Computer and Modernization

Network Clustering Layout Algorithm Based on Detecting Community Structure

ZHOU Xian1,2, HUANG Ting-lei1, LIANG Xiao1

2017, 0(12): 1-5+11. doi:10.3969/j.issn.1006-2475.2017.12.001

Asbtract ( 222 )

References | Related Articles | Metrics

The complex network is becoming increasingly concerned by the experts and scholars. The visualization of the complex network can help the users to discover the hidden knowledge and information in the complex system represented by complex network, which is of great significance to the fields of computer science, sociology, and biology. The force-directed layout algorithm is the mainstream algorithm in the field of complex network visualization. It uses the form of node connection graph to abstract the complex network, the layout follows aesthetic standards such as the uniform distribution of nodes and the uniform of edges, to a certain extent, which hinders the display of the community structure of complex networks. Aiming at above problems, this paper introduces the repulsion and gravitational force of the community based on the degree centrality to improve the clustering layout of the complex network. The experimental results show that the proposed algorithm can effectively display the community structure of complex networks while preserving the information of margin nodes between communities.

A Fast Algorithm for Calculating APSP by Paths Block

LIN Jia-qi, LU Gang, XU Nan-shan

2017, 0(12): 6-11. doi:10.3969/j.issn.1006-2475.2017.12.002

Asbtract ( 259 )

References | Related Articles | Metrics

The problem of All Pairs of Shortest Paths (APSP) has been a hot topic in the fields of computer science, traffic engineering， geographic information system, and so on. With the increasing size of the network, the time complexity of calculating APSP is increasing rapidly. Therefore, the efficiency of APSP algorithm is a general concern and is urgent in practical application. Based on the BFS, this paper introduces the path blocking strategy, which uses the results obtained by solving Single Source Shortest Path (SSSP) to accelerate the process of APSP. The experimental results show that this method realizes the acceleration.

Mixed Intrusion Detection Algorithm Based on k-means and Decision Tree

LI Peng， ZHOU Wen-huan

2017, 0(12): 12-16. doi:10.3969/j.issn.1006-2475.2017.12.003

Asbtract ( 201 )

References | Related Articles | Metrics

With the growth of the network complexity, the traditional intrusion detection methods have been unable to meet the high-level security requirements. How to use data mining algorithm to improve accuracy rate of intrusion detection is a hot spot in current research. For this purpose, a hybrid intrusion detection algorithm based on k-means and decision tree algorithm (KDI) is proposed. Firstly, an improvement on data discretization method is advanced, in order to obtain high quality sample data, and then the k-mean algorithm is utilized to classify the sample data based on the feature of slight difference between information divergence ratio in many real situations, subsequently, the decision trees is constructed, therefore, the detection rate is enhanced. The experimental results show that the KDI algorithm can effectively detect both known and unknown intrusion behaviors sealed in network data.

An Explicit Track Continuity Algorithm for SMC-PHD Filter

GAO Yi-yue1,2, JIANG De-fu2, LIU Ming2, FU Wei2

2017, 0(12): 17-22+116. doi:10.3969/j.issn.1006-2475.2017.12.004

Asbtract ( 179 )

References | Related Articles | Metrics

In multi-target tracking, the real-time performance, state-estimates accuracy, and track continuity are affected by clutter, missed detection, and closely spaced targets. To solve these problems, an improved sequential Monte Carlo implementation (SMC) of the probability hypothesis density (PHD) filter is proposed. First, based on double one-to-one principles, particle labeling approach and weight redistribution scheme for particle cloud are proposed to shield against the negative effects of clutter in high prior density region and the detection uncertainty on the estimation. Second, the multi-estimate extraction is converted into multiple single-estimate extractions, which can provide the identity of the individual target; thus, explicit track maintenance can be obtained. Finally, a novel resampling scheme is proposed to reduce the effects of closely spaced targets on individual posterior information. The results of numerical experiments demonstrate that the proposed approach can achieve explicit track continuity and better performance compared to the basic SMC-PHD filter, in terms of faster processing speed and superior estimation accuracy.

