With rapid development of network technologies, many universities have realized coursework electronically in many courses. But students copy electronic coursework more and more commonly. This paper proposes two methods of anti-plagiarism plagiarism both from Internet and among students: If the source of plagiarism is from Internet, we adopt the technology based on the semantic tree similarity detection, in which distributed database and parallel computation are used. If the source of plagiarism is among students, we use a new way based on digital watermarking and information hiding technology. Our program can embed the information of originators into the characters of coursework by the watermarking algorithm with high embedding capacity. When the coursework is copied by others, the program can detect the similar parts and locate the source of plagiarism accurately.
{"title":"Research on the Model of Similar Electronic Coursework Detection","authors":"Fu Bing","doi":"10.1109/WGEC.2009.27","DOIUrl":"https://doi.org/10.1109/WGEC.2009.27","url":null,"abstract":"With rapid development of network technologies, many universities have realized coursework electronically in many courses. But students copy electronic coursework more and more commonly. This paper proposes two methods of anti-plagiarism plagiarism both from Internet and among students: If the source of plagiarism is from Internet, we adopt the technology based on the semantic tree similarity detection, in which distributed database and parallel computation are used. If the source of plagiarism is among students, we use a new way based on digital watermarking and information hiding technology. Our program can embed the information of originators into the characters of coursework by the watermarking algorithm with high embedding capacity. When the coursework is copied by others, the program can detect the similar parts and locate the source of plagiarism accurately.","PeriodicalId":277950,"journal":{"name":"2009 Third International Conference on Genetic and Evolutionary Computing","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126957309","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The rise in peer-to-peer (P2P) networking has been tremendous in last several years; a large amount of network bandwidth backbone is consumed by P2P traffic. Although many methods have been proposed to manage P2P traffic, these methods require a lot of knowledge about the workloads and are generally difficult to implement. In this paper, we propose a mechanism of traffic cache based on P2P networks and simply modify LRU algorithm to improve cache hit ratio. A series of simulation experiments on the OMNeT++ show that the mechanism can greatly increase the proportion of local area network traffic while P2P downloads are done and effectively reduce the cross-border traffic for having a good way to reduce backbone load.
{"title":"A Traffic Cache for Structure Peer-to-Peer Networks","authors":"Kuisheng Lin, Ya Zhou, Guimin Huang","doi":"10.1109/WGEC.2009.198","DOIUrl":"https://doi.org/10.1109/WGEC.2009.198","url":null,"abstract":"The rise in peer-to-peer (P2P) networking has been tremendous in last several years; a large amount of network bandwidth backbone is consumed by P2P traffic. Although many methods have been proposed to manage P2P traffic, these methods require a lot of knowledge about the workloads and are generally difficult to implement. In this paper, we propose a mechanism of traffic cache based on P2P networks and simply modify LRU algorithm to improve cache hit ratio. A series of simulation experiments on the OMNeT++ show that the mechanism can greatly increase the proportion of local area network traffic while P2P downloads are done and effectively reduce the cross-border traffic for having a good way to reduce backbone load.","PeriodicalId":277950,"journal":{"name":"2009 Third International Conference on Genetic and Evolutionary Computing","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125713507","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In this paper, we consider a class of time-delay dynamical systems with nonlinear perturbation. The nonlinear perturbation functions are assumed bounded. we provide a robust stabilization criterion via designing a memoryless state feedback controller for the time-delay dynamical neural networks with nonlinear perturbation. The sufficient criterion is given in terms of linear matrix inequality (LMI). The checking for robust stabilization of time-delay dynamical neural networks with nonlinear perturbation by our result can be carried out rather simply, and convenient for the application. The applicability of our results is demonstrated by means of two specific examples.
{"title":"A Method of Robust Stabilization for the Delay Neural Networks with Nonlinear Perturbations","authors":"Ruliang Wang, Hong Lei, Jin Wang","doi":"10.1109/WGEC.2009.126","DOIUrl":"https://doi.org/10.1109/WGEC.2009.126","url":null,"abstract":"In this paper, we consider a class of time-delay dynamical systems with nonlinear perturbation. The nonlinear perturbation functions are assumed bounded. we provide a robust stabilization criterion via designing a memoryless state feedback controller for the time-delay dynamical neural networks with nonlinear perturbation. The sufficient criterion is given in terms of linear matrix inequality (LMI). The checking for robust stabilization of time-delay dynamical neural networks with nonlinear perturbation by our result can be carried out rather simply, and convenient for the application. The applicability of our results is demonstrated by means of two specific examples.","PeriodicalId":277950,"journal":{"name":"2009 Third International Conference on Genetic and Evolutionary Computing","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113942304","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Through analyzing the advantages and disadvantages between anomaly detection and misuse detection, a mixed intrusion detection system (IDS) model is designed. First, data is examined by the misuse detection module, then abnormal data detection is examined by anomaly detection module. In this model, the anomaly detection module is built using unsupervised clustering method, and the algorithm is an improved algorithm of K-means clustering algorithm and it is proved to have high detection rate in the anomaly detection module.
