Computer and Modernization

An Iterated Local Search Algorithm for Aircraft Recovery Problem

XIAO Wan-xia1,2, DONG Xing-ye1,2， LIN You-fang1,2

2019, 0(09): 1. doi:10.3969/j.issn.1006-2475.2019.09.001

Asbtract ( 145 )

PDF (847KB) ( 96 )

References | Related Articles | Metrics

Airlines are required to take corresponding measures to recover the flights when they cannot be implemented as original plan due to certain disturbations. This paper puts forward a flight recovery model based on the classical resource assignment model, taking into account five recovery strategies, i.e adjusting time, changing aircraft, adjusting connecting flight, cancelling flight and deadhead flight. The model minimizes total weighted cost and an iterative local search algorithm is designed. Firstly, the feasible solution is constructed by construct-repair heuristic method, and then the local search is carried out from it in a multi-neighborhood of the aircraft route. When the search is trapped into a local optimum, the current solution is disturbed, and then the local search is performed again from the disturbed solution. To accelerate the local search and reduce the probability of falling into the local optimal, a simulated annealing algorithm is used. Experimental results demonstrate that the proposed model and algorithm can recover the large-scale flight schedule that is affected in a short time.

An Assistant Decision-making Algorithm for Public Security Emergencies #br# Based on Case-based Reasoning and Rule-based Reasoning

CAI Sheng-sheng， BU Fan-liang

2019, 0(09): 7. doi:10.3969/j.issn.1006-2475.2019.09.002

Asbtract ( 194 )

PDF (861KB) ( 106 )

References | Related Articles | Metrics

In order to improve the speed of the decision-making of public security command department in the event of an emergency, this paper proposes an assistant decision-making algorithm based on case-based reasoning (CBR) and rule-based reasoning(RBR). The algorithm retrieves the most similar cases of the same level and type in the case base by using CBR according to the level, type and specific data in the emergency, such as the number of casualties, etc., and then modifies and optimizes the results of the retrieval cases using RBR to make them more suitable for the actual situation of the emergency. Finally, the algorithm is verified successfully by an example. This algorithm can provide reference for the construction of public security emergency plan and auxiliary decision-making platform.

Dongba Hieroglyph Feature Curve Simplification Algorithm Based on Discrete Curve Evolution

YANG Yu-ting1， KANG Hou-liang2

2019, 0(09): 12. doi: 10.3969/j.issn.1006-2475.2019.09.003

Asbtract ( 81 )

PDF (1450KB) ( 57 )

References | Related Articles | Metrics

Dongba hieroglyph is a kind of very primitive picture hieroglyphs， it has a characteristic of pictograph to express meaning by using pictures, but also has a feature of modern word to express the meaning with simple strokes. Therefore, starting from the structure of glyphic, we analyze the feature of Dongba hieroglyphs and combine with the research results of shape simplification in computer vision, and give a simplification algorithm for Dongba hieroglyphic feature curve. Through a large number of experiments, the algorithm can effectively remove the redundant and noise points, reduce the calculation of the similarity measure, and lay a solid foundation for the detection and recognition of Dongba hieroglyphics.

An Improved Optimal Clustering Algorithm Based on SEP Protocol

HU Nai-ping， WANG Dong， ZHOU Yan-ping

2019, 0(09): 17. doi:10.3969/j.issn.1006-2475.2019.09.004

Asbtract ( 199 )

PDF (1121KB) ( 98 )

References | Related Articles | Metrics

An improved optimal clustering algorithm based on SEP protocol is proposed. According to the cluster structure of SEP protocol, the network region is optimized by using the first election strategy with different competition time and residual energy factors, so as to balance the energy consumption in the region. The optimal number of cluster heads and the common distance factor are considered to select cluster heads. The single hop and cluster interval forwarding in the cluster is combined organically, the region head and the cluster head are transmited two-layer routing. Matlab is used to carry out simulation analysis of the improved algorithm. The results show that the improved algorithm based on SEP （P-SEP） effectively reduces the average energy consumption of sensor nodes and increases the life cycle of wireless sensor network compared with SEP and non-uniform clustering NHRPNC based on new clustering.

