Pub Date : 2010-11-22DOI: 10.1109/CINC.2010.5643755
Wenhao Ou, W. Gao, Zhen Li, Shuliang Zhang, Qing Wang
This paper describes the Microsoft speech recognition technology and SAPI recognition interface provided by Microsoft speech development platform. Command mode of speech recognition, with custom keywords, can improve speech recognition accuracy. Then, an agricultural voice information system based on speech recognition is designed and implemented on the Microsoft speech development platform, which can improve the complicated touch-tone operations. The users can access the voice information system easily only through oral description. This technology also simplifies the process of system response.
{"title":"Application of keywords speech recognition in agricultural voice information system","authors":"Wenhao Ou, W. Gao, Zhen Li, Shuliang Zhang, Qing Wang","doi":"10.1109/CINC.2010.5643755","DOIUrl":"https://doi.org/10.1109/CINC.2010.5643755","url":null,"abstract":"This paper describes the Microsoft speech recognition technology and SAPI recognition interface provided by Microsoft speech development platform. Command mode of speech recognition, with custom keywords, can improve speech recognition accuracy. Then, an agricultural voice information system based on speech recognition is designed and implemented on the Microsoft speech development platform, which can improve the complicated touch-tone operations. The users can access the voice information system easily only through oral description. This technology also simplifies the process of system response.","PeriodicalId":227004,"journal":{"name":"2010 Second International Conference on Computational Intelligence and Natural Computing","volume":"31 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122577706","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 : 2010-11-22DOI: 10.1109/CINC.2010.5643848
Zheng Li, Luo Jun, L. Tao
The camera calibration and projector calibration are very crucial since the coordinate computation depends on the accuracy of calibration. This calibration procedure consists of camera calibration and projector calibration, done in this order so that the calibrated camera can be used to calibrate the projector. The digital camera is firstly calibrated by the algorithm with 2D direct linear transformation (2D-DLT) and collinear equations. Based on the same calibration model, the calibration precision of projector is lower than that of CCD camera. It is analyzed by the following aspects, such as image and space. For the space point error by paper thickness and distortion, the Z value of space point is compensated through stimulant data. Then the improvement of projector calibration is completed successfully after bundle adjustment and the calculation to the projector parameters again.
{"title":"Research on the improvement of slide projector calibration precision","authors":"Zheng Li, Luo Jun, L. Tao","doi":"10.1109/CINC.2010.5643848","DOIUrl":"https://doi.org/10.1109/CINC.2010.5643848","url":null,"abstract":"The camera calibration and projector calibration are very crucial since the coordinate computation depends on the accuracy of calibration. This calibration procedure consists of camera calibration and projector calibration, done in this order so that the calibrated camera can be used to calibrate the projector. The digital camera is firstly calibrated by the algorithm with 2D direct linear transformation (2D-DLT) and collinear equations. Based on the same calibration model, the calibration precision of projector is lower than that of CCD camera. It is analyzed by the following aspects, such as image and space. For the space point error by paper thickness and distortion, the Z value of space point is compensated through stimulant data. Then the improvement of projector calibration is completed successfully after bundle adjustment and the calculation to the projector parameters again.","PeriodicalId":227004,"journal":{"name":"2010 Second International Conference on Computational Intelligence and Natural Computing","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123138744","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 : 2010-11-22DOI: 10.1109/CINC.2010.5643904
Deng Mei-yin, Ren Weiwei, Zhang Jinliang
Many oilfield have gone into the intermediary or later stage of development, with the raise of the development level, reservoir geologic research urgently need some new practical technique method to describe reservoir properties accurately and carefully. Basing on principles of sedimentology and quantitative analysis of well logging interpretation, carrying out micro-phase study, and using the research results of micro-facies to constrain the spatial distribution of reservoir parameters. Establishing a fine reservoir geological model, and solve the problem of sedimentary facies modeling can not effective combination in the process of modeling. Practices have proved that this method is feasible, especially in the heterogeneity reservoirs. Application of phase control modeling technique not only provide a more accurate reservoir property model, but also can provide a geological basis for the remaining petroleum development and development adjustment.