{"title":"A Mixed Unsupervised Clustering-Based Intrusion Detection Model","authors":"Cuixiao Zhang, Guobing Zhang, Shanshan Sun","doi":"10.1109/WGEC.2009.72","DOIUrl":"https://doi.org/10.1109/WGEC.2009.72","url":null,"abstract":"Through analyzing the advantages and disadvantages between anomaly detection and misuse detection, a mixed intrusion detection system (IDS) model is designed. First, data is examined by the misuse detection module, then abnormal data detection is examined by anomaly detection module. In this model, the anomaly detection module is built using unsupervised clustering method, and the algorithm is an improved algorithm of K-means clustering algorithm and it is proved to have high detection rate in the anomaly detection module.","PeriodicalId":277950,"journal":{"name":"2009 Third International Conference on Genetic and Evolutionary Computing","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121714900","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This paper analyses the BP algorithm in detail, including the number of hidden layer, the amount of neural node and training algorithm. In order to improve the training speed, this paper adopts the automatic and adaptive step to perfect the BP algorithm. In addition, because the traditional BP neural network is easy to trap into local minimum, this paper makes use of the characteristic of simulated annealing algorithm and let it unite with BP algorithm. Because the simulated annealing algorithm can get optimal approximation by searching local, it can help BP algorithm not to trap into local minimum.
{"title":"A Method of Improved BP Neural Algorithm Based on Simulated Annealing Algorithm","authors":"Kai Bai, Jing Xiong","doi":"10.1109/WGEC.2009.39","DOIUrl":"https://doi.org/10.1109/WGEC.2009.39","url":null,"abstract":"This paper analyses the BP algorithm in detail, including the number of hidden layer, the amount of neural node and training algorithm. In order to improve the training speed, this paper adopts the automatic and adaptive step to perfect the BP algorithm. In addition, because the traditional BP neural network is easy to trap into local minimum, this paper makes use of the characteristic of simulated annealing algorithm and let it unite with BP algorithm. Because the simulated annealing algorithm can get optimal approximation by searching local, it can help BP algorithm not to trap into local minimum.","PeriodicalId":277950,"journal":{"name":"2009 Third International Conference on Genetic and Evolutionary Computing","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123806948","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Operation and operator technologies used in new generation Geometrical Product Specifications (GPS) provide the necessary knowledge basis for digitization and standardization in verification process of geometrical products. This paper analyzes the operator formation for perpendicularity error evaluation of an axis, and presents mathematical models and the objective optimization functions of every association operation based on the minimum zone solution. A multi-population genetic algorithm based read-coded is then introduced to solve the optimization problem. The basic idea and steps of the algorithm are described in detail. Finally, the measurement process of the perpendicularity error evaluation of an axis based on real-coded multi-population genetic algorithm is realized through an example. The experiment indicates that the proposed method is efficient and feasible. The result of evaluation is accurate and unique.
{"title":"Perpendicularity Error Evaluation of an Axis Based on New Generation GPS","authors":"J. Peng, Y. Zhong, Kewei Liu, Meifa Huang","doi":"10.1109/WGEC.2009.105","DOIUrl":"https://doi.org/10.1109/WGEC.2009.105","url":null,"abstract":"Operation and operator technologies used in new generation Geometrical Product Specifications (GPS) provide the necessary knowledge basis for digitization and standardization in verification process of geometrical products. This paper analyzes the operator formation for perpendicularity error evaluation of an axis, and presents mathematical models and the objective optimization functions of every association operation based on the minimum zone solution. A multi-population genetic algorithm based read-coded is then introduced to solve the optimization problem. The basic idea and steps of the algorithm are described in detail. Finally, the measurement process of the perpendicularity error evaluation of an axis based on real-coded multi-population genetic algorithm is realized through an example. The experiment indicates that the proposed method is efficient and feasible. The result of evaluation is accurate and unique.","PeriodicalId":277950,"journal":{"name":"2009 Third International Conference on Genetic and Evolutionary Computing","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121357404","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The particle swarm optimization (PSO) is an adaptive optimization based on swarm intelligence. The basic principle and the method of it being used in seismic location were introduced. To get a more accurate result, the objective function is the residual square sum of the observational travel-time and theoretical travel-time of the same earthquake return two stations. Compared with Genetic Algorithm on Seismic Location, PSO, after numerous experiments, proved its distinct superiority to locate the hypocenter more quickly and accurately. PSO is potentially useful for seismic location.
