chaotic encryption and the problems of simple structure and low security, the hyperchaotic color image encryption algorithm based on DNA sequences is proposed. Firstly, the color images are layered and encoded by DNA, then, the hyper-chaotic sequence is used to scramble the DNA matrix, the hyper-chaos is used to generate natural DNA matrix and DNA addition operations is dynamically selected to perform the DNA rule operations, Finally, the cipher-text image is obtained. The performance test of the ciphertext image shows that the gray sca le distribution of the histogram is relatively uniform; the test values of the related index parameters NPCR and UACI are 99.65% and 33.51%, respectively, which are close to the theoretical value. Through simulation experiments, The algorithm can effectively improve various anti-attack capabilities of the encryption system and has high security.
Keywords: Image encryption; Hyperchaotic Lorenz systems; DNA coding; Chaotic encryption.
Research on Image Denoising Algorithm Based on Non-local Block Matching
by Ying Yang, Dongrui LI, Xiaofeng Huang
Abstract: In order to study how to better suppress image noise, improve image resolution, and enhance the visual effect of images, three-dimensional joint filtering - block matching (BM3D) algorithm is used to explore image denoising and image detail retention, and in image denoising, sparse expression and low rank recovery theory are introduced. The results show that BM3D algorithm has a good effect in removing Gaussian white noise, but it is lacking in suppressing impulse noise and mixed noise. The non-local BM3D algorithm is superior to sparse expression and low rank recovery in removing Gaussian white noise, but sparse expression and low rank recovery has a good effect in removing impulse noise.
Keywords: non-local block matching; image denoising; BM3D; sparse expression; low rank recovery.
Optimization of Surrounding Layout of Enterprise Building using an Improved Genetic Algorithm
by Lin Cheng
Abstract: In order to achieve the optimal design of environment and overall layout of enterprise building, the improved genetic algorithm is applied in it. Firstly, the relationship between the environment and layout of enterprise building. Secondly, the optimal model of environment and overall layout of enterprise building is constructed, and the objective function and boundary conditions are confirmed. Thirdly, the procedure of improved genetic algorithm is designed, and the mathematical models of cross operation and niche computation are established. Finally, the simulation analysis of environment and overall layout of enterprise building is carried out, and simulation results show that the improved genetic algorithm can obtain the better environment and overall plan of enterprise building.
Keywords: Optimization; Environment; Overall layout; enterprise building; Improved genetic algorithm.
Research on Fault Diagnosis Technology based on FD-GT method
by Weijie Kang, Jiyang Xiao, Mingqing Xiao, Xilang Tang, Bin Hu
Abstract: Fault diagnosis can be divided into two main tasks: fault feature extraction and fault data classification. Firstly, aiming at the problem that the fault feature extraction method is not significant, this paper proposes a fault feature extraction method based on fuzzy distance. The concept of feature separation is proposed. The initial fuzzy distance calculation method is established by expert knowledge. The key parameters of fuzzy distance are optimized based on DE algorithm combined with historical test data. This method can effectively distinguish fault data from normal data and achieve more significant fault characteristics extract. Secondly, aiming at the problem of low accuracy when classifying fault data, this paper proposes a fault data classification method based on grey target decision. The concept of fault type grey scale is proposed, and the grey number decay matrix is updated with the current test data. The fault data classification is realized by calculating the target distance of each fault type with the current input signal set. The method can effectively improve the accuracy of fault data classification and has a certain time cost advantage. Finally, the FD-GT method is verified by an example. The results show that it can effectively improve the saliency of fault feature extraction and the accuracy of fault type classification, thus achieving more efficient and reliable fault diagnosis.
Keywords: Fuzzy Reasoning; Grey Target Decision; Fault Diagnosis; Differential Evolution Algorithm; Grey Number.
Research on highway vehicle detection algorithm based on video image
by Yucai Zhou, Zhimin Lv, Yuelin Li, Jiangchun Mo
Abstract: In order to solve problem that vehicle detection rate can affected in complex scenarios, authors put forward the adaptive method based on GMM which sets up and updates the background, and use the average neighborhood based on HSV fast shadow elimination algorithm which improves the speed of shadow elimination. For occluded vehicles, authors use the recognition algorithm based on Kalman Filter which blocks vehicle identification, then authors adopts pyramid hierarchical search algorithm based on the template matching which segments the occluded vehicles. The experimental results show that the algorithm is simple and effective, and the detection rate of vehicle is 97%, which meets the requirements of vehicle detection completely.
Keywords: vehicle occlusion; GMM; shadow removal; The Kalman Filter; vehicle detection.
Traffic incident detection based on the width characteristic of the moving object marker
by Shangbing Gao
Abstract: Aiming at the current situation that the existing traffic event detection algorithm is complex and cumbersome, a traffic incident detection method based on the width characteristics of the moving object was proposed. Firstly, the foreground object is extracted by ViBe (visual background extractor), and the foreground target is subjected to hole removal and smoothing processing. Then, the moving target is marked with a label, the width change characteristic of the moving target mark frame is analyzed, and the traffic event detection model is introduced, thereby achieving detection of traffic events. The experimental results show that the method can effectively detect the rear-end event, the crossing event and the collision-fixing event in the traffic incident.
Keywords: ViBe (visual background extractor); Classification of vehicle types; Traffic incident detection; Image preprocessing.
Design of orthogonal phase encoding for basis function based on genetic algorithm
by Kui Li, Ting Zhang, Hao Guo, Hua Wang
Abstract: A new basis function generation algorithm based on genetic algorithm is proposed to overcome the drawbacks of the traditional basis function phase encoding algorithm in transform domain communication system (TDCS). Firstly, by analyzing the requirements and the characteristics of the basis function in TDCS, the evaluation criterion of the basis function is presented, and the corresponding genetic algorithm is designed according to the criterion. Then, the algorithm is used to generate the orthogonal basis function set. The proposed algorithm not only improves the correlation performance and randomness of the basis function, but also improves the system multiple access performance and security. Furthermore, the length and quantity of the basis functions can be flexibly selected and the systems applicability is improved. By analyzing the simulation results, the feasibility and validity of the algorithm are verified.
Keywords: Basis Function; Phase Encoding; Genetic Algorithm; Multiple Access.
A Method of Character Verification Code Recognition in Network based on Artificial Intelligence Technology
by Yongzhuo Wu
Abstract: In order to solve the problem of low recognition rate of network character captcha, a method of network character captcha recognition based on artificial intelligence is proposed. Firstly, the image preprocessing of character verification code is carried out. The weighted average method and the iterative optimal threshold method were used to process and binarize the character verification code image, and the denoised character image was obtained. For the character verification code image after binarization, Laplace operator is used to segment the image, and the characters in the image are divided into blocks. Finally, according to the feature vector, the artificial neural network model is used for sample training and adaptive learning. Simulation results show that this method has higher recognition rate, better adaptability and robustness than the existing methods. This method can effectively recognize character verification codes.
Keywords: Artificial intelligence; Network; Character type; Verification code; Recognition.
The Adaptive Key Frames Extraction Method Based on Representativeness and Independence Features
by Wenbin Xie, Zhen Zhang, Yuefei Wang, Yuanyuan Zhang, Liucun Zhu
Abstract: For the existing traditional method to extract key frames from the video sequence with gradual change of content, there are problems of having too much redundancy or too much loss in the extraction results and other issues, a new key frames extracting method for adaptively extracting the video key frames has proposed in the paper. The experimental results have shown that the proposed method can effectively extract video key frames, especially for the video with gradual change of content, which can express more succinctly and comprehensively. The experiments on a large number of videos containing various scenes have shown that the key frames extracted by the proposed algorithm can more fully express the main content of video. When dealing with content gradient video, the effect is better. The content adaptively determines the number of key frames based on video.
