Pub Date : 2009-12-28DOI: 10.1109/ICACIA.2009.5361142
He Jia, Zhang Xiangfeng
This paper proposed a new algorithm of facial feature extraction and recognition based on Curvelet transform and SVD (Singular Value Decomposition). Firstly, the method carries on the Curvelet transform to the face images, extracts the Curvelet energy features of low frequency and the high frequency, and then carries on the singular value compression and feature fusion to this component. Finally, by using the nearest neighbor classifier in the ORL person face database, the classified recognition was carried out so that to confirm the validity of the algorithm.
{"title":"Facial feature extraction and recognition based on Curvelet transform and SVD","authors":"He Jia, Zhang Xiangfeng","doi":"10.1109/ICACIA.2009.5361142","DOIUrl":"https://doi.org/10.1109/ICACIA.2009.5361142","url":null,"abstract":"This paper proposed a new algorithm of facial feature extraction and recognition based on Curvelet transform and SVD (Singular Value Decomposition). Firstly, the method carries on the Curvelet transform to the face images, extracts the Curvelet energy features of low frequency and the high frequency, and then carries on the singular value compression and feature fusion to this component. Finally, by using the nearest neighbor classifier in the ORL person face database, the classified recognition was carried out so that to confirm the validity of the algorithm.","PeriodicalId":423210,"journal":{"name":"2009 International Conference on Apperceiving Computing and Intelligence Analysis","volume":"35 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":"133735069","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/ICACIA.2009.5361130
Yong Liu, Sunjun Liu
In this thesis, memory principle and ant colony algorithm are fused and applied in intrusion detection system. The method of controlling pheromone used in ant colony algorithm is applied to simulate the memory process of human brain, and the concept of pheromone is put forth. The processes of memorizing and forgetting are reasonably interpreted through the increase and decrease of pheromone, and in the algorithm, new memory algorithm is formed to finish the processes of memorizing and forgetting after considering the impact of abnormal characteristics weight value on pheromone. Examples show that the algorithm is capable of realizing memorizing and forgetting processes and increasing the robustness and self adaptability of IDS.
{"title":"Intrusion detection system based on ant colony memory principle","authors":"Yong Liu, Sunjun Liu","doi":"10.1109/ICACIA.2009.5361130","DOIUrl":"https://doi.org/10.1109/ICACIA.2009.5361130","url":null,"abstract":"In this thesis, memory principle and ant colony algorithm are fused and applied in intrusion detection system. The method of controlling pheromone used in ant colony algorithm is applied to simulate the memory process of human brain, and the concept of pheromone is put forth. The processes of memorizing and forgetting are reasonably interpreted through the increase and decrease of pheromone, and in the algorithm, new memory algorithm is formed to finish the processes of memorizing and forgetting after considering the impact of abnormal characteristics weight value on pheromone. Examples show that the algorithm is capable of realizing memorizing and forgetting processes and increasing the robustness and self adaptability of IDS.","PeriodicalId":423210,"journal":{"name":"2009 International Conference on Apperceiving Computing and Intelligence Analysis","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":"120961152","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/ICACIA.2009.5361109
Kexin Jia, Zishu He
In this paper, the statistic characteristics of the digital channelizied receiver are studied in the context of additive white Gaussian noise. Based on the statistic characteristics, the automatic censored mean level (ACML) detector is proposed and its performance is analyzed by simulation. The results show that the simulated performance curves are very similar to the theoretical curves for the detection of complex sinusoid signal. The detection performance degrades if the input signal bandwidth is large compared to an channel bandwidth.
{"title":"Detection performance analysis of the digital channelized receiver-based ACML detector","authors":"Kexin Jia, Zishu He","doi":"10.1109/ICACIA.2009.5361109","DOIUrl":"https://doi.org/10.1109/ICACIA.2009.5361109","url":null,"abstract":"In this paper, the statistic characteristics of the digital channelizied receiver are studied in the context of additive white Gaussian noise. Based on the statistic characteristics, the automatic censored mean level (ACML) detector is proposed and its performance is analyzed by simulation. The results show that the simulated performance curves are very similar to the theoretical curves for the detection of complex sinusoid signal. The detection performance degrades if the input signal bandwidth is large compared to an channel bandwidth.","PeriodicalId":423210,"journal":{"name":"2009 International Conference on Apperceiving Computing and Intelligence Analysis","volume":"3 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":"122040266","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/ICACIA.2009.5361134
Guang-yan Wang, Xiaoqun Zhao, Xia Wang
The proposed speech enhancement system combining the spectral subtraction and wavelet thresholding techniques together is used to reduce the additive wideband noise. The objective of this paper is to research the adaptability and efficiency of the wavelet types and levels to the noises. Large amount of experiments were implemented in different schemes according to the types of the wavelet function, thresholding criterions and the modifying manners for the noise wavelet coefficients. Simulation results in terms of both objective and subjective evaluations show that the 5-layer db3 wavelet function using heursure criterion, incorporating with the first-layer coefficient been modified, is more efficient than other schemes of the wavelet thresholding denoising method designed in the experimental procedure.
