A novel method named wavelet packet transform based Elman recurrent neural network (WPTERNN) was proposed for simultaneous determination of Co (II), Zn (II) and Cu (II) by combining wavelet packet denoising with Elman recurrent neural network. Wavelet packet representations of signals provided a local time–frequency description, thus in the wavelet packet domain, the quality of the noise removal can be improved. Elman recurrent network was applied for non-linear multivariate calibration. In this case, by trials, wavelet function, decomposition level and numbers of hidden nodes for WPTERNN method were selected as Daubechies 2, 3 and 9 respectively. A program PWPTERNN was designed to perform simultaneous determination of Co (II), Zn (II) and Cu (II). The relative standard errors of prediction (RSEP) for all components with WPTERNN, Elman recurrent neural network (ERNN) and partial least squares (PLS), principal component regression (PCR) and Fourier transform based PCR (FTPCR) were 6.7, 14.7, 9.2, 25.6 and 25.2 % respectively. Experimental results demonstrated that the WPTERRN method had the best performance among the five methods.
{"title":"Improvement of Prediction Ability of Multicomponent Regression Model","authors":"Ling Gao, S. Ren","doi":"10.1109/WKDD.2009.82","DOIUrl":"https://doi.org/10.1109/WKDD.2009.82","url":null,"abstract":"A novel method named wavelet packet transform based Elman recurrent neural network (WPTERNN) was proposed for simultaneous determination of Co (II), Zn (II) and Cu (II) by combining wavelet packet denoising with Elman recurrent neural network. Wavelet packet representations of signals provided a local time–frequency description, thus in the wavelet packet domain, the quality of the noise removal can be improved. Elman recurrent network was applied for non-linear multivariate calibration. In this case, by trials, wavelet function, decomposition level and numbers of hidden nodes for WPTERNN method were selected as Daubechies 2, 3 and 9 respectively. A program PWPTERNN was designed to perform simultaneous determination of Co (II), Zn (II) and Cu (II). The relative standard errors of prediction (RSEP) for all components with WPTERNN, Elman recurrent neural network (ERNN) and partial least squares (PLS), principal component regression (PCR) and Fourier transform based PCR (FTPCR) were 6.7, 14.7, 9.2, 25.6 and 25.2 % respectively. Experimental results demonstrated that the WPTERRN method had the best performance among the five methods.","PeriodicalId":430882,"journal":{"name":"2008 Congress on Image and Signal Processing","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127786470","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}
Fude Guo, Yahui Yang, Tao Ning, Bin Chen, Lieijin Guo
In this paper an edge detection algorithm base on wavelet transform with Gaussian filter was proposed. In this algorithm original images are firstly converted into gray images and then each pixel was analyzed using wavelet transform to find the local maximum of the gray gradient of each pixel along the phase angle direction and compared with a given threshold value, through which real edge can be kept and fake ones will be eliminated. In the computation of local maximum, the gray gradients computed in eight directions, which can improve precision of edge detection. After the investigation of influence of filter length, scale and threshold value on the edge detection the proposed algorithm is validated by the comparison with N.L. Fenández-García’s Minimean and Minimax methods for 100 real color images. The extraction result is more close to the real image which indicates the algorithm is effective and can be used to extract edges in different research areas.
{"title":"Edge Detection Based on Wavelet Analysis with Gaussian Filter","authors":"Fude Guo, Yahui Yang, Tao Ning, Bin Chen, Lieijin Guo","doi":"10.1109/CISP.2008.369","DOIUrl":"https://doi.org/10.1109/CISP.2008.369","url":null,"abstract":"In this paper an edge detection algorithm base on wavelet transform with Gaussian filter was proposed. In this algorithm original images are firstly converted into gray images and then each pixel was analyzed using wavelet transform to find the local maximum of the gray gradient of each pixel along the phase angle direction and compared with a given threshold value, through which real edge can be kept and fake ones will be eliminated. In the computation of local maximum, the gray gradients computed in eight directions, which can improve precision of edge detection. After the investigation of influence of filter length, scale and threshold value on the edge detection the proposed algorithm is validated by the comparison with N.L. Fenández-García’s Minimean and Minimax methods for 100 real color images. The extraction result is more close to the real image which indicates the algorithm is effective and can be used to extract edges in different research areas.","PeriodicalId":430882,"journal":{"name":"2008 Congress on Image and Signal Processing","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115408430","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}
In order to encapsulate data and to convey information more efficiently and more security, a draft frame based on active block ciphers for application layer of Internet which could transmit orange data into semantic security and semantic integrity was designed according to scalable purpose. To different network environment, there were different intelligent choices about block cipher algorithms to enforce secure. A proposal which used different block cipher algorithms in reason was demonstrated its security. The secure structure layer was designed by intelligent method. It took the approach that both the intelligent access authentication based on block ciphers and data secure by block ciphers were flexible and scalable means for information secure conveyed through the network application layer.