Keywords: Representativeness; Independence; Adaptive Key Frame; Video Sequence.
Radar Signal Sorting Method Based on Support Vector Clustering and Gray Relational Grade
by Shiqiang Wang, Caiyun Gao, Yanlong Zhang, Qin Zhang, Huiyong Zeng, Juan Bai
Abstract: Aiming at the issue of complicated feature distribution and undistinguishable boundary between clusters of radar signals, a support vector clustering (SVC) algorithm based on grey correlation degree (GCD) is proposed. In the algorithm, the SVC sorting model is constructed to obtain the cluster division firstly. Secondly, grey correlation degree is designed to measure the similarity between clusters, and to verify the clustering validity. Finally, the clustering parameters are adjusted adaptively to achieve the best clusters division. In this paper, clustering validity sorting experiments of interleaved pulse streams is implemented. The results show that this method can obtain better clustering results.
Keywords: Radar Signal Sorting; Support Vector Clustering; Gray Relational Analysis; Grey Correlation Degree; Verification; Cluster Validity Index.
Ontology Expansion Based on UWN Reusability
by Hankiz Yilahun, Sayyare Imam, Askar Hamdulla
Abstract: In the present era of Big Data the demand for developing efficient knowledge representation techniques for different applications is expanding steadily. Knowledge representation is largely based on ontology in the Semantic Web. However, one of the major difficulties to construct a new ontology require users the high cost and long time. Collecting complete knowledge about the domain of opening is time consuming and cannot guarantee expected results too. Therefore, reuse of existing resources can offer a cost and time benefit than building a new one from scratch. Hence, an approach is proposed to reuse the existing ontologies available on the web or online libraries then enrich it. This paper proposed Uyghur domain ontology constructing method based on UWN reusability, which can extract domain ontology factors from UWN and get the initial ontology in which the concepts and relations are already relative standard, then expand it automatically via word2vec models, at last construct the final higher quality version after revising and improving. The method is simple, but effective on ontology enrichment. After evaluating the accuracy, the experimental results show that our method is feasible and effective.
Keywords: Uyghur WordNet; Domain Ontology; Reusability; Word2vec; Expand ontology.
Study on Optimal Urban Land Classification Method Based on Remote Sensing Images
by Lede Niu, Liran Xiong
Abstract: Traditional urban land classification methods are relatively complicated in information collection, resulting in large time consumption and low classification accuracy. Therefore, an optimal urban land classification method based on remote sensing images is proposed in this paper. In this paper, four influencing factors of urban land classification are clarified based on the actual situation, on which the information about urban land in urban areas is extracted through the NDBI index method, and the ETM remote sensing image information of urban land is obtained. The genetic algorithm based on K-Means mutation operator is adopted to classify the ETM remote sensing image information of urban land and finally the optimal classification results of urban land are obtained. In order to test the superiority of the method, a simulation comparison experiment was carried out. The simulation results show that the proposed method can provide overall accuracy of 93.75% and classification accuracy of 96.18% in urban land information collection, has the overall Kappa coefficient of 0.8967 and cost 10 s averagely, indicating that this method is superior in time consumption during urban information collection, collection accuracy and land classification accuracy, so it has high application value.
Keywords: Remote sensing image; urban land; modeling; K-Means method; NDBI index.
Parallel Mining Method for Symbol Application Features of Complex Network Images
by Chiyu Pan
Abstract: Aiming at the problems of poor denoising effect, low recognition rate and longtime of feature mining in current methods, a parallel feature mining method for symbol application features of complex network images based on neural network learning control is proposed. Firstly, the standard deviation of image symbol noise is calculated, and the denoising is carried out by using filtering parameters. The gray value of image and the two-dimensional histogram of image symbol are calculated. The discrete measure matrix between image background and object is defined, and the occurrence probability of image background and object is obtained. On this basis, the two-dimensional maximum inter-class variance method is used to segment image symbols. The wavelet basis function in the neural network is replaced by wavelet basis function. By introducing momentum coefficient and learning efficiency to calculate the parameters of the neural network, and using the improved simulated annealing algorithm to adjust the learning efficiency of the neural network, the parallel mining of symbolic application features of complex network images is finally realized. The experimental results show that the proposed method has good image denoising effect, high image recognition rate and short time for feature mining. The above results verify the comprehensive effectiveness of the proposed method.
Keywords: Complex networks; Image symbols; Application features; Parallel mining;.
Trust circle recommended model based on different fields
by Yun Bai, Wandong Cai
Abstract: A trust-based recommendation system recommends the resources needed for users by system rating data and users trust relationship. In current relevant work, an over-generalized trust relationship is likely to be considered without exploiting the relationship between trust information and interest fields, affecting the precision and reliability of the recommendation. This research, therefore, proposes a users interest-field-based trust circle model. Based on different interest fields, it exploits potential implicit trust relationships in separated layers. Besides, it conducts user rating by combining explicit trust relationships. This model not only considers the matching between trust information and fields, but also explores the implicit trust relationships between users in specific fields, thus it is able to improve the precision and coverage of rating prediction. The experiments made with the Epinions data set proved that the recommendation model based on trust circle exploiting in users interest fields proposed in this research, compared with the traditional recommendation algorithm based on generalized trust relationship, is able to effectively improve the precision and coverage of the recommendation rating prediction. rnrn
Keywords: trust relationship; interest field; recommendation algorithm; trust circle; social network.
Research on Improved modulation Routing and Spectrum Allocation Algorithm in Elastic Optical Networks
by Li Li
Abstract: With the rapid development of services such as mobile Internet, high-definition video, and cloud computing, users' bandwidth requirements are increasing, and the demand for bandwidth granularity is becoming more diverse. In order to solve this problem, the researchers proposed the concept of elastic optical networks. The Elastic optical network adopts the flexible grid transmission mode, which can flexibly allocate spectrum resources while meeting high bandwidth and diversity requirements. Considering the modulation, routing and spectrum allocation (RMSA) of modulation mode selection on different paths is an extremely important problem in elastic optical networks. This paper presents a RMSA algorithm for Elastic Optical Networks with a Tradeoff between consumed resources and interval with boundary (Tradeoff-RnI). For a connection, the amount of resources consumed (R) and the interval between the spectrum blocks and the boundary (I) are indicators that need to be minimized. For these two indicators, the RMSA problem is first modeled as a multi-objective optimization model, and then a linear combination αR+ (1-α) I of R and I is designed. The target RMSA algorithm takes a compromise between R and I. The simulation results show that the Tradeoff-RnI algorithm has a much lower connection request blocking rate than the First-Last Fit algorithm and the Block-Assignment algorithm.
Keywords: Elastic optical network (EON); Routing; Spectrum Allocation; Improved; Tradeoff-RnI Algorithm; Blocking Probability.
An Energy Efficient and Load Balanced Sink Mobility for Wireless Sensor Networks
by Vivekanand Jha, Amar Mohapatra, Nupur Prakash
Abstract: The uniform energy dissipation of sensor nodes is a key objective to optimize network lifetime of Wireless sensor networks (WSNs). In recent studies, a mobile sink implementation has been used instead of static sink and it offers better energy balanced network. This approach used four design constraints of sink mobility in WSN to achieve uniform energy dissipation of nodes in the network. These design constraints are: sink mobility pattern, node deployment technique, scheduling of node activities, and routing of data to the sink. In the literature, the existing approaches have utilized only subset of these design constraints. In our proposed approach all four design constraints have been used in an integrated manner and have been implemented in a three steps solution to achieve the energy load balanced sink mobility in the WSNs. The results have been compared using performance metrics such as coverage density, network lifetime, and energy balancing condition. These metrics are derived and further implemented through simulation. The simulation results confirm that the proposed solution outperforms the existing sink mobility patterns.