Multiple Target Localizationin WSNs via CS Reconstruction Method Based on Discrete CSO Algorithm

DONG Yuan-quan1, WANG Hao2

2017, 0(12): 23-27. doi:10.3969/j.issn.1006-2475.2017.12.005

Asbtract ( 171 )

References | Related Articles | Metrics

The multiple target localization problem of WSNs is studied, and a multiple target localization method based on discrete chicken swarm optimization (DCSO) and compressed sensing (CS) theory is proposed. Firstly, some definitions related to DCSO algorithm are given, and the discrete chicken coding method and the iterative evolution strategy are designed. Based on this, a WSNs application model based on CS is established, and the measurement matrix and sparse matrix are chosen. Finally, the DCSO is applied to the CS sparse signal reconstruction algorithm, which realizes unknown sparsity multi-objective information reconstruction. The simulation results show that, compared with OMP and MLE, this method has better effect in multiple target locating precision.

A Method of Automatic Color Correction for Remote Sensing Image  Based on CNN Regression Network

DU Shang-shang1,2,3, LEI Bin1,2,3, GUO Jia-yi1,2,3, LU Xiao-jun4

2017, 0(12): 28-32+121. doi:10.3969/j.issn.1006-2475.2017.12.006

Asbtract ( 294 )

References | Related Articles | Metrics

At present, there are a lot of mature and effective image color correction algorithms. However there isn’t an effective automatic color correction method for massive remote sensing image data. In order to solve the problem, this paper proposes a fully automatic method named ACCN（Auto Color Correction Network）to correct multispectral remote sensing images’ color based on CNN (Convolutional Neural Network). The model corrects the multispectral remote sensing images’ color by predicting its’ Ground-truth color histogram of each color channel. The model is trained on 20 thousand pieces of remote sensing images in the Tensorflow framework. We get the optimal model which realizes automatic color correction for multispectral remote sensing image through many times repeated fine-tuning. Experiments show that the multispectral remote sensing image through automatic color correction becomes harmonious and flaming. This method can correct the color of large-scale remote sensing images automatically. 

A Fragile Video Watermarking Algorithm Based on Fractal Theory

YANG Shu-guo1, ZHANG Bo1, XIONG Peng-cheng2, XUE Ming-yu3

2017, 0(12): 33-38. doi:10.3969/j.issn.1006-2475.2017.12.007

Asbtract ( 162 )

References | Related Articles | Metrics

Aiming at the video integrity authentication problem, this paper proposes a fragile video watermarking algorithm based on fractal theory, which converts the color pattern RGB into color pattern YUV and embeds the watermark into the component Y. Transformed by DWT, the fractal feature of I-frame is extracted, which combines with the position feature of each frame to generate authentication code. Then, the authentication code which is scrambled by Logistic chaos mapping is embedded into the LSB bit of last two non-zero coefficients of DCT block. In the process of video authentication, it is possible to realize the blind detection without reference to the original video. The experimental results show that the proposed algorithm can effectively detect and locate the position of the original video which is attacked and tampered with, without degrading image quality.

Blind Image Deblurring with Sparse Representation via Gradient Prior

XUE Yi-mei

2017, 0(12): 39-42. doi:10.3969/j.issn.1006-2475.2017.12.008

Asbtract ( 234 )

References | Related Articles | Metrics

In view of the limited ability in detail preserving of sparse representation-based blind image convolution algorithm， this paper proposes a blind image convolution algorithm based on sparsity constraints of image patches and gradient prior. Although each image patch can be approximated by a sparse linear combination of atom signals in an over-complete dictionary, it brings about the artificial effects among image blocks. In order to solve this problem, the image gradient prior and Hyper-Laplacian priors are incorporated into the sparse representation blind convolution model to estimate the blur kernel. Once the blur kernel is known, we can apply the non-blind deconvolution algorithm to obtain the latent image, which brings about some ringing effects. Therefore we utilize the Hyper-Laplacian priors to recover the final latent image. Experimental results demonstrate that the proposed improved method can remove artifacts and render better deblurring images, compared to other state-of-the-art deblurring methods.

