Lin Cheng, Zhou Fengjun, C. Wan-ke, Wang Gang, Zhang Xiaohua
As the key technology of electric vehicles(EV) ", "control systems is always the research hotspot of EV field. When the battery component of HEV operates at charge sustaining (CS) mode, the most important problem is how to split the whole vehicle's required power between engine and battery component reasonably and effectively so as to make the good economy and driving performance. Taking battery component of Plug-in Hybrid Electric Bus as the research object", "this paper established the model of feedback control system for battery component. Then the feedback control systems gains are optimized with the objective function of equivalent fuel consumption and accumulated power requirement error", "which is based on BUSRTE driving cycle. The obtained gains are testified and verified by NEWYORK and CBDBUS driving cycle respectively. The results indicate that the optimized control system for batteries has good fuel economy and driving performance.
{"title":"Battery Component Control System Design for PHEV Based on ECE Cycle","authors":"Lin Cheng, Zhou Fengjun, C. Wan-ke, Wang Gang, Zhang Xiaohua","doi":"10.1109/GCIS.2012.56","DOIUrl":"https://doi.org/10.1109/GCIS.2012.56","url":null,"abstract":"As the key technology of electric vehicles(EV) \", \"control systems is always the research hotspot of EV field. When the battery component of HEV operates at charge sustaining (CS) mode, the most important problem is how to split the whole vehicle's required power between engine and battery component reasonably and effectively so as to make the good economy and driving performance. Taking battery component of Plug-in Hybrid Electric Bus as the research object\", \"this paper established the model of feedback control system for battery component. Then the feedback control systems gains are optimized with the objective function of equivalent fuel consumption and accumulated power requirement error\", \"which is based on BUSRTE driving cycle. The obtained gains are testified and verified by NEWYORK and CBDBUS driving cycle respectively. The results indicate that the optimized control system for batteries has good fuel economy and driving performance.","PeriodicalId":337629,"journal":{"name":"2012 Third Global Congress on Intelligent Systems","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130657328","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 economic development, the environmental pollution becomes increasingly serious. Through the analysis of causes and propagation characteristics of urban heavy metals pollution, the location of the various sources of pollution is confirmed. By using the principal component analysis model, the specific distributions of different pollutants in each area are obtained firstly. In order to ascertain the sources of heavy metal pollution, three-dimensional diffusion model between the concentration of heavy metal elements and geographic position of elements is established. With the help of the least squares method solving differential equations, the specific location of the sources of pollution is ascertained ultimately.
{"title":"The Use of Principal Component Analysis and Three-Dimensional Diffusion Model of Urban Heavy Metal Pollution","authors":"Longyan Gong, Juping Zhou, Zhisen Ye, Taigui Qin","doi":"10.1109/GCIS.2012.65","DOIUrl":"https://doi.org/10.1109/GCIS.2012.65","url":null,"abstract":"With the rapid economic development, the environmental pollution becomes increasingly serious. Through the analysis of causes and propagation characteristics of urban heavy metals pollution, the location of the various sources of pollution is confirmed. By using the principal component analysis model, the specific distributions of different pollutants in each area are obtained firstly. In order to ascertain the sources of heavy metal pollution, three-dimensional diffusion model between the concentration of heavy metal elements and geographic position of elements is established. With the help of the least squares method solving differential equations, the specific location of the sources of pollution is ascertained ultimately.","PeriodicalId":337629,"journal":{"name":"2012 Third Global Congress on Intelligent Systems","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124913370","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 means of rigid mathematical deductions we prove that weight vectors cannot promote the performance of the optimal classifier, i.e. the Bayesian classifier in terms of the error, F-one score, or breakeven point. The conclusion is important in that people used to promote the performance of a classifier by trying various weight vectors in text classification.