Keywords: energy hole; coverage hole; sink mobility; network lifetime; wireless sensor networks; routing; energy efficient.
Research on security monitoring system for wind-solar complementary power generation based on internet of things
by Bin Dai
Abstract: When traditional system is used to monitor wind-solar complementary power generation, there are problems such as large errors in temperature and wind speed acquired and high power consumption of nodes when the sensor transmits signals. Therefore, a security monitoring system for wind-solar complementary power generation based on Internet of Things (IoT) is designed. The system hardware is composed of I/O control panel, sensor, GPRS and data processing board. The system software mainly acquires data and processes the acquisition interrupt program. On this basis, the security monitoring of wind-solar complementary power generation is finally realized. The analysis of simulation experiments shows that compared with the traditional system, the data acquisition error of the proposed system is small, which is in good agreement with the actual value. Moreover, the power consumption of nodes is only 15.8 mw when the sensor transmits the signal, indicating that the system has strong reliability and practical application value.
Keywords: Internet of Things (IoT); wind-solar complementary; sensor; data acquisition; power generation security; monitoring system.
Interrupt Nesting Method Based On Time Slice In Embedded Software
by Yingjie Wang, Kuanjiu Zhou, Jie Pan, Mingchu Li
Abstract: For the limitation of embedded system resources, processing capacity, storage capacity, and executing time are important factors to evaluate an interrupt handler. For an interrupt handler, the more numbers of the interrupt thread rotations, the more times of the increase in record information on the interrupted site, and consumption of additional time and space. When the high-priority interrupt is preempting the low-priority interrupt and the low-priority interrupt deadline is approaching, this paper proposed an interrupt handler with a time slice, which is enabled to complete the executing sections of low priority interrupt within the time period of the time slice. This method could not only reduce the numbers of interrupt threads rotations but also save the space to record the interruption scene for interrupt execution. The experimental part used the two types of interrupt handlers by the ordinary queuing model and inserting time slices consecutively, to simulate two-priority interrupt processing in a system. The comparison of simulation experiments shows that: the interrupt handler with time slices could obviously reduce the rotation number of interrupt handling thread switched, thereby saving the space for the interruption of site preservation and providing a reference for further research on the interruption of embedded systems.
Keywords: Interrupt priority; Interrupt time slice; Queuing model.
Using Priced Timed Automata for the Specification and Verification of CSMA/CA in WSNs
by Zohra Hmidi, Laid Kahloul, Saber Benharzallah
Abstract: Several contention-based MAC protocols for WSNs have been proposed. The control channel is accessed with CSMA/CA (Carrier Sense Multiple Access with Collision Avoidance) method. The complexity of this method and its criticality motivate the formal specification and verification of its basic algorithms. Most existing works do not deal with all possible aspects such as topology, number of nodes, node behavior, and number of possible retransmissions. In this paper, we propose a stochastic generic model for the 802.11 MAC protocol for an arbitrary network topology which is independent of the number of sensors.rnIn addition to the qualitative evaluation that proves the correctness of the model, we will make a quantitative evaluation using the statistical model checking to measure the probabilistic performance of the protocol.
Keywords: WSNs; CSMA/CA; Statistical model checking; Priced timed automata; Formal Modeling; Formal Verification; UPPAAL.
Reduced Complexity Per-Survivor Iterative Timing Recovery using Max-Log-MAP algorithm
by Chuan Hsian Pu, Ezra Morris Abraham Gnanamuthu, Fook Loong Lo
Abstract: In this paper, we propose a reduced-complexity (RC) per-survivor-processing (RC-PSP) iterative timing recovery scheme. The objective is to lessen the computational burden while approaching the optimal system performance of the existing full-complexity (FC) Log-MAP (FC-PSP) iterative recovery scheme. This is achieved by utilizing the Max-Log-MAP framework, which converts the multiplications and additions to maximum operations. According to Spasov, Gushev and Ristov, such framework consumes less power, reduces space on a chip and increases decoding speed. Robertson et al. showed that Max-Log-MAP PSP requires only 5
Keywords: Max-Log-MAP; MAP; maximum-a-posteriori; SNR; TED; timing error detection; turbo-codes; trellis; timing recovery; PSP; per-survivor processing; synchronizations; complexity; BER; bit error rate; timing errors; Mueller and Müller; LDPC; low-density parity-check.
Research on Anomaly Detection Method for Hybrid Big Data Subarea based on Ant Colony Algorithm
by Shu Xu
Abstract: Due to the problems of low accuracy and poor degree of freedom of the existing big data anomaly detection methods, a mixed big data partition anomaly detection method based on ant colony algorithm is proposed. The number of common neighborhood between nodes in weighted network is redefined and the mixed big data sub-region is realized. Combining the operation, vulnerability and threat of the database, the security situation value is substituted into the abnormal location part to form the coordinate matrix. The pheromone concentration of each region was calculated, and the region where the concentration was reduced was defined as the abnormal region to complete the big data anomaly detection. Experimental results show that this method has high accuracy, freedom of anomaly location and good accuracy performance, which is a great progress of big data anomaly detection technology. In the future, an effective method to repair abnormal data and improve the specific application scope of this method should be developed on the basis of this method.
Keywords: Mixed type; Big data; Subarea; Anomaly detection;.
Construction of Performance Monitoring Model for Cloud Computing Service Platform based on Label technology
by Lishou Zhang, Yiyi Liu, Shaojun Shen
Abstract: To solve the problems of low service efficiency, large change in total system requests and high blocking probability of the current performance monitoring model for cloud computing service platform, a performance monitoring model for cloud computing service platform based on label technology is proposed. By using the model, the concept and characteristics of cloud computing are analyzed, the purpose of performance management and performance monitoring structure of cloud computing service platform are summarized, the service efficiency, time characteristics, resource utilization and efficiency compliance of cloud computing service platform are evaluated, the structure model of cloud computing service platform is established, and the label technology is introduced, to build the performance monitoring model for cloud computing service platform. Finally, the performance monitoring of cloud computing service platform is realized. The experimental results show that the proposed model has high service efficiency, stable change of the total number of system requests and low blocking probability, which verifies the validity and superiority of the proposed model, and provides a new idea for the development and progress of performance monitoring technology of cloud computing service platform.
Keywords: Label technology; Cloud computing; Service platform; Performance monitoring model;.
Symbolic Feature Extraction of Art Graphics based on Time Constraint
by Xiaofeng Liu
Abstract: Aiming at the problem of time-consuming and large error in current image feature extraction results, a symbolic feature extraction method for art graphics based on time constraint is proposed. Gauss filtering method is used to filter out the image noise, and Laplacian sharpening operation is used to enhance the edge of graphic symbols. According to the enhancement results, an active contour model is introduced to define a closed contour, and a driving force is used to realize the evolution of the contour to the target boundary to complete the graph segmentation. The geometric transformation of the segmentation results is analyzed by translation transformation, scale transformation and rotation transformation. Based on graphics enhancement, segmentation and geometric transformation analysis, time constraints are introduced. By analyzing the mean value and variance level of time-constrained laminar flow features, the average value and divergence degree of time-constrained laminar flow features are analyzed, and the time-constrained symbols are regarded as a vector to realize the symbolic feature extraction of fine arts graphics. The experimental results show that the proposed method is efficient and accurate, and it is a reliable method for extracting symbolic features of fine arts graphics.
