Pub Date : 2004-06-25DOI: 10.1109/ICIA.2004.1373345
Junjie Chen, Weiyi Huang
Genetic neural network model of solving the problems on nonlinearity rectification of sensor systems, was put forward, for the shortcoming of least square and other conventional methods. Computer simulations are given to demonstrate that approximation accuracy of the model is far higher than least square method that are extensively applied conventionally and the model possesses stronger robustness through adopting the standpoints and methods in this paper. And the research indicates that the model can be also used to realize nonlinearity rectification in other similar systems
{"title":"Research on non-linearity rectification of sensor systems","authors":"Junjie Chen, Weiyi Huang","doi":"10.1109/ICIA.2004.1373345","DOIUrl":"https://doi.org/10.1109/ICIA.2004.1373345","url":null,"abstract":"Genetic neural network model of solving the problems on nonlinearity rectification of sensor systems, was put forward, for the shortcoming of least square and other conventional methods. Computer simulations are given to demonstrate that approximation accuracy of the model is far higher than least square method that are extensively applied conventionally and the model possesses stronger robustness through adopting the standpoints and methods in this paper. And the research indicates that the model can be also used to realize nonlinearity rectification in other similar systems","PeriodicalId":297178,"journal":{"name":"International Conference on Information Acquisition, 2004. Proceedings.","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123227177","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 : 2004-06-21DOI: 10.1109/ICIA.2004.1373384
Qinmin Yang, Kui Yuan, Jiangfeng Li, Hui Wang
We describe a new method for a mobile robot equipped with ultrasonic sensors to construct and maintain a map of the environment for the purpose of obstacle avoidance and navigation. A new sonar model is given, which is a simplified Gaussian model for the sake of computing time. Furthermore, incidence angle information of sonar is combined with the range measurement to construct a two-dimensional histogram grid. The histogram grid shows a quick and accurate mapping. At the same time, with the incidence angle information, the method exhibits a good performance in solving the problem of door-finding and reducing phantom targets. Finally, the map-building system is experimentally evaluated in the real environment.
{"title":"A histogram sensor fusion method for mobile robots","authors":"Qinmin Yang, Kui Yuan, Jiangfeng Li, Hui Wang","doi":"10.1109/ICIA.2004.1373384","DOIUrl":"https://doi.org/10.1109/ICIA.2004.1373384","url":null,"abstract":"We describe a new method for a mobile robot equipped with ultrasonic sensors to construct and maintain a map of the environment for the purpose of obstacle avoidance and navigation. A new sonar model is given, which is a simplified Gaussian model for the sake of computing time. Furthermore, incidence angle information of sonar is combined with the range measurement to construct a two-dimensional histogram grid. The histogram grid shows a quick and accurate mapping. At the same time, with the incidence angle information, the method exhibits a good performance in solving the problem of door-finding and reducing phantom targets. Finally, the map-building system is experimentally evaluated in the real environment.","PeriodicalId":297178,"journal":{"name":"International Conference on Information Acquisition, 2004. Proceedings.","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-06-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121132534","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 : 2004-06-21DOI: 10.1109/ICIA.2004.1373347
W. Ren, Zhenggang Zhang, Y. Zhao, Zhenghui Zhang
Since the present backwardness of pump-jack fault diagnosis method and the waste of time and labor, we adopt wavelet network to transform the working current of pump-jacks and get the detail coefficient and then make it fault characteristics. To adjust the parameters of neural network, we adopt the self-tuning learning rate conjugated gradient method to optimize the object function. The application on thirty five pump-jacks indicates that this method can be used on the fault diagnosis of pump-jacks with the accuracy over ninety five percent.
{"title":"Fault diagnosis of pump-jack based on neural network","authors":"W. Ren, Zhenggang Zhang, Y. Zhao, Zhenghui Zhang","doi":"10.1109/ICIA.2004.1373347","DOIUrl":"https://doi.org/10.1109/ICIA.2004.1373347","url":null,"abstract":"Since the present backwardness of pump-jack fault diagnosis method and the waste of time and labor, we adopt wavelet network to transform the working current of pump-jacks and get the detail coefficient and then make it fault characteristics. To adjust the parameters of neural network, we adopt the self-tuning learning rate conjugated gradient method to optimize the object function. The application on thirty five pump-jacks indicates that this method can be used on the fault diagnosis of pump-jacks with the accuracy over ninety five percent.","PeriodicalId":297178,"journal":{"name":"International Conference on Information Acquisition, 2004. Proceedings.","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-06-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127520013","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 new approach for rapid detection of hazardous gas using a single SnO/sub 2/ gas sensor based on dynamic measurement was investigated. Experimental results showed that hazardous gas such as LPG had obvious properties by using dynamic measurement. The qualitative analysis was also studied by means of fast Fourier transform(FFT), and power spectrum showed that different properties appeared on different concentrations of LPG.