{"title":"The Intelligent Secure Structure Based on Active Block Ciphers for Application Layer of Internet","authors":"Lan Luo, Zhiguang Qin, Shaoquan Jiang","doi":"10.1109/CISP.2008.22","DOIUrl":"https://doi.org/10.1109/CISP.2008.22","url":null,"abstract":"In order to encapsulate data and to convey information more efficiently and more security, a draft frame based on active block ciphers for application layer of Internet which could transmit orange data into semantic security and semantic integrity was designed according to scalable purpose. To different network environment, there were different intelligent choices about block cipher algorithms to enforce secure. A proposal which used different block cipher algorithms in reason was demonstrated its security. The secure structure layer was designed by intelligent method. It took the approach that both the intelligent access authentication based on block ciphers and data secure by block ciphers were flexible and scalable means for information secure conveyed through the network application layer.","PeriodicalId":430882,"journal":{"name":"2008 Congress on Image and Signal Processing","volume":"109 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115660877","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This paper proposed an interactive genetic algorithm (IGA) for football video scenes retrieval with multimodal features. Four audio-visual features (average shot duration, average motion activity average sound energy, and average speech rate) were extracted from each of the videos. Then they were encoded as chromosomes and indexed into search table. First, the proposed algorithm randomly selected the videos from the initial population of videos database, and the user selected what he (she) wanted in mind. Next, the associated chromosomes of selected videos were regarded as target chromosomes after crossover and chromosomes in the database videos were compared based on similarity function to obtain the most similar videos as solutions of the next generation. By iterating this process, a new population of videos was retrieved. This approach of retrieval shows about 84% of effectiveness on the average over 200 videos.
{"title":"Footballs Video Scene Retrieval with Interactive Genetic Algorithm","authors":"Qing-kai Bu, A. Hu","doi":"10.1109/CISP.2008.137","DOIUrl":"https://doi.org/10.1109/CISP.2008.137","url":null,"abstract":"This paper proposed an interactive genetic algorithm (IGA) for football video scenes retrieval with multimodal features. Four audio-visual features (average shot duration, average motion activity average sound energy, and average speech rate) were extracted from each of the videos. Then they were encoded as chromosomes and indexed into search table. First, the proposed algorithm randomly selected the videos from the initial population of videos database, and the user selected what he (she) wanted in mind. Next, the associated chromosomes of selected videos were regarded as target chromosomes after crossover and chromosomes in the database videos were compared based on similarity function to obtain the most similar videos as solutions of the next generation. By iterating this process, a new population of videos was retrieved. This approach of retrieval shows about 84% of effectiveness on the average over 200 videos.","PeriodicalId":430882,"journal":{"name":"2008 Congress on Image and Signal Processing","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124381732","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
With the ubiquitous application of Internet and wireless networks, H.264 video communication becomes more and more popular. However, due to the high-efficiently predictive coding and the variable length entropy coding, it is more sensitive to transmission errors. Error concealment (EC) is just an approach to utilize the spatial and temporal correlations to conceal the corrupted region. In this paper, first we propose variable block size error concealment (VBSEC) scheme inspired by variable block size motion estimation (VBSME) in H.264. This scheme provides four EC modes and four sub-block partitions. The whole corrupted macro-block (MB) will be divided into variable block size adoptively according to the actual motion. More precise motion vectors (MV) will be predicted for each sub-block Then MV refinement (MVR) scheme is proposed to refine the MV of the heterogeneous sub-block by utilizing three step search (TSS) algorithm adaptively. Both VBSEC and MVR are based on our improved spatio-temporal boundary matching algorithm (STBMA). By utilizing these schemes, we can reconstruct the corrupted MB in the inter frame more accurately. The experimental results show that our proposed scheme can obtain maximum PSNR gain up to 1.82dB and 1.52dB, respectively compared with the boundary matching algorithm (BMA) adopted in the JM11.0 reference software and STBMA.
