Pub Date : 2016-10-01DOI: 10.1109/CISP-BMEI.2016.7852830
Na Xiao, Dan Liu, Ailing Luo, Xiangwei Kong, Tianshe Yang, Nan Xing, Fangzheng Li
As the important power equipment in the mechanical system, fault diagnosis for asynchronous motor is helpful to monitor working status and prevent failure causing unnecessary loss. In the fault diagnosis domain, feature extraction is the key step which is related to the performance of diagnosis results. For the asynchronous motor, the motor current signature analysis (MCSA) is one of the most powerful diagnosis method with stator-current signals. However, MCSA has some shortcomings, which degrade performance and accuracy of a motor-diagnosis system. Therefore, advanced feature extraction algorithm of current signal using Stacked Denoising Auto-encoders (SDAE) is proposed in this paper. The method of SDAE and application in motor are discussed in detail. Then, the features learned from the SDAE is displayed and a softmax regression model is used to verify the discriminability of the features. The experiments show that SDAE is an effective feature extraction technique for asynchronous motor fault diagnosis.
{"title":"Adaptive feature extraction based on Stacked Denoising Auto-encoders for asynchronous motor fault diagnosis","authors":"Na Xiao, Dan Liu, Ailing Luo, Xiangwei Kong, Tianshe Yang, Nan Xing, Fangzheng Li","doi":"10.1109/CISP-BMEI.2016.7852830","DOIUrl":"https://doi.org/10.1109/CISP-BMEI.2016.7852830","url":null,"abstract":"As the important power equipment in the mechanical system, fault diagnosis for asynchronous motor is helpful to monitor working status and prevent failure causing unnecessary loss. In the fault diagnosis domain, feature extraction is the key step which is related to the performance of diagnosis results. For the asynchronous motor, the motor current signature analysis (MCSA) is one of the most powerful diagnosis method with stator-current signals. However, MCSA has some shortcomings, which degrade performance and accuracy of a motor-diagnosis system. Therefore, advanced feature extraction algorithm of current signal using Stacked Denoising Auto-encoders (SDAE) is proposed in this paper. The method of SDAE and application in motor are discussed in detail. Then, the features learned from the SDAE is displayed and a softmax regression model is used to verify the discriminability of the features. The experiments show that SDAE is an effective feature extraction technique for asynchronous motor fault diagnosis.","PeriodicalId":275095,"journal":{"name":"2016 9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"315 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122025506","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 : 2016-10-01DOI: 10.1109/CISP-BMEI.2016.7852898
Ying Xiao, Yu-Hua Dong
To solve the mode mixing problem of local mean decomposition (LMD), hereby a de-correlation improved LMD algorithm was proposed. If the multi-components signal includes two signal components with similar frequency, LMD will produce mode mixing which has serious impact on signal feature extraction and subsequent time frequency analysis. The essence of the mode mixing is that the information of product functions (PF) obtained by LMD mutual coupling each other. That is the PF is incomplete orthogonality. For the zero mean value random signal, the orthogonality and non-correlation are equivalent. By embedding the de-correlation operation in the LMD process, the orthogonality between the PF can be further guaranteed, and the purpose of suppressing the mode mixing is achieved. The simulation results show that the LMD algorithm improved by de-correlation has superior performance in suppressing the mode mixing.
{"title":"Local mean decomposition algorithm improved by de-correlation","authors":"Ying Xiao, Yu-Hua Dong","doi":"10.1109/CISP-BMEI.2016.7852898","DOIUrl":"https://doi.org/10.1109/CISP-BMEI.2016.7852898","url":null,"abstract":"To solve the mode mixing problem of local mean decomposition (LMD), hereby a de-correlation improved LMD algorithm was proposed. If the multi-components signal includes two signal components with similar frequency, LMD will produce mode mixing which has serious impact on signal feature extraction and subsequent time frequency analysis. The essence of the mode mixing is that the information of product functions (PF) obtained by LMD mutual coupling each other. That is the PF is incomplete orthogonality. For the zero mean value random signal, the orthogonality and non-correlation are equivalent. By embedding the de-correlation operation in the LMD process, the orthogonality between the PF can be further guaranteed, and the purpose of suppressing the mode mixing is achieved. The simulation results show that the LMD algorithm improved by de-correlation has superior performance in suppressing the mode mixing.","PeriodicalId":275095,"journal":{"name":"2016 9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123938768","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 : 2016-10-01DOI: 10.1109/CISP-BMEI.2016.7853022
Zhenfeng Lei, Shunfang Wang, Dongshu Xu
Data dimension reduction and classification are the key steps in protein sub-cellular localization. With the rapid development of biological science and technology, a plenty of high dimensional biological data have generated, accompanied by certain noise. How to express high dimensional data in low dimension space and achieve better classification effect have become one of the significant tasks for researchers in the application of protein sub-cellular localization. Both the traditional dimension reduction algorithm of linear discriminant analysis (LDA) and the popular classifier of k-nearest neighbor (KNN) cannot meet the needs of the current application well if they are simply used without improvements. The aim of LDA is to seek out a projecting line at certain direction letting the projection of samples as far away as possible. However, noise jamming expands the within-class distance and makes the classes uneasily separated even by LDA. Besides, KNN has not taken samples' inequality into consideration primely. Therefore, this paper first uses the noise intensity as a kind of weight in LDA, then improves KNN algorithm by considering the inequality of samples from different classes with a within-class KNN method. Experimental results show that the proposed method by combining the above two improvements gets ideal feasibility and effectiveness in classification through the verification of Jackknife.