{"title":"Rapid detection of hazardous gas using one SnO/sub 2/ gas sensor based on dynamic measurement","authors":"Jinhuai Liu, Fanli Meng, Xingjiu Huang, Weihong Xu, Jiarui Huang","doi":"10.1109/ICIA.2004.1373429","DOIUrl":"https://doi.org/10.1109/ICIA.2004.1373429","url":null,"abstract":"A new approach for rapid detection of hazardous gas using a single SnO/sub 2/ gas sensor based on dynamic measurement was investigated. Experimental results showed that hazardous gas such as LPG had obvious properties by using dynamic measurement. The qualitative analysis was also studied by means of fast Fourier transform(FFT), and power spectrum showed that different properties appeared on different concentrations of LPG.","PeriodicalId":297178,"journal":{"name":"International Conference on Information Acquisition, 2004. Proceedings.","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-06-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126184230","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 : 2004-06-21DOI: 10.1109/ICIA.2004.1373421
Yan-Sheng Yao
This paper introduces the history, classes and characters of cryptography and indicates the necessity of guard against code theft. In order to protect just identity and secret information, a new kind of cryptography and its application and advantages has been given and analyzed. To develop a better character of guard against theft, the operator must rightly use fixed first code with validation code which is decided by algorithm of each time to pass identity verification. The paper illuminates the theory of software control, puts forward a novel secure cryptography that has not been found before.
{"title":"Application and research on cryptography of guard against theft","authors":"Yan-Sheng Yao","doi":"10.1109/ICIA.2004.1373421","DOIUrl":"https://doi.org/10.1109/ICIA.2004.1373421","url":null,"abstract":"This paper introduces the history, classes and characters of cryptography and indicates the necessity of guard against code theft. In order to protect just identity and secret information, a new kind of cryptography and its application and advantages has been given and analyzed. To develop a better character of guard against theft, the operator must rightly use fixed first code with validation code which is decided by algorithm of each time to pass identity verification. The paper illuminates the theory of software control, puts forward a novel secure cryptography that has not been found before.","PeriodicalId":297178,"journal":{"name":"International Conference on Information Acquisition, 2004. Proceedings.","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-06-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115059140","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 : 2004-06-21DOI: 10.1109/ICIA.2004.1373364
X. Dai, M. Yin, Qin Wang, Wancheng Wang
A novel dynamic compensator of sensors based on ANN (artificial neural networks) inversion is proposed according to the theory of inverse methods and excellent approach abilities of ANN. ANN inversion-based dynamic compensator of sensor is achieved through offline training the ANN inversion that combines the static ANN and dynamic factors. The dynamic performance of sensor is improved effectively by cascading ANN inversion with the original sensor. Simulation and experiment results indicate that the dynamic performance of sensor is remarkably improved and enhanced using the proposed compensator.
{"title":"Artificial neural networks inversion based dynamic compensator of sensors","authors":"X. Dai, M. Yin, Qin Wang, Wancheng Wang","doi":"10.1109/ICIA.2004.1373364","DOIUrl":"https://doi.org/10.1109/ICIA.2004.1373364","url":null,"abstract":"A novel dynamic compensator of sensors based on ANN (artificial neural networks) inversion is proposed according to the theory of inverse methods and excellent approach abilities of ANN. ANN inversion-based dynamic compensator of sensor is achieved through offline training the ANN inversion that combines the static ANN and dynamic factors. The dynamic performance of sensor is improved effectively by cascading ANN inversion with the original sensor. Simulation and experiment results indicate that the dynamic performance of sensor is remarkably improved and enhanced using the proposed compensator.","PeriodicalId":297178,"journal":{"name":"International Conference on Information Acquisition, 2004. Proceedings.","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-06-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116385290","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 : 2004-06-21DOI: 10.1109/ICIA.2004.1373420
Jianguo Zheng, Mingquan Zhou, Zengping Chen
Based on bidirectional lamp tracking and utilizing performances of Monte Carlo method, A novel algorithm is proposed here which makes it easy for an user to simulate the bright region of lamp-source on the testing screen. Comparing with the forward lamp integral method, this model is not only applicable to reflectors of any figure but also far more rapid than using forward working. Simulations show that this algorithm is not only effective but also feasible.
