Pub Date : 2009-12-28DOI: 10.1109/ICICISYS.2009.5358234
Q. Jin, S. Ren, Ling Quan
Base on the traditional internal model control(IMC) principle, the linear quadric Gauss optimal control(LQG) was adopted into the IMC construct in this article. Considering system random noise and measurement noise, based on the system performance index, the process model state feedback controller(LQ) and Kalman filter was designed, Thus the system controller is LQG controller which consist of LQ with Kalman filter and IMC controller, and has the advantages of LQG optimum control and tradition IMC. The simulation shows that this new method can overcome the influence of the parameter variation and system noise of the controlled object with time delay on control performance, and has strong robustness and good stability. In addition, the proposed method is easy to regulate, and it is fit for engineering applications.
{"title":"LQG optimum controller design and simulation base on inter model control theory","authors":"Q. Jin, S. Ren, Ling Quan","doi":"10.1109/ICICISYS.2009.5358234","DOIUrl":"https://doi.org/10.1109/ICICISYS.2009.5358234","url":null,"abstract":"Base on the traditional internal model control(IMC) principle, the linear quadric Gauss optimal control(LQG) was adopted into the IMC construct in this article. Considering system random noise and measurement noise, based on the system performance index, the process model state feedback controller(LQ) and Kalman filter was designed, Thus the system controller is LQG controller which consist of LQ with Kalman filter and IMC controller, and has the advantages of LQG optimum control and tradition IMC. The simulation shows that this new method can overcome the influence of the parameter variation and system noise of the controlled object with time delay on control performance, and has strong robustness and good stability. In addition, the proposed method is easy to regulate, and it is fit for engineering applications.","PeriodicalId":206575,"journal":{"name":"2009 IEEE International Conference on Intelligent Computing and Intelligent Systems","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133718892","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 : 2009-12-28DOI: 10.1109/ICICISYS.2009.5357691
Lei Zhang, Jing-xin Chang, Xuezhi Xiang, Xiaosen Feng
For topic indexing of spoken documents, the word error rate is hopefully decreased instead of the whole sentence error rate, so the center hypothesis among the N-best results is selected as the final output in speech recognition system. Then all spoken documents can be represented as vectors with high dimensions in vector space model, which can be combined with non-negative matrix factorization or singular value decomposition to map the vector space into semantic space. Experiment results show that optimized N-best approach is more suitable to the topic indexing system than one-best method. Combined with the non-negative matrix factorization, the correct topic indexing can achieve 98.1% in optimized N-best approach, which is 0.9% higher than the one-best approach under the same condition. When the semantic space is decreased to 10, there is about 11.1% difference between these two approaches. Furthermore, compared with singular value decomposition method, non-negative matrix factorization has the advantages of better performance, faster computation speed and less storage space.
{"title":"Topic indexing of spoken documents based on optimized N-best approach","authors":"Lei Zhang, Jing-xin Chang, Xuezhi Xiang, Xiaosen Feng","doi":"10.1109/ICICISYS.2009.5357691","DOIUrl":"https://doi.org/10.1109/ICICISYS.2009.5357691","url":null,"abstract":"For topic indexing of spoken documents, the word error rate is hopefully decreased instead of the whole sentence error rate, so the center hypothesis among the N-best results is selected as the final output in speech recognition system. Then all spoken documents can be represented as vectors with high dimensions in vector space model, which can be combined with non-negative matrix factorization or singular value decomposition to map the vector space into semantic space. Experiment results show that optimized N-best approach is more suitable to the topic indexing system than one-best method. Combined with the non-negative matrix factorization, the correct topic indexing can achieve 98.1% in optimized N-best approach, which is 0.9% higher than the one-best approach under the same condition. When the semantic space is decreased to 10, there is about 11.1% difference between these two approaches. Furthermore, compared with singular value decomposition method, non-negative matrix factorization has the advantages of better performance, faster computation speed and less storage space.","PeriodicalId":206575,"journal":{"name":"2009 IEEE International Conference on Intelligent Computing and Intelligent Systems","volume":"90 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115439775","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 : 2009-12-28DOI: 10.1109/ICICISYS.2009.5358146
H. Xiang, X. Zhuang, Zhen Zhao
Fineblanking combined with various metal-forming processes has been an important sheet metal forming process nowadays in industry. However, there are tremendous difficulties in process planning especially strip layout design. It still depends on the engineer's experience and know-how. This paper presents a knowledge-based system for strip layout design in fineblanking. The system speeds up the design process by automating the strip layout design. An example is included to show the system is effective for industry application.
