Pub Date : 1900-01-01DOI: 10.1109/ICIVPR.2017.7890873
Jinfang Wang, Hailong Du, Ming Guo, Xinli Nie, Shu-xin Luan, Chang Liu
This paper presents an improved locally optimized short-time fractional Fourier transform (STFRFT), HHT-based locally optimized STFRFT, by finding the optimal order using phase information ignoring the premise of the known chirp rate of signal and pre-estimated pitch of speech. The feature derived from the optimal order FRFT's magnitude spectrum, HHT-based locally optimized STFRFT Mel-frequency cepstral coefficients (HLO-STFRFT-MFCC), reveals the definite advantage in speaker recognition experiments on the TIMIT database. Furthermore, HLO-STFRFT-MFCC yields a gain of 13.0% relative to the baseline feature of Mel-frequency cepstral coefficients (MFCC) in the recognition accuracy on 2004 NIST SRE corpora.
{"title":"Feature extraction using HHT-based locally optimized short-time fractional Fourier transform for speaker recognition","authors":"Jinfang Wang, Hailong Du, Ming Guo, Xinli Nie, Shu-xin Luan, Chang Liu","doi":"10.1109/ICIVPR.2017.7890873","DOIUrl":"https://doi.org/10.1109/ICIVPR.2017.7890873","url":null,"abstract":"This paper presents an improved locally optimized short-time fractional Fourier transform (STFRFT), HHT-based locally optimized STFRFT, by finding the optimal order using phase information ignoring the premise of the known chirp rate of signal and pre-estimated pitch of speech. The feature derived from the optimal order FRFT's magnitude spectrum, HHT-based locally optimized STFRFT Mel-frequency cepstral coefficients (HLO-STFRFT-MFCC), reveals the definite advantage in speaker recognition experiments on the TIMIT database. Furthermore, HLO-STFRFT-MFCC yields a gain of 13.0% relative to the baseline feature of Mel-frequency cepstral coefficients (MFCC) in the recognition accuracy on 2004 NIST SRE corpora.","PeriodicalId":126745,"journal":{"name":"2017 IEEE International Conference on Imaging, Vision & Pattern Recognition (icIVPR)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128223408","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 : 1900-01-01DOI: 10.1109/ICIVPR.2017.7890875
Sharmin Ahmed, W. Rahiman
Robustness analysis of dynamic system is one of the major research concerns in present times. Among many features, lane keeping of ground vehicle has caught the attention of researchers for its immense need in the passenger cars to avoid accidents and congestion. In this paper, robustness analysis of a mathematical model of ground vehicle along with a model predictive controller is simulated. The steering angle and the road curvature acts as the control input and the disturbance input of the vehicle respectively. For robustness analysis, parametric uncertainty is added in the vehicle model, where road-tire friction coefficient and look ahead distance are assumed as uncertain parameters. MATLAB-Simulink software simulation results show that that the model predictive controller of the lane keeping system is robust enough in the presence of uncertain road-tire friction coefficient and look ahead distance.
{"title":"Robustness analysis of lane keeping system for autonomous ground vehicle","authors":"Sharmin Ahmed, W. Rahiman","doi":"10.1109/ICIVPR.2017.7890875","DOIUrl":"https://doi.org/10.1109/ICIVPR.2017.7890875","url":null,"abstract":"Robustness analysis of dynamic system is one of the major research concerns in present times. Among many features, lane keeping of ground vehicle has caught the attention of researchers for its immense need in the passenger cars to avoid accidents and congestion. In this paper, robustness analysis of a mathematical model of ground vehicle along with a model predictive controller is simulated. The steering angle and the road curvature acts as the control input and the disturbance input of the vehicle respectively. For robustness analysis, parametric uncertainty is added in the vehicle model, where road-tire friction coefficient and look ahead distance are assumed as uncertain parameters. MATLAB-Simulink software simulation results show that that the model predictive controller of the lane keeping system is robust enough in the presence of uncertain road-tire friction coefficient and look ahead distance.","PeriodicalId":126745,"journal":{"name":"2017 IEEE International Conference on Imaging, Vision & Pattern Recognition (icIVPR)","volume":"78 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117103488","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 : 1900-01-01DOI: 10.1109/ICIVPR.2017.7890862
T. Sarker, S. Paul, A. Rayhan, I. Zabir, C. Shahnaz
Recently the development of brain-computer interface applications has drawn the attention of researchers as it can assist physically challenged people to communicate with their brain electroencephalogram signal. In this paper, a Brain-Computer Interface (BCI) is designed using EEG signals to differentiate between two mental arithmetic tasks performed by the same subject. The presented BCI approach includes three stages: (a) Elimination of power-line frequency components and segmentation of the raw signals (b) bi-spectral analysis as well as time and frequency domain features extraction (c) classification using SVM classifier. Bi-spectrum is proposed in order to characterize the non-Gaussian information contained within the EEG signals. Higher-order statistics of Bi-spectrum are used for classification. Time domain features as Generalized HFD and frequency domain features as frequency band powers and asymmetry among the channels are used to enhance the classification performances up to 100