{"title":"Protein sub-cellular localization based on noise-intensity-weighted linear discriminant analysis and an improved k-nearest-neighbor classifier","authors":"Zhenfeng Lei, Shunfang Wang, Dongshu Xu","doi":"10.1109/CISP-BMEI.2016.7853022","DOIUrl":"https://doi.org/10.1109/CISP-BMEI.2016.7853022","url":null,"abstract":"Data dimension reduction and classification are the key steps in protein sub-cellular localization. With the rapid development of biological science and technology, a plenty of high dimensional biological data have generated, accompanied by certain noise. How to express high dimensional data in low dimension space and achieve better classification effect have become one of the significant tasks for researchers in the application of protein sub-cellular localization. Both the traditional dimension reduction algorithm of linear discriminant analysis (LDA) and the popular classifier of k-nearest neighbor (KNN) cannot meet the needs of the current application well if they are simply used without improvements. The aim of LDA is to seek out a projecting line at certain direction letting the projection of samples as far away as possible. However, noise jamming expands the within-class distance and makes the classes uneasily separated even by LDA. Besides, KNN has not taken samples' inequality into consideration primely. Therefore, this paper first uses the noise intensity as a kind of weight in LDA, then improves KNN algorithm by considering the inequality of samples from different classes with a within-class KNN method. Experimental results show that the proposed method by combining the above two improvements gets ideal feasibility and effectiveness in classification through the verification of Jackknife.","PeriodicalId":275095,"journal":{"name":"2016 9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124027766","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 : 2016-10-01DOI: 10.1109/CISP-BMEI.2016.7852811
J. Sun, Yuzhong Ma, Han Yang, Xinglong Zhu
The trajectory tracking system of particle motion on sieve surface was designed by the combination of the analysis of image sequences based on binocular stereo vision and three-dimensional position reconstruction based on artificial neural network. Firstly, the calibration plane with uniformly distributed solid circles was placed in multiple positions within the effective field of view. The images of the calibration plane in each position can be captured by the binocular stereo vision system. Then, after image processing, the two-dimensional coordinates of the center of the circles were used as the input sample set for training. The artificial neural network was used to establish an implicit vision model. By this model, the three-dimensional position of the materials can be acquired without any complex camera calibration operation. Lastly, experiments showed that the proposed scheme is feasible, which will provide a good basis for further research.