Quantum-inspired Cuckoo Search Algorithm with Application to Stratigraphic Correlation

CAO Mao-jun1, XUE Cheng1, ZHAO Jing2, SUN Wen-long2

2017, 0(12): 43-48. doi:10.3969/j.issn.1006-2475.2017.12.009

Asbtract ( 135 )

References | Related Articles | Metrics

In order to improve the search ability of cuckoo search algorithm, by introducing the quantum computing mechanism into the classical cuckoo search algorithm, a quantum-inspired cuckoo search algorithm is proposed. In the proposed algorithm, the qubits are used to encode individuals, the Pauli matrixes are employed to determine rotation axis, the Levy flight principle is applied to obtain rotation angle, and the rotation of the qubits on the Bloch sphere is used to update the individuals. Aiming at the specific features of stratigraphic correlation of logging section and the constraint conditions that need to be satisfied, a scheme of applying quantum-inspired cuckoo algorithm to stratigraphic correlation is proposed. This method can not only compare the similarity between different strata, but also deal with the faults caused by faults or sharp extinction. The experimental results show that the algorithm is effective and feasible in complex geological conditions.

Fall Detection Algorithm Based on SVM_KNN

ZHANG Shu-ya, WU Ke-yan, HUANG Yan-zi, LIU Shou-yin

2017, 0(12): 49-55. doi:10.3969/j.issn.1006-2475.2017.12.010

Asbtract ( 441 )

References | Related Articles | Metrics

Falling is one of the main causes of casualties in the elderly, every year about 40 million people over the age of 65 fall accidentally. To improve the accuracy in human fall detection, a fall detection algorithm based on acceleration sensor and barometer in a smart phone is proposed, the algorithm is an improved support vector machine (SVM). Firstly, it uses the SVM to train the training set to obtain a weak 2-classifier (including the optimal hyperplane and support vector set), and then calculates the distance from the sample to the optimal hyperplane. If the distance is greater than the given threshold, the tested sample would be classified with SVM. Otherwise, the K-nearest-neighbor classifier (KNN) method will be used. In addition, in the KNN method, the distance between the eigenvectors is calculated using the standard Euclidean distance. Simulation results show that compared with the non-optimized support vector machine algorithm, this algorithm can effectively improve the fall detection accuracy and smartphones can be placed casually.

A Real-time Positioning Algorithm Using Fading Factor Kalman  Filter Based on WiFi and Inertial Fusion

DUAN Shan-shan1, LI Xin 2

2017, 0(12): 56-60. doi:10.3969/j.issn.1006-2475.2017.12.011

Asbtract ( 159 )

References | Related Articles | Metrics

Due to the indoor positioning errors produced by the unsteadiness of received WiFi signal for fingerprint-based WLAN location technique, a new positioning technology by fusing inertial measuring unit(IMU) and WiFi wireless signals with fading-factor-based extended Kalman filter (EKF) is proposed. A multiple restrictions for peak-valley detection is developed on acceleration for real-time step recognition. Then the paper utilizes the feature of indoor environment to amend the orientation for getting a correct heading angle. Finally, this paper proposes a fading-factor-based EKF fusion model based on displacement constraint with WiFi and inertial sensors positioning techniques for user’s location estimation. The experimental result shows that， this algorithm can effectively suppress the unsteadiness of jump or centralization, and enhance the indoor location robustness and reliability. The average positioning accuracy is about two meters.

A Healthy Big Data Classification Model Based on Improved Bayesian Network

LIANG Cong1,2, LIAO Xin 3, ZHENG Xin1, CHEN Lei-ting1,4

2017, 0(12): 61-64. doi:10.3969/j.issn.1006-2475.2017.12.012

Asbtract ( 176 )

References | Related Articles | Metrics

Bayesian network is a research hotspot in the field of data mining. It is an effective tool for the determination of the uncertain dependencies. This paper studies the advantages and disadvantages of the traditional Bayesian network structure learning algorithm, and determines the dependencies among the various health attributes in the data set, establishes the network structure of dependency relation between related attributes. Finally, the network structure is used to automatically classify the data in the data set. Experiments show that the health big data classification model based on Bayesian network has a good performance and achieves the expected effect.

Realization of Load Balancing Mechanism in Storm Streaming Processing Platform

ZHANG Nan, CHAI Xiao-li, XIE Bin, TANG Peng

2017, 0(12): 65-70+76. doi:10.3969/j.issn.1006-2475.2017.12.013

Asbtract ( 245 )

References | Related Articles | Metrics

Compared with Hadoop, Storm has advantage of real-time data stream processing, which provides an efficient, fast and real-time data processing framework for multi-source heterogeneous data processing. However, the worker assignments in the Storm cluster only consider the sort of available Slot between different nodes, while ignoring the current load condition of different nodes, which may fail to meet the command of load balancing when more than one topology running in the cluster. In order to improve the efficiency and achieve load balancing of real-time stream processing, a Storm scheduling algorithm is proposed which is weighted sorting of available Slot and node load conditions and based on Storm-based distributed flow processing system to reduce load imbalance. And through designing the data structure reasonably, the paper designs the rowkey in Hbase randomly and evenly, which can ensure the load balance of the various RegionServer，improve the utilization of cluster resources and increase the speed of data writing greatly. Through the comparison experiment with the original Storm system, it is shown that the above algorithm improvement and mechanism optimization ensure the fast writing of data and improve the utilization rate of cluster resources. The improved system has obvious advantages in practicality and efficiency. 