{"title":"Application of facies-controlling stochastic modeling technique in heterogeneity reservoir and its effective application analysis","authors":"Deng Mei-yin, Ren Weiwei, Zhang Jinliang","doi":"10.1109/CINC.2010.5643904","DOIUrl":"https://doi.org/10.1109/CINC.2010.5643904","url":null,"abstract":"Many oilfield have gone into the intermediary or later stage of development, with the raise of the development level, reservoir geologic research urgently need some new practical technique method to describe reservoir properties accurately and carefully. Basing on principles of sedimentology and quantitative analysis of well logging interpretation, carrying out micro-phase study, and using the research results of micro-facies to constrain the spatial distribution of reservoir parameters. Establishing a fine reservoir geological model, and solve the problem of sedimentary facies modeling can not effective combination in the process of modeling. Practices have proved that this method is feasible, especially in the heterogeneity reservoirs. Application of phase control modeling technique not only provide a more accurate reservoir property model, but also can provide a geological basis for the remaining petroleum development and development adjustment.","PeriodicalId":227004,"journal":{"name":"2010 Second International Conference on Computational Intelligence and Natural Computing","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122262983","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 : 2010-11-22DOI: 10.1109/CINC.2010.5643899
Jinlong Jiang, Daifeng Zha, Qian Zhang
A fast algorithm of logarithm-form fractional lower-order spectrums is proposed in this paper in order to be facilitative for practice application that traditional fractional lower-order spectrums need to identify characteristic exponent alpha and improve its calculating speed for alpha stable distribution signal or noise. The algorithm is not depended on a prior knowledge of characteristic exponent alpha, and ease to apply to DSP systems by assembly language instructions and fast Fourier transform (FFT). The application in a TMS320VC5416 DSP system shows that the algorithm is effective.
{"title":"A fast algorithm of logarithm-form fractional lower-order spectrums","authors":"Jinlong Jiang, Daifeng Zha, Qian Zhang","doi":"10.1109/CINC.2010.5643899","DOIUrl":"https://doi.org/10.1109/CINC.2010.5643899","url":null,"abstract":"A fast algorithm of logarithm-form fractional lower-order spectrums is proposed in this paper in order to be facilitative for practice application that traditional fractional lower-order spectrums need to identify characteristic exponent alpha and improve its calculating speed for alpha stable distribution signal or noise. The algorithm is not depended on a prior knowledge of characteristic exponent alpha, and ease to apply to DSP systems by assembly language instructions and fast Fourier transform (FFT). The application in a TMS320VC5416 DSP system shows that the algorithm is effective.","PeriodicalId":227004,"journal":{"name":"2010 Second International Conference on Computational Intelligence and Natural Computing","volume":"80 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127603010","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 : 2010-11-22DOI: 10.1109/CINC.2010.5643732
Cui Guang-zuo
This paper, based on the cognitive architecture of learning and thinking [7], proposes a cognitive learning model in classroom interaction, which bridges the gap between classroom interaction and learning outcome. In this model, a learning activity is defined as a cognitive matrix at a low level in which M rows and N columns are set, each row represents a logical cognitive step of learning procedure, and each column contains all the contents processed by a corresponding component in cognitive architecture. At the meantime, the learning outcome can be produced from contents of column LTDM, AO and AADM of cognitive architecture [7]. A memory consolidation model is also proposed and simulated with PDP tool. Experiment of teaching concept knowledge indicates the effectiveness of the proposed models.
{"title":"A cognitive learning model in classroom interaction","authors":"Cui Guang-zuo","doi":"10.1109/CINC.2010.5643732","DOIUrl":"https://doi.org/10.1109/CINC.2010.5643732","url":null,"abstract":"This paper, based on the cognitive architecture of learning and thinking [7], proposes a cognitive learning model in classroom interaction, which bridges the gap between classroom interaction and learning outcome. In this model, a learning activity is defined as a cognitive matrix at a low level in which M rows and N columns are set, each row represents a logical cognitive step of learning procedure, and each column contains all the contents processed by a corresponding component in cognitive architecture. At the meantime, the learning outcome can be produced from contents of column LTDM, AO and AADM of cognitive architecture [7]. A memory consolidation model is also proposed and simulated with PDP tool. Experiment of teaching concept knowledge indicates the effectiveness of the proposed models.","PeriodicalId":227004,"journal":{"name":"2010 Second International Conference on Computational Intelligence and Natural Computing","volume":"247 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133785322","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 : 2010-11-22DOI: 10.1109/CINC.2010.5643751
Wenbing Lu, Xiaowei Bi, P. Li, Bin Hu
Traditional TWACS system can realize the uplink demodulation by judging the positive and negative of sampling modulation current's accumulation. The demodulation algorithm often uses the square wave to match, but this way is lack of anti-interference ability. In this paper, according to the uplink encoding and the difference time domain, the sampling current signal can be synthesized to a sine signal nearly. Then with the help of the complex wavelet analysis and the algorithm, the synthesis sampling value can be handled and the demodulation will be realized. The simulation and experimental results indicate that the algorithm effectively improve the performance of the traditional demodulation method.
