Pub Date : 1900-01-01DOI: 10.1109/ISCID.2019.10114
Zhifei Wang
In order to solve the problem of stranded passengers and foreign bodies between platform and high-speed railway, between platform doors and high-speed railway, a safety detection and protection system and method based on target detection and recognition are proposed in this paper. Firstly, the image features of stranded passengers and foreign bodies are obtained by target detection, feature extraction and image matching. Secondly, the central control system of the protection system completes the protection instruction, and realizes the protection. Finally, on the basis of the prototype test, the line test is completed. The test results show that this method can not only effectively reduce the operation time of image target recognition, but also judge whether there is a foreign body between the train door and the platform, as well as the state of the train entering and leaving the station, and make intelligent judgment and decision, so as to effectively ensure the safe and energy-saving operation of the railway and the safety of passengers, as well as the safety, reliability and availability of the system.
{"title":"Study on Safety Detection and Protection Technology Between Platform and High-speed Train","authors":"Zhifei Wang","doi":"10.1109/ISCID.2019.10114","DOIUrl":"https://doi.org/10.1109/ISCID.2019.10114","url":null,"abstract":"In order to solve the problem of stranded passengers and foreign bodies between platform and high-speed railway, between platform doors and high-speed railway, a safety detection and protection system and method based on target detection and recognition are proposed in this paper. Firstly, the image features of stranded passengers and foreign bodies are obtained by target detection, feature extraction and image matching. Secondly, the central control system of the protection system completes the protection instruction, and realizes the protection. Finally, on the basis of the prototype test, the line test is completed. The test results show that this method can not only effectively reduce the operation time of image target recognition, but also judge whether there is a foreign body between the train door and the platform, as well as the state of the train entering and leaving the station, and make intelligent judgment and decision, so as to effectively ensure the safe and energy-saving operation of the railway and the safety of passengers, as well as the safety, reliability and availability of the system.","PeriodicalId":294370,"journal":{"name":"International Symposium on Computational Intelligence and Design","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124333430","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}
By applying the laser-linear array CCD detective technology, a high speed and high accuracy method for detecting roll wear is brought forward. The principle and composition of the detecting system has been expatiated. And a simulation-software program is compiled with Microsoft Visual Basic 6.0 based on this detecting principle. By using this simulation-software, the date of I/O signal for this system is gained. Also the signal verse is automatically drawn by this software. The experiment proves that the accuracy of the detecting system reaches to the demand of practical production process. This method offers the advantages of sensitivity, immediate response, no electromagnetic interference, simplicity and on-line non-contact detecting for roll wear.
{"title":"An Optical Fiber Sensor System of On-line Detecting Roll Wear and Software Imitation","authors":"Yuan Guo, W. Qu","doi":"10.1109/ISCID.2009.174","DOIUrl":"https://doi.org/10.1109/ISCID.2009.174","url":null,"abstract":"By applying the laser-linear array CCD detective technology, a high speed and high accuracy method for detecting roll wear is brought forward. The principle and composition of the detecting system has been expatiated. And a simulation-software program is compiled with Microsoft Visual Basic 6.0 based on this detecting principle. By using this simulation-software, the date of I/O signal for this system is gained. Also the signal verse is automatically drawn by this software. The experiment proves that the accuracy of the detecting system reaches to the demand of practical production process. This method offers the advantages of sensitivity, immediate response, no electromagnetic interference, simplicity and on-line non-contact detecting for roll wear.","PeriodicalId":294370,"journal":{"name":"International Symposium on Computational Intelligence and Design","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123088096","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 : 1900-01-01DOI: 10.1109/ISCID.2018.00091
Chao Yang, Zhennan Wang, Xuepu Jiang, Hongyang Yu, Sai Liu, Liangzhu Deng
In recent years, image classification has become a research hot area in computer vision, Most of the methods directly train data sets to obtain classifiers. However, if the images in the data set contain massive backgrounds, causing the image itself to have a lot of noise will degrade the classification results. This paper presents a new object classification method based on salient object detection. Firstly, a salient object detection method based on CNN is applied to the dataset image to locate the object in the image. Then use the Bag of Feature model to vectorize the salient region features. Finally, use the multi-class linear SVM to classify the feature vectors. For marveldataset2016, the classification accuracy of the pre-processed classification method is 10.8% higher than that of the non-preprocessing classification method, and the classifier-training is 44% less time-consuming.
