Pub Date : 2018-07-01DOI: 10.1109/ICWAPR.2018.8521272
N. Ikawa, A. Morimoto, R. Ashino
It is well known that discrete stationary wavelet analysis (DSWA) is applied to waveform analysis of auditory evoked potentials (AEPs). We also applied the DSWA to Auditory Brainstem Responses (ABRs), where an ABR is a type of AEPs. An ABR is evoked as human brain responses during 10 ms from input sound stimulation to the ears. The ABR is one of important indicators for the human objective audiometry. The ABR has been obtained by averaging many waveforms. Therefore the conventional methods sometimes need about two thousands waveforms for averaging. In this paper, the DSWA is applied to each process of averaging waveforms. The ABR consists of fast ABR and slow ABR. The fast ABR can be obtained by averaging only ten waveforms. On the other hand, the slow ABR seems to be a spontaneous electroencephalographic synchronization signal. To obtain the slow ABR needs to average three hundreds waveforms. We propose a concurrent processing method to detect peak latencies of ABR. Our proposed method detects peak latencies six times faster than the conventional methods.
{"title":"A New Detection Method for Short Latency of Auditory Evoked Potentials Using Stationary Wavelets","authors":"N. Ikawa, A. Morimoto, R. Ashino","doi":"10.1109/ICWAPR.2018.8521272","DOIUrl":"https://doi.org/10.1109/ICWAPR.2018.8521272","url":null,"abstract":"It is well known that discrete stationary wavelet analysis (DSWA) is applied to waveform analysis of auditory evoked potentials (AEPs). We also applied the DSWA to Auditory Brainstem Responses (ABRs), where an ABR is a type of AEPs. An ABR is evoked as human brain responses during 10 ms from input sound stimulation to the ears. The ABR is one of important indicators for the human objective audiometry. The ABR has been obtained by averaging many waveforms. Therefore the conventional methods sometimes need about two thousands waveforms for averaging. In this paper, the DSWA is applied to each process of averaging waveforms. The ABR consists of fast ABR and slow ABR. The fast ABR can be obtained by averaging only ten waveforms. On the other hand, the slow ABR seems to be a spontaneous electroencephalographic synchronization signal. To obtain the slow ABR needs to average three hundreds waveforms. We propose a concurrent processing method to detect peak latencies of ABR. Our proposed method detects peak latencies six times faster than the conventional methods.","PeriodicalId":385478,"journal":{"name":"2018 International Conference on Wavelet Analysis and Pattern Recognition (ICWAPR)","volume":"97 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133518059","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 addresses a method of automatic detection of digital audio signal tampering based on feature fusion. Aiming at the insertion and deletion operations in the digital audio signal tamper chain. In this paper, the Electric Network Frequency (ENF) component of the digital audio signal is extracted and the consistency of the ENF component is analyzed to determine whether the audio signal is tampered with. In this paper, a general framework for passive tamper detection of audio signal based on ENF component consistency and a general framework for ENFC feature extraction are proposed. The feature set is used to quantify the amplitude of the phase and instantaneous frequency variations of the ENF component and to serve as an indicator of the consistency of the ENF component. SVM classifier is used to classify the extracted feature sets. The experimental results show that this method can classify the original signal and the edit signal which is inserted and deleted.
{"title":"Digital Audio Tampering Detection Based on ENF Consistency","authors":"Zhifeng Wang, Jing Wang, Chunyan Zeng, Qiu-Sha Min, Yuan Tian, Mingzhang Zuo","doi":"10.1109/ICWAPR.2018.8521378","DOIUrl":"https://doi.org/10.1109/ICWAPR.2018.8521378","url":null,"abstract":"This paper addresses a method of automatic detection of digital audio signal tampering based on feature fusion. Aiming at the insertion and deletion operations in the digital audio signal tamper chain. In this paper, the Electric Network Frequency (ENF) component of the digital audio signal is extracted and the consistency of the ENF component is analyzed to determine whether the audio signal is tampered with. In this paper, a general framework for passive tamper detection of audio signal based on ENF component consistency and a general framework for ENFC feature extraction are proposed. The feature set is used to quantify the amplitude of the phase and instantaneous frequency variations of the ENF component and to serve as an indicator of the consistency of the ENF component. SVM classifier is used to classify the extracted feature sets. The experimental results show that this method can classify the original signal and the edit signal which is inserted and deleted.","PeriodicalId":385478,"journal":{"name":"2018 International Conference on Wavelet Analysis and Pattern Recognition (ICWAPR)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133327883","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 : 2018-07-01DOI: 10.1109/ICWAPR.2018.8521328
Han Liu, Huihuang Zhao
Image segmentation is a popular application area of machine learning. In this context, each target region drawn from an image is defined as a class towards recognition of instances that belong to this region (class). In order to train classifiers that recognize the target region to which an instance belongs, it is important to extract and select features relevant to the region. In traditional machine learning, all features extracted from different regions are simply used together to form a single feature set for training classifiers, and feature selection is usually designed to evaluate the capability of each feature or feature subset in discriminating one class from other classes. However, it is possible that some features are only relevant to one class but irrelevant to all the other classes. From this point of view, it is necessary to undertake feature selection for each specific class, i.e, a relevant feature subset is selected for each specific class. In this paper, we propose the so-called multi-task feature selection approach for identifying features relevant to each target region towards effective image segmentation. This way of feature selection requires to transform a multi-class classification task into $n$ binary classification tasks, where $n$ is the number of classes. In particular, the Prism algorithm is used to produce a set of rules for class specific feature selection and the K nearest neighbour algorithm is used for training a classifier on a feature subset selected for each class. The experimental results show that the multi-task feature selection approach leads to an significant improvement of classification performance comparing with traditional feature selection approaches.