Keywords: Time constraint; Art graphics; Symbolization; Feature extraction.
Analysis of Data Mining Method for Short-term Wind Measurement of Wind Farm based on Multi-technology Fusion
by Jianfeng CHE, Bo Wang, Shitao Chen
Abstract: Aiming at the problems of poor noise reduction effect of current methods for short-term wind measurement data, poor fitting between wind measurement values and real values, and long running time of the methods, a data mining method for short-term wind measurement of wind farm based on multi-technology fusion is proposed. The anomaly points in the short-term wind data are found and corrected. The short-term wind data are de-noised by wavelet decomposition and normalized. The short-term wind speed measurement of wind farms at each time is carried out, and the short-term wind measurement data mining of wind farms is finally realized. The experimental results show that the proposed method has better noise reduction effect for short-term wind measurement data, the fitting degree between wind measurement value and real value is higher, and the running time of the method is shorter. All the above results verify the effectiveness of the proposed method.
Keywords: Multi-technology fusion; Wind farm; Short-term wind measurement; Data mining;.
Network Teaching Target Classification System Based on Cloud Computing Technology
by Tianming Feng, Lin Chen, Dahang Fan
Abstract: Aiming at the problems of low security, low storage utilization and low classification accuracy of the current network teaching target classification system, a classification system based on cloud computing technology is proposed. Considering the above design functions from the perspective of teachers and managers, the teacher's functions are resource management, sub-category management, information induction, and student management. The functions of managers are unit management, classification management, subject management, teacher management. Through the classification management method and resource management method, the classification of teaching resources is realized. The TEM based on cloud computing technology adjusts the resource classification result through clear and detailed resource data structure, and combines feature extraction, training algorithm and classification algorithm to complete the network teaching resources. classification. The experimental results show that the security, storage utilization and classification accuracy are high, which provides a guarantee for the development of the network teaching target classification system.
Keywords: cloud computing technology; network teaching; teaching objectives; classification system.
Modeling the Impact of Communication Technology on E-Commerce Operation Mode
by Chaosheng Han
Abstract: In order to solve the problems of high modeling complexity and low coincidence degree of traditional methods of studying the relationship between communication technology and e-commerce operation mode, a new analysis model of the influence of communication technology on e-commerce operation mode is proposed. This paper from China, Alexa.com and the selected site object data, using online desktop data acquisition method for part of open data comparison, The experimental results show that the approximate mean square error of the model is lower than 0.035, the fitting index is higher than 0.9, and the complexity is lower than 184, which proves that the method in this paper has higher accuracy and lower complexity, and the practical application effect is better.
Keywords: Communication technology; E-commerce; Operation mode; Impact modeling.
Identity Authentication System for Mobile Terminal Equipment based on SDN Network
by Hao Yang, Wen Cai, Yibo Xia, Wenhua Ouyang, Xin Xie
Abstract: Aiming at the disadvantages of the existing mobile terminal equipment identity authentication system, such as poor anti-attack performance and slow speed, the mobile terminal equipment identity authentication system based on SDN network is designed. The architecture of mobile terminal device authentication system consists of sensor, data center and management center. This paper analyzes the requirements and performance of mobile terminal device identity authentication system, processes the key information through the combination of hashing algorithm and public/key system, and determines whether the mobile terminal device is attacked, so as to realize the identity authentication of mobile terminal device. Experimental results show that when the number of network attacks is 30, the designed system can resist about 92% of the attacks, and the speed of identity authentication is always below 2.7s, indicating that the system has good anti-attack performance and fast speed of identity authentication.
Keywords: SDN Network; Mobile terminal equipment; Identity authenticationrnrn.
Impact of co-channel interference on performance of Power domain based multiple access
by Thuan Do, Tu-Trinh Nguyen
Abstract: Power domain based Non-orthogonal multiple access (PDMA) is one emerging technology thanks to higher system capacity, lower latency, and massive connectivity. Such PDMA is proposed to address several challenges in the fifth-generation wireless systems. In this paper, we first reveal that the NOMA techniques have evolved from fairness assurance under impact of co-channel interference (CCI). Then, we comprehensively investigate on signal to noise ratio (SNR) to detect two separated signals, then outage performance evaluations of the two users are conduced. Monte- Carlo simulations are deployed to verify exactness of outage probabilities.
Keywords: Power Domain based Non-orthogonal multiple access (PDMA); co-channel interference (CCI); outage probability.
Research on Detection Method of Abnormal Capital Transfer in Electronic Commerce Based on Machine Learning
by Guiming Zhu
Abstract: In order to overcome the problems of long detection time, low detection efficiency and high false alarm rate, a new method based on machine learning is proposed. Data mining in e-commerce platform. The improved k-means algorithm was used to cluster the data, and the five steps of preparation, detection, location acquisition, modification and verification were used to clean up the clustering results and remove redundant data. The machine learning method is used to determine whether there are suspicious transaction fragments in the database through four steps: data preprocessing, generating reference sequence and query sequence, calculating similarity and sequence classification, and to complete abnormal fund transfer detection in e-commerce. Experimental results show that the detection time of this method is kept below 3s, the highest false detection rate is only 11%, and the detection rate is always higher than 90%, with high detection efficiency, low false alarm rate, high detection rate.
Keywords: Machine Learning; E-Commerce; Capital Transfer; Anomaly Detection;.
Inter-contact delay and location information based routing (ICDLIR) with adaptive threshold buffer management for delay tolerant networks
by Savita , Daya Krishan Lobiyal
Abstract: Most of the routing algorithms in delay tolerant networks use multicopy approach and messages stay for long time in the buffer because of no end-to-end connectivity between source to destination node. On one hand these activities ensure the high delivery probability, while on the other hand they introduce high resource overheads per message in the network. Therefore, limited storage capacity of buffer bound us to use intelligent message control buffer management policies. In this paper, we have proposed a combination of buffer management scheme for location information and inter-contact based routing approach. The proposed buffer management scheme is a combination of message scheduling and message drop policy grounded on the concept of inter-contact delay based on delivery probability, hop count and number of copies of a message in the network. We also used adaptive threshold scheme which depends on average transferred bytes in the network to prioritize messages. It has been observed that our schemes results in reduction of overheads as compared to previous schemes. The probabilistic analysis of location dependent and independent encounters of nodes has been made to gain better insights of encounter timings. Experimental results obtained demonstrate the effectiveness of our proposed scheme.
Keywords: delay tolerant networks (DTNs); power control; opportunistic networks; overhead; buffer management.
Research on Automatic Annotation of Pathological Image Detail Information Based on Machine Learning
by Xiang SUN, Qianmu LI
Abstract: Aiming at the inaccuracy of pathological image diagnosis results of traditional models, the machine learning technology is introduced and a new pathological image diagnosis method is then proposed. In this method, the accuracy of traditional pathological image diagnosis is transformed into the accuracy of detailed information annotation of pathological image. Pathological image pooling is completed through convolutional neural network, and some pathological images with dimensional blurring phenomenon are sharpened. On the basis of the pooling and sharpening of pathological image, the features of pathological image based on convolutional neural network are extracted. And then machine learning technology is used to annotate the extracted pathological image features and complete the automatic annotation of pathological image details. The experimental results show that the proposed model can improve the accuracy of pathological image feature annotation, and can accurately detect the pathological image of cancer cells, providing a new solution for pathological image diagnosis.
