Pub Date : 2019-04-01DOI: 10.2991/ICMEIT-19.2019.102
Peng Ge, Yanping Hu
There are few differences in the characteristics of vehicles and many interference factors in vehicle identification, especially in complex backgrounds. In order to improve the accuracy of image feature extraction and recognition in complex background, a vehicle-types recognition technology based on improved HOG_SVM is proposed in this paper. In order to obtain abundant vehicle identification information, we perform targeted image preprocessing methods such as grayscale stretching and Gaussian filtering on the original image to reduce background interference factors. The HOG feature is then introduced to obtain rich features of the image, and the SVM classifier in machine learning is trained at the output layer by multitasking learning of a large amount of tagged data. Different from the traditional method, the PCA dimension reduction process is used to speed up the recognition of the improved HOG feature, and the method of SVM is used to avoid the classifier from falling into the local minimum. In this paper, the public vehicle dataset is used as the classifier training dataset and test dataset, and the proposed method is verified by experiments.
{"title":"Vehicle Type Classification based on Improved HOG_SVM","authors":"Peng Ge, Yanping Hu","doi":"10.2991/ICMEIT-19.2019.102","DOIUrl":"https://doi.org/10.2991/ICMEIT-19.2019.102","url":null,"abstract":"There are few differences in the characteristics of vehicles and many interference factors in vehicle identification, especially in complex backgrounds. In order to improve the accuracy of image feature extraction and recognition in complex background, a vehicle-types recognition technology based on improved HOG_SVM is proposed in this paper. In order to obtain abundant vehicle identification information, we perform targeted image preprocessing methods such as grayscale stretching and Gaussian filtering on the original image to reduce background interference factors. The HOG feature is then introduced to obtain rich features of the image, and the SVM classifier in machine learning is trained at the output layer by multitasking learning of a large amount of tagged data. Different from the traditional method, the PCA dimension reduction process is used to speed up the recognition of the improved HOG feature, and the method of SVM is used to avoid the classifier from falling into the local minimum. In this paper, the public vehicle dataset is used as the classifier training dataset and test dataset, and the proposed method is verified by experiments.","PeriodicalId":223458,"journal":{"name":"Proceedings of the 3rd International Conference on Mechatronics Engineering and Information Technology (ICMEIT 2019)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128815293","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}
Pub Date : 2019-04-01DOI: 10.2991/ICMEIT-19.2019.33
Chongli Zhong, Zhenyu Cao
{"title":"Study on Student Growth Tracking System based on Educational Big Data","authors":"Chongli Zhong, Zhenyu Cao","doi":"10.2991/ICMEIT-19.2019.33","DOIUrl":"https://doi.org/10.2991/ICMEIT-19.2019.33","url":null,"abstract":"","PeriodicalId":223458,"journal":{"name":"Proceedings of the 3rd International Conference on Mechatronics Engineering and Information Technology (ICMEIT 2019)","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127715463","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}
Pub Date : 2019-04-01DOI: 10.2991/ICMEIT-19.2019.80
Suo Siliang, W. Xi, C. Tiantian, Jian Ganyang, Hao Yao, Jin Li
With the rapid development of network, all kinds of information systems bring convenience to enterprises at the same time, it also brings more and more hidden dangers to information security. Encryption technology is the core technology of network security technology, which plays an increasingly important role in protecting network information security. This paper analyses the current information encryption technology, expounds the advantages and disadvantages of encryption algorithm, and expounds the application scenario and development trend of encryption technology.
{"title":"Encryption Technology in Information System Security","authors":"Suo Siliang, W. Xi, C. Tiantian, Jian Ganyang, Hao Yao, Jin Li","doi":"10.2991/ICMEIT-19.2019.80","DOIUrl":"https://doi.org/10.2991/ICMEIT-19.2019.80","url":null,"abstract":"With the rapid development of network, all kinds of information systems bring convenience to enterprises at the same time, it also brings more and more hidden dangers to information security. Encryption technology is the core technology of network security technology, which plays an increasingly important role in protecting network information security. This paper analyses the current information encryption technology, expounds the advantages and disadvantages of encryption algorithm, and expounds the application scenario and development trend of encryption technology.","PeriodicalId":223458,"journal":{"name":"Proceedings of the 3rd International Conference on Mechatronics Engineering and Information Technology (ICMEIT 2019)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126285855","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}
Pub Date : 2019-04-01DOI: 10.2991/ICMEIT-19.2019.49
Wenhao Qiu, Guangyao Lian, Huijie Li, Tian Xiao
A general fault injection system is designed for the problem that the existing fault injection equipment cannot meet the requirements of testability verification test. Firstly, according to the requirements of testability verification test for fault injection and state monitoring, an injection system framework including hardware platform and software platform is designed. The detailed design scheme of the system hardware platform, as well as the design architecture and operating principle of the software platform are presented. Then, various fault injectors are integrated, and the signaloriented fault model is constructed to realize the effective simulation of the fault. Finally, the system is applied to the testability verification test of a control system, and 58 fault samples are actually injected, which shows that the system can meet the requirements of the testability verification test.