{"title":"Multi-Task Feature Selection for Advancing Performance of Image Segmentation","authors":"Han Liu, Huihuang Zhao","doi":"10.1109/ICWAPR.2018.8521328","DOIUrl":"https://doi.org/10.1109/ICWAPR.2018.8521328","url":null,"abstract":"Image segmentation is a popular application area of machine learning. In this context, each target region drawn from an image is defined as a class towards recognition of instances that belong to this region (class). In order to train classifiers that recognize the target region to which an instance belongs, it is important to extract and select features relevant to the region. In traditional machine learning, all features extracted from different regions are simply used together to form a single feature set for training classifiers, and feature selection is usually designed to evaluate the capability of each feature or feature subset in discriminating one class from other classes. However, it is possible that some features are only relevant to one class but irrelevant to all the other classes. From this point of view, it is necessary to undertake feature selection for each specific class, i.e, a relevant feature subset is selected for each specific class. In this paper, we propose the so-called multi-task feature selection approach for identifying features relevant to each target region towards effective image segmentation. This way of feature selection requires to transform a multi-class classification task into $n$ binary classification tasks, where $n$ is the number of classes. In particular, the Prism algorithm is used to produce a set of rules for class specific feature selection and the K nearest neighbour algorithm is used for training a classifier on a feature subset selected for each class. The experimental results show that the multi-task feature selection approach leads to an significant improvement of classification performance comparing with traditional feature selection approaches.","PeriodicalId":385478,"journal":{"name":"2018 International Conference on Wavelet Analysis and Pattern Recognition (ICWAPR)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129835818","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 : 2018-07-01DOI: 10.1109/ICWAPR.2018.8521253
Rujun Li, U. KinTak
Among various de-fog algorithms, dark channel prior de-fog algorithm is one of simple and effective dehazing algorithm. The disadvantages of dark channel prior include that there is a certain degree of color distortion in bright areas such as sky and water surface. Aiming at the problem, improved algorithm based on reference-less prediction of perceptual fog density model, Fog Aware Density Evaluator (FADE) is introduced to get more exact estimation of atmospheric light A and medium transmission in the bright areas to avoid the color shift in the sky region. Fast guided filtering is also used in this paper to refine the medium transmission. The result of experiment shows that there is no serious color distortion problem in the sky region of the restored image obtained by the improved algorithm proposed in this paper and the algorithm is more effective than dark channel prior de-fog algorithm.