Semantic Reasoning for Knowledge Graph

GUO Lin, ZHAI She-ping, GAO Shan

2017, 0(12): 71-76. doi:10.3969/j.issn.1006-2475.2017.12.014

Asbtract ( 310 )

References | Related Articles | Metrics

For the purpose of improving the adaptability of the query reasoning system to the highly dynamic and rapidly expanding knowledge graph returning more efficient, real-time and accurate results to the users, a reasoning algorithm based on semantic tensor is proposed through comparative study of the prevailing knowledge graph reasoning algorithms. Two open network knowledge graphs were selected and simplified to be tested and trained by this algorithm. The experimental results show that this algorithm can adapt to the highly dynamic and consistently evolving data and information of the knowledge graph, improve the accuracy of the reasoning, intelligence of the search engine, and save the memory.

Topic Event Extraction Technology Based on LDA Model and AP Clustering Method

ZHANG Jian-heng, HUANG Wei, HU Guo-chao

2017, 0(12): 77-81+87. doi: 10.3969/j.issn.1006-2475.2017.12.015

Asbtract ( 171 )

References | Related Articles | Metrics

At present, the event extraction technology is usually the direct extraction of the event information of the text, ignoring the information structure of text, and the result is susceptible to the distribution of the words in texts. This paper analyzes the hierarchical concept structure of the text, and proposes a method of extracting the topic event information of news based on two-stage clustering and subdividing. This method can extract the hierarchical topic-event information, and reduce the influence of the information of the relevant events by the two-stage extraction of information words. This way optimizes the performance of the extraction. And experiment shows that this method can extract the topic event information of the text effectively.

Trajectory Adjoint Pattern Analysis Based on OPTICS Clustering and Association Analysis

HU Wen-bo, HUANG Wei, HU Guo-chao

2017, 0(12): 82-87. doi:10.3969/j.issn.1006-2475.2017.12.016

Asbtract ( 324 )

References | Related Articles | Metrics

At present, the mainstream trajectory adjoint pattern mining methods are usually for short time analysis, and most of them mine trajectory data once, rarely taking into account the relevant analysis between before and after discontinuous time, so the implicit adjoint pattern mining is not accurate. This paper analyzes the trajectory adjoint pattern, and puts forward an adjoint pattern mining method based on density clustering and association analysis. Firstly, the local pattern clusters in the trajectory data are mined, and the mining results are optimized by the association analysis of the local pattern clusters in discontinuous time slices. Experimental results show that the method can effectively and accurately mine the adjoint model of the trajectory.

Instance Alignment Algorithm Between Encyclopedia Based on Semi-supervised Co-training

ZHANG Wei-li1,2, HUANG Ting-lei1, LIANG Xiao1

2017, 0(12): 88-93. doi:10.3969/j.issn.1006-2475.2017.12.017

Asbtract ( 225 )

References | Related Articles | Metrics

Traditional supervised learning algorithms of instance alignment depend on large amounts of labeled data, and the feature representation methods are not suitable for data in encyclopedia. In view of these issues, a semi-supervised co-training instance alignment method is proposed. Instance alignment is modeled as a constrained binary classification problem. Then multiple features are extracted by fully utilizing different categories of existing information, including instance names, attributes, description texts and the critical discrete values extracted from the texts, such as temporal and numerical values. The features are divided into two relatively independent views, and two models are trained interactively on these two views, in order to learn more about the distribution of synonymous instances from the unlabeled data iteratively. Experimental results between two Chinese encyclopedia datasets show that the proposed method achieves a 84.3% F1-value on aligning instances, and outperforms other comparative methods, proving the effectiveness and applicability of the semi-supervised co-training instance alignment method.