{"title":"Speech enhancement based on the combination of spectral subtraction and wavelet thresholding","authors":"Guang-yan Wang, Xiaoqun Zhao, Xia Wang","doi":"10.1109/ICACIA.2009.5361134","DOIUrl":"https://doi.org/10.1109/ICACIA.2009.5361134","url":null,"abstract":"The proposed speech enhancement system combining the spectral subtraction and wavelet thresholding techniques together is used to reduce the additive wideband noise. The objective of this paper is to research the adaptability and efficiency of the wavelet types and levels to the noises. Large amount of experiments were implemented in different schemes according to the types of the wavelet function, thresholding criterions and the modifying manners for the noise wavelet coefficients. Simulation results in terms of both objective and subjective evaluations show that the 5-layer db3 wavelet function using heursure criterion, incorporating with the first-layer coefficient been modified, is more efficient than other schemes of the wavelet thresholding denoising method designed in the experimental procedure.","PeriodicalId":423210,"journal":{"name":"2009 International Conference on Apperceiving Computing and Intelligence Analysis","volume":"114 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":"121702841","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/ICACIA.2009.5361143
Hui Gao, Yan Fu, Jia-Ping Li
The classical union-find algorithm is the basis for many graph algorithms and for dealing with equality. The easiest way to implement concurrent objects is by means of classical software solutions, but this leads to blocking when the process that holds exclusive access to the object is delayed or stops functioning. Thus we require our solutions to the data structure problem have the lock-free property. In this paper, we present an efficient lock-free algorithm for union-find with deletion, which promises more robust performance and reliability than conventional lock-based implementations.
{"title":"A lock-free algorithm for union-find with deletion","authors":"Hui Gao, Yan Fu, Jia-Ping Li","doi":"10.1109/ICACIA.2009.5361143","DOIUrl":"https://doi.org/10.1109/ICACIA.2009.5361143","url":null,"abstract":"The classical union-find algorithm is the basis for many graph algorithms and for dealing with equality. The easiest way to implement concurrent objects is by means of classical software solutions, but this leads to blocking when the process that holds exclusive access to the object is delayed or stops functioning. Thus we require our solutions to the data structure problem have the lock-free property. In this paper, we present an efficient lock-free algorithm for union-find with deletion, which promises more robust performance and reliability than conventional lock-based implementations.","PeriodicalId":423210,"journal":{"name":"2009 International Conference on Apperceiving Computing and Intelligence Analysis","volume":"2 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":"114246295","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/ICACIA.2009.5361166
H. Tai, Yadong Jiang, G. Xie
A novel chemical micro-gas sensor array composed of polyaniline (PANI) and its nanocomposite thin film was fabricated for NH3, CO and H2 gas classification. Itanium dioxide (TiO2), indium oxide (In2O3) and multi-walled carbon nanotube (PANI/MWNT) combined with PANI were chosen as the sensing materials by the step-clustering analysis. The normalization method was developed to eliminate the dispersion of the array data. Probabilistic neuron network (PNN) was designed and trained with the processed data, and the different discrimination results were discussed under the different spread constant (SP). The accurate classification result was achieved when SP was set as 0.05 or 0.1.
{"title":"Development of polyaniline nanocomposite thin film micro-gas sensor array for the qualitative analysis of inorganic vapor","authors":"H. Tai, Yadong Jiang, G. Xie","doi":"10.1109/ICACIA.2009.5361166","DOIUrl":"https://doi.org/10.1109/ICACIA.2009.5361166","url":null,"abstract":"A novel chemical micro-gas sensor array composed of polyaniline (PANI) and its nanocomposite thin film was fabricated for NH3, CO and H2 gas classification. Itanium dioxide (TiO2), indium oxide (In2O3) and multi-walled carbon nanotube (PANI/MWNT) combined with PANI were chosen as the sensing materials by the step-clustering analysis. The normalization method was developed to eliminate the dispersion of the array data. Probabilistic neuron network (PNN) was designed and trained with the processed data, and the different discrimination results were discussed under the different spread constant (SP). The accurate classification result was achieved when SP was set as 0.05 or 0.1.","PeriodicalId":423210,"journal":{"name":"2009 International Conference on Apperceiving Computing and Intelligence Analysis","volume":"41 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":"125610728","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/ICACIA.2009.5361115
Wenming Yuan, Jianhua Xiao, Dong Wang
RFID complex event processing technology is the key point of RFID researching in these years. For the trend of great network application of RFID, this paper presents an RFID complex event processing model according to the features of RFID data and the disadvantage of the current models. Besides, the application in real scenario is also discussed.