Keywords: pathological image; machine learning; information annotation; automatic detection.
Deep Features Based Dialect and Mood Recognition Using Assamese Telephonic Speech
by Mridusmita Sharma, Kandarpa Kumar Sarma
Abstract: Learning aided methods are popular for modeling the phenomena associated with auditory signals and design of Automatic Speech Recognition (ASR) systems. A vast majority of the works have used shallow models like conventional Artificial Neural Network (ANN) and Hidden Markov Model (HMM) in combination with Mel Frequency Cepstral Coefficients (MFCC) and other relevant features for speech recognition applications. Although these shallow models are effective but there is a need to increase the efficiency by incorporating deep features in the mechanism for speech processing applications. Considerable amount of works have been reported on the design of deep learning topologies and training paradigms in supervised domain. Despite these works, exploring new horizons with speech applications in mind, very few works have concentrated on deep features which are essential to capture detailed information of speech especially while dealing with telephonic content. This work focuses on the generation of deep features using stacked auto-encoder for normal and time shifted telephonic speech samples in Assamese language with mood and dialect variations. The deep features are then tested with softmax classifier which has been integrated to certain deep learning topology. Experimental results show that the deep features learned by the stacked auto-encoder performs better while it is configured for Assamese speech recognition with mood and dialect variations.
Keywords: Deep features; Auto-encoder; Assamese language; Dialects; Moods; Recognition; Artificial Neural Network.
MISO Assisted Multiple Access By Removing Orthogonal: Enabling D2D Transmission And Performance Anlysis
by Thuan Do, Minh-Sang Nguyen, Thi-Anh Hoang
Abstract: As a breakthrough system model adopted in the fifth generation (5G) wireless networks, Multiple Input Single Output (MISO) based Non-orthogonal multiple access (NOMA) has been introduced and investigated. With device-to-device (D2D) transmission taken into account, we consider a NOMA-based downlink network under Rayleigh fading in this paper. To look main metric, we study the system outage behavior, and close-form expressions for the exact outage probability of two NOMA users are obtained. By further evaluating the outage probability under different power allocation factors, fairness in NOMA still is guaranteed. Finally, numerical results are presented to demonstrate the validity of our analysis and show the advantages of NOMA scheme.
Keywords: MISO; non-orthogonal multiple access (NOMA); transmit antenna
Multi-Agent approach for data mining based Bagging Ensembles to improve the decision process for Big Data
by Ahmed Ghenabzia, Okba Kazar
Abstract: Today, data growth is accelerating to create a Big Data in various fields, such as social media, websites, emails, finance, and medicine. It needs analysis and knowledge extraction. In addition, Data Mining is a technology whose purpose is to promote information and knowledge extraction from a Big Data. In this paper, a multi-layered approach based on agents is proposed to extract knowledge from Big Dataset with Bagging algorithm. To achieve this, we call the paradigm of a multi-agent system in Hadoop to distribute the complexity and processing of large data sets across several autonomous entities called agents. The goal is to predict the target class or value for each case in the data using the Bagging technique that is dedicated to the task of Classification or Regression. This proposition will help decision-makers to take right decisions and provide a perfect response time by the use of the multi-agent system in Hadoop. Therefore, to implement the proposed architecture, It is more convenient to use the Apache Hadoop Framework, Apache Spark MLlib framework for building scalable Machine Learning algorithms and JADE platform which provides a complete set of services and agents.
Keywords: Big Data; Apache Hadoop; Apache Spark MLlib; Multi-Agents system (MAS); Bagging; JADE.
AN EFFECTIVE SECURE DATA RETRIEVAL APPROACH USING TRUST EVALUATION: HBSEE-CBC
by Rosy Swami, Prodipto Das
Abstract: In recent times, cloud computing has become more predominant and the secret data are centralized into the cloud to a great extent. But, for the security and privacy of the data, it is essential to encrypt the data before outsourcing; this generates the effective utilization of data as a critical task. In traditional works, the utilization of data based on the keyword search was in practice. Since normal keyword searches and search using encrypted query over encrypted data is very difficult, hence, facilitating an encrypted cloud data searching scheme is supreme prominence. But it has the major drawback of security while retrieving the information. Though many encryption algorithms are utilized for information security, still it has some issues like increased time consumption for encryption, decryption and key generation. Hence to avoid these issues, an Effective Secure Data Retrieval Approach (HSBEE-CBC) is introduced in this work. Here, the data are encrypted by using novel Elliptic Curve Cryptography (ECC) algorithm namely Hierarchical Scalar Based ECC Encryption (HSBEE). Depending on the cosine similarity the encrypted data are clustered by using Cosine Based Clustering (CBC) and transferred to the server. For improving the security, trust evaluation is carried out for the user who intends to retrieve the information. After evaluating the trust of the user, the data is decrypted in order to retrieve it. The performance of the HSBEE-CBC is analysed and compared with traditional approaches. The experimental analysis revealed the superiority of this proposed approach by providing effective results.
Keywords: Cloud Computing; Information Retrieval; Elliptic Curve Cryptography; Cosine Similarity; Trust Evaluation.
LoRaWAN Possible Attacks, Proposed Countmeasures and Enhanced Solution
by Sarra Naoui, Mohamed Houcine Elhdhili, Leila Azouz Saidane
Abstract: The Internet of things (IoT) is pervading our lives to provide a comfortable and smarter human living space by connecting sensors and objects directly with one another without human intervention. The requirements for the deployment of millions of IoT objects are increasing rapidly with a major security concern. To face this challenge, security solutions based on cryptography might be used. In this paper, we investigate one of the widespread IoT security solutions, that is LoRaWAN technology. We evaluate its security by gathering the possible attacks. Afterwards, we propose an enhanced LoRaWAN architecture that faces these attacks. We evaluate the proposed solution in terms of security and performance parameters and compare it to existing solutions.
Keywords: LoRaWAN; Vulnerabilities; Security; Countermeasures.
Fast Road Scenarios Recognition of Intelligent Vehicles by Image Processing
by Huawei Wu, Yicheng Li, Jie Zhang, Yong Kuang
Abstract: Road scenarios recognition is a key point for intelligent vehicles (IVs) self-localization. This paper proposes a fast road scenarios recognition method by image processing, which is based on a visual road model. First, a sequence of images is used to set up the visual road model. Second, we use the classic ORB (Oriented FAST and Rotated BRIEF) method to encode both holistic and local features of a query image. In the step of holistic feature extraction, each query image is treat as a feature and the feature size is only 63
Keywords: intelligent vehicle; computer vision; road scenario recognition; holistic feature; local feature;hybird KNN.
Security Protocol of Internet of Things based on NTRU Encryption Model
by Ying Li
Abstract: In view of the low security and reliability of the current Internet of things security protocols, a NTRU encryption model based Internet of things security protocol method is proposed. This method uses NTRU-PGP to construct the security protocol of the Internet of Things, reduces the amount of data through PKZIP algorithm, introduces AES symmetric encryption algorithm to encrypt the information data that need to be transmitted in the Internet of Things, re-encrypts the encrypted information according to NTRU encryption algorithm, and implements information signature by NTRUSign algorithm to ensure the security of the Internet of Things. The experimental results show that when the proposed method is attacked by active attack, passive attack, eavesdropping data, counterfeiting and other types of attacks, the estimated attack time is over 1025, which is significantly higher than other data, which proves that the protocol is more secure and reliable.
Keywords: NTRU; Internet of Things; Security protocol.