{"title":"Technique of upstream signal detection in TWACS","authors":"Wenbing Lu, Xiaowei Bi, P. Li, Bin Hu","doi":"10.1109/CINC.2010.5643751","DOIUrl":"https://doi.org/10.1109/CINC.2010.5643751","url":null,"abstract":"Traditional TWACS system can realize the uplink demodulation by judging the positive and negative of sampling modulation current's accumulation. The demodulation algorithm often uses the square wave to match, but this way is lack of anti-interference ability. In this paper, according to the uplink encoding and the difference time domain, the sampling current signal can be synthesized to a sine signal nearly. Then with the help of the complex wavelet analysis and the algorithm, the synthesis sampling value can be handled and the demodulation will be realized. The simulation and experimental results indicate that the algorithm effectively improve the performance of the traditional demodulation method.","PeriodicalId":227004,"journal":{"name":"2010 Second International Conference on Computational Intelligence and Natural Computing","volume":"120 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130121824","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 : 2010-11-22DOI: 10.1109/CINC.2010.5643825
Liang Tang, Mingzhong Yang, Xiaomin Wang
The firing process of roller kiln consists of several sub-processes and there exists unknown complex nonlinear mapping between the sub-process set points and the final firing quality. To meet this demand, a training algorithm for the radial basis function (RBF) network using GAP method based on the “significance” of a specified neuron is proposed in the paper. The training algorithm which uses GAP method to train the network has a number of advantages such as could be constructed and updated based on the new data sequentially collected from the real process in order to optimize the set point of each sub-process dynamically. Simulation results shows that this training system can work accurately and reliably.
{"title":"Modelling and optimization of the firing process for roller kiln using GAP-RBF neutral network","authors":"Liang Tang, Mingzhong Yang, Xiaomin Wang","doi":"10.1109/CINC.2010.5643825","DOIUrl":"https://doi.org/10.1109/CINC.2010.5643825","url":null,"abstract":"The firing process of roller kiln consists of several sub-processes and there exists unknown complex nonlinear mapping between the sub-process set points and the final firing quality. To meet this demand, a training algorithm for the radial basis function (RBF) network using GAP method based on the “significance” of a specified neuron is proposed in the paper. The training algorithm which uses GAP method to train the network has a number of advantages such as could be constructed and updated based on the new data sequentially collected from the real process in order to optimize the set point of each sub-process dynamically. Simulation results shows that this training system can work accurately and reliably.","PeriodicalId":227004,"journal":{"name":"2010 Second International Conference on Computational Intelligence and Natural Computing","volume":"451 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133270043","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 : 2010-11-22DOI: 10.1109/CINC.2010.5643890
Yuzhen Liu, Shoufu Li
In order to improve the ability of neighborhood search of differential evolutionary (DE) algorithm, we propose a new variant of DE with linear neighborhood search, called LiNDE, for global optimization problems (GOPs). LiNDE employs a linear combination of triple vectors taken randomly from evolutionary population. The main characteristics of LiNDE are less parameters and powerful neighborhood search ability. Experimental studies are carried out on a benchmark set, and the results show that LiNDE significantly improved the performance of DE.