{"title":"Camera calibration and its application of binocular stereo vision based on artificial neural network","authors":"J. Sun, Yuzhong Ma, Han Yang, Xinglong Zhu","doi":"10.1109/CISP-BMEI.2016.7852811","DOIUrl":"https://doi.org/10.1109/CISP-BMEI.2016.7852811","url":null,"abstract":"The trajectory tracking system of particle motion on sieve surface was designed by the combination of the analysis of image sequences based on binocular stereo vision and three-dimensional position reconstruction based on artificial neural network. Firstly, the calibration plane with uniformly distributed solid circles was placed in multiple positions within the effective field of view. The images of the calibration plane in each position can be captured by the binocular stereo vision system. Then, after image processing, the two-dimensional coordinates of the center of the circles were used as the input sample set for training. The artificial neural network was used to establish an implicit vision model. By this model, the three-dimensional position of the materials can be acquired without any complex camera calibration operation. Lastly, experiments showed that the proposed scheme is feasible, which will provide a good basis for further research.","PeriodicalId":275095,"journal":{"name":"2016 9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"77 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125997735","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 : 2016-10-01DOI: 10.1109/CISP-BMEI.2016.7852955
Eman T. Alharbi, Saim Rasheed, S. Buhari
In this paper, a single trial classification is introduced for the Electroencephalography (EEG) signals evoked by RGB colors. The effectiveness of a single trial classification is an important step towards online classification of EEG signals. Signals are analyzed by Empirical Mode Decomposition (EMD) technique, and the last decomposition is used in the feature extraction stage. We investigate different feature extraction methods in order to find out the best method which can be used with colors dataset. These methods are: Event-Related Spectral Perturbations (ERSP), Target mean, AutoRegressive and EMD residual. In addition, we propose a new feature selection algorithm, which focuses on selecting the best features by studying the behavior of EEG components that appear due to the introduced color. We introduced a comparison between the classification results of using all extracted features, the results of using the selected features by the proposed algorithm and the results of using the selected features by recursive feature elimination algorithm, which is used by similar study. The proposed algorithm is proved with all the investigated feature extraction methods as the classification accuracies are increased. Support Vector Machine (SVM) is used in the classification process. We found that the execution time of using color's stimulus is only 0.23s, which is much less than the time which was required by any other stimulus such as imagery and spelling word presented in the previous researches. The best feature extraction method that gives the highest classification accuracy and can be used with real time BCI systems are Target Mean and EMD residual, as their accuracies are high and the computation time is very low.
{"title":"Feature selection algorithm for evoked EEG signal due to RGB colors","authors":"Eman T. Alharbi, Saim Rasheed, S. Buhari","doi":"10.1109/CISP-BMEI.2016.7852955","DOIUrl":"https://doi.org/10.1109/CISP-BMEI.2016.7852955","url":null,"abstract":"In this paper, a single trial classification is introduced for the Electroencephalography (EEG) signals evoked by RGB colors. The effectiveness of a single trial classification is an important step towards online classification of EEG signals. Signals are analyzed by Empirical Mode Decomposition (EMD) technique, and the last decomposition is used in the feature extraction stage. We investigate different feature extraction methods in order to find out the best method which can be used with colors dataset. These methods are: Event-Related Spectral Perturbations (ERSP), Target mean, AutoRegressive and EMD residual. In addition, we propose a new feature selection algorithm, which focuses on selecting the best features by studying the behavior of EEG components that appear due to the introduced color. We introduced a comparison between the classification results of using all extracted features, the results of using the selected features by the proposed algorithm and the results of using the selected features by recursive feature elimination algorithm, which is used by similar study. The proposed algorithm is proved with all the investigated feature extraction methods as the classification accuracies are increased. Support Vector Machine (SVM) is used in the classification process. We found that the execution time of using color's stimulus is only 0.23s, which is much less than the time which was required by any other stimulus such as imagery and spelling word presented in the previous researches. The best feature extraction method that gives the highest classification accuracy and can be used with real time BCI systems are Target Mean and EMD residual, as their accuracies are high and the computation time is very low.","PeriodicalId":275095,"journal":{"name":"2016 9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128438465","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 : 2016-10-01DOI: 10.1109/CISP-BMEI.2016.7852768
Lingfeng Kong, Qingxiang Wu
In order to identify a large number of very similar objects, a novel recognition approach is proposed by mean of combination of two dynamic grouping algorithms, the visual processing mechanism, PCA and multi-pathway SVM. The samples have been segmented to appropriate groups by grouping features, and then features with rotation invariance and translation invariance of each group are extracted. Finally, the features' reduced by PCA are put into the SVM to build classification models. The experimental results show that the proposed algorithms in this paper error rates are obviously less than the algorithms in which samples not be grouped and put the classification features into SVM to build a classification model directly.
{"title":"Recognition algorithm for huge number of very similar objects","authors":"Lingfeng Kong, Qingxiang Wu","doi":"10.1109/CISP-BMEI.2016.7852768","DOIUrl":"https://doi.org/10.1109/CISP-BMEI.2016.7852768","url":null,"abstract":"In order to identify a large number of very similar objects, a novel recognition approach is proposed by mean of combination of two dynamic grouping algorithms, the visual processing mechanism, PCA and multi-pathway SVM. The samples have been segmented to appropriate groups by grouping features, and then features with rotation invariance and translation invariance of each group are extracted. Finally, the features' reduced by PCA are put into the SVM to build classification models. The experimental results show that the proposed algorithms in this paper error rates are obviously less than the algorithms in which samples not be grouped and put the classification features into SVM to build a classification model directly.","PeriodicalId":275095,"journal":{"name":"2016 9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128282017","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 : 2016-10-01DOI: 10.1109/CISP-BMEI.2016.7852852
S. Ou, W. Liu, Suojin Shen, Ying Gao
Estimating the amplitude spectral of noise signal is a very important part in many noise reduction systems. The conventional voice activity detection (VAD)-based method updates the amplitude spectral estimate only in speech absence areas and fails to deal with non-stationary noise. To overcome this problem, this paper proposes two methods to estimate the noise amplitude spectral for non-stationary environments: One is an indirect method, which obtains the estimate of noise amplitude spectral using its relationship with noise power spectral, while the other is the minimum mean-square error (MMSE)-based estimator. The proposed estimators are based on that the speech and noise are both Gaussian distributed and can update the estimate of noise amplitude spectral during speech activity as well as absence periods. Objective evaluations using several measures show that the proposed two estimators for noise amplitude spectral performed significantly better than the VAD-based method in all the tested non-stationary noise conditions.