Design of Competitive Data Distribution System Based on Middleware

MA Jia-yan, WANG Ping, SHEN Hong-wei

2017, 0(12): 94-97. doi:10.3969/j.issn.1006-2475.2017.12.018

Asbtract ( 164 )

References | Related Articles | Metrics

For complex structure of sports competition system, much scale and various kinds of data among the isomeric business terminals, achieving direct exchange of data is difficult. To solve the problem, competitive data distribution system based on middleware is proposed. Middleware encapsulates all the functions and methods of the terminal and data distribution center, which solves the heterogeneity problem of different terminals, increases the reliability and timeliness of data transmission. The experiment results show that the system can meet the data exchange among multiple terminals and the requirements of the competition.

Design of Power Monitoring and Management System Based on WeChat Mini Program

ZHANG Xue-yun, MU Yan, ZHANG Jiu-bo

2017, 0(12): 98-102+107. doi:10.3969/j.issn.1006-2475.2017.12.019

Asbtract ( 445 )

References | Related Articles | Metrics

In view of the current lower intelligence of engineering maintenance in power failure detection and needing artificial inspection, the power monitoring and management system based on WeChat Mini Program is put forward. Users can view real-time running state of the power monitoring points by WeChat Mini Program. The system uses Socket technology based on Java NIO and WebSocket technology based on HTML5 to achieve real-time acquisition and distribution of the power collectors’ data. System development cycle is short, software maintenance and upgrade are convenient. The measured results show that the system is stable and reliable, and it can meet the requirements of real-time monitoring of power points.

Model Construction for Commanding Process in Ship  Damage Control Based on T-Petri Nets

LI Kai, GUO Fu-liang, ZHOU Gang

2017, 0(12): 103-107. doi:10.3969/j.issn.1006-2475.2017.12.020

Asbtract ( 149 )

References | Related Articles | Metrics

The activities and procedures of the ship damage control process are analyzed.Based on the theory of T-Petri nets, the T-Petri nets model of ship damage control process is established. Through proper simplification and comparative study of the model, an improvement is proposed to reduce the average latency of the entire ship damage control process. The study provides a theoretical basis for the development of ship damage control simulation model.

A Forecasting Method of Fuzzy Time Series for Imbalanced Data

HUO Xu1, WU Tao 1,2

2017, 0(12): 108-110. doi:10.3969/j.issn.1006-2475.2017.12.021

Asbtract ( 204 )

References | Related Articles | Metrics

Fuzzy time series has been widely concerned since it was put forward. It is the most important to increase accuracy of prediction when using fuzzy time series to forecast. In order to make the forecast more accurate, firstly imbalanced data are classified, then prediction is made by fuzzy time series. At last the method is shown its practicability by experiments.

Battery SOC Prediction Based on Improved Fuzzy C-means Clustering and ANFIS

YANG Hui-jie, LIU Wei, HUANG Xian-li, LIU Shou-yin

2017, 0(12): 111-116. doi:10.3969/j.issn.1006-2475.2017.12.022

Asbtract ( 142 )

References | Related Articles | Metrics

The prediction of surplus capacity of battery can be used to reasonably control the battery charge and discharge situation and extend the battery life as the core of intelligent battery management system. However, the complicated influence factors of surplus capacity cause the difficulty of predicting accurately. To solve this challenging problem, a prediction algorithm based on the improved fuzzy C-means clustering and Adaptive Network-based Fuzzy Inference System is proposed. The initial fuzzy inference system is built by subtractive clustering and weighted fuzzy C-means clustering, then the hybrid algorithm is used to train the parameters of fuzzy system to establish a nonlinear prediction model. The simulation results show that the improved clustering algorithm not only solves the shortcomings of traditional fuzzy C-means clustering but also accelerates the convergence rate and the battery surplus capacity prediction model has a high prediction accuracy.

Design of Wireless Control System About Spray Line Based on PLC

SU Bai-yan1,2, TANG Min2, NI Jian-jun2

2017, 0(12): 117-121. doi:10.3969/j.issn.1006-2475.2017.12.023

Asbtract ( 210 )

References | Related Articles | Metrics

According to the surface treatment process of mechanical components, the overall plan of the production line about mechanical component surface polishing, spaying and drying was designed. The plan is consist of wireless control system composition and function planning, wireless control system program flow design, PLC selection analysis, I/O contact distribution design, wireless communication configuration, man-machine interface design. The whole system operates stably and efficiently.

Table of Content