Lightweight Information Integration Model of IOT based on VMware Cluster Technology
by Ying Li
Abstract: In order to overcome the problems existing in the current Internet of things information integration model, Lightweight Information Integration Model of IOT based on VMware Cluster Technology was proposed. This model designs the standard coded identification for each node in the Internet of things, constructs the category of node attributes and node object categories of the Internet of things, and the node LDAP information model, and constructs the node management platform of the Internet of things. VMware cluster technology is introduced, and VMware Infrastructure is used to realize the virtualization and integration of lightweight Internet of things information from server, network and storage. The results show that the number of servers used in this paper is 4, with the least number. The server occupies less space than 8U; The power consumption of the server is lower than 3500W/h, and the power consumption is lower, showing a good performance.
Keywords: VMware cluster technology; Lightweight; IOT information; Integration.
The Research of Human Interaction Recognition Based on Fusion Features of Key Frame Feature Library
by Haiyan Zhang, Shangbing Gao
Abstract: Some issues such as computational complexity and low recognition accuracy still exist in human interaction recognition. In order to solve the problem, the paper has proposed innovative and effective method based on fixed features of key frame feature library. Firstly, GIST feature and HOG feature were extracted from the pre-processed videos. Secondly, training videos with different kinds of actions were clustered by the K-means algorithm respectively to get key frame feature of each action for constructing key frame feature library. And similarity measure was utilized to calculate the frequency of different key frames in every interactive video, and statistical histogram representation of interactive videos were obtained. Finally, the decision level fusion was achieved by using SVM classifier based on histogram intersection kernel to obtain impressive results on UT-interaction dataset. The correct recognition rate of the proposed algorithm is 85%, which indicates that the proposed algorithm is simple and effective than others.
Keywords: GIST Feature; HOG Feature; Key Frame Feature Library; Histogram Intersection Kernel; UT-interaction Dataset.
Research on Stability Modeling of High Speed Electronic Communication Based on Hierarchical Optimal Mining Algorithms
by Lin Tang
Abstract: In order to solve the problems of low accuracy, bad network topological data integrity and low communication transmission efficiency in the current stability modeling methods for high-speed electronic communication, a new stability modeling method for high-speed electronic communication based on hierarchical optimization mining algorithm is proposed. This paper analyzes the transmission characteristics of high-speed signals in the process of electronic communication, constructs a wireless channel model by using hierarchical optimization mining algorithm, and carries out distance correspondence based on the wireless channel model. The stability of high-speed electronic communication is modeled and analyzed by using one-step transition probability matrix, node relative distribution and link duration. Experimental results show that this method has the advantages of high model accuracy, good topological data integrity and high communication transmission efficiency.
Keywords: Hierarchical optimization mining algorithm; High-speed electronic communication; Stability; Modeling and analysis; Transfer probability matrix;.
Self-adaptive Process Optimization Method for SBS Cloud Application based on Reinforcement Learning
by Haiyan Hu, Chang Su
Abstract: To solve the problem of poor comprehensive performance of the traditional SBS cloud application adaptive process optimization method, a new SBS cloud application adaptive process optimization method based on reinforcement learning was proposed. Establish the adaptive action type selection model, realize the optimal choice of operation type, build the cloud application adaptive process optimization model for resource cost, convert the problem into the corresponding mathematical model, solve and make the mathematical model of the algorithm, and obtain the best adaptive process optimization scheme SBS cloud application. The simulation results show that the predicted load value of the method is the closest to the actual load value, the relative error of the prediction is less than 21.03, and the average time is less than 2.3s, indicating that the method has good performance and high practical application value.
Keywords: Enhanced learning; SBS cloud application; self-adaptive process optimization; system performance optimizationrnrn.
Cross-domain Single Sign-on Authentication of Information Security in Network Environment
by Ajun Cui, Wei WANG, Hua-feng ZHANG, Yan-hong MA, Chen LI, Xiao-ming WANG
Abstract: Aiming at the problems of long response time, poor security and information integrity in cross-domain single sign-on authentication research of network security, this paper proposes a cross-domain single sign-on authentication method based on SAML, including the design of login authentication control and revocation authentication scheme. In login authentication, efficient interaction between identity providers and service providers reduces unnecessary steps to achieve single sign-on. At the same time, a revocation scheme based on cumulative function is proposed to ensure that the local root signature is used for system parameter information, thus further ensuring network security. The experimental results show that the login time of the proposed method is below 400ms, and the login response takes a short time. The success rate of the proposed method against false login is over 90%, and the security is good. The data packet loss rate of this method is below 2%, high integrity and reliability.
Keywords: Network security; cross-domain single sign-on; parameter information; revocation of authentication.
Machine Learning Method Based on Improved Drosophila Optimization Algorithm
by Haiying Wang
Abstract: Aiming at the problems of poor classification effect and high CPU ratio of traditional machine learning methods, a machine learning method based on improved drosophila optimization algorithm was proposed.The rank one data mapping and the low order data are established.In low rank support vector set, CP rank organization of traditional support vector machine is used to improve data security.The traditional drosophila algorithm was improved and optimized to increase the number of data iterations, ensure the compatibility of rank one data, improve the optimal calculation of drosophila, and increase the density clustering.The decomposition process is designed to evaluate the objective function value of the optimal solution.In the evaluation process, support vector machine is used to complete the label classification of learning data.Experimental data show that this method performs well in data classification effect, low-rank data storage dimension characteristic performance and CPU operation proportion performance.
Keywords: Machine learning; Drosophila algorithm; Low rank data; Support vector machine.
Research on Blurred Edge Information Segmentation of Image based on Computer Vision
by Xu Zhang
Abstract: In the process of image fuzzy edge information segmentation by traditional methods, the segmentation effect is not ideal, the completion time is long and the accuracy is low.A fuzzy edge information segmentation method based on computer vision is proposed.After image denoising, image sharpening is carried out to extract image fuzzy edge information features.By designing a super-pixel grid, the pixels of the fuzzy edge information features of the image are matched, the inverse tensor information of the fuzzy edge of the image is analyzed, and the multi-threshold values are normalized.The processing results are overlaid on the single object in the image to realize the fuzzy edge information segmentation.Experimental results show that the proposed method has better segmentation effect, shorter completion time and higher accuracy, and is of practical significance.
Keywords: Computer vision; Image blurring; Edge information; Multi-threshold segmentation.
Multi-Tag Cleaning Software For Cyclic Redundant Data Stream Based On Rfid In Cloud Computing
by Yujiang Fei
Abstract: In order to overcome the problems of poor accuracy and recall and low data integrity existing in the current research results of multi-tag cleaning for cyclic redundant data streams, this paper designs a multi-tag cleaning software for cyclic redundant data streams in cloud computing based on RFID. According to the factor graph model, the software models cloud computing network, infers the overall quality of network link connection by cyclic reliability propagation method, and realizes data acquisition by probability graph reasoning. The improved RFID reader reads the information of the tag data to realize the preliminary processing of the cyclic redundant data stream. Multi-label cleaner and RFID reader cooperate to complete multi-label cleaning of cyclic redundant data stream under cloud computing. The experimental results show that the proposed multi-tag cleaning software for cyclic redundant data streams has higher accuracy and recall than the results of references, and has higher data integrity.
Keywords: RFID; Cloud computing; Cyclic redundancy; Data stream; Multi-tag; Cleaning;.