{"title":"Application of Particle Swarm Optimization to Seismic Location","authors":"Dong-xue Han, Gai-yun Wang","doi":"10.1109/WGEC.2009.48","DOIUrl":"https://doi.org/10.1109/WGEC.2009.48","url":null,"abstract":"The particle swarm optimization (PSO) is an adaptive optimization based on swarm intelligence. The basic principle and the method of it being used in seismic location were introduced. To get a more accurate result, the objective function is the residual square sum of the observational travel-time and theoretical travel-time of the same earthquake return two stations. Compared with Genetic Algorithm on Seismic Location, PSO, after numerous experiments, proved its distinct superiority to locate the hypocenter more quickly and accurately. PSO is potentially useful for seismic location.","PeriodicalId":277950,"journal":{"name":"2009 Third International Conference on Genetic and Evolutionary Computing","volume":"85 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132914490","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Xiangjiao Tang, Ting-Pei Huang, Xiaoyu Liu, J. Wang
As the liquid position control system has the characteristic of a large time delay, instability and non-linear, a neural network self-adaptive PID controller based on self-adaptive PID and neural network is introduced in this paper, it can optimize and adjust the controller parameters on line. The system simulation is carried out in the end. The simulation results show that the control effect of this method has good dynamic performance, robustness and good practicality.
{"title":"Application of PID with Single-Neuron Adaptive Control in Liquid Level Control","authors":"Xiangjiao Tang, Ting-Pei Huang, Xiaoyu Liu, J. Wang","doi":"10.1109/WGEC.2009.66","DOIUrl":"https://doi.org/10.1109/WGEC.2009.66","url":null,"abstract":"As the liquid position control system has the characteristic of a large time delay, instability and non-linear, a neural network self-adaptive PID controller based on self-adaptive PID and neural network is introduced in this paper, it can optimize and adjust the controller parameters on line. The system simulation is carried out in the end. The simulation results show that the control effect of this method has good dynamic performance, robustness and good practicality.","PeriodicalId":277950,"journal":{"name":"2009 Third International Conference on Genetic and Evolutionary Computing","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131880450","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
At present, phosphate in one trough is a research focus. Traditional research methods have unfavorable factors, such as time-consuming, material costs, pollution, unsafe and so on. In this paper, intelligent simulation system is constructed based on neural network. For any combination of a set of experimental data, the system can calculate the membrane weight and corrosion resistance results. Based on the calculating results, users can choose an optimizing combination data to arrange experiment for verification. The intelligent simulation methods not only resolve the huge experiments problems, but also achieve the optimal data selection, at the same time saving experiment’s resource.
{"title":"Intelligent Simulation on Phosphate in One Trough Based on Neural Network","authors":"Li-fang Chen, Liang Chen, Jian-tao Gu, Xiaohui Yuan","doi":"10.1109/WGEC.2009.36","DOIUrl":"https://doi.org/10.1109/WGEC.2009.36","url":null,"abstract":"At present, phosphate in one trough is a research focus. Traditional research methods have unfavorable factors, such as time-consuming, material costs, pollution, unsafe and so on. In this paper, intelligent simulation system is constructed based on neural network. For any combination of a set of experimental data, the system can calculate the membrane weight and corrosion resistance results. Based on the calculating results, users can choose an optimizing combination data to arrange experiment for verification. The intelligent simulation methods not only resolve the huge experiments problems, but also achieve the optimal data selection, at the same time saving experiment’s resource.","PeriodicalId":277950,"journal":{"name":"2009 Third International Conference on Genetic and Evolutionary Computing","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133365591","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
With the rapid development of Web services, feature interactions have become one of the critical problems in Web services composition. This paper proposes a model checking method for detecting feature interactions in Web services composition. By the proposed method, the Web services descriptions written in WS-BPEL are translated into timed automata, and then we apply a well known model checking tool UPPAAL that supports this formalism to modeling Web services composition and analyzing feature interactions. We take a particular case study, an automatic stock trading system, as an example to illustrate the effectiveness of the proposed method.
{"title":"Detecting Feature Interactions in Web Services with Timed Automata","authors":"Xiangyu Luo, Aicheng Xuan, Rongsheng Dong","doi":"10.1109/WGEC.2009.144","DOIUrl":"https://doi.org/10.1109/WGEC.2009.144","url":null,"abstract":"With the rapid development of Web services, feature interactions have become one of the critical problems in Web services composition. This paper proposes a model checking method for detecting feature interactions in Web services composition. By the proposed method, the Web services descriptions written in WS-BPEL are translated into timed automata, and then we apply a well known model checking tool UPPAAL that supports this formalism to modeling Web services composition and analyzing feature interactions. We take a particular case study, an automatic stock trading system, as an example to illustrate the effectiveness of the proposed method.","PeriodicalId":277950,"journal":{"name":"2009 Third International Conference on Genetic and Evolutionary Computing","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116750608","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：