{"title":"Mathematical Analysis on Weight Vectors in Text Classification","authors":"Fengxi Song, Qinglong Chen, Zhongwei Guo, Xiumei Gao","doi":"10.1109/GCIS.2012.14","DOIUrl":"https://doi.org/10.1109/GCIS.2012.14","url":null,"abstract":"By means of rigid mathematical deductions we prove that weight vectors cannot promote the performance of the optimal classifier, i.e. the Bayesian classifier in terms of the error, F-one score, or breakeven point. The conclusion is important in that people used to promote the performance of a classifier by trying various weight vectors in text classification.","PeriodicalId":337629,"journal":{"name":"2012 Third Global Congress on Intelligent Systems","volume":"345 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122852386","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 proposes a new algorithm FIM_AIUA, which updates association rules with incremental transactions and minimum support changes simultaneously. The algorithm expands FIM algorithm and AIUA algorithm, improves the efficiency and corrects the mistakes of My_IUA algorithm. Moreover, it modifies FIM algorithm with a new argument and presents a new function fim_aiua_gen() that rewrites the function aiua_gen() of AIUA algorithm. Experiments with real transaction data of a supermarket show that our proposed algorithm FIM_AIUA is efficient and outperforms both My_IUA algorithm and Apriori algorithm.
{"title":"An Efficient Algorithm for Updating Association Rules with Incremental Transactions and Minimum Support Changes Simultaneously","authors":"Li Sun, Yu-Chen Cai, Jiyun Li, Juntao Lv","doi":"10.1109/GCIS.2012.42","DOIUrl":"https://doi.org/10.1109/GCIS.2012.42","url":null,"abstract":"This paper proposes a new algorithm FIM_AIUA, which updates association rules with incremental transactions and minimum support changes simultaneously. The algorithm expands FIM algorithm and AIUA algorithm, improves the efficiency and corrects the mistakes of My_IUA algorithm. Moreover, it modifies FIM algorithm with a new argument and presents a new function fim_aiua_gen() that rewrites the function aiua_gen() of AIUA algorithm. Experiments with real transaction data of a supermarket show that our proposed algorithm FIM_AIUA is efficient and outperforms both My_IUA algorithm and Apriori algorithm.","PeriodicalId":337629,"journal":{"name":"2012 Third Global Congress on Intelligent Systems","volume":"41 6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115912589","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 research of this paper is about the control strategy of tracked robots for intelligent transportation based on parallel formation. Firstly, the sliding turning model of tracked mobile robot is introduced and the kinematics analysis of this model based on the pose information is also researched. Then, the problem of tracked robots formation could be reduced to the tracking approach by the theory of virtual-structure, and the control strategy of tracked robots is achieved by the relative algorithm. At last, the feasibility and stability of tracked robots' formation for intelligent transportation is simulated by the software of Matlab.
{"title":"The Control Strategy of Swarm Tracked Robots for Intelligent Transportation Based on Parallel Formation","authors":"Jianhua Wu, Zhao Liu","doi":"10.1109/GCIS.2012.66","DOIUrl":"https://doi.org/10.1109/GCIS.2012.66","url":null,"abstract":"The research of this paper is about the control strategy of tracked robots for intelligent transportation based on parallel formation. Firstly, the sliding turning model of tracked mobile robot is introduced and the kinematics analysis of this model based on the pose information is also researched. Then, the problem of tracked robots formation could be reduced to the tracking approach by the theory of virtual-structure, and the control strategy of tracked robots is achieved by the relative algorithm. At last, the feasibility and stability of tracked robots' formation for intelligent transportation is simulated by the software of Matlab.","PeriodicalId":337629,"journal":{"name":"2012 Third Global Congress on Intelligent Systems","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115391545","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 paper presents the architecture of the MAS-based distributed fish disease diagnosis expert system on the basis of the analysis and summary on the characteristics of the existing distributed fish disease diagnosis expert system. That gives full play to the MAS-based distributed computing and to build flexibly. For heterogeneous knowledge sources of the distributed expert system, use the distributed computing agent to achieve the distributed diagnosis and management of fish diseases, and reduce the burden of the centralized processing. Meanwhile, it uses the modified contract net model, and designs a task allocation model of the collaborative diagnosis based on MAS for the distributed fish diseases, which describes the task allocation process concretely. Experiments proved that the system not only overcomes the limitations of single expert in the field, can also be cross-regional collaborative diagnosis. It improves the efficiency of the distribution of tasks and increases the accuracy of the results of fish disease diagnosis.