Intelligent Evaluation Model Of E-Commerce Transaction Volume Based On The Combination Of K-Means And Som Algorithms
by Junjie Niu
Abstract: Due to the lack of steps to process sensitive data in the traditional intelligent evaluation model of e-commerce transaction volume, which leads to poor evaluation effect, an intelligent evaluation model of e-commerce transaction volume based on the combination of k-mean and SOM algorithm is proposed.Taking system intelligent clustering as the core, the transaction volume data in the Web log is collected through the collection system.The desensitization rule is used to establish the data transmission model of trading volume.The detection of sensitive data adopts signal detection technology and analytical processing.Based on k-means algorithm, data desensitization is accomplished to achieve data denoising, and a clustering evaluation model is established to complete data mining and analysis.The experimental results show that the model has a good denoising effect, and the ROC curve is closer to the upper left corner with an AUC value of 0.9712, which verifies the effectiveness and superiority of the model.
Keywords: System intelligent clustering; E-commerce transaction volume; Evaluation model; K-means; SOM.
A PSO Based Improved Clustering Algorithm for Lifetime Maximization in Wireless Sensor Networks
by Santar Pal Singh, S.C. Sharma
Abstract: A wireless sensor network (WSN) is comprised of enormous amount of miniature devices known as sensor nodes. Sensor nodes are highly energy restrained due to their battery dependent operations and because of the harsh area deployment it is not feasible to change or revitalize their batteries. For maximizing the network lifetime, energy conservation is a crucial measure of performance improvement of WSNs. So, energy consumption and network lifetime are crucial issues in WSNs. Large portion of energy are consumed in communication process of sensor network. Several routing algorithms have been projected to accurately rout the packet in WSNs. Usually classification of routing algorithms can be done into two categories: based on network structure or based on protocol operations. Based on network structure, these algorithms are broadly divided into flat based, hierarchy based or cluster based, and location based routing algorithms. Due to energy efficiency and network stability, cluster based routing is the best choice. In this paper, we propose a swarm optimization based clustering algorithms for WSNs. We perform the analysis of our new clustering algorithms with LEACH, LEACH-C, and HEED on the basis of performance metrics that contain energy, number of alive nodes, delay, PDR, and throughput. Simulation outcomes confirm that proposed clustering algorithm outperform the other ones.
Keywords: wireless sensor network; clustering algorithm; energy efficiency; network stability; network lifetime.
Virtual Machine Allocation Method For Cloud Computing Based On Multi-Objective Evolutionary Algorithm
by Jinling Ma
Abstract: In order to overcome the problems of data access delay and high energy consumption in virtual machine configuration of cloud computing, a new virtual machine allocation method for cloud computing based on multi-objective evolutionary algorithm is proposed in this paper. Based on multi-objective evolutionary algorithm, the objective of energy consumption and access delay optimization is replaced by an objective model, which is used as the allocation objective model of computational virtual machine. The ant colony algorithm and K-NN local search method are introduced to obtain the optimal solution of the allocation target model and realize the output of the optimal allocation scheme for cloud computing virtual machines. The experimental results show that the access delay and energy consumption of the proposed method are significantly lower than those of other methods, which proves that the proposed method has better performance.
Keywords: Multi-objective evolution; Cloud computing; Virtual machine; Allocation.
Automatic Repair of Pollution Attacks in SDN Topology Network Based on SOM Algorithm
by Xiaoliang Yang, Yi Dai, A. Lun
Abstract: When using the current method to recover the vulnerabilities caused by pollution attacks in SDN network, there are some problems, such as low coverage, low accuracy of vulnerability detection results and low repair efficiency. To this end, an automatic repair method for topology pollution attacks in SDN network based on SOM algorithm is proposed. This paper analyzes the security vulnerabilities in SDN architecture and SDN network, and extracts the attack flow characteristics of topology pollution attacks in SDN network. The extracted attack flow features are input into SOM algorithm to detect and identify vulnerabilities caused by pollution attacks. Combining the theory of vertex concavity and convexity and geometric triangle, the detected vulnerabilities are repaired to realize the automatic repair of topology pollution attacks in SDN network. The experimental results show that the proposed method has high coverage, high accuracy of vulnerability detection and high efficiency of vulnerability repair.
Keywords: SDN network; Pollution attack; Vulnerability detection; Vulnerability repair; SOM algorithm;.
Unlabeled Facial Expression Capture Method In Virtual Reality System Based On Big Data
by Feng Gao
Abstract: In view of the problems of high error rate and low efficiency in the traditional method of facial expression capture without markers, a method of facial expression capture without markers based on large amount of data is proposed. Haar feature is used to determine the initial position of human face, and active shape model is used to extract unmarked facial feature points. The extracted feature points and the generated triangle mesh are tracked by the optical flow tracking method. The displacement of the face feature points is used to promote the overall change of the mesh and complete the unmarked facial expression capture. The experimental results show that the error rate of this method is in the range of 1.2% - 1.7%, the error rate is small, and it needs 20s-34s to capture facial expression, which is more practical and efficient.
Keywords: Big data; Virtual reality system; Unlabeled; Facial expression capture.
BB84 with Several Intercepts and Resend Attacks using Partially Non-orthogonal Basis States through a Depolarizing channel
by Mustapha DEHMANI, El Mehdi Salmani, Hamid Ez-Zahraouy, Abdelilah Benyoussef
Abstract: The paper presents the partially non-orthogonal basis states effect in presence of several intercept and resend attacks through a depolarizing channel. The quantum error and the mutual information are computed for arbitrary angles of the non-orthogonal basis states and the depolarizing channel parameter. It is found that the information security depends strongly on the non-orthogonal basis states angle, the depolarizing channel parameter, the intercepts and resend attack probability and the eavesdropper number. Besides, it is found that for any eavesdroppers number and basis states angle; the protocol is more secure if the depolarization parameter is lower than a threshold value and the maximum value of the quantum error decreases by increasing the depolarizing parameter and / or the eavesdroppers number. While for the depolarization parameter above the threshold value the protocol is not secured independently of any values of the non-orthogonal basis states angle and/or the eavesdroppers number.
Keywords: Quantum cryptography; Intercepts- resend attacks; Non-orthogonal basis states; depolarizing channel; Quantum error; Information Security.
Research On Web Users Behavior Data Mining Based On Feature Orientation
by Hui Zhang, Xiao-ling Jiang, Fa Zhang
Abstract: In view of the problems of long mining time and high error rate in the existing network user behavior data mining methods, a network user behavior data mining method based on feature preference is proposed.The interaction relationship in social network is analyzed as the constraint condition of feature selection.Laplasian operator is used to construct the feature selection model of network user correlation and to quantify the relationship between users.The improved ant colony algorithm is used to obtain the optimal feature subset to realize the network user behavior data mining.The experimental results show that, compared with the traditional methods, the mining time of the proposed method is shorter and the mining error rate is lower under the condition of low and high excavation strength, which verifies the effectiveness of the proposed method.
Keywords: Feature orientation; Web user’s behavior; Data mining.
Research On Global Tourism Information Query Method Based On Association Mining
by Zhongqi Zhao, Yanjie Tan
Abstract: The traditional global tourism information query method can not mine the intrinsic relevance of the discrete information because of its strong discreteness, which results in inaccurate query results and long query response time. To overcome this problem, a global tourism information query method based on association mining is proposed. Using SAS/ME tools, data missing processing, data normalization, correlation analysis and data filtering of global tourism information data in the data are carried out, and the global tourism information data set is constructed according to the results of data processing. This paper uses C4.5 decision tree algorithm and SAS Miner Enterprise to mine the association of global tourism information in data centralization. According to the result of association mining, a global tourism information query system is established to realize the global tourism information query. The experimental results show that the method has the shortest query response time and higher query accuracy, which shows that the method is more suitable for global tourism information query.