在各种去雾算法中，暗通道先验去雾算法是一种简单有效的去雾算法。暗通道先验的缺点包括在天空和水面等明亮区域存在一定程度的色彩失真。针对这一问题，提出了基于无参考预测感知雾密度模型的改进算法——雾感密度评估器(fog - Aware density Evaluator, FADE)，以更精确地估计明亮区域的大气光A和介质透射，避免天空区域的色移。本文还采用了快速引导滤波来细化介质传输。实验结果表明，本文提出的改进算法得到的恢复图像的天空区域没有出现严重的色彩失真问题，并且比暗通道先验去雾算法更有效。
{"title":"Haze Density Estimation and Dark Channel Prior Based Image Defogging","authors":"Rujun Li, U. KinTak","doi":"10.1109/ICWAPR.2018.8521253","DOIUrl":"https://doi.org/10.1109/ICWAPR.2018.8521253","url":null,"abstract":"Among various de-fog algorithms, dark channel prior de-fog algorithm is one of simple and effective dehazing algorithm. The disadvantages of dark channel prior include that there is a certain degree of color distortion in bright areas such as sky and water surface. Aiming at the problem, improved algorithm based on reference-less prediction of perceptual fog density model, Fog Aware Density Evaluator (FADE) is introduced to get more exact estimation of atmospheric light A and medium transmission in the bright areas to avoid the color shift in the sky region. Fast guided filtering is also used in this paper to refine the medium transmission. The result of experiment shows that there is no serious color distortion problem in the sky region of the restored image obtained by the improved algorithm proposed in this paper and the algorithm is more effective than dark channel prior de-fog algorithm.","PeriodicalId":385478,"journal":{"name":"2018 International Conference on Wavelet Analysis and Pattern Recognition (ICWAPR)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123136492","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 : 2018-07-01DOI: 10.1109/ICWAPR.2018.8521307
Gong Cheng, X. Tong
In order to improve the classification speed and accuracy of support vector machines, a fuzzy clustering multi-kernel support vector machine algorithm is proposed. In this paper, the fuzzy clustering method is used to cluster the training datasets into several clusters. By introducing effective clustering centers, the training of the original training datasets is simplified to the training of the effective clustering center datasets. So as to reduce the training time and improve the training accuracy. At the same time, this paper uses Multiple Kernel Support Vector Machine to replace the traditional single kernel support vector machine to carry on the operation, which can handle complex data structures and improve the training precision effectively. Numerical experiments show that the fuzzy clustering Multiple Kernel Support Vector Machine has the advantages of higher classification accuracy and shorter classification time than the traditional Multiple Kernel support vector machine.
{"title":"Fuzzy Clustering Multiple Kernel Support Vector Machine","authors":"Gong Cheng, X. Tong","doi":"10.1109/ICWAPR.2018.8521307","DOIUrl":"https://doi.org/10.1109/ICWAPR.2018.8521307","url":null,"abstract":"In order to improve the classification speed and accuracy of support vector machines, a fuzzy clustering multi-kernel support vector machine algorithm is proposed. In this paper, the fuzzy clustering method is used to cluster the training datasets into several clusters. By introducing effective clustering centers, the training of the original training datasets is simplified to the training of the effective clustering center datasets. So as to reduce the training time and improve the training accuracy. At the same time, this paper uses Multiple Kernel Support Vector Machine to replace the traditional single kernel support vector machine to carry on the operation, which can handle complex data structures and improve the training precision effectively. Numerical experiments show that the fuzzy clustering Multiple Kernel Support Vector Machine has the advantages of higher classification accuracy and shorter classification time than the traditional Multiple Kernel support vector machine.","PeriodicalId":385478,"journal":{"name":"2018 International Conference on Wavelet Analysis and Pattern Recognition (ICWAPR)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130859979","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 : 2018-07-01DOI: 10.1109/ICWAPR.2018.8521262
Li Zhang, Bob Zhang
Diabetes and lung disease are some of the most common medical conditions in the world. The economic costs and social burdens brought by these two diseases are considerable. Even though there are proven methodologies for diagnosing each disease individually in practice, there does not exist a single non-invasive methodology/procedure that can detect both diseases. With recent advancements made in machine learning and pattern recognition, the Convolutional Neural Network (CNN) has been widely used in many recognition applications due to its high efficiency and performance. Therefore, in this paper we propose an approach using CNN for non-invasive multi-disease classification called Multi-Disease CNN (MD-CNN). Facial images are first captured using our specially designed device. Next, four facial blocks are extracted located at specific regions on the face. Finally, the facial blocks are concatenated and used as input for our MD-CNN. Based on three datasets consisting of healthy control, diabetes and lung disease, the proposed method achieved an average accuracy of 73%. When compared to other classifiers not employing a deep learning architecture, MD-CNN produced the highest result. This show a potentially new way to perform multi-disease classification.