{"title":"Differential Evolution with Neighborhood Search","authors":"Yuzhen Liu, Shoufu Li","doi":"10.1109/CINC.2010.5643890","DOIUrl":"https://doi.org/10.1109/CINC.2010.5643890","url":null,"abstract":"In order to improve the ability of neighborhood search of differential evolutionary (DE) algorithm, we propose a new variant of DE with linear neighborhood search, called LiNDE, for global optimization problems (GOPs). LiNDE employs a linear combination of triple vectors taken randomly from evolutionary population. The main characteristics of LiNDE are less parameters and powerful neighborhood search ability. Experimental studies are carried out on a benchmark set, and the results show that LiNDE significantly improved the performance of DE.","PeriodicalId":227004,"journal":{"name":"2010 Second International Conference on Computational Intelligence and Natural Computing","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133893219","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 : 2010-11-22DOI: 10.1109/CINC.2010.5643768
Zhang Chun, Fan Xiying
ℌFlower Basin Effectℍ exists universally in foreign language study. This paper first studied incomparable superiority of classroom teaching(ℌflower basinℍ environment) to language acquisition in natural environment , as well as its inherent limitations. In order to overcome limitations of classroom teaching and maximize the learning efficiency, the paper explored the development of the students' autonomous learning ability in the new environment ----network and multimedia environment. The main ways are: we should socialize classroom teaching, give students diagnosis and training of their learning strategies, adopt teaching mode combining classroom teaching and network autonomous learning and establish network autonomous learning resource bank.
{"title":"ℌFlower basin effectℍ and autonomous foreign language learning with the aid of network and multimedia","authors":"Zhang Chun, Fan Xiying","doi":"10.1109/CINC.2010.5643768","DOIUrl":"https://doi.org/10.1109/CINC.2010.5643768","url":null,"abstract":"ℌFlower Basin Effectℍ exists universally in foreign language study. This paper first studied incomparable superiority of classroom teaching(ℌflower basinℍ environment) to language acquisition in natural environment , as well as its inherent limitations. In order to overcome limitations of classroom teaching and maximize the learning efficiency, the paper explored the development of the students' autonomous learning ability in the new environment ----network and multimedia environment. The main ways are: we should socialize classroom teaching, give students diagnosis and training of their learning strategies, adopt teaching mode combining classroom teaching and network autonomous learning and establish network autonomous learning resource bank.","PeriodicalId":227004,"journal":{"name":"2010 Second International Conference on Computational Intelligence and Natural Computing","volume":"126 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122050845","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 : 2010-11-22DOI: 10.1109/CINC.2010.5643833
Yanping Yang, E. Song, Guangzhi Ma
The goal of active learning is to minimize the amount of labeled data required for machine learning. Some methods have focused on exploiting the samples with high uncertainty, but those methods fail in getting a representative set of the data samples. Other methods try to explore the representative samples by utilizing the prior distribution of the dataset. However, they are often computationally expensive and need a large amount of labeled data for initialization. In this paper we develop a hierarchical exploration based active learning algorithm that takes into account both the distribution of the dataset and the decision boundary of the current hypothesis. Our method uses the support vector machine (SVM) as the classifier. The hierarchical clustering algorithm is used to discover the dataset's structure step by step in a top-down manner. In each step of hierarchical structure discovery, the representative samples will be queried for labels to check the relative cluster's purity. The cluster with low purity will be divided further. After the draft SVM model is built with those representative samples, the uncertain samples near decision boundary will be further labeled if it can help reduce the entropy of the classifier. To show the effectiveness of the proposed method, our proposed method is compared with five state-of-art algorithms on six datasets from UCI. Our method shows the best performance through the comparison.
{"title":"Hierarchical exploration based active learning with support vector machine","authors":"Yanping Yang, E. Song, Guangzhi Ma","doi":"10.1109/CINC.2010.5643833","DOIUrl":"https://doi.org/10.1109/CINC.2010.5643833","url":null,"abstract":"The goal of active learning is to minimize the amount of labeled data required for machine learning. Some methods have focused on exploiting the samples with high uncertainty, but those methods fail in getting a representative set of the data samples. Other methods try to explore the representative samples by utilizing the prior distribution of the dataset. However, they are often computationally expensive and need a large amount of labeled data for initialization. In this paper we develop a hierarchical exploration based active learning algorithm that takes into account both the distribution of the dataset and the decision boundary of the current hypothesis. Our method uses the support vector machine (SVM) as the classifier. The hierarchical clustering algorithm is used to discover the dataset's structure step by step in a top-down manner. In each step of hierarchical structure discovery, the representative samples will be queried for labels to check the relative cluster's purity. The cluster with low purity will be divided further. After the draft SVM model is built with those representative samples, the uncertain samples near decision boundary will be further labeled if it can help reduce the entropy of the classifier. To show the effectiveness of the proposed method, our proposed method is compared with five state-of-art algorithms on six datasets from UCI. Our method shows the best performance through the comparison.","PeriodicalId":227004,"journal":{"name":"2010 Second International Conference on Computational Intelligence and Natural Computing","volume":"135 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122134927","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：