{"title":"Adaptive Motion Vector Retrieval Schemes for H.264 Error Concealment","authors":"Lei Wang, Jun Wang, S. Goto, T. Ikenaga","doi":"10.1109/CISP.2008.334","DOIUrl":"https://doi.org/10.1109/CISP.2008.334","url":null,"abstract":"With the ubiquitous application of Internet and wireless networks, H.264 video communication becomes more and more popular. However, due to the high-efficiently predictive coding and the variable length entropy coding, it is more sensitive to transmission errors. Error concealment (EC) is just an approach to utilize the spatial and temporal correlations to conceal the corrupted region. In this paper, first we propose variable block size error concealment (VBSEC) scheme inspired by variable block size motion estimation (VBSME) in H.264. This scheme provides four EC modes and four sub-block partitions. The whole corrupted macro-block (MB) will be divided into variable block size adoptively according to the actual motion. More precise motion vectors (MV) will be predicted for each sub-block Then MV refinement (MVR) scheme is proposed to refine the MV of the heterogeneous sub-block by utilizing three step search (TSS) algorithm adaptively. Both VBSEC and MVR are based on our improved spatio-temporal boundary matching algorithm (STBMA). By utilizing these schemes, we can reconstruct the corrupted MB in the inter frame more accurately. The experimental results show that our proposed scheme can obtain maximum PSNR gain up to 1.82dB and 1.52dB, respectively compared with the boundary matching algorithm (BMA) adopted in the JM11.0 reference software and STBMA.","PeriodicalId":430882,"journal":{"name":"2008 Congress on Image and Signal Processing","volume":"184 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121833482","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}
In this paper, a robust FGS video transmission scheme is proposed for streaming video over bandwidth-constrained packet loss channel, which aims to reducing both the overall distortion and quality fluctuation at the same time. We first use channel budget and packet loss property to determine the bits of enhancement layers that should be allocated per frame. Then unequal loss protection (ULP) using forward error correction (FEC) is applied to different FGS enhancement layers based on their significance. Effects of quality fluctuations by packet loss are considered while optimizing FGS bits allocation and FGS unequal loss protection. Experimental results show that the proposed method can guarantee received video quality and efficiently reduce quality fluctuations.
{"title":"Joint Source/FEC Rate Optimization for Constant Quality FGS Video Streaming","authors":"Sun Gang, Xing Wei, Wei Ping, Lu Dongming","doi":"10.1109/CISP.2008.326","DOIUrl":"https://doi.org/10.1109/CISP.2008.326","url":null,"abstract":"In this paper, a robust FGS video transmission scheme is proposed for streaming video over bandwidth-constrained packet loss channel, which aims to reducing both the overall distortion and quality fluctuation at the same time. We first use channel budget and packet loss property to determine the bits of enhancement layers that should be allocated per frame. Then unequal loss protection (ULP) using forward error correction (FEC) is applied to different FGS enhancement layers based on their significance. Effects of quality fluctuations by packet loss are considered while optimizing FGS bits allocation and FGS unequal loss protection. Experimental results show that the proposed method can guarantee received video quality and efficiently reduce quality fluctuations.","PeriodicalId":430882,"journal":{"name":"2008 Congress on Image and Signal Processing","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124270226","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}
Hong-da Zhang, Xiao-dan Wang, Hai-long Xu, Yan-lei Li, Wen Quan
To improve the training speed of SVM, we propose a new SVM training approach which takes thick convex-hull as training set. The approach makes better use of the margin information for classification of data sets, and thus extends the use of convex hull to approximately linearly separable problems. Experiments on 5 UCI data sets indicate that the approach speeds up training of SVM with guarantee of generalization accuracy.
{"title":"Fast SVM Training Based on Thick Convex-hull","authors":"Hong-da Zhang, Xiao-dan Wang, Hai-long Xu, Yan-lei Li, Wen Quan","doi":"10.1109/CISP.2008.575","DOIUrl":"https://doi.org/10.1109/CISP.2008.575","url":null,"abstract":"To improve the training speed of SVM, we propose a new SVM training approach which takes thick convex-hull as training set. The approach makes better use of the margin information for classification of data sets, and thus extends the use of convex hull to approximately linearly separable problems. Experiments on 5 UCI data sets indicate that the approach speeds up training of SVM with guarantee of generalization accuracy.","PeriodicalId":430882,"journal":{"name":"2008 Congress on Image and Signal Processing","volume":"134 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116884015","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The localization algorithm in wireless sensor network is always a hot spot. Information collected by the sensors is meaningless without the position of the sensors. Now, paying little attention to 3-D space, most of the algorithms are for 2-D space. In this paper we introduce a novel algorithm for 3-D space called OBS (Optimal Beacon Selection) algorithm. In this algorithm we launched the concept of position error parameter, with consideration of communication range and position accuracy of beacon. The experiment results show that this method can minimize the accumulation error and improve the location precision.