{"title":"Fast Object Classification Method Based on Saliency Detection","authors":"Chao Yang, Zhennan Wang, Xuepu Jiang, Hongyang Yu, Sai Liu, Liangzhu Deng","doi":"10.1109/ISCID.2018.00091","DOIUrl":"https://doi.org/10.1109/ISCID.2018.00091","url":null,"abstract":"In recent years, image classification has become a research hot area in computer vision, Most of the methods directly train data sets to obtain classifiers. However, if the images in the data set contain massive backgrounds, causing the image itself to have a lot of noise will degrade the classification results. This paper presents a new object classification method based on salient object detection. Firstly, a salient object detection method based on CNN is applied to the dataset image to locate the object in the image. Then use the Bag of Feature model to vectorize the salient region features. Finally, use the multi-class linear SVM to classify the feature vectors. For marveldataset2016, the classification accuracy of the pre-processed classification method is 10.8% higher than that of the non-preprocessing classification method, and the classifier-training is 44% less time-consuming.","PeriodicalId":294370,"journal":{"name":"International Symposium on Computational Intelligence and Design","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115931757","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}
A database system is the core and foundation of an information system. And a security audit system is needed to a database system. Limitations of current database auditing are discussed in this research and a security framework is proposed to overcome them. The proposed framework provides the functions of audit system management, audit strategy management, log auditing, statistics report, real – time monitoring, and database system detection. There are six components are used for achieve the functions, event manager, event generator, event collector, event analyzer, event reporter, and event memorizer. The proposed framework is based on fine – grained auditing method which can provide a better performance.
{"title":"A Security Framework for Database Auditing System","authors":"Huijie Wang","doi":"10.1109/ISCID.2017.64","DOIUrl":"https://doi.org/10.1109/ISCID.2017.64","url":null,"abstract":"A database system is the core and foundation of an information system. And a security audit system is needed to a database system. Limitations of current database auditing are discussed in this research and a security framework is proposed to overcome them. The proposed framework provides the functions of audit system management, audit strategy management, log auditing, statistics report, real – time monitoring, and database system detection. There are six components are used for achieve the functions, event manager, event generator, event collector, event analyzer, event reporter, and event memorizer. The proposed framework is based on fine – grained auditing method which can provide a better performance.","PeriodicalId":294370,"journal":{"name":"International Symposium on Computational Intelligence and Design","volume":" 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113950737","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}
Based on the data collected by 3D body scanner, the research on body surface variations were conducted. The shoulders, the elbows, the waist-to-hip area, and knees were selected as key objects of the study. The appropriate actions and the movement scope were determined according to the dynamic features of different parts. The dynamic changes of body surface were investigated by regress analysis, and the significance and goodness of fit were tested to obtain the meaningful regression equations. Taking the lateral raise of back as case study, the paper revealed the methods of data analysis on the variation of human body in movement.