{"title":"Two methods for estimating noise amplitude spectral in non-stationary environments","authors":"S. Ou, W. Liu, Suojin Shen, Ying Gao","doi":"10.1109/CISP-BMEI.2016.7852852","DOIUrl":"https://doi.org/10.1109/CISP-BMEI.2016.7852852","url":null,"abstract":"Estimating the amplitude spectral of noise signal is a very important part in many noise reduction systems. The conventional voice activity detection (VAD)-based method updates the amplitude spectral estimate only in speech absence areas and fails to deal with non-stationary noise. To overcome this problem, this paper proposes two methods to estimate the noise amplitude spectral for non-stationary environments: One is an indirect method, which obtains the estimate of noise amplitude spectral using its relationship with noise power spectral, while the other is the minimum mean-square error (MMSE)-based estimator. The proposed estimators are based on that the speech and noise are both Gaussian distributed and can update the estimate of noise amplitude spectral during speech activity as well as absence periods. Objective evaluations using several measures show that the proposed two estimators for noise amplitude spectral performed significantly better than the VAD-based method in all the tested non-stationary noise conditions.","PeriodicalId":275095,"journal":{"name":"2016 9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128431288","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 : 2016-10-01DOI: 10.1109/CISP-BMEI.2016.7852728
Shaoyi Li, Jun Ma
Because the contrast of the image for guiding the high-speed infrared air-to-air missile is low, its signal to noise ratio is poor and the target and its background gray-scale coupling is strong, the paper analyzes the reasons why the threshold value segmentation method and the fuzzy C-means clustering method have the over-segmentation and under-segmentation in segmenting the above type of image. Hence we propose the kernel fuzzy clustering segmentation algorithm based on histogram and spatial constraint, which utilizes the global first-moment histogram of the infrared image to restrict the number of clusters and the clustering center, improves the spatial correlation function that fully manifests the correlations among pixels inside a neighbor domain and reconstructs the membership degree matrix and the clustering central function, thus segmenting the infrared image with the kernel fuzzy clustering algorithm. The results on the experiments on a sequential infrared image show preliminarily that, compared with the traditional threshold value segmentation algorithm, the fuzzy C-means segmentation algorithm and the kernel fuzzy clustering algorithm, the improved algorithm proposed in the paper can reduce entropy segmentation by about 60% on average and increase the correlation degrees among clusters by around 10%, thus enhancing to a certain extent the efficiency and precision for segmenting the fuzzy image whose target gray-scale and background gray-scale are strongly coupled.