{"title":"Building of an Architecture for the Fish Disease Diagnosis Expert System Based on Multi-agent","authors":"Dongping Ma, Ming Chen","doi":"10.1109/GCIS.2012.21","DOIUrl":"https://doi.org/10.1109/GCIS.2012.21","url":null,"abstract":"The paper presents the architecture of the MAS-based distributed fish disease diagnosis expert system on the basis of the analysis and summary on the characteristics of the existing distributed fish disease diagnosis expert system. That gives full play to the MAS-based distributed computing and to build flexibly. For heterogeneous knowledge sources of the distributed expert system, use the distributed computing agent to achieve the distributed diagnosis and management of fish diseases, and reduce the burden of the centralized processing. Meanwhile, it uses the modified contract net model, and designs a task allocation model of the collaborative diagnosis based on MAS for the distributed fish diseases, which describes the task allocation process concretely. Experiments proved that the system not only overcomes the limitations of single expert in the field, can also be cross-regional collaborative diagnosis. It improves the efficiency of the distribution of tasks and increases the accuracy of the results of fish disease diagnosis.","PeriodicalId":337629,"journal":{"name":"2012 Third Global Congress on Intelligent Systems","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127461845","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}
Feature extraction is one of the most important technologies for underwater targets recognition. In the past few decades, a number of methods for feature extraction have been developed, and under certain conditions they can achieve high recognition rate. However, for complex environments, it is still difficult to improve the robustness of the recognition system, and new robust feature extraction methods are expectant. This paper presents a novel method of feature extraction based on the spectrogram of acoustic signals. The image moment features and image texture features are extracted and the algorithms of LDA, PCA and their combinations are used to select the effective features respectively. The experimental results show that, these selected image features can achieve high recognition rate.
{"title":"Image Representation of Acoustic Features for the Automatic Recognition of Underwater Noise Targets","authors":"Zeng Xiangyang, He Jiaruo, Ma Lixiang","doi":"10.1109/GCIS.2012.49","DOIUrl":"https://doi.org/10.1109/GCIS.2012.49","url":null,"abstract":"Feature extraction is one of the most important technologies for underwater targets recognition. In the past few decades, a number of methods for feature extraction have been developed, and under certain conditions they can achieve high recognition rate. However, for complex environments, it is still difficult to improve the robustness of the recognition system, and new robust feature extraction methods are expectant. This paper presents a novel method of feature extraction based on the spectrogram of acoustic signals. The image moment features and image texture features are extracted and the algorithms of LDA, PCA and their combinations are used to select the effective features respectively. The experimental results show that, these selected image features can achieve high recognition rate.","PeriodicalId":337629,"journal":{"name":"2012 Third Global Congress on Intelligent Systems","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131342571","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 describes a Computer-Aided Diagnosis (CAD) system for automatic pulmonary nodules detection on serial CT scans based on shape features. The system recognizes nodules by 3D geometric information through the process of interpolation, segmentation, suspicious area searching and recognition. Firstly, the serial CT images are interpolated to equal scales in X, Y and Z dimensions, in order to recover the original 3D shape of nodules. Secondly, pretreatment is implemented to segment the lung parenchyma region. Thirdly, detect objects called regions of interest (ROIs) as potential nodules by threshold of gray level and region growing. Finally, distinguish ROIs to find real nodules using moment invariants. The experimental results from CT scans data sets demonstrate that the proposed method yields a good performance of nodule detection. The system recognizes all the nodules of the data sets with a reasonable false positive (FP) 1/serial scans.
