Table of Content

26 October 2018, Volume 0 Issue 10

Previous Issue    Next Issue

A Rank-based Q-routing Algorithm

WANG Yue-juan1, ZHANG Su-ning1, WU Shui-ming1, ZHU Fei2

2018, 0(10):  1.  doi:10.3969/j.issn.1006-2475.2018.10.001

Asbtract ( 242 )  

References | Related Articles | Metrics

How to achieve efficient routing in the dynamical and complex network is one of current research hotspots. Q-learning, a frequently used reinforcement learning method, which can solve the optimal control problem in unknown environment by continuously interacting with the environment, is able to achieve on-line learning task. A rank-based Q-routing algorithm (RQ routing) is proposed. RQ routing algorithm, taking Q-learning algorithm as learning framework, and preserving the efficiency of the Q-routing algorithm, introduces the rank function that can be dynamically calculated to represent the priority of the current state in the scene, so as to solve the optimal solution of the route selection, which can avoid long waiting queue, reduce network congestion and improve the transmission speed. The rank function in the RQ routing algorithm is flexible. People can use different rank functions to meet the needs of various scenes, ensure the better generalization ability of the algorithm, and overcome the inflexibility of the traditional Q-routing application scene. The experiment verifies the effectiveness of the algorithm.


Global Center Fast Update Clustering Algorithm Based on Spectral Clustering

ZOU Chen-song1, LIU Song2

2018, 0(10):  6.  doi:10.3969/j.issn.1006-2475.2018.10.002

Asbtract ( 159 )  

References | Related Articles | Metrics

Aiming at the problems of high iteration number and long computation time in the clustering process of high dimensional data, an improved clustering algorithm is proposed. The algorithm first uses spectral clustering to reduce the dimension of samples, then selects k data objects with the end to end and the largest distance product as the initial clustering center, in the update process of cluster centers, selects data objects nearest to cluster mean as cluster centers. And other data objects are divided into corresponding clusters according to the minimum distance, iterated iteratively until convergence. The experimental results show that the Rand index, Jaccard coefficient and Adjusted Rand Index of  the new algorithm are better than K-means algorithm and other 3 kinds of improved clustering algorithms. In terms of operational efficiency, the new algorithm has shorter clustering time and fewer iterations.

K-means-based KDJ Integrated Analyzing Methods for Stock Transactions

LI Na, MAO Guo-jun, DENG Kang-li

2018, 0(10):  12.  doi:10.3969/j.issn.1006-2475.2018.10.003

Asbtract ( 278 )  

References | Related Articles | Metrics

Stock technical analysis is one of the means of securities analysis. There are two main problems in the current stock technical analysis. Firstly, one technical index is always analyzed in a dimension, and so the general investors are difficult to put them together to form an investment decision; secondly, any single technical index has its limitations, and so they need been integrated to make better investment decisions. In response to these major issues, this article discusses how to use the data mining technology for multi-dimensional comprehensive analysis of stocks. First of all, it analyzes the problems that data mining can solve in stock analysis and its possible challenges. Secondly, a stock selection model based on data mining clustering methods is proposed. Finally, using the 1364 Shanghai Stocks, some empirically analyzing results are given.


Lawyers Recommendation Algorithm and Improvement Scheme Based on Eigenvalue

WANG Hai-peng, ZHENG Yang-fei

2018, 0(10):  18.  doi:10.3969/j.issn.1006-2475.2018.10.004

Asbtract ( 176 )  

References | Related Articles | Metrics

With the development of the country’s legalization process, the selection of suitable lawyers becomes increasingly important for citizens to safeguard their rights in accordance with the law. However, the traditional lawyer industry lacks an objective and fair evaluation mechanism, and the judgement of the lawyer’s ability mainly comes from the evaluation of legal professionals. The user can only select lawyers extensively with a part of the luck component. Based on the traditional lawyers recommendation algorithm, this paper proposes an improvement plan. The parameter of degree of difficulty is introduced into the feature value of the lawyers evaluation, and the lawyers management system of the Beijing Municipal Bureau of Justice is added with the lawyers recommendation function, aiming at selecting the lawyer for the user so as to provide more objective references and help.