{"title":"Spacial Localization in Wireless Sensor Networks Based on Beacon Selection","authors":"Shuo Xiao, Xueye Wei, Yu Wang","doi":"10.1109/CISP.2008.474","DOIUrl":"https://doi.org/10.1109/CISP.2008.474","url":null,"abstract":"The localization algorithm in wireless sensor network is always a hot spot. Information collected by the sensors is meaningless without the position of the sensors. Now, paying little attention to 3-D space, most of the algorithms are for 2-D space. In this paper we introduce a novel algorithm for 3-D space called OBS (Optimal Beacon Selection) algorithm. In this algorithm we launched the concept of position error parameter, with consideration of communication range and position accuracy of beacon. The experiment results show that this method can minimize the accumulation error and improve the location precision.","PeriodicalId":430882,"journal":{"name":"2008 Congress on Image and Signal Processing","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117235071","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}
It has been proved that acquired training is important to the development of stereopsis experience. Month-old babies already have the initial experience of invariance recognition of 3D objects. There is a slight lack of precision in the interpretation of biological vision. However, the small cost and the fast speed in calculation meet the requirements of invariance recognition, the rich visual experience in which play an important role. But what is the experience, how to acquire and how to use, these problems have never been satisfactorily resolved. In this paper we simulate the learning of visual experience in children, and solve a view angle estimated problem by using self-organizing network, which make the hidden experience clarified. Compared to the Classic camera calibration, which a large number of parameters need to be estimated, this method needs only one image and does not aim to 3D reconstruction. By avoiding the complex calibration and registration process, an amount of computation has been reduced. Visual experiences are all obtained from the most ordinary examples, and the characterization based on the geometric feature. Therefore, this method has strong expansibility and good generalization ability.
{"title":"Acquiring 3D Experience of View Angle Estimation Based on Monocular and Single Image","authors":"Hui Wei, Z. Qiu","doi":"10.1109/CISP.2008.619","DOIUrl":"https://doi.org/10.1109/CISP.2008.619","url":null,"abstract":"It has been proved that acquired training is important to the development of stereopsis experience. Month-old babies already have the initial experience of invariance recognition of 3D objects. There is a slight lack of precision in the interpretation of biological vision. However, the small cost and the fast speed in calculation meet the requirements of invariance recognition, the rich visual experience in which play an important role. But what is the experience, how to acquire and how to use, these problems have never been satisfactorily resolved. In this paper we simulate the learning of visual experience in children, and solve a view angle estimated problem by using self-organizing network, which make the hidden experience clarified. Compared to the Classic camera calibration, which a large number of parameters need to be estimated, this method needs only one image and does not aim to 3D reconstruction. By avoiding the complex calibration and registration process, an amount of computation has been reduced. Visual experiences are all obtained from the most ordinary examples, and the characterization based on the geometric feature. Therefore, this method has strong expansibility and good generalization ability.","PeriodicalId":430882,"journal":{"name":"2008 Congress on Image and Signal Processing","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121255455","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}
Optical-fiber vortex flowmeters are particularly applied in the measurement of fluid flows where instruments with no moving parts and wide range ability are required, especially under the flammable explosive environment. But because there is the impurity unavoidably, including the air bubble, the solid particle and so on, which makes the signal includes the massive noises and other indefinite ingredient, thus affects the authenticity of the data. It is widely acknowledged that process conditions influence the operation of a vortex flowmeter and that fluctuations in the flow affect the complex phenomenon of vortex street formation. In this paper, a digital signal processing algorithm based on wavelet method is presented. In the algorithm, a powerful mathematical tool—wavelet transform method is used to check out the frequency of the signal of the vortex flowmeter which has been submerged under the noises, and simulation results prove its feasibility.
{"title":"Optical-Fiber Vortex Flowmeter Signal Processing Using Wavelet","authors":"Xiaolin Lin, Yutian Wang, Yang Ni, Jianxia Li","doi":"10.1109/CISP.2008.769","DOIUrl":"https://doi.org/10.1109/CISP.2008.769","url":null,"abstract":"Optical-fiber vortex flowmeters are particularly applied in the measurement of fluid flows where instruments with no moving parts and wide range ability are required, especially under the flammable explosive environment. But because there is the impurity unavoidably, including the air bubble, the solid particle and so on, which makes the signal includes the massive noises and other indefinite ingredient, thus affects the authenticity of the data. It is widely acknowledged that process conditions influence the operation of a vortex flowmeter and that fluctuations in the flow affect the complex phenomenon of vortex street formation. In this paper, a digital signal processing algorithm based on wavelet method is presented. In the algorithm, a powerful mathematical tool—wavelet transform method is used to check out the frequency of the signal of the vortex flowmeter which has been submerged under the noises, and simulation results prove its feasibility.","PeriodicalId":430882,"journal":{"name":"2008 Congress on Image and Signal Processing","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127190318","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：