{"title":"Non-Invasive Multi-Disease Classification via Facial Image Analysis Using a Convolutional Neural Network","authors":"Li Zhang, Bob Zhang","doi":"10.1109/ICWAPR.2018.8521262","DOIUrl":"https://doi.org/10.1109/ICWAPR.2018.8521262","url":null,"abstract":"Diabetes and lung disease are some of the most common medical conditions in the world. The economic costs and social burdens brought by these two diseases are considerable. Even though there are proven methodologies for diagnosing each disease individually in practice, there does not exist a single non-invasive methodology/procedure that can detect both diseases. With recent advancements made in machine learning and pattern recognition, the Convolutional Neural Network (CNN) has been widely used in many recognition applications due to its high efficiency and performance. Therefore, in this paper we propose an approach using CNN for non-invasive multi-disease classification called Multi-Disease CNN (MD-CNN). Facial images are first captured using our specially designed device. Next, four facial blocks are extracted located at specific regions on the face. Finally, the facial blocks are concatenated and used as input for our MD-CNN. Based on three datasets consisting of healthy control, diabetes and lung disease, the proposed method achieved an average accuracy of 73%. When compared to other classifiers not employing a deep learning architecture, MD-CNN produced the highest result. This show a potentially new way to perform multi-disease classification.","PeriodicalId":385478,"journal":{"name":"2018 International Conference on Wavelet Analysis and Pattern Recognition (ICWAPR)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121740439","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 : 2018-07-01DOI: 10.1109/ICWAPR.2018.8521310
M. Bahri, R. Ashino
An alternative proof of scalar Parseval's formula with respect to the two-sided quaternion Fourier transform is presented. It is shown that the inverse of the two-sided quaternion Fourier transform is continuous and bounded on R 2. The duality property of the two-sided quaternion Fourier transform is established. The alternative form of the Hausdorff-Young inequality associated with the two-sided quaternion Fourier transform is expressed. AMS Subject Classification: 11R52, 42A38, 15A66
{"title":"Duality Property of Two-Sided Quaternion Fourier Transform","authors":"M. Bahri, R. Ashino","doi":"10.1109/ICWAPR.2018.8521310","DOIUrl":"https://doi.org/10.1109/ICWAPR.2018.8521310","url":null,"abstract":"An alternative proof of scalar Parseval's formula with respect to the two-sided quaternion Fourier transform is presented. It is shown that the inverse of the two-sided quaternion Fourier transform is continuous and bounded on R 2. The duality property of the two-sided quaternion Fourier transform is established. The alternative form of the Hausdorff-Young inequality associated with the two-sided quaternion Fourier transform is expressed. AMS Subject Classification: 11R52, 42A38, 15A66","PeriodicalId":385478,"journal":{"name":"2018 International Conference on Wavelet Analysis and Pattern Recognition (ICWAPR)","volume":"181 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122287125","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 : 2018-07-01DOI: 10.1109/ICWAPR.2018.8521321
Huihuang Zhao, Han Liu
Recognition of handwritten digits is a very popular application of machine learning. In this context, each of the ten digits (0–9) is defined as a class in the setting of machine learning based classification tasks. In general, popular learning methods, such as support vector machine, neural networks and K nearest neighbours, have been used for classifying instances of handwritten digits to one of the ten classes. However, due to the diversity of handwriting styles from different people, it can happen that some handwritten digits (e.g. 4 and 9) are very similar and are thus difficult to distinguish. Also, each single learning algorithm may have its own advantages and disadvantages, which means that a single algorithm would be capable of learning some but not all specific characteristics of handwritten digits. From this point of view, a method for handwritten digits recognition is proposed in the setting of ensemble learning, towards encouraging the diversity among different classifiers trained by different learning algorithms. In particular, the image features of handwritten digits are extracted by using the Convolutional Neural Network architecture. Furthermore, single classifiers trained respectively by K nearest neighbours and random forests are fused as an ensemble one. The experimental results show that the ensemble classifier was able to achieve a recognition accuracy of ≥ 98 % using the MNISET data set.