{"title":"Design and Application of Fault Injection System for Testability Verification Test","authors":"Wenhao Qiu, Guangyao Lian, Huijie Li, Tian Xiao","doi":"10.2991/ICMEIT-19.2019.49","DOIUrl":"https://doi.org/10.2991/ICMEIT-19.2019.49","url":null,"abstract":"A general fault injection system is designed for the problem that the existing fault injection equipment cannot meet the requirements of testability verification test. Firstly, according to the requirements of testability verification test for fault injection and state monitoring, an injection system framework including hardware platform and software platform is designed. The detailed design scheme of the system hardware platform, as well as the design architecture and operating principle of the software platform are presented. Then, various fault injectors are integrated, and the signaloriented fault model is constructed to realize the effective simulation of the fault. Finally, the system is applied to the testability verification test of a control system, and 58 fault samples are actually injected, which shows that the system can meet the requirements of the testability verification test.","PeriodicalId":223458,"journal":{"name":"Proceedings of the 3rd International Conference on Mechatronics Engineering and Information Technology (ICMEIT 2019)","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121667536","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}
Pub Date : 2019-04-01DOI: 10.2991/ICMEIT-19.2019.150
Yang Li, Z. Dai
This study takes advantage of the combination of heterogeneous platform control and computing power, and optimizes the parallelization of the popular collaborative filtering recommendation algorithm. Compared with the traditional algorithm, the speedup has a certain degree of improvement and power consumption has also declined as well. Keyowrds: heterogeneous computing platform, Recommendation System.
{"title":"Design and Implementation of Hardware Accelerator for Recommendation System based on Heterogeneous Computing Platform","authors":"Yang Li, Z. Dai","doi":"10.2991/ICMEIT-19.2019.150","DOIUrl":"https://doi.org/10.2991/ICMEIT-19.2019.150","url":null,"abstract":"This study takes advantage of the combination of heterogeneous platform control and computing power, and optimizes the parallelization of the popular collaborative filtering recommendation algorithm. Compared with the traditional algorithm, the speedup has a certain degree of improvement and power consumption has also declined as well. Keyowrds: heterogeneous computing platform, Recommendation System.","PeriodicalId":223458,"journal":{"name":"Proceedings of the 3rd International Conference on Mechatronics Engineering and Information Technology (ICMEIT 2019)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117289560","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}
Pub Date : 2019-04-01DOI: 10.2991/ICMEIT-19.2019.101
Guomin Li, Ning Li, Lihua Pang
Abstract. This paper studies a resource allocation method based on power optimization for singlecell multi-user downlink Massive MIMO wireless communication system with energy harvesting function. The proposed method uses a ZF precede for precoding. Under the premise that the noncausal knowledge of the energy harvesting process is available, the base station only uses renewable energy to provide the energy required for the system to operate. The relationship between power and system throughput is derived with consideration of both battery capacity constraints and energy causal constraints. Through the Varangian dual method, resource utilization is optimized. The simulation results show that the proposed algorithm tends to converge with fewer iterations.
{"title":"Power Allocation in Massive MIMO System with Energy Harvesting Base Station","authors":"Guomin Li, Ning Li, Lihua Pang","doi":"10.2991/ICMEIT-19.2019.101","DOIUrl":"https://doi.org/10.2991/ICMEIT-19.2019.101","url":null,"abstract":"Abstract. This paper studies a resource allocation method based on power optimization for singlecell multi-user downlink Massive MIMO wireless communication system with energy harvesting function. The proposed method uses a ZF precede for precoding. Under the premise that the noncausal knowledge of the energy harvesting process is available, the base station only uses renewable energy to provide the energy required for the system to operate. The relationship between power and system throughput is derived with consideration of both battery capacity constraints and energy causal constraints. Through the Varangian dual method, resource utilization is optimized. The simulation results show that the proposed algorithm tends to converge with fewer iterations.","PeriodicalId":223458,"journal":{"name":"Proceedings of the 3rd International Conference on Mechatronics Engineering and Information Technology (ICMEIT 2019)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131527324","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}
Pub Date : 2019-04-01DOI: 10.2991/ICMEIT-19.2019.151
Shuxing Feng, X. Su, Yongping Wang
. It is becoming the high topic to keep space security in the world, and it is great useful for making decision and making a choice to analyze development strategy of space security based on SWOT, with analyzing the strength, the weakness, the opportunity the threat, with qualitative estimate and quantitative evaluation which depends on applying the matrix model about the influent factors and strategy measures. To some extent, it uses for reference to carry out development strategy.