Model and Approach for Extracting Key Elements #br# From Topic Information in Intelligence Analysis

TIAN Li

2018, 0(10):  22.  doi:10.3969/j.issn.1006-2475.2018.10.005

Asbtract ( 273 )  

References | Related Articles | Metrics

Based on analysis on the characteristics of the topic information and according to principles of statistics, the paper puts forwards a mathematical model for space of intelligence topic information by means of the constructive theories of vector space and random event space; strategy of retrieving components from topic information is proposed and design rule of constructing a maximum approximate space of topic information is given. The paper also raises a concrete method to extract the keywords from topic information. The method consists of 3 parts with 9 steps, can extract the keywords with maximal common views in topic information that is built from samples of with universality and representativeness. In the end, the paper presents an example that mines the key elements for a topic of scientific research from the topic information of choosing a scientific subject.


User-defined Function Extending in a Complex Event Processing Language

LIU Jing-yan, LIAO Hu-sheng, GAO Hong-yu

2018, 0(10):  26.  doi:10.3969/j.issn.1006-2475.2018.10.006

Asbtract ( 135 )  

References | Related Articles | Metrics

When a complex event processing language is used in the stock analysis, fault monitoring and other industries, the demand for fine-grained query is increasing. To meet these requirements, this paper extends user-defined function that supports fine-grained data processing in a complex event processing language CEStream. Functions implement fine-grained processing by processing data one by one and function overloading. In addition, the function provides the user with the encapsulation function of the statement and improves the reusability of the language. The experimental results show that the extended function enables the language to support more fine-grained query requirements. At the same time, using the function when completing the same query requirement is basically the same as using the original statement.

Application of Fatigue Driving Detection Based on Wavelet Transform and Multiple Indicators

WANG Hai-yu1, WANG Ying-long1, MIN Jian-liang2, HU Jian-feng2

2018, 0(10):  32.  doi:10.3969/j.issn.1006-2475.2018.10.007

Asbtract ( 177 )  

References | Related Articles | Metrics

In order to study EEG for fatigue driving, this article collects and extracts data from experiments using wavelet transform. This article is based on the subjects signs and brain electrical device collection pretreatments. The mean amplitudes of four wave bands of α wave, β wave, θ wave, and δ wave, and other indicators (α+β)/β,α/β,(δ+α)/(α+β),(α+β)/θ,  are extracted by the wavelet transform experiment, total eight synthetic indicators are integrated into EEG characteristic parameters. The experiment extracts principal component feature information with a contribution rate of 90% or more by KPCA to form characteristic set, and the feature information is input into least square support vector machine(LSSVM). The KPCA-LSSVM prediction model is established and compared with other four model tests. Finally, the model obtains the average correct rate of 89.47%. The comparative experiment proves the effectiveness of the experiment and its advantages in data processing speed.

Energy Consumption Prediction Model of Air-conditioning System #br# in Subway Station Based on ISOA-LS-SVM

GAO Xue-jin1,2,3,4, FU Long-xiao1,2,3,4, WU Cui-xia1,2,3,4, WANG Pu1,2,3,4

2018, 0(10):  36.  doi:10.3969/j.issn.1006-2475.2018.10.008

Asbtract ( 146 )  

References | Related Articles | Metrics

To improve the prediction accuracy of energy consumption of air conditioning system in subway station, it is an effective method to establish energy consumption forecasting model by Least Squares Support Vector Machines (LS-SVM). However, LS-SVM is difficult to determine the optimal model parameter value in dealing with regression problem for large datasets, which affects the fitting precision and generalization ability of the model to a large extent. An Improved Seeker Optimization Algorithm (ISOA) is proposed to optimize the model parameters in the LS-SVM modeling process by introducing an improved algorithm from search step and search direction. The energy consumption forecasting model based on ISOA-LS-SVM is applied to the training platform of subway in a school of Beijing. The results show that the model can accurately predict the energy consumption of the system. Compared with the grid search method, the particle swarm algorithm and the traditional population search algorithm, the LS-SVM is improved in speed and precision.

Predicting Crop Water Requirements Based on Particle Swarm Optimization #br# and Least Square Support Vector Machine

SHANG Zhi-gen, DUAN Xiao-hui

2018, 0(10):  44.  doi:10.3969/j.issn.1006-2475.2018.10.009

Asbtract ( 138 )  

References | Related Articles | Metrics

To improve the accuracy of crop water requirement prediction, a model based on Least Square Support Vector Machine (LS-SVM) optimized by Particle Swarm Optimization (PSO) is put forward. Relative humidity, air temperature,  solar radiation and wind speed are considered as input variables. A nonnegative linear combination of polynomial kernel function and radial basis kernel function is used as the kernel function of LS-SVM. PSO and cross validation are applied to optimize the parameters of LS-SVM. Experimental results indicate that LS-SVM optimized by PSO outperforms neural network and random forest. It can be used for water-saving irrigation, and has good application value.