{"title":"Knowledge-based system for strip layout design in fineblanking","authors":"H. Xiang, X. Zhuang, Zhen Zhao","doi":"10.1109/ICICISYS.2009.5358146","DOIUrl":"https://doi.org/10.1109/ICICISYS.2009.5358146","url":null,"abstract":"Fineblanking combined with various metal-forming processes has been an important sheet metal forming process nowadays in industry. However, there are tremendous difficulties in process planning especially strip layout design. It still depends on the engineer's experience and know-how. This paper presents a knowledge-based system for strip layout design in fineblanking. The system speeds up the design process by automating the strip layout design. An example is included to show the system is effective for industry application.","PeriodicalId":206575,"journal":{"name":"2009 IEEE International Conference on Intelligent Computing and Intelligent Systems","volume":"83 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115738910","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 : 2009-12-28DOI: 10.1109/ICICISYS.2009.5358255
Xiaonan Li, Lijuan Bai, Jing Li
This article established a double antennas positioning method and system model. Considering the impact of white Gaussian noise, SNR difference and time difference of arrival of dual-antenna can be calculated at the receiving end to make equations in multi-path fading channel. In the space of two-dimensional the wave source location can be expressed as the function of SNR difference and time difference.
{"title":"ADOA / TDOA combined positioning with dual-antenna over fading channel","authors":"Xiaonan Li, Lijuan Bai, Jing Li","doi":"10.1109/ICICISYS.2009.5358255","DOIUrl":"https://doi.org/10.1109/ICICISYS.2009.5358255","url":null,"abstract":"This article established a double antennas positioning method and system model. Considering the impact of white Gaussian noise, SNR difference and time difference of arrival of dual-antenna can be calculated at the receiving end to make equations in multi-path fading channel. In the space of two-dimensional the wave source location can be expressed as the function of SNR difference and time difference.","PeriodicalId":206575,"journal":{"name":"2009 IEEE International Conference on Intelligent Computing and Intelligent Systems","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115827378","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 : 2009-12-28DOI: 10.1109/ICICISYS.2009.5357616
Keyan Ren, Hanxu Sun, Q. Jia, Jianbo Shi
We propose a novel building detection algorithm for processing high-resolution aerial images. Our algorithm exploits the building-shadow geometric relationship according to lighting models, making it suitable to detect buildings in a more general setting, possibly with irregular shapes. We use image segmentation to provide spatial support for both building and shadow detections. A novel confidence method is developed to label building and shadow segments by jointly reasoning: 1) the likelihood of shadows; 2) building-shadow configuration, and 3) building-building similarity. Our method is tested on a wide range of aerial images. Qualitative and quantitative results demonstrate its effectiveness on detecting and extracting buildings from background clutter.
{"title":"Building recognition from aerial images combining segmentation and shadow","authors":"Keyan Ren, Hanxu Sun, Q. Jia, Jianbo Shi","doi":"10.1109/ICICISYS.2009.5357616","DOIUrl":"https://doi.org/10.1109/ICICISYS.2009.5357616","url":null,"abstract":"We propose a novel building detection algorithm for processing high-resolution aerial images. Our algorithm exploits the building-shadow geometric relationship according to lighting models, making it suitable to detect buildings in a more general setting, possibly with irregular shapes. We use image segmentation to provide spatial support for both building and shadow detections. A novel confidence method is developed to label building and shadow segments by jointly reasoning: 1) the likelihood of shadows; 2) building-shadow configuration, and 3) building-building similarity. Our method is tested on a wide range of aerial images. Qualitative and quantitative results demonstrate its effectiveness on detecting and extracting buildings from background clutter.","PeriodicalId":206575,"journal":{"name":"2009 IEEE International Conference on Intelligent Computing and Intelligent Systems","volume":"119 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115879649","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 : 2009-12-28DOI: 10.1109/ICICISYS.2009.5357742
Ma Li, Junyong Mao, Huang Kejie
The integration of local uncertainty measure with local randomized Hough transform (RHT) is proposed for line detection in the paper to tackle the problems of decrease in detection accuracy in noised images for line detection of complicated parts. The proposed scheme firstly partitions a machine-part into several regions. Then a probability model of uncertainty that an edge pixel belongs to a line is built and accumulated uncertainty measures for lines, formed by any random selected pair of two edge points, are computed according to two point combination and Bayesian rule. Lines are finally detected using soft voting in parameter spaces. The capability of anti-noise and fast processing speed is the key feature of the algorithm. Experimental results show that accuracy error of proposed method less than 1% when noise variance equals to 0.06 and detection accuracy could reach 90%.