{"title":"Research on Development Strategy of Space Security based on AHP-SWOT","authors":"Shuxing Feng, X. Su, Yongping Wang","doi":"10.2991/ICMEIT-19.2019.151","DOIUrl":"https://doi.org/10.2991/ICMEIT-19.2019.151","url":null,"abstract":". It is becoming the high topic to keep space security in the world, and it is great useful for making decision and making a choice to analyze development strategy of space security based on SWOT, with analyzing the strength, the weakness, the opportunity the threat, with qualitative estimate and quantitative evaluation which depends on applying the matrix model about the influent factors and strategy measures. To some extent, it uses for reference to carry out development strategy.","PeriodicalId":223458,"journal":{"name":"Proceedings of the 3rd International Conference on Mechatronics Engineering and Information Technology (ICMEIT 2019)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127360515","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}
Pub Date : 2019-04-01DOI: 10.2991/ICMEIT-19.2019.65
L. Hong
Abstract. Due to the different national conditions, the driving forces and factors of national terrorist attacks vary. Therefore, this paper takes GTD China sample data as the research object to study and predict. The prediction process is as follows: On the basis of the BP network-based model for predicting the most dangerous areas, combined with the GTD sample data, the best number of nodes in the implicit layer of the prediction model is automatically selected by combining the empirical formula with the MATLAB program. Three improved BP algorithms are used to train the network model. The results show that the training error of Levenburg Marquardt algorithm is minimal and the convergence speed is fastest. Through the training and simulation of the model, it is proved that the model has high precision and can meet the requirement of practical application.
{"title":"Prediction of Terrorist Attacks in China based on BP improved Algorithm and GTD","authors":"L. Hong","doi":"10.2991/ICMEIT-19.2019.65","DOIUrl":"https://doi.org/10.2991/ICMEIT-19.2019.65","url":null,"abstract":"Abstract. Due to the different national conditions, the driving forces and factors of national terrorist attacks vary. Therefore, this paper takes GTD China sample data as the research object to study and predict. The prediction process is as follows: On the basis of the BP network-based model for predicting the most dangerous areas, combined with the GTD sample data, the best number of nodes in the implicit layer of the prediction model is automatically selected by combining the empirical formula with the MATLAB program. Three improved BP algorithms are used to train the network model. The results show that the training error of Levenburg Marquardt algorithm is minimal and the convergence speed is fastest. Through the training and simulation of the model, it is proved that the model has high precision and can meet the requirement of practical application.","PeriodicalId":223458,"journal":{"name":"Proceedings of the 3rd International Conference on Mechatronics Engineering and Information Technology (ICMEIT 2019)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124267089","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}
Pub Date : 2019-04-01DOI: 10.2991/ICMEIT-19.2019.136
Zhihui Hu, Xiao-Lan Tang, Chengyan Lu, Jun Zhang
Antenna is the main energy converter of radar seeker. It converts the transmitted signal into space radiation field, and converts the echo signal reflected by the target into guided wave field and sends it to the receiver. Therefore, antenna design plays an important role in the design of radar seeker. The development of radar seeker antenna mainly includes cone-scan antenna, monopulse parabolic antenna and waveguide slot array antenna. Although this kind of antenna can search and track the target, its scanning mode is mechanical scanning, which needs precise servo system to complete. Therefore, its angle scanning range is small, tracking speed is slow and volume is large. Phased array antenna has the advantages of fast beam scanning speed, flexible control and strong anti-jamming performance because it uses electronic scanning instead of mechanical scanning. At present, the phased array antenna is mainly planar array antenna. Its design technology is relatively mature, but there are some shortcomings. Its beam scanning range is narrow, beam width and sidelobe level will increase with the increase of scanning angle, and array gain will decrease with the increase of scanning angle. In order to fully satisfy the design requirements of the moving platform, the radiation units of the phased array antenna are installed on the surface of the moving platform to make it coincide with the surface of the moving platform. A conformal phased array antenna can be formed, where the moving platform can be a carrier of aircraft, missiles, ships and so on. Conformal phased array antenna is the combination of conformal array and phased array, so it can overcome the shortcomings of planar antenna, realize beam scanning with wide angle and wide range, and keep the antenna gain and beam shape unchanged during scanning. It can also improve the aerodynamic performance of carrier and reduce the cross-section area of radar. Therefore, conformal phased array antenna has become a new important development direction of radar antenna technology.