{"title":"The Data Analysis on the Variation of Human Body in Movement","authors":"Xiaopeng Chen, Jin Meng, Yinhan Liu","doi":"10.1109/ISCID.2011.22","DOIUrl":"https://doi.org/10.1109/ISCID.2011.22","url":null,"abstract":"Based on the data collected by 3D body scanner, the research on body surface variations were conducted. The shoulders, the elbows, the waist-to-hip area, and knees were selected as key objects of the study. The appropriate actions and the movement scope were determined according to the dynamic features of different parts. The dynamic changes of body surface were investigated by regress analysis, and the significance and goodness of fit were tested to obtain the meaningful regression equations. Taking the lateral raise of back as case study, the paper revealed the methods of data analysis on the variation of human body in movement.","PeriodicalId":294370,"journal":{"name":"International Symposium on Computational Intelligence and Design","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114287552","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}
Aiming at the special process requirements of steelmaking-continuous casting (SCC) scheduling, a constraint satisfaction model is established with the objectives of the total waiting time, idle time of the machines, and the earliness and tardiness time of the casts. Furthermore, an NSGA-MOPSO algorithm with the adaptive grid selection strategy (AGSS) is proposed, which effectively overcome the problem of easily losing the useful information that use traditional Pareto domination method. Finally, experiments and compared algorithm are set up and the results show that the feasibility and effectiveness of the proposed NSGA-MOPSO algorithm
{"title":"Hybrid Metaheuristic for Multi-objective Steelmaking-Continuous Casting Scheduling","authors":"S. Yuan, Tieke Li, B. Wang","doi":"10.1109/ISCID.2017.21","DOIUrl":"https://doi.org/10.1109/ISCID.2017.21","url":null,"abstract":"Aiming at the special process requirements of steelmaking-continuous casting (SCC) scheduling, a constraint satisfaction model is established with the objectives of the total waiting time, idle time of the machines, and the earliness and tardiness time of the casts. Furthermore, an NSGA-MOPSO algorithm with the adaptive grid selection strategy (AGSS) is proposed, which effectively overcome the problem of easily losing the useful information that use traditional Pareto domination method. Finally, experiments and compared algorithm are set up and the results show that the feasibility and effectiveness of the proposed NSGA-MOPSO algorithm","PeriodicalId":294370,"journal":{"name":"International Symposium on Computational Intelligence and Design","volume":"412 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115916112","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}
It is a key problem to approximate data of complex surface in many graphics and image processing applications. It is difficult to compute the control parameters of NURBS (Non Uniform Rational B-Spline) effecting the result of fitted shape. An evolutionary programming algorithm is used to optimize the weight and knot by minimizing the sum square error between the fitted and target curve and surface. The results obtained from curves and surfaces shows that comparing to knot optimization, the weight optimization is a better option because knot optimization requires a good initial location of knot vector.
{"title":"Optimized NURBS Curve and Surface Fitting Using Simulated Annealing","authors":"Jing Zhang, Shaowei Feng, Hanguo Cui","doi":"10.1109/ISCID.2009.227","DOIUrl":"https://doi.org/10.1109/ISCID.2009.227","url":null,"abstract":"It is a key problem to approximate data of complex surface in many graphics and image processing applications. It is difficult to compute the control parameters of NURBS (Non Uniform Rational B-Spline) effecting the result of fitted shape. An evolutionary programming algorithm is used to optimize the weight and knot by minimizing the sum square error between the fitted and target curve and surface. The results obtained from curves and surfaces shows that comparing to knot optimization, the weight optimization is a better option because knot optimization requires a good initial location of knot vector.","PeriodicalId":294370,"journal":{"name":"International Symposium on Computational Intelligence and Design","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120839520","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 weighted mean squares error (WMSE) function, each sample error multiplies a weighting coefficient, then it can make noise error have a smaller proportion in the cost function, even the outliers can’t affect the learning of the neural networks by tuning the smooth parameter , which enhances the anti-noise ability of neural networks. If the samples don’t have noise samples, weighted mean squares error function can make neural networks avoid over-fitting. When the neural networks are linear models, the new cost function turns into a realization of weighted least squares method, the simulation results show the advantages and application conditions of the weighted squares error function.