{"title":"A complex event processing model based on RFID network","authors":"Wenming Yuan, Jianhua Xiao, Dong Wang","doi":"10.1109/ICACIA.2009.5361115","DOIUrl":"https://doi.org/10.1109/ICACIA.2009.5361115","url":null,"abstract":"RFID complex event processing technology is the key point of RFID researching in these years. For the trend of great network application of RFID, this paper presents an RFID complex event processing model according to the features of RFID data and the disadvantage of the current models. Besides, the application in real scenario is also discussed.","PeriodicalId":423210,"journal":{"name":"2009 International Conference on Apperceiving Computing and Intelligence Analysis","volume":"86 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":"129356595","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/ICACIA.2009.5361085
Pu Han, Jianming Liao
This paper describes the basic principles that using adaboost arithmetic to achieve face detection, through OPENCV software, selects the expansion of the harr-like characteristics and achieves the training of face detection classifier. Finally, we analyze how the number of the classifiers affects the results of the experiments, and then we give a more appropriate general size for the samples after comparison.
{"title":"Face detection based on adaboost","authors":"Pu Han, Jianming Liao","doi":"10.1109/ICACIA.2009.5361085","DOIUrl":"https://doi.org/10.1109/ICACIA.2009.5361085","url":null,"abstract":"This paper describes the basic principles that using adaboost arithmetic to achieve face detection, through OPENCV software, selects the expansion of the harr-like characteristics and achieves the training of face detection classifier. Finally, we analyze how the number of the classifiers affects the results of the experiments, and then we give a more appropriate general size for the samples after comparison.","PeriodicalId":423210,"journal":{"name":"2009 International Conference on Apperceiving Computing and Intelligence Analysis","volume":"39 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":"123061850","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/ICACIA.2009.5361063
Jin-qiu Li, Di Liu
This paper designs and implements a MBS (Micro Bank System) based on IBM Z900 to fit the rapid development of small bank business. First, the meaning of implementing MBS is analyzed. Then the details of three layers architecture are described. Then the details of designing the Micro Bank System's several sub-systems are described. The designation of MBS provides a convenient way to expand bank sub-system. Finally, the result of stress test of MBS was shown by compare with different number of accounts in database.
{"title":"Micro Bank System based on mainframe","authors":"Jin-qiu Li, Di Liu","doi":"10.1109/ICACIA.2009.5361063","DOIUrl":"https://doi.org/10.1109/ICACIA.2009.5361063","url":null,"abstract":"This paper designs and implements a MBS (Micro Bank System) based on IBM Z900 to fit the rapid development of small bank business. First, the meaning of implementing MBS is analyzed. Then the details of three layers architecture are described. Then the details of designing the Micro Bank System's several sub-systems are described. The designation of MBS provides a convenient way to expand bank sub-system. Finally, the result of stress test of MBS was shown by compare with different number of accounts in database.","PeriodicalId":423210,"journal":{"name":"2009 International Conference on Apperceiving Computing and Intelligence Analysis","volume":"1 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":"124580766","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/ICACIA.2009.5361128
Ping Sun, Yadong Jiang, G. Xie, Junsheng Yu, Xian Li, Jia Hu
In this paper, solvent-functionalized CNTs are coated on mass-sensitive quartz crystal microbalance (QCM) devices to study their gas-sensing properties for volatile organic compounds (VOCs) at room temperature. The results indicate that different solvent-functionalized CNTs under the same conditions have the dissimilar response and similar VOCs to the polarity of the solvent show better gas-sensing properties such as high sensitivity, good repeatability and reversibility. This has a certain significance to improve the selectivity of CNT based sensors.
{"title":"Gas sensitivities of solvent-functionalized CNTs to volatile organic compounds","authors":"Ping Sun, Yadong Jiang, G. Xie, Junsheng Yu, Xian Li, Jia Hu","doi":"10.1109/ICACIA.2009.5361128","DOIUrl":"https://doi.org/10.1109/ICACIA.2009.5361128","url":null,"abstract":"In this paper, solvent-functionalized CNTs are coated on mass-sensitive quartz crystal microbalance (QCM) devices to study their gas-sensing properties for volatile organic compounds (VOCs) at room temperature. The results indicate that different solvent-functionalized CNTs under the same conditions have the dissimilar response and similar VOCs to the polarity of the solvent show better gas-sensing properties such as high sensitivity, good repeatability and reversibility. This has a certain significance to improve the selectivity of CNT based sensors.","PeriodicalId":423210,"journal":{"name":"2009 International Conference on Apperceiving Computing and Intelligence Analysis","volume":"28 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":"131726151","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：