{"title":"Line detection of parts using local uncertainty measure and local RHT in noised images","authors":"Ma Li, Junyong Mao, Huang Kejie","doi":"10.1109/ICICISYS.2009.5357742","DOIUrl":"https://doi.org/10.1109/ICICISYS.2009.5357742","url":null,"abstract":"The integration of local uncertainty measure with local randomized Hough transform (RHT) is proposed for line detection in the paper to tackle the problems of decrease in detection accuracy in noised images for line detection of complicated parts. The proposed scheme firstly partitions a machine-part into several regions. Then a probability model of uncertainty that an edge pixel belongs to a line is built and accumulated uncertainty measures for lines, formed by any random selected pair of two edge points, are computed according to two point combination and Bayesian rule. Lines are finally detected using soft voting in parameter spaces. The capability of anti-noise and fast processing speed is the key feature of the algorithm. Experimental results show that accuracy error of proposed method less than 1% when noise variance equals to 0.06 and detection accuracy could reach 90%.","PeriodicalId":206575,"journal":{"name":"2009 IEEE International Conference on Intelligent Computing and Intelligent Systems","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124368958","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 : 2009-12-28DOI: 10.1109/ICICISYS.2009.5357835
Meng I. Lei, Zhang Shu
Based on finite element method and genetic algorithms dynamic mathematical model is established, and the simulation of stress distribution around the defects of single crystal nickel-based superalloysis also established with ANSYS. After the change of stress field with time is analyzed, the result is compared with that achieved through numerical calculation and experimental analysis. The comparison shows that the combination of Finite element method and genetic algorithm is an effective way to micro-simulation. a model is established and simulated for nickel-based superalloys by finite element Method tool, the paper also analysis the stress field of microstructure defects. An Optimization Method is used to the Simulation by Genetic Algorithm, and the results are compared with experimental analysis. The comparison shows the model and Algorithm are correct and can provide basis for the study of creep features and microstructure evolution
{"title":"Simulation of microstructure defects creep on nickel-based superalloys by Genetic Algorithm","authors":"Meng I. Lei, Zhang Shu","doi":"10.1109/ICICISYS.2009.5357835","DOIUrl":"https://doi.org/10.1109/ICICISYS.2009.5357835","url":null,"abstract":"Based on finite element method and genetic algorithms dynamic mathematical model is established, and the simulation of stress distribution around the defects of single crystal nickel-based superalloysis also established with ANSYS. After the change of stress field with time is analyzed, the result is compared with that achieved through numerical calculation and experimental analysis. The comparison shows that the combination of Finite element method and genetic algorithm is an effective way to micro-simulation. a model is established and simulated for nickel-based superalloys by finite element Method tool, the paper also analysis the stress field of microstructure defects. An Optimization Method is used to the Simulation by Genetic Algorithm, and the results are compared with experimental analysis. The comparison shows the model and Algorithm are correct and can provide basis for the study of creep features and microstructure evolution","PeriodicalId":206575,"journal":{"name":"2009 IEEE International Conference on Intelligent Computing and Intelligent Systems","volume":"231 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124552231","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 : 2009-12-28DOI: 10.1109/ICICISYS.2009.5358020
Yucheng Kao, Szu-Yuan Lee
This paper presents a new dynamic data clustering algorithm based on K-means and Combinatorial Particle Swarm Optimization, called KCPSO. Unlike the traditional K-means method, KCPSO does not need a specific number of clusters given before performing the clustering process and is able to find the optimal number of clusters during the clustering process. In each iteration of KCPSO, a discrete PSO is used to optimize the number of clusters with which the K-means is used to find the best clustering result. KCPSO has been developed into a software system and evaluated by testing some datasets. Encouraging results show that KCPSO is an effective algorithm for solving dynamic clustering problems.