{"title":"A novel MC algorithm and its application","authors":"Jianguo Zheng, Mingquan Zhou, Zengping Chen","doi":"10.1109/ICIA.2004.1373420","DOIUrl":"https://doi.org/10.1109/ICIA.2004.1373420","url":null,"abstract":"Based on bidirectional lamp tracking and utilizing performances of Monte Carlo method, A novel algorithm is proposed here which makes it easy for an user to simulate the bright region of lamp-source on the testing screen. Comparing with the forward lamp integral method, this model is not only applicable to reflectors of any figure but also far more rapid than using forward working. Simulations show that this algorithm is not only effective but also feasible.","PeriodicalId":297178,"journal":{"name":"International Conference on Information Acquisition, 2004. Proceedings.","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-06-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123890148","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 : 2004-06-21DOI: 10.1109/ICIA.2004.1373323
Qing-shan Song, S. Xia, Shaofeng Chen, Zheng Cui
A new microdevice for measuring the thermal conductivity of thin film is presented. It is based on the static-state method, which is widely used and a simple technique for measuring the lateral thermal conductivity of thin film. The device is fabricated using micromachining process, which is 800/spl times/2000/spl mu/m bridge membrane with 30/spl times/100/spl mu/m beams. The heater and thermometer across the bridge membrane through the beams are used to create heat flux and to measure the temperature. On the membrane, heat flux is very uniform and the temperature is evenly distributed, which has been verified by simulation, making the system error smaller than conventional rectangular structure. Silicon nitride thin films with thickness from 0.5/spl mu/m to 2/spl mu/m have been investigated using the technique. The measurement result supports the size effect of the thermal conductivity for thin film.
{"title":"A new structure for measuring the thermal conductivity of thin film","authors":"Qing-shan Song, S. Xia, Shaofeng Chen, Zheng Cui","doi":"10.1109/ICIA.2004.1373323","DOIUrl":"https://doi.org/10.1109/ICIA.2004.1373323","url":null,"abstract":"A new microdevice for measuring the thermal conductivity of thin film is presented. It is based on the static-state method, which is widely used and a simple technique for measuring the lateral thermal conductivity of thin film. The device is fabricated using micromachining process, which is 800/spl times/2000/spl mu/m bridge membrane with 30/spl times/100/spl mu/m beams. The heater and thermometer across the bridge membrane through the beams are used to create heat flux and to measure the temperature. On the membrane, heat flux is very uniform and the temperature is evenly distributed, which has been verified by simulation, making the system error smaller than conventional rectangular structure. Silicon nitride thin films with thickness from 0.5/spl mu/m to 2/spl mu/m have been investigated using the technique. The measurement result supports the size effect of the thermal conductivity for thin film.","PeriodicalId":297178,"journal":{"name":"International Conference on Information Acquisition, 2004. Proceedings.","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-06-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114089189","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 : 2004-06-21DOI: 10.1109/ICIA.2004.1373331
X. Wang, S.X. Yang, Weiren Shi, M. Meng
This paper proposes a coevolution approach to optimal sensor placement and controller design for a mobile robot to facilitate its navigation and obstacle avoidance in an unknown environment. The mobile robots considered in this paper have flexible sensor and control structure. A genetic algorithm is developed to evolve the parameters of optimal sensor placement and fuzzy logic controller simultaneously. The preliminary results indicate that the proposed coevolution approach can lead to efficient robot sensor placement and control design.
{"title":"A co-evolution approach to sensor placement and control design for robot obstacle avoidance","authors":"X. Wang, S.X. Yang, Weiren Shi, M. Meng","doi":"10.1109/ICIA.2004.1373331","DOIUrl":"https://doi.org/10.1109/ICIA.2004.1373331","url":null,"abstract":"This paper proposes a coevolution approach to optimal sensor placement and controller design for a mobile robot to facilitate its navigation and obstacle avoidance in an unknown environment. The mobile robots considered in this paper have flexible sensor and control structure. A genetic algorithm is developed to evolve the parameters of optimal sensor placement and fuzzy logic controller simultaneously. The preliminary results indicate that the proposed coevolution approach can lead to efficient robot sensor placement and control design.","PeriodicalId":297178,"journal":{"name":"International Conference on Information Acquisition, 2004. Proceedings.","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-06-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124300709","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 : 2004-06-21DOI: 10.1109/ICIA.2004.1373374
Song Wang, Weihong Wang
We propose an image segmentation algorithm that is based on spatially adaptive color and texture features. The features are first developed independently, and then combined to obtain an overall segmentation. We combine a previously proposed adaptive clustering algorithm for color segmentation with a simple but effective texture segmentation approach to obtain an overall image segmentation. Our focus is in the domain of photographic images with an essentially unlimited range of topics. The images are assumed to be of relatively low resolution and may be degraded or compressed.
{"title":"Unsupervised image segmentation by combining spatially adaptive color and texture features","authors":"Song Wang, Weihong Wang","doi":"10.1109/ICIA.2004.1373374","DOIUrl":"https://doi.org/10.1109/ICIA.2004.1373374","url":null,"abstract":"We propose an image segmentation algorithm that is based on spatially adaptive color and texture features. The features are first developed independently, and then combined to obtain an overall segmentation. We combine a previously proposed adaptive clustering algorithm for color segmentation with a simple but effective texture segmentation approach to obtain an overall image segmentation. Our focus is in the domain of photographic images with an essentially unlimited range of topics. The images are assumed to be of relatively low resolution and may be degraded or compressed.","PeriodicalId":297178,"journal":{"name":"International Conference on Information Acquisition, 2004. Proceedings.","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-06-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128132552","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：