A Color Image Steganography Algorithm Based on Modulus Computation

XIAO Wen-guo1, GE Hua-yong1,2, PENG Yang-yang1

2018, 0(10):  48.  doi: 10.3969/j.issn.1006-2475.2018.10.010

Asbtract ( 88 )  

References | Related Articles | Metrics

Since the 21st century, with the development of computer science and the perfection of digital-multimedia communication, people pay more attention to information security, image steganography technology is developed rapidly as a means to ensure information communication security. This paper proposes a color image steganography algorithm that utilizes the periodic features of model operation for information encryption. This algorithm introuduces a new steganography function and calculates the differences between the original image data and the secret data, and is combined with steganography function to get the amount of modification to achieve information hiding. This method realizes the information encryption and ensures a high embedding rate on the premise of security. Sufficient experiments show this algorithm has good image visual quality and information security performance, and a higher and more flexible embedding rate. Therefore, it can replace most color steganography algorithms.


Weak Target Robust Real-time Tracking Algorithm Based on SIFT and YOLO

LIU Yuan, YAO Wen-ming

2018, 0(10):  53.  doi:10.3969/j.issn.1006-2475.2018.10.011

Asbtract ( 196 )  

References | Related Articles | Metrics

This paper proposes a robust real-time tracking algorithm for weak targets based on SIFT and YOLO. It can continuously and steadily track the target under complex conditions such as dramatic scene changes and object occlusion.The implementation of the algorithm is based on a reasonable algorithm architecture design, uses YOLO to select candidate targets, and uses SIFT to select the tracked targets from the candidate targets.The tracking algorithm proposed in this paper not only meets the real-time performance, but also obtains better experimental results than KCF and CamShift in the normal test set, the target existence occlusion test set, and the camera rotation test set.The results show that the tracking algorithm proposed in this paper has outstanding performance in solving problems such as target occlusion and dramatic scene changes.

Space Plant Image Segmentation Based on Deep Features Fusion

CAO Jing-kang1, DUAN Jiang-yong2, MENG Juan2

2018, 0(10):  58.  doi:10.3969/j.issn.1006-2475.2018.10.012

Asbtract ( 147 )  

References | Related Articles | Metrics

As a key research in space science, space plant experiment usually obtains massive plant sequence images. The traditional processing methods are mostly observed manually for further analysis. This paper proposes a space plant image segmentation algorithm based on multi-scale deep feature fusion. This method uses a full-convolution deep neural network to extract multi-scale features, and hierarchically fuses features from deep to shallow to achieve pixel-level segmentation of plants. The hierarchical features fuse semantic information, middle layer information, and geometric features to improve segmentation accuracy. Experiments demonstrate that the method performs well in segmentation accuracy and can automatically extract useful information in space plant experiments.

Automatization of Vehicle License Tag Copying Based on Quad-rotor Unmanned Aerial Vehicle

LI Xiao-long, CHEN Guo-liang, GE Kai-kai

2018, 0(10):  63.  doi:10.3969/j.issn.1006-2475.2018.10.013

Asbtract ( 133 )  

References | Related Articles | Metrics

In view of the low efficiency of traditional vehicle license tag copying, a method of automatic vehicle license tag copying is proposed based on quad-rotor UAV helicopter. UAV is used to collect a large number of vehicle overlook maps of vehicle. The overlook maps are preprocessed and lower sampled. Then  the gradient histogram feature of the vehicle image is extracted. The image features are input into the convolution neural network for training. Vehicle identification model is obtained after training. The model is used to recognize vehicles. According to the shape feature of vehicle, vehicle attitude is estimated. The position and angle of the camera on the UAV are calculated according to the position and orientation of the vehicle. UAV experimental platform is built to test system of automatic vehicle license tag copying. The experimental results show that the UAV can independently capture the clear license tag image of vehicle. Automatization of vehicle license tag copying is realized.

Identifying Transportation Mode Based on Improved LightGBM Algorithm

XIONG Su-sheng1，2

2018, 0(10):  68.  doi:10.3969/j.issn.1006-2475.2018.10.014

Asbtract ( 646 )  

References | Related Articles | Metrics

Aiming at the low accuracy of the motorized traffic mode identification in the residents traffic mode identification, this paper proposes an improved LightGBM algorithm combined with a traffic mode classification method of mobile terminal. This method filters the data set, selects the time domain and frequency domain features of three kinds of sensor data: triaxial accelerometer, gyroscope and magnetometer as the pattern recognition features, and uses the Filter correlation measure CFS algorithm to sort the scores according to the features, and selects the optimal feature set. The recognition process adopts the K-lightGBM recognition algorithm based on the residents travel rules and the first-order hidden Markov chain. At the same time, some machine learning algorithms are used for comparison experiments. The experimental results show that this method not only can identify multiple modes of traffic, but also has a high average accuracy of residents traffic pattern recognition, reaching 94%.