Keywords: Association mining; Global; Tourism information; Query; Normalization processing; Discrete attributes;.
Abnormal State Recognition Method for Online Intelligent Examination based on Improved Genetic Algorithm
by Bo Yang, Hongbin Li, Huan Xie, Jianyong Zhao, Rong Zhu, Lei Zhao
Abstract: In order to overcome the defects of the traditional test monitoring scheme, this paper proposes a new method of online intelligent test abnormal state recognition based on improved genetic algorithm.This method sets the test status parameters and defines the criteria of abnormal status, collects the online test information and builds the information database.Image preprocessing is realized from two aspects of image segmentation and grayscale processing.The improved genetic algorithm is used to analyze and collect data intelligently and search image feature points to obtain abnormal feature extraction results.Match the extracted feature results with the established database information to realize the abnormal state recognition results, and start the corresponding abnormal alarm program.The experimental results show that the accuracy of the proposed method is 18.57% higher than that of the traditional method, indicating that the method has a better application prospect.
Keywords: Improved genetic algorithm; Online examination system; Intelligent examination; Abnormal state; State recognition;.
Analysis of Intelligent Test Paper Generation Method for Online Examination based on UML and Particle Swarm Optimization
by Bo Yang, Huan Xie, Kuan Ye, Huan Qin, Rong Zhu, Anchang Liu
Abstract: In order to overcome the problems of unclear objective function and inaccurate optimal solution in traditional test paper generation methods, an online intelligent test paper generation method based on UML and particle swarm optimization is proposed. A mathematical model of test paper generation based on UML modeling tool is established, and the objective function of test paper generation is obtained. The improved particle swarm optimization algorithm is used to solve the objective function of test paper generation. The optimal solution of the objective function is introduced into the question bank. The test questions in the test bank are combined and imported into the online examination system to realize the intelligent test paper formation of online examination. The experimental results show that this method has strong adaptability and can achieve better performance than the traditional intelligent test paper generation method.
Keywords: UML; Particle swarm optimization; Online examination; Intelligent test paper generation; Constrained project indicators; State object matrix.
Research on Dynamic Performance Regulation Method of Bidirectional Relay Network Based on SDN Architecture
by Jianxin Qiu
Abstract: In order to overcome the shortcomings of the traditional dynamic regulation methods of bidirectional relay network, such as low resource utilization and high energy consumption of nodes, a dynamic regulation method of bidirectional relay network performance based on SDN architecture is proposed. SDN architecture is used to construct the bidirectional relay network model. The subcarrier pairing algorithm is used to pair the subcarriers, and then the model of two-way relay network is optimized. The optimal configuration of node power and subcarrier power is carried out respectively, and the joint energy consumption control model of two-way relay network is constructed by using game theory. In this way, the performance of bidirectional relay network can be dynamically adjusted. Through experiments, compared with the traditional method, the proposed method improves resource utilization, reduces node energy consumption, and has better performance.
Keywords: SDN Architecture; Bidirectional; Relay; Performance; Dynamic; Adjustment;.
Intrusion Detection of Hierarchical Distribution Network System based on Machine Computation
by Xiaohong HE
Abstract: In order to solve the problems of low detection accuracy and long detection time of traditional hierarchical distributed system intrusion detection method, a hierarchical distributed system intrusion detection method based on machine computing is proposed. By judging the Chinese protocol type of IP message and the control bit value of TCP, the network traffic is transformed into different sub-flows, and the characteristic parameters of traffic behavior are extracted from the sub-flows. Based on the invasion behavior characteristics obtained, the vector with six - dimensional characteristics is selected as the important symbol of invasion. By combining rule detection method, support vector machine and machine learning classification, the intrusion detection of hierarchical distribution network system is realized by embedding detection modules at different levels. Experimental results show that this method can effectively reduce intrusion detection time and improve detection accuracy.
Keywords: Machine computation; Hierarchical distribution network; System intrusion detection.
Digital English Teaching Resource Sharing System Based On Logical Database
by Fengtian Xu
Abstract: The traditional English teaching resource sharing system has the problems of low distributed computing performance and low data steady-state transmission rate. This paper proposes a design method of digital English teaching resource sharing system based on logical database. The hardware part of the system constructs the logical database of the system, designs the business layer of the logical database in the system, and reads and writes the resources. Establish a database resource search engine, reduce the calculation process and realize the effective use of digital English teaching resources and course recommendation. Using multi type system development software, the system file configuration and service address are developed to complete the system design. The experimental results show that compared with the traditional teaching resource sharing system, the distributed computing performance of the designed system is improved by 37%, and the data steady-state transmission rate is increased by 29%, which has distinct advantages.
Keywords: Logical database; Digitalization; English teaching; Resource sharing; Virtual server.
Research on High Accuracy Mandarin Emotion Recognition Method Based on Local Optimal Algorithms
by Caihua Chen
Abstract: In order to overcome the problem that the traditional Mandarin emotion recognition method does not optimize the result of emotion classification, which leads to low accuracy and recognition efficiency, a high-precision Mandarin emotion recognition method based on local optimization algorithm is proposed. The emotion database of Putonghua is constructed by the dimension emotion model. On this basis, the emotion signals of Putonghua speech are preprocessed and extracted. Through clustering analysis, emotion features are statistically calculated and classified, and local optimization algorithm is used to optimize the classification results to achieve high-precision recognition of Mandarin emotion. The experimental results show that compared with the traditional method, the accuracy and recognition efficiency of the proposed method have been improved to a certain extent, and the shortest recognition time is only 19 ms.
Keywords: Local Optimization Algorithm; High Precision; Mandarin Emotion Recognition; Emotion Feature Extraction.
Construction Of Load Balancing Scheduling Model For Cloud Computing Task Based On Chaotic Ant Colony Algorithm
by Jie Yu
Abstract: In order to overcome the problem of low scheduling balance and long time in traditional load scheduling model for cloud computing task, a load balancing scheduling model for cloud computing task based on chaotic ant colony algorithm is proposed. Task scheduling strategy is selected through task scheduling framework to achieve parallel task scheduling. Based on chaotic ant colony algorithm, cloud computing resources are deployed, and the load objective function of cloud computing task is constructed. Based on the constructed objective function, a load balancing scheduling model for cloud computing tasks is established, thereby achieving load balancing scheduling for cloud computing tasks. The experimental results show that the model has a high scheduling balance, the scheduling time is always less than 5 ms, and the scheduling efficiency is high. This model is more suitable for the balanced scheduling of cloud computing resources, which is feasible.
Keywords: Chaotic ant colony algorithm; Cloud computing; Task load; Balanced scheduling model;.
A Sample De-noising Method for FCM Clustering Induced by Gauss Kernel
by Yunxing Wang, Liyan Li, Zhicheng Wen
Abstract: Aiming at the problem of instability of clustering result because of the existence of noise samples in general FCM algorithm, an improved FCM algorithm induced by Gauss kernel induced is proposed. Firstly, the influence of samples distribution on clustering is analyzed, and the Gauss kernel function is used to nonlinear map of the samples, then the improvement of the objective function of the FCM algorithm and clustering of samples are achieved, thus the purpose of suppressing noise is achieved. The experimental comparison shows that compared with other FCM algorithms, the proposed algorithm's successful classification rate is about 10% higher and the partition coefficient is about 10% lower than other FCM algorithms, indicating that the algorithm has higher clustering effectiveness.
Keywords: Fuzzy C-Means; Gaussian Kernel Function; Noise Sample; Samples.