Prediction of Water Quality Based on Least Square Support Vector Regression

LIU Hong-mei1, XU Ying-lan1, ZHANG Bo2， LI Rong1

2019, 0(09): 31. doi:10.3969/j.issn.1006-2475.2019.09.006

Asbtract ( 138 )

PDF (699KB) ( 107 )

References | Related Articles | Metrics

The water quality system is an open, complex, and nonlinear dynamic system with time-varying complexity. Although some achievements have been made in the research of water quality prediction methods, there are still some difficulties such as prediction accuracy and computational complexity. Therefore, this paper proposes a water quality prediction algorithm based on least squares support vector regression. Support vector machine (SVM) is a kind of commonly used machine learning classification model, nonlinear data are mapped from low-dimensional space to high-dimensional space through the kernel function,
linear classification and regression are realized in the high dimensional space, the least squares support vector regression (LS-SVR) uses all samples to participate in regression fitting, which makes the regression loss function be no longer only related to a small number of support vector samples, but all samples participate in learning to correct error and improve the prediction precision. At the same time, by this algorithm, the standard SVR solving problem is transformed from inequality constraint conditions and convex quadratic programming problem into solving linear equations, which increases operation speed and solves the water quality prediction problem with nonlinear complex characteristics.

Construction and Application of Water Conservancy Information Knowledge Graph

FENG Jun, XU Xin, LU Jia-min

2019, 0(09): 35. doi:10.3969/j.issn.1006-2475.2019.09.007

Asbtract ( 878 )

PDF (1521KB) ( 155 )

References | Related Articles | Metrics

In recent years, knowledge graph technology has been widely used as a new method for describing concepts, entities and their relationships in the objective world. The use of knowledge graph can effectively expand the breadth of search results. At present, the keyword-based search technology adopted by the water conservancy industry is difficult to use the relationship between objects for information retrieval. To this end, this paper first proposes a knowledge graph construction method for water conservancy object data, which is used to realize the construction of water conservancy information knowledge graph. Then, a knowledge reasoning method based on inference rules is proposed, and the knowledge hidden in the knowledge graph of water conservancy information is used to realize intelligent data retrieval. Finally, the above technology is applied in the field of water conservancy, and the water conservancy information knowledge graph construction and retrieval system is realized. Through this system, the relationship between water conservancy objects can be effectively utilized, and the value of water conservancy information resources can be fully utilized.

Security Analysis for PLC Access Control

MIAO Si-wei1， YU Wen-hao1， YAO Feng2， GAO Jing3

2019, 0(09): 41. doi:10.3969/j.issn.1006-2475.2019.09.008

Asbtract ( 278 )

PDF (678KB) ( 133 )

References | Related Articles | Metrics

PLC is a very common ICS device that receives and processes data from input devices and controls the output devices. As the core equipment in industrial control systems, PLC has always been the target of choice for attackers. For example, the Stuxnet for ICS, its main target is PLC. Currently, most attacks against PLCs originate from unauthorized access by PLCs. In order to improve the security of PLC equipment, this paper studies the PLC access control problem and discusses several access control models. The password-based access control model is the focus of this paper. Through the traffic analysis and violent cracking methods, this paper analyzes the security of password-based access control mechanism, shows how to store passwords in PLC memory, how to intercept passwords in the network, how to crack passwords, and so on. And through these vulnerabilities, this paper launches more advanced attacks on the ICS system, such as replay, PLC memory corruption, and so on. Finally, in view of the above security issues, this paper gives recommendations and summary of security protection.

Cloud platform Based Blockchain Networking and Data Storage Mechanism

YUAN Min-fu, LI Yin， CHEN Sheng-jian， ZHENG Xiang-wei

2019, 0(09): 46. doi:10.3969/j.issn.1006-2475.2019.09.009

Asbtract ( 285 )

PDF (1293KB) ( 168 )

References | Related Articles | Metrics

In order to solve the problem of low transaction confirmation efficiency and low storage space utilization in the process of data storage and sharing on the blockchain, this paper proposes a blockchain networking scheme based on cloud platform deployment and its adapted data shared storage solution. Firstly, by decomposing and reconstructing the traditional fully connected blockchain network, a subnet-based non-all-connection networking scheme is formed, which limits the scope of transaction confirmation to a limited number of nodes. Secondly, through managing the data sharing mechanism of cloud computing which divides the data into three levels: transaction data-sensitive state data-non-sensitive state data, the node only saves the transaction data related to the state transition to ensure the non-destructive modification, and the state data is supported by the cloud. The calculated features can enable different levels of shared storage and maximize storage space. The experimental results show that the scheme can provide new ideas for the storage and sharing of trusted data in the blockchain.