{"title":"Learning of Neural Networks Based on Weighted Mean Squares Error Function","authors":"Sai Yang, Jinxia Ren, Zhongxia Li","doi":"10.1109/ISCID.2009.67","DOIUrl":"https://doi.org/10.1109/ISCID.2009.67","url":null,"abstract":"In weighted mean squares error (WMSE) function, each sample error multiplies a weighting coefficient, then it can make noise error have a smaller proportion in the cost function, even the outliers can’t affect the learning of the neural networks by tuning the smooth parameter , which enhances the anti-noise ability of neural networks. If the samples don’t have noise samples, weighted mean squares error function can make neural networks avoid over-fitting. When the neural networks are linear models, the new cost function turns into a realization of weighted least squares method, the simulation results show the advantages and application conditions of the weighted squares error function.","PeriodicalId":294370,"journal":{"name":"International Symposium on Computational Intelligence and Design","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123435182","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}
Focuses on the demand of the opening administration for the laboratory in high school, combined with the fingerprint recognition technology, this paper designs a universal laboratory management system, which contains checking on work attendance, students information management, querying, printing report sheet and course management functions. The fingerprint recognition technology is analyzed in detail. The two manners of the computer system applying the fingerprint recognition technology both verification and identification are introduced. Using fingerprint collection technique, software program and database technology, the architecture of the system and the realization method of each function are provided. The system gets a good stability and accuracy through the practical test.
{"title":"An Open Laboratory Management System Based on Fingerprints Recognition","authors":"Wenliang Niu, Xi Han, Zheying Li, Shuying Wang","doi":"10.1109/ISCID.2009.134","DOIUrl":"https://doi.org/10.1109/ISCID.2009.134","url":null,"abstract":"Focuses on the demand of the opening administration for the laboratory in high school, combined with the fingerprint recognition technology, this paper designs a universal laboratory management system, which contains checking on work attendance, students information management, querying, printing report sheet and course management functions. The fingerprint recognition technology is analyzed in detail. The two manners of the computer system applying the fingerprint recognition technology both verification and identification are introduced. Using fingerprint collection technique, software program and database technology, the architecture of the system and the realization method of each function are provided. The system gets a good stability and accuracy through the practical test.","PeriodicalId":294370,"journal":{"name":"International Symposium on Computational Intelligence and Design","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125018353","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 : 1900-01-01DOI: 10.1109/ISCID51228.2020.00010
Xue Yang, Wanjun Huang, Hongyang Yu
Aiming at the optimization problem of object detection technology, an instance segmentation model algorithm based on the improved Cascade Mask R-CNN is proposed. Firstly, information fusion is performed on the mask branches of each cascade stage, so that the mask information of the current stage is jointly determined by the segmentation results of the previous stage and the current stage. Secondly, GA-RPN is used to replace the original RPN to generate high-confidence and low-density proposal regions. At the beginning of the cascade, the IoU threshold is increased for training, thereby improving the performance of the network model. Finally, the model of this paper is implemented, and compared with the official implementation on the public data set, which verifies the efficiency of improved algorithm.
{"title":"Research on Optimization of Object Detection Technology Based on Convolutional Neural Network","authors":"Xue Yang, Wanjun Huang, Hongyang Yu","doi":"10.1109/ISCID51228.2020.00010","DOIUrl":"https://doi.org/10.1109/ISCID51228.2020.00010","url":null,"abstract":"Aiming at the optimization problem of object detection technology, an instance segmentation model algorithm based on the improved Cascade Mask R-CNN is proposed. Firstly, information fusion is performed on the mask branches of each cascade stage, so that the mask information of the current stage is jointly determined by the segmentation results of the previous stage and the current stage. Secondly, GA-RPN is used to replace the original RPN to generate high-confidence and low-density proposal regions. At the beginning of the cascade, the IoU threshold is increased for training, thereby improving the performance of the network model. Finally, the model of this paper is implemented, and compared with the official implementation on the public data set, which verifies the efficiency of improved algorithm.","PeriodicalId":294370,"journal":{"name":"International Symposium on Computational Intelligence and Design","volume":"16 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120991131","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：