Method of Off-line Signature Recognition Based on Improved LPP and ECOC-SVMS

JIANG Qing-yun

2018, 0(10):  74.  doi:10.3969/j.issn.1006-2475.2018.10.015

Asbtract ( 160 )  

References | Related Articles | Metrics

A method of off-line signature recognition based on locality preserving projection(LPP) and Error Correcting Output Code support vector machine(ECOC-SVMS) is proposed. After selecting multiple features from preprocessed signature images, high dimensionality feature vectors are constructed. Then, an improved LPP method is used to extract effect features and reduce dimensionality. A multi-classification classifier based on Hadamard code ECOC-SVMS is used to deal with signature recognition problem. A proximate probability output of SVMS is employed to improve the decoding processing of ECOC framework to enhance the performance of multi-classification. The experiment result shows that the proposed method is feasible and effective.

Intelligent Equipment Maintenance and Management Platform#br# Based on Microservice Architecture

WANG Yi-chao1, WANG Yu-mei2

2018, 0(10):  79.  doi:10.3969/j.issn.1006-2475.2018.10.016

Asbtract ( 165 )  

References | Related Articles | Metrics

In order to meet the requirements of the equipment information supervision of the army, this paper proposes an intelligent equipment maintenance and management platform based on microservice architecture. Using the subdomain virtualization technology and the terminal RFID technology, and so on, a monitoring and management platform of the whole link of the equipment data is realized, and the typical software deployment and the use mode are put forward. By building commercial and autonomous controlled virtual clusters, the problems of regional decentralization, safety and reliability of equipment maintenance and management are solved, and the effectiveness and efficiency of equipment maintenance and management are improved.

High-risk Warehouse Wireless Monitor System Based on #br# Software Defined Wireless Sensor Network

GUO Xin, YAN Lian-shan, LI Hong-zhe, ZHANG Xiao-wei

2018, 0(10):  84.  doi:10.3969/j.issn.1006-2475.2018.10.017

Asbtract ( 230 )  

References | Related Articles | Metrics

Aiming at the wide-region distribution and high complexity of the high-risk warehouse, a safety monitoring system based on the software defined wireless sensor network (SD-WSN) is designed.The system consists of wireless sensor nodes, controller and monitor software.In order to monitor environment inside the warehouse, the wireless sensor nodes are used for data acquisition by matching the flow table, the routing protocols and the sensor tasks can be configured by the central controller, environment data can be collected and graphically displayed by monitor software. In addition, monitor system can formulate sensor tasks through the interfaces provided by the controller. The reconfiguration of sensor nodes can be realized by updating the flow table. The testing results indicate that the designed system is programmable, can monitor the various safety indicators, and has good communication reliability.


Information Quality Evaluation of Command and Control Systems at Architecture Level

WANG Xiang， FAN Zhi-qiang， XU Luo

2018, 0(10):  89.  doi:10.3969/j.issn.1006-2475.2018.10.018

Asbtract ( 93 )  

References | Related Articles | Metrics

As command and control(C2) systems become larger and more complex, architecture plays a more essential role during the whole life-cycle of the systems. Thereby, capability evaluation of C2 systems at architecture level becomes necessary and important for improving the system capability at the stage of architecture design. This paper proposes a method for information quality evaluation of C2 system at architecture level. First, the information quality model is proposed, including measures of information quality and methods of weights assignment and synthesis of the measures. Second, a framework for systematically conducting architecture-level information quality evaluation is provided. Finally, based on the framework, an experiment is conducted to validate the proposed information quality evaluation method. Experiment results show that the proposed method can effectively evaluate the information quality based on architecture models of C2 systems, which can help to identify key factors of impacting information quality and improve the system capability at the stage of architecture design of C2 system.

Application of Automated Test Technology in FADEC Control Software

XIONG Bo, BAI Han, HAO Xiao-lei

2018, 0(10):  94.  doi:10.3969/j.issn.1006-2475.2018.10.019

Asbtract ( 155 )  

References | Related Articles | Metrics

It is a big chanllenge to develop regression test fastly and effectively because engine control software have features of complicated configuration, high frequency of change and long maintenance cycle. This paper focuses on how to bulid a ATP(Automation Test Platform), which can excute test case, analyse result and test coverage automatically. And then it improves the quality through automatic regression test based on the ATP.