A Topology Discovery Method for Software-defined Mobile Ad Hoc Networks

GENG Lan-lan1, SUN Yan-tao2, DAI Song1

2019, 0(09): 53. doi:10.3969/j.issn.1006-2475.2019.09.010

Asbtract ( 180 )

PDF (1464KB) ( 115 )

References | Related Articles | Metrics

It’s difficult for mobile Ad Hoc networks based on traditional distributed networking to meet the high requirements of complex business demand for network QoS and security. The proposal of SD-MANET, which is designed for the mobile Ad Hoc networks based on software defined network, provides an effective solution to this problem. In SD-MANET, topology discovery is a prerequisite for controller to perform traffic scheduling and security control. This paper proposed a topology discovery method for SD-MANET. The main idea is to use connected dominating set algorithm to generate the backbone network in which backbone nodes report local topology information to the controller through the uplink path, then the controller calculates the whole network topology based on the collected neighbor information. This method reduces the extra overhead during the process of topology information by limiting the number of nodes which is responsible for reporting local topology information to controller. Simulation results illustrate that, this method can accurately generate and maintain the network topology with a less control overhead.

Hot Network Information Extraction Based on Key Nodes

LI Pan1, LI Yi-guang2, XU Chun1

2019, 0(09): 60. doi:10.3969/j.issn.1006-2475.2019.09.011

Asbtract ( 144 )

PDF (971KB) ( 111 )

References | Related Articles | Metrics

Firstly, the paper demonstrates that the key nodes of social networks play an important role in the generation, dissemination and guidance of hotspot information. On this basis, the hotspot information of key nodes will be processed as follows: Firstly, the word segmentation processing is performed on a single piece of information, and the set of word segmentation is obtained, and the meaningless word segmentation words are filtered out; Secondly, the obtained segmentation words are spliced renewedly, and the meaningless splicing sequences are filtered out, we will obtain a summary of the single hotspot information; Thirdly, merging the hotspot information summary of the same meaning, and obtaining the hotspot information summary set, which is the network hotspot information.In this way, the accuracy and comprehensiveness of hot spot information extraction are greatly improved, and good verification results are obtained on social networks.

New Radio and Television Program Collaborative Recommendation Process Based on TF-IDF

XIE Hao-ran1, WEI Wei2, YANG Zhi-hui3, DENG Ju-zhi1, GE Kun-peng1

2019, 0(09): 65. doi:10.3969/j.issn.1006-2475.2019.09.012

Asbtract ( 156 )

PDF (1500KB) ( 155 )

References | Related Articles | Metrics

With the rapid development of Internet technology and application expansion, triple play (Internet, telecommunication network, broadcast TV network) has brought development opportunities for traditional broadcast TV media. However, with the increase of data size, the existing recommendation algorithm does not meet the expected requirements for the accurate recommendation of many “category” broadcast TV users, and has obvious deficiencies. In this paper, based on the similarity between users and the similarity between products, Pearson correlation coefficient, TF-IDF-based cosine similarity and collaborative recommendation are used to construct two algorithm flows that can be accurately recommended for new broadcast TV users, and can get accurate classification and accurate delivery of products.

An Element of UWB Phased Array Antenna

HOU Jian-chun1,2， ZHAO Feng-jun2， WU Liang2， YUAN Cheng1,2

2019, 0(09): 72. doi:10.3969/j.issn.1006-2475.2019.09.013

Asbtract ( 243 )

PDF (2952KB) ( 112 )

References | Related Articles | Metrics

To improve the ultra-wideband and wide-angle scanning performance of phased array antennas, an all-metal Vivaldi antenna element with ultra-wideband characteristics is designed. The model of the Vivaldi antenna is built and its size is optimized with the simulation software CST. Finally, the VSWR is less than 2 in the bandwidth from 2 to 18 GHz. To solve the problem of scan blindness, an innovative structure with a thicker bottom is proposed, which changes the current path and eliminates the scan blindness, thus achieving a wide scanning angle of ±45° in the whole bandwidth. The results indicate that the antenna has ultra-wideband characteristics and wide scanning angle. So it can be applied as UWB phased array antenna element.