{"title":"Combining K-means and particle swarm optimization for dynamic data clustering problems","authors":"Yucheng Kao, Szu-Yuan Lee","doi":"10.1109/ICICISYS.2009.5358020","DOIUrl":"https://doi.org/10.1109/ICICISYS.2009.5358020","url":null,"abstract":"This paper presents a new dynamic data clustering algorithm based on K-means and Combinatorial Particle Swarm Optimization, called KCPSO. Unlike the traditional K-means method, KCPSO does not need a specific number of clusters given before performing the clustering process and is able to find the optimal number of clusters during the clustering process. In each iteration of KCPSO, a discrete PSO is used to optimize the number of clusters with which the K-means is used to find the best clustering result. KCPSO has been developed into a software system and evaluated by testing some datasets. Encouraging results show that KCPSO is an effective algorithm for solving dynamic clustering problems.","PeriodicalId":206575,"journal":{"name":"2009 IEEE International Conference on Intelligent Computing and Intelligent Systems","volume":"149 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114501905","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 : 2009-12-28DOI: 10.1109/ICICISYS.2009.5357617
Wu Xue-fei, Bai Hua
Many underground water pipelines are old and approaching their service lives in a great number of cities. With the promotion of sustaining buried infrastructure, it's necessary to pay much attention on how to effectively extract defect characteristics of damaged pipelines. Detection of defects in underground pipes is a crucial step to assess the deterioration degree of pipeline for municipal operators. Based on the image processing theory, a defect feature extracting method under HSV color space is proposed in this paper. QFCM (Quick Fuzzy C-Mean clustering) segmentation arithmetic is applied to extract characteristics parameters. The proposed algorithm can identify defects from background, and the types of defects in the buried pipes can be categorized in the estimation stage. Then, different methodologies of parameters extraction are applied in different types of pipe defects, features like area, angle, length and width of defects can also be calculated. And then, a method of assessing the accuracy of feature extraction algorithm is discussed. Finally, the proposed detection approach has been experimentally tested using a group of images acquired by CCD camera from real inspection scenarios. The experimental results proved that it is feasible and effective to apply the system in feature extraction of pipe defects of the underground water-pipelines.
{"title":"Automated assessment of buried pipeline defects by image processing","authors":"Wu Xue-fei, Bai Hua","doi":"10.1109/ICICISYS.2009.5357617","DOIUrl":"https://doi.org/10.1109/ICICISYS.2009.5357617","url":null,"abstract":"Many underground water pipelines are old and approaching their service lives in a great number of cities. With the promotion of sustaining buried infrastructure, it's necessary to pay much attention on how to effectively extract defect characteristics of damaged pipelines. Detection of defects in underground pipes is a crucial step to assess the deterioration degree of pipeline for municipal operators. Based on the image processing theory, a defect feature extracting method under HSV color space is proposed in this paper. QFCM (Quick Fuzzy C-Mean clustering) segmentation arithmetic is applied to extract characteristics parameters. The proposed algorithm can identify defects from background, and the types of defects in the buried pipes can be categorized in the estimation stage. Then, different methodologies of parameters extraction are applied in different types of pipe defects, features like area, angle, length and width of defects can also be calculated. And then, a method of assessing the accuracy of feature extraction algorithm is discussed. Finally, the proposed detection approach has been experimentally tested using a group of images acquired by CCD camera from real inspection scenarios. The experimental results proved that it is feasible and effective to apply the system in feature extraction of pipe defects of the underground water-pipelines.","PeriodicalId":206575,"journal":{"name":"2009 IEEE International Conference on Intelligent Computing and Intelligent Systems","volume":"209 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114742965","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 : 2009-12-28DOI: 10.1109/ICICISYS.2009.5357919
Shan Jian-fang, Zongtian Liu, Fu Jian-feng, Zhong Zhaoman
A document is represented as an event network, the nodes represent events, and the edges represent the correlations between events. Our experiment shows that the event network has the small-world properties, i.e., highly clustered and short path length. We pick out important events according to event's importance to make the event network small. Our experiment shows that these important events can make a good summarization of the document. Although there is much research on text processing and applications based on small-world, it is novel to analyze document based on event with the small-world properties of event network.
{"title":"Important event extraction of chinese document based on small world model","authors":"Shan Jian-fang, Zongtian Liu, Fu Jian-feng, Zhong Zhaoman","doi":"10.1109/ICICISYS.2009.5357919","DOIUrl":"https://doi.org/10.1109/ICICISYS.2009.5357919","url":null,"abstract":"A document is represented as an event network, the nodes represent events, and the edges represent the correlations between events. Our experiment shows that the event network has the small-world properties, i.e., highly clustered and short path length. We pick out important events according to event's importance to make the event network small. Our experiment shows that these important events can make a good summarization of the document. Although there is much research on text processing and applications based on small-world, it is novel to analyze document based on event with the small-world properties of event network.","PeriodicalId":206575,"journal":{"name":"2009 IEEE International Conference on Intelligent Computing and Intelligent Systems","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114896147","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：