Frequency Hopping Spread Spectrum Based on ZigBee Wireless Transmission

GUO Hao-xing， YAN Lian-shan， YE Jia

2018, 0(10):  101.  doi:10.3969/j.issn.1006-2475.2018.10.020

Asbtract ( 193 )  

References | Related Articles | Metrics

Although ZigBee technology makes fast networking more convenient, its network security completely depends on the network keys and lacks effective security configuration options, which makes the leak of keys and the lack of user information security. Based on frequency hopping spread spectrum technology, a ZigBee transmission method is proposed, which makes it difficult to track and catch the information of keys and enhances the ZigBee network security. Based on the proposed method, the model of QPSK frequency hopping spread spectrum transmission system is established and verified by simulation. The simulation results show that the QPSK wireless transmission system with frequency hopping spread spectrum technology has a good reliability.

Application of Mobile Payment in Subway Ticket Vending Machine System

OU Jin-rong, XU Jun-shan

2018, 0(10):  106.  doi:10.3969/j.issn.1006-2475.2018.10.021

Asbtract ( 161 )  

References | Related Articles | Metrics

In order to enrich the mode of ticket payment for passengers and improve the travel experience, it is necessary to introduce the mobile payment function into the subway Ticket Vending Machine(TVM) system. This article analyzes the software system framework of Metro vending machine, designs the function of mobile payment, and puts forward the combination form and workflow of mobile payment and Metro vending machine. The Internet Ticket Vending Machine designed according to this scheme is applied to the Nanjing Metro Auto Fare Collection system, and the feasibility of the scheme is verified through testing and acceptance. It has a certain reference value for the development of the mobile payment function of the Ticket Vending Machine in other cities.


Dynamic Opportunity Routing Algorithm Based on Reservation Mechanism

GUAN Xue-ming, QI Xian-fei, MA Yao-zhi

2018, 0(10):  111.  doi:10.3969/j.issn.1006-2475.2018.10.022

Asbtract ( 178 )  

References | Related Articles | Metrics

This paper focuses on the research on the opportunistic routing in wireless Mesh network. Traditional opportunistic routing can lead to problems like a low rate of bandwidth utilization and poor load balancing, and the selection and ranking of candidate node can also bring burden to the network. A dynamic opportunistic routing algorithm based on the reservation (BRDOA) is proposed in order to solve the problems above. Some nodes are set on the forwarding node through studying the candidate node state, thereby reducing the network burden brought by the candidate node. The results of the experiment also show that the algorithm can effectively improve the network throughput, shorten the delay, and remarkably enhance the performance of the wireless network QoS.

Auction-based Resource Match Algorithm in Data Centers

WANG Xu1,2, NI Hong2, HAN Rui2

2018, 0(10):  114.  doi:10.3969/j.issn.1006-2475.2018.10.023

Asbtract ( 120 )  

References | Related Articles | Metrics

Hosts and workload in data-centers are heterogeneous, resulting in imbalanced utilization of host resources. This imbalanced utilization then results in poor overall utilization, waste of host resources and high operating cost. Aiming at the task assignment problem of data-centers in cloud platform, where different resources are not utilized evenly, a virtual machine allocation and migration algorithm based on continuous double auction is proposed. On the one hand, the algorithm uses a variety of heuristics to filter hosts and virtual machines, placing overloaded and underloaded hosts in data-center auction market. On the other hand, by rationally constructing pricing strategies and auction trading strategies, a complete auction process is formed. Furthermore, in order to solve the problem of multi-resource transactions, a trading strategy of auction process based on resource matching is proposed. Simulation experiments show that the proposed method can effectively match the resources of the data center host and the virtual machine. By introducing the resource matching, the proposed algorithm can balance the utilization of each kind of resource and improve the overall resource utilization.

Determination of Structure Soundness for Service Processes Based on Petri Net

GAO Qiang1, HU Qiang2

2018, 0(10):  122.  doi:10.3969/j.issn.1006-2475.2018.10.024

Asbtract ( 112 )  

References | Related Articles | Metrics

Determination of structure soundness is an important research issue in the domain of service composition. The existing research focuses qualitative analysis of structure soundness and cannot accurately evaluate the structure quality of service processes. To address such problem, a hierarchy evaluation method for structure soundness based on Petri net is proposed. The four-level divided principle of structure soundness for service processes is put forward and its determining algorithm is also presented. Finally, application instances with the background of online-trade service processes are given to show how to judge the different level of structure soundness and the effectiveness of the proposed method.