{"title":"A kernel fuzzy clustering infrared image segmentation algorithm based on histogram and spatial restraint","authors":"Shaoyi Li, Jun Ma","doi":"10.1109/CISP-BMEI.2016.7852728","DOIUrl":"https://doi.org/10.1109/CISP-BMEI.2016.7852728","url":null,"abstract":"Because the contrast of the image for guiding the high-speed infrared air-to-air missile is low, its signal to noise ratio is poor and the target and its background gray-scale coupling is strong, the paper analyzes the reasons why the threshold value segmentation method and the fuzzy C-means clustering method have the over-segmentation and under-segmentation in segmenting the above type of image. Hence we propose the kernel fuzzy clustering segmentation algorithm based on histogram and spatial constraint, which utilizes the global first-moment histogram of the infrared image to restrict the number of clusters and the clustering center, improves the spatial correlation function that fully manifests the correlations among pixels inside a neighbor domain and reconstructs the membership degree matrix and the clustering central function, thus segmenting the infrared image with the kernel fuzzy clustering algorithm. The results on the experiments on a sequential infrared image show preliminarily that, compared with the traditional threshold value segmentation algorithm, the fuzzy C-means segmentation algorithm and the kernel fuzzy clustering algorithm, the improved algorithm proposed in the paper can reduce entropy segmentation by about 60% on average and increase the correlation degrees among clusters by around 10%, thus enhancing to a certain extent the efficiency and precision for segmenting the fuzzy image whose target gray-scale and background gray-scale are strongly coupled.","PeriodicalId":275095,"journal":{"name":"2016 9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128657711","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 : 2016-10-01DOI: 10.1109/CISP-BMEI.2016.7852958
Fei Du, Shitong Wang, Jun Wang, Jiafei Dai, F. Hou, Jin Li
The physiological analysis of electroencephalogram (EEG) signals is of great significance in assessing the activity of the brain function and the physiological state. EEG is a means of clinical examination of brain diseases. Age is one of the important factors that affect the results of the EEG. EEG signal analysis is mainly to analyze the time series of the signal, multiscale entropy (MSE) analysis [1-3] is the method that used to analyze the finite length of the time series. Multiscale sign series entropy (MSSE) method is proposed for the analysis of EEG signals in the young and middle-aged. We use the proposed method to analyze the signals from several aspects of data length, word length, noise, multi scale etc. By analyzing the influence of these factors, we can still distinguish the EEG signals of different ages. Multiscale sign series entropy (MSSE) analysis algorithm can effectively separate the brain electrical signals from the young and middle aged, which is expected to have a certain reference value for the traditional pathological analysis of the EEG signals.
{"title":"Analysis of multiscale sign series entropy of the young and middle-aged electroencephalogram signals","authors":"Fei Du, Shitong Wang, Jun Wang, Jiafei Dai, F. Hou, Jin Li","doi":"10.1109/CISP-BMEI.2016.7852958","DOIUrl":"https://doi.org/10.1109/CISP-BMEI.2016.7852958","url":null,"abstract":"The physiological analysis of electroencephalogram (EEG) signals is of great significance in assessing the activity of the brain function and the physiological state. EEG is a means of clinical examination of brain diseases. Age is one of the important factors that affect the results of the EEG. EEG signal analysis is mainly to analyze the time series of the signal, multiscale entropy (MSE) analysis [1-3] is the method that used to analyze the finite length of the time series. Multiscale sign series entropy (MSSE) method is proposed for the analysis of EEG signals in the young and middle-aged. We use the proposed method to analyze the signals from several aspects of data length, word length, noise, multi scale etc. By analyzing the influence of these factors, we can still distinguish the EEG signals of different ages. Multiscale sign series entropy (MSSE) analysis algorithm can effectively separate the brain electrical signals from the young and middle aged, which is expected to have a certain reference value for the traditional pathological analysis of the EEG signals.","PeriodicalId":275095,"journal":{"name":"2016 9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128969453","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 : 2016-10-01DOI: 10.1109/CISP-BMEI.2016.7852995
Yiwen Su, D. Liu, Yingfeng Wu
Fall is a major threat to elders' health. The goal of our study is to establish a pre-impact fall detection system to reduce the harm of falls. For the problem that single-sensor based system can't achieve high accuracy, we propose a multi-sensor based system, which can fuse the data from waist and thigh. Collected data are transferred to a computer or a cellphone using wireless Bluetooth technique. A discrimination analysis based pre-impact fall detection model is developed. Human activities can be classified into three categories (non-fall, backward fall and forward fall) using a hierarchical classifier. In order to improve the classification accuracy, optimal discriminant features are selected for each layer of classifier. Then, experiments are conducted and the results show that our method can both achieve high sensitivity and specificity as well as long lead time.
{"title":"A multi-sensor based pre-impact fall detection system with a hierarchical classifier","authors":"Yiwen Su, D. Liu, Yingfeng Wu","doi":"10.1109/CISP-BMEI.2016.7852995","DOIUrl":"https://doi.org/10.1109/CISP-BMEI.2016.7852995","url":null,"abstract":"Fall is a major threat to elders' health. The goal of our study is to establish a pre-impact fall detection system to reduce the harm of falls. For the problem that single-sensor based system can't achieve high accuracy, we propose a multi-sensor based system, which can fuse the data from waist and thigh. Collected data are transferred to a computer or a cellphone using wireless Bluetooth technique. A discrimination analysis based pre-impact fall detection model is developed. Human activities can be classified into three categories (non-fall, backward fall and forward fall) using a hierarchical classifier. In order to improve the classification accuracy, optimal discriminant features are selected for each layer of classifier. Then, experiments are conducted and the results show that our method can both achieve high sensitivity and specificity as well as long lead time.","PeriodicalId":275095,"journal":{"name":"2016 9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128978435","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：