{"title":"Design and Simulation of Conformal Phased Array Antenna","authors":"Zhihui Hu, Xiao-Lan Tang, Chengyan Lu, Jun Zhang","doi":"10.2991/ICMEIT-19.2019.136","DOIUrl":"https://doi.org/10.2991/ICMEIT-19.2019.136","url":null,"abstract":"Antenna is the main energy converter of radar seeker. It converts the transmitted signal into space radiation field, and converts the echo signal reflected by the target into guided wave field and sends it to the receiver. Therefore, antenna design plays an important role in the design of radar seeker. The development of radar seeker antenna mainly includes cone-scan antenna, monopulse parabolic antenna and waveguide slot array antenna. Although this kind of antenna can search and track the target, its scanning mode is mechanical scanning, which needs precise servo system to complete. Therefore, its angle scanning range is small, tracking speed is slow and volume is large. Phased array antenna has the advantages of fast beam scanning speed, flexible control and strong anti-jamming performance because it uses electronic scanning instead of mechanical scanning. At present, the phased array antenna is mainly planar array antenna. Its design technology is relatively mature, but there are some shortcomings. Its beam scanning range is narrow, beam width and sidelobe level will increase with the increase of scanning angle, and array gain will decrease with the increase of scanning angle. In order to fully satisfy the design requirements of the moving platform, the radiation units of the phased array antenna are installed on the surface of the moving platform to make it coincide with the surface of the moving platform. A conformal phased array antenna can be formed, where the moving platform can be a carrier of aircraft, missiles, ships and so on. Conformal phased array antenna is the combination of conformal array and phased array, so it can overcome the shortcomings of planar antenna, realize beam scanning with wide angle and wide range, and keep the antenna gain and beam shape unchanged during scanning. It can also improve the aerodynamic performance of carrier and reduce the cross-section area of radar. Therefore, conformal phased array antenna has become a new important development direction of radar antenna technology.","PeriodicalId":223458,"journal":{"name":"Proceedings of the 3rd International Conference on Mechatronics Engineering and Information Technology (ICMEIT 2019)","volume":"418 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115926320","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}
Pub Date : 2019-04-01DOI: 10.2991/ICMEIT-19.2019.122
Jie Ling, Chen-He Wu
The intrusion detection system deals with huge amount of data containing redundant and noisy features and the poor classifier algorithm causing the degradation of detection accuracy, in this paper, we introduce the random forest feature selection algorithm and propose a method that multi-classifier ensemble based on deep learning for intrusion detection. It used the random forest feature selection algorithm to extract optimal feature subset that are used to train by support vector machine, decision tree, naïve bayes and k-nearest neighbor classification algorithm, then, applying the deep learning to stack the output of four classifiers. The experimental results show that the proposed method can effectively improve the accuracy of intrusion detection compared with the majoring voting algorithm.
{"title":"Feature Selection and Deep Learning based Approach for Network Intrusion Detection","authors":"Jie Ling, Chen-He Wu","doi":"10.2991/ICMEIT-19.2019.122","DOIUrl":"https://doi.org/10.2991/ICMEIT-19.2019.122","url":null,"abstract":"The intrusion detection system deals with huge amount of data containing redundant and noisy features and the poor classifier algorithm causing the degradation of detection accuracy, in this paper, we introduce the random forest feature selection algorithm and propose a method that multi-classifier ensemble based on deep learning for intrusion detection. It used the random forest feature selection algorithm to extract optimal feature subset that are used to train by support vector machine, decision tree, naïve bayes and k-nearest neighbor classification algorithm, then, applying the deep learning to stack the output of four classifiers. The experimental results show that the proposed method can effectively improve the accuracy of intrusion detection compared with the majoring voting algorithm.","PeriodicalId":223458,"journal":{"name":"Proceedings of the 3rd International Conference on Mechatronics Engineering and Information Technology (ICMEIT 2019)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121924038","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：