An Anomaly Detection Approach on Servers Traffic in Smart #br# Grid Based on Breadth Learning Algorithm

YANG Yong-jiao， QIU Yu， ZHAN Li-chao

2019, 0(09): 77. doi:10.3969/j.issn.1006-2475.2019.09.014

Asbtract ( 152 )

PDF (2280KB) ( 127 )

References | Related Articles | Metrics

The information network of the power system is an important part of the long-term continuous and effective operation in power industry. The complex network structure between power network and information network in the smart grid brings great challenges to the anomaly detection on network flow in information communication network security. Traditional machine learning algorithms and newly developing deep learning algorithms often have shortcomings such as low detection accuracy and poor real-time performance in solving the problem of network flow anomaly detection, while the network anomaly detection process that combines breadth learning and control chart has the advantages of faster training speed and more accurate detecting results. These advantages can meet the needs of anomaly detection requirement in smart grid to a certain extent, thereby achieving the purpose of improving the security of information network.

Fine-grained Image Recognition Based on Deep Neural Network #br# with Amplified Multi-attention Mechanism

ZHOU Chen-yi, FENG Yu, XU Yi-bai, LU Shan

2019, 0(09): 83. doi:10.3969/j.issn.1006-2475.2019.09.015

Asbtract ( 147 )

PDF (1438KB) ( 131 )

References | Related Articles | Metrics

Most of the existing fine-grained image recognition methods based on attention mechanism do not consider the local correlation of the target. In addition, most of the previous methods use multi-stage or multi-scale mechanism, which leads to low efficiency and difficulty in end-to-end training. This paper proposes that the relationship between different parts of different input images can be adjusted. The method based on the attention mechanism of the above ideas is to learn the characteristics of each focus area of each graph. Then the amplified multi-attention method is used to enhance the effect, so that the same category of images have similar attention mechanism, and different categories of images have different attention mechanism and can also be trained end-to-end.

A SAR Ship Detection Method Based on Improved Faster R-CNN

YUE Bang-zheng1，2, HAN Song2

2019, 0(09): 90. doi:10.3969/j.issn.1006-2475.2019.09.016

Asbtract ( 308 )

PDF (3488KB) ( 423 )

References | Related Articles | Metrics

SAR ship detection plays an important role in marine traffic monitoring. Traditional SAR target detection algorithms are mostly based on contrast difference between target and background clutter, whose performance is limited especially in complex scenes, for instance coastal areas. In order to improve the detection performance in complex scenes, a SAR ship detection algorithm based on Faster R-CNN is proposed in this paper. After analyzing the influence of feature resolution on detection performance, a feature extraction network suitable for SAR ship target detection is designed based on the idea of VGG and dilated convolution to improve the detection capability of small ship targets. In addition, a small size anchor is selected according to the target size distribution in the sentinel-1A dataset. And by removing the redundant anchor, the detection speed is improved. Experiments on the sentinel-1A dataset demonstrate that the proposed algorithm can detect ship targets in SAR images of complex scenes with high speed and accuracy.

Real Time Rendering of Human Face Skin Based on BSSRDF Model

CAO Ying， LIU Hui-yi， QIAN Su-bin

2019, 0(09): 96. doi:10.3969/j.issn.1006-2475.2019.09.017

Asbtract ( 246 )

PDF (1793KB) ( 109 )

References | Related Articles | Metrics

In this paper, the rendering based on the three-layer material model, and the scattering effect of light on the surface of skin is simulated by bidirectional surface scattering reflectance distribution function (BSSRDF). A approach is proposed for real-time rendering of human skin, which uses the Radial Basis Function neural network to fit the subsurface scattering profile. The training data for neural network are precomputed by offline render. Experimental results show that the approach is capable of reducing the redundant training data, evaluating fast and rendering well.

Research and Development of Mould Teaching System Based on Virtual Reality Technology

WEI Ke-jun

2019, 0(09): 102. doi:10.3969/j.issn.1006-2475.2019.09.018

Asbtract ( 124 )

PDF (1939KB) ( 88 )

References | Related Articles | Metrics

This paper describes a virtual reality technology, designs a virtual reality system for mould teaching. The teaching system is customized for mould assembly and try-out. It is designed in accordance with the working conditions and operation requirements of the mould assembly process, and ensures the friendliness and stability.A database for assembly and try-out of the large covering parts is built. Users can take efficient and accurate implementation of the design concept in the process of operation based on virtual reality environment, and can get rid of the issue that have idea but can’t be realized in conventional CAD software quickly. If this system is applied to the teaching system, students can quickly acquire relevant knowledge and increase their interest, which fundamentally solves the boring of mould teaching.