{"title":"Algebraic Fusion of Multiple Classifiers for Handwritten Digits Recognition","authors":"Huihuang Zhao, Han Liu","doi":"10.1109/ICWAPR.2018.8521321","DOIUrl":"https://doi.org/10.1109/ICWAPR.2018.8521321","url":null,"abstract":"Recognition of handwritten digits is a very popular application of machine learning. In this context, each of the ten digits (0–9) is defined as a class in the setting of machine learning based classification tasks. In general, popular learning methods, such as support vector machine, neural networks and K nearest neighbours, have been used for classifying instances of handwritten digits to one of the ten classes. However, due to the diversity of handwriting styles from different people, it can happen that some handwritten digits (e.g. 4 and 9) are very similar and are thus difficult to distinguish. Also, each single learning algorithm may have its own advantages and disadvantages, which means that a single algorithm would be capable of learning some but not all specific characteristics of handwritten digits. From this point of view, a method for handwritten digits recognition is proposed in the setting of ensemble learning, towards encouraging the diversity among different classifiers trained by different learning algorithms. In particular, the image features of handwritten digits are extracted by using the Convolutional Neural Network architecture. Furthermore, single classifiers trained respectively by K nearest neighbours and random forests are fused as an ensemble one. The experimental results show that the ensemble classifier was able to achieve a recognition accuracy of ≥ 98 % using the MNISET data set.","PeriodicalId":385478,"journal":{"name":"2018 International Conference on Wavelet Analysis and Pattern Recognition (ICWAPR)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131814058","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 : 2018-07-01DOI: 10.1109/ICWAPR.2018.8521245
Cuilian Zhang, Xu Yang, Lilingbo, Derek F. Wong
Particle filter samplers, Markov chain Monte Carlo (MCM-C)samplers, and swarm intelligence can be used for parameter estimation with posterior probability distribution in nonlinear dynamic system. However the global exploration capabilities and efficiency of the sampler rely on the moving step of particle filter sampler. In this paper, we presented a mixing sampler algorithm: particle filter grey wolf optimization sampler(PF -GWO). PF-GWO sampler is operated by combining grey wolf optimization with Metropolis ratio into framework of particle filter, which is suitable to estimate unknown static parameters of nonlinear dynamic models. Based on Bayesian framework, parameter estimation of Lorenz model shows that PF -GWO sampler is superior to other combined particle filter sampler algorithms with large range prior distribution.
{"title":"Particle Filter Grey Wolf Optimization for Parameter Estimation of Nonlinear Dynamic System","authors":"Cuilian Zhang, Xu Yang, Lilingbo, Derek F. Wong","doi":"10.1109/ICWAPR.2018.8521245","DOIUrl":"https://doi.org/10.1109/ICWAPR.2018.8521245","url":null,"abstract":"Particle filter samplers, Markov chain Monte Carlo (MCM-C)samplers, and swarm intelligence can be used for parameter estimation with posterior probability distribution in nonlinear dynamic system. However the global exploration capabilities and efficiency of the sampler rely on the moving step of particle filter sampler. In this paper, we presented a mixing sampler algorithm: particle filter grey wolf optimization sampler(PF -GWO). PF-GWO sampler is operated by combining grey wolf optimization with Metropolis ratio into framework of particle filter, which is suitable to estimate unknown static parameters of nonlinear dynamic models. Based on Bayesian framework, parameter estimation of Lorenz model shows that PF -GWO sampler is superior to other combined particle filter sampler algorithms with large range prior distribution.","PeriodicalId":385478,"journal":{"name":"2018 International Conference on Wavelet Analysis and Pattern Recognition (ICWAPR)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133386886","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 : 2018-07-01DOI: 10.1109/ICWAPR.2018.8521338
Zhong Zhang, Jyunji Suzuki, H. Toda, T. Akiduki
The real signal mother wavelet (RMW) is a special wavelet constructed by using real measured signals. Wavelet instantaneous correlation (WIC) is a correlation analysis by using the RMW without expansion and contraction. WIC is well suited to various abnormality diagnosis systems. However, it is necessary for a specilist to select to “sample” and abnormal phenomena required for the composition of the RMW. There are still many problems to overcome for standardization of the method. Therefore, this research focuses on this problem, and examines the composition method of the RMW by principal component analysis using the circulant matrix. A new circulant wavelet instantaneous correlation using the constructed RMW is proposed and applied to leakage diagnosis. Its effectiveness is shown.
{"title":"Circulant Wavelet Instantaneous Correlation and its Application to Water Leakage","authors":"Zhong Zhang, Jyunji Suzuki, H. Toda, T. Akiduki","doi":"10.1109/ICWAPR.2018.8521338","DOIUrl":"https://doi.org/10.1109/ICWAPR.2018.8521338","url":null,"abstract":"The real signal mother wavelet (RMW) is a special wavelet constructed by using real measured signals. Wavelet instantaneous correlation (WIC) is a correlation analysis by using the RMW without expansion and contraction. WIC is well suited to various abnormality diagnosis systems. However, it is necessary for a specilist to select to “sample” and abnormal phenomena required for the composition of the RMW. There are still many problems to overcome for standardization of the method. Therefore, this research focuses on this problem, and examines the composition method of the RMW by principal component analysis using the circulant matrix. A new circulant wavelet instantaneous correlation using the constructed RMW is proposed and applied to leakage diagnosis. Its effectiveness is shown.","PeriodicalId":385478,"journal":{"name":"2018 International Conference on Wavelet Analysis and Pattern Recognition (ICWAPR)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126642466","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：