{"title":"Pulmonary Nodules 3D Detection on Serial CT Scans","authors":"Suiyuan Wu, Junfeng Wang","doi":"10.1109/GCIS.2012.46","DOIUrl":"https://doi.org/10.1109/GCIS.2012.46","url":null,"abstract":"This paper describes a Computer-Aided Diagnosis (CAD) system for automatic pulmonary nodules detection on serial CT scans based on shape features. The system recognizes nodules by 3D geometric information through the process of interpolation, segmentation, suspicious area searching and recognition. Firstly, the serial CT images are interpolated to equal scales in X, Y and Z dimensions, in order to recover the original 3D shape of nodules. Secondly, pretreatment is implemented to segment the lung parenchyma region. Thirdly, detect objects called regions of interest (ROIs) as potential nodules by threshold of gray level and region growing. Finally, distinguish ROIs to find real nodules using moment invariants. The experimental results from CT scans data sets demonstrate that the proposed method yields a good performance of nodule detection. The system recognizes all the nodules of the data sets with a reasonable false positive (FP) 1/serial scans.","PeriodicalId":337629,"journal":{"name":"2012 Third Global Congress on Intelligent Systems","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134207349","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}
Hongyan Xing, Kaisheng Huang, Chungui Zhang, Yuqing Tu
In this paper, we study supervisory control of a nondeterministic systems -- probabilistic discrete event systems. As language equivalence is not an adequate notion of behavioral equivalence for some nondeterministic systems, here we use the finest known notion of equivalence: bisimulation equivalence. The design of a supervisor such that the controlled system is bisimilar to the specification is studied and a model theorem obtained, in which it shows that a supervisor exists if and only if it exists over a certain finite state space. Also, notions about state-controllability are introduced as part of a necessary and sufficient condition for the existence of the supervisor.
{"title":"Supervisory Control of PDESs Based on Bisimulation Relations","authors":"Hongyan Xing, Kaisheng Huang, Chungui Zhang, Yuqing Tu","doi":"10.1109/GCIS.2012.53","DOIUrl":"https://doi.org/10.1109/GCIS.2012.53","url":null,"abstract":"In this paper, we study supervisory control of a nondeterministic systems -- probabilistic discrete event systems. As language equivalence is not an adequate notion of behavioral equivalence for some nondeterministic systems, here we use the finest known notion of equivalence: bisimulation equivalence. The design of a supervisor such that the controlled system is bisimilar to the specification is studied and a model theorem obtained, in which it shows that a supervisor exists if and only if it exists over a certain finite state space. Also, notions about state-controllability are introduced as part of a necessary and sufficient condition for the existence of the supervisor.","PeriodicalId":337629,"journal":{"name":"2012 Third Global Congress on Intelligent Systems","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132954753","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}
J. L. Vásquez, C. Travieso, T. S. Perez, J. B. Alonso, J. Briceño
In this work, a temperature predictor has been designed and implemented based on different series of meteorological data. The prediction is built by an artificial neural network multilayer perceptron, using 5 samples as window size of meteorological data. Besides, the floating point algorithm was evaluated, reaching a mean square error of 0.35, meaning a variation of 0.28 Celsius degrees versus the real temperature. Different approaches will be applied in order to show our best proposal.
{"title":"Temperature Prediction Based on Different Meteorological Series","authors":"J. L. Vásquez, C. Travieso, T. S. Perez, J. B. Alonso, J. Briceño","doi":"10.1109/GCIS.2012.103","DOIUrl":"https://doi.org/10.1109/GCIS.2012.103","url":null,"abstract":"In this work, a temperature predictor has been designed and implemented based on different series of meteorological data. The prediction is built by an artificial neural network multilayer perceptron, using 5 samples as window size of meteorological data. Besides, the floating point algorithm was evaluated, reaching a mean square error of 0.35, meaning a variation of 0.28 Celsius degrees versus the real temperature. Different approaches will be applied in order to show our best proposal.","PeriodicalId":337629,"journal":{"name":"2012 Third Global Congress on Intelligent Systems","volume":"23 5","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113975717","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：