An Optimized Sub-aperture PACE Motion Compensation Method Based on Polynomial Fitting

YUAN Yan1， LI He-ping2

2019, 0(09): 106. doi:10.3969/j.issn.1006-2475.2019.09.019

Asbtract ( 138 )

PDF (5163KB) ( 70 )

References | Related Articles | Metrics

Platform of airborne Synthetic Aperture Radar (SAR) is easily influenced by environmental factors in flight, which would introduce phase error and lead to image blurring. As an image autofocus algorithm, even though PACE algorithm have advantages on high robustness and can estimate high-frequency phase error, it’s limited in high real-time demanded situation by its computation complexity. So we proposed a new optimized PACE algorithm which combined the primary PACE algorithm with a sub-aperture polynomial fitting PACE algorithm to optimize the processing efficiency in this article and make a detailed explanation of the principle and realization of this optimized PACE algorithm. Our experiment on real data proved that the new optimized PACE algorithm can achieve the same compensated image accuracy in less processing time compared with the primary PACE algorithm.

Research on Car’s Suspension Performance Based on Computer Virtual Prototype Technology

CHEN Peng-fei1，2， FENG Jin-zhi1，2， LIU Shu-fan1，2， WANG Bin1，2

2019, 0(09): 112. doi:10.3969/j.issn.1006-2475.2019.09.020

Asbtract ( 128 )

PDF (4975KB) ( 72 )

References | Related Articles | Metrics

The load spectrum of the test loop road for maneuverability and smoothness of Guangde test field was collected. The load spectrum of the road was edited and processed with nCode software to obtain the load spectrum of random short-wave road, asphalt vibration belt and other road surfaces which import into ADAMS for suspension dynamic simulation. Because the traditional system parameter design based on static K&C characteristic analysis is not enough to meet the performance requirements of the whole vehicle under complex working conditions, while the dynamic K&C test has more accurate response results, which can better reflect the actual use state of the suspension. Finally, the dynamic K&C test bed was used for the test, and the results of dynamic, static and bench tests were compared to verify that the dynamic K&C simulation results were closer to the test results and had more accurate simulation results. Therefore, the study of dynamic characteristics of automotive suspension is helpful for engineering applications.

Connecting Plate Screw Loosening Recognition of Medium #br# and Low Speed Maglev Contact Rail Based on YOLO v2 and OTSU

CHEN Jian-xiong， NING Hang

2019, 0(09): 118. doi:10.3969/j.issn.1006-2475.2019.09.021

Asbtract ( 129 )

PDF (2051KB) ( 74 )

References | Related Articles | Metrics

To deal with the screw looseness of connecting plate of medium and low speed maglev contact rail, a recognition method based on YOLO v2 network and OTSU is proposed. First, YOLO v2 network is used to locate the connecting plate. Then, the head of the screw is further localized on the connecting plate area. This paper uses OTSU to segment the screw head and the edge of the connecting plate. Finally, the status of the screw could be judged by the distance from the head of the screw to the edge of the connecting plate which is normalized by the width of the screw head. The experimental result shows that the method can accurately identify the looseness of the connecting plate screws.

A Detection Method of Medicine Box and Vacancy on Conveyor Based on Faster R-CNN Model

ZHANG Rui-xun1， SHAO Xiu-li2， LUO Sheng-li2， ZHOU Hong-yu2

2019, 0(09): 122. doi:10.3969/j.issn.1006-2475.2019.09.022

Asbtract ( 202 )

PDF (2029KB) ( 97 )

References | Related Articles | Metrics

In order to find the congestion of the conveyor, the pharmaceutical company needs to locate the medicine boxes and vacancies on the conveyor, but the manual method is of inefficiency and has poor real-time performance. In this context, combining with the Faster R-CNN model, a target detection method is proposed. In this method, training set and testing set are constructed based on the conveyor images, then, the training set is processed through the ZFNet convolutional neural network to calculate the convolution characteristics, and the RPN (Region Proposal Network) is used to generate accurate candidate regions. On this basis, the classification and regression based on the Faster R-CNN model are performed on the candidate regions, and the rectangular boxes of the kit and the vacancy are calculated. At last, the trained model is tested by using the testing set to label the target and to calculate the probability. The result shows that the method has good detection accuracy for the conveyor belt target.

Table of Content