{"title":"Bi-spectral higher order statistics and time-frequency domain features for arithmetic task classification from EEG signals","authors":"T. Sarker, S. Paul, A. Rayhan, I. Zabir, C. Shahnaz","doi":"10.1109/ICIVPR.2017.7890862","DOIUrl":"https://doi.org/10.1109/ICIVPR.2017.7890862","url":null,"abstract":"Recently the development of brain-computer interface applications has drawn the attention of researchers as it can assist physically challenged people to communicate with their brain electroencephalogram signal. In this paper, a Brain-Computer Interface (BCI) is designed using EEG signals to differentiate between two mental arithmetic tasks performed by the same subject. The presented BCI approach includes three stages: (a) Elimination of power-line frequency components and segmentation of the raw signals (b) bi-spectral analysis as well as time and frequency domain features extraction (c) classification using SVM classifier. Bi-spectrum is proposed in order to characterize the non-Gaussian information contained within the EEG signals. Higher-order statistics of Bi-spectrum are used for classification. Time domain features as Generalized HFD and frequency domain features as frequency band powers and asymmetry among the channels are used to enhance the classification performances up to 100","PeriodicalId":126745,"journal":{"name":"2017 IEEE International Conference on Imaging, Vision & Pattern Recognition (icIVPR)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114402825","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 : 1900-01-01DOI: 10.1109/ICIVPR.2017.7890856
Farshad Mashhadi, A. Asaduzzaman, M. Mridha
Approaches such as increasing the number of intermediate stages are introduced to increase the reliability and throughput of Multistage Interconnection Networks (MINs). However, they mainly try to change the network architecture to achieve the goal of having more reliable network. When multiple sources in such a network try to send data, collision of packets and blocking problems are inevitable. Using existing networks, they cant be prevented completely and a multiple access protocol must be used to that end. Time division multiple access (TDMA) protocol can be used to overcome these problems. To improve the performance of this protocol, we propose an adaptive slot allocation approach using Monte Carlo random sampling method. This approach is applied to Shuffle-exchange network (SEN) and Shuffle-exchange network with one additional stage (SEN+). Results for 4000 simulation cycles using Network Simulator 2 (NS2) show that the new SENs perform better in terms of reliability and throughput compared to their regular types.
通过增加中间级的数量来提高多级互连网络的可靠性和吞吐量。然而，他们主要试图改变网络架构，以达到拥有更可靠的网络的目的。当这种网络中的多个源试图发送数据时，不可避免地会出现数据包碰撞和阻塞问题。使用现有的网络，它们不能被完全阻止，因此必须使用多址访问协议。时分多址(TDMA)协议可以克服这些问题。为了提高该协议的性能，我们提出了一种采用蒙特卡洛随机抽样方法的自适应插槽分配方法。该方法应用于Shuffle-exchange network (SEN)和Shuffle-exchange network with one stage (SEN+)。使用Network Simulator 2 (NS2)进行了4000次模拟循环，结果表明，与常规类型的SENs相比，新型SENs在可靠性和吞吐量方面表现更好。
{"title":"A novel resource scheduling approach to improve the reliability of Shuffle-exchange networks","authors":"Farshad Mashhadi, A. Asaduzzaman, M. Mridha","doi":"10.1109/ICIVPR.2017.7890856","DOIUrl":"https://doi.org/10.1109/ICIVPR.2017.7890856","url":null,"abstract":"Approaches such as increasing the number of intermediate stages are introduced to increase the reliability and throughput of Multistage Interconnection Networks (MINs). However, they mainly try to change the network architecture to achieve the goal of having more reliable network. When multiple sources in such a network try to send data, collision of packets and blocking problems are inevitable. Using existing networks, they cant be prevented completely and a multiple access protocol must be used to that end. Time division multiple access (TDMA) protocol can be used to overcome these problems. To improve the performance of this protocol, we propose an adaptive slot allocation approach using Monte Carlo random sampling method. This approach is applied to Shuffle-exchange network (SEN) and Shuffle-exchange network with one additional stage (SEN+). Results for 4000 simulation cycles using Network Simulator 2 (NS2) show that the new SENs perform better in terms of reliability and throughput compared to their regular types.","PeriodicalId":126745,"journal":{"name":"2017 IEEE International Conference on Imaging, Vision & Pattern Recognition (icIVPR)","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126571660","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 : 1900-01-01DOI: 10.1109/ICIVPR.2017.7890883
Sumya Akter, Aysa Siddika Asa, Md. Palash Uddin, M. Hossain, Shikhor Kumer Roy, M. I. Afjal
Text summarization, a field of data mining, is very important for developing various real-life applications. Many techniques have been developed for summarizing English text(s). But, a few attempts have been made for Bengali text because of its some multifaceted structure. This paper presents a method for text summarization which extracts important sentences from a single or multiple Bengali documents. The input document(s) should be pre-processed by tokenization, stemming operation etc. Then, word score is calculated by Term-Frequency/Inverse Document Frequency (TF/IDF) and sentence score is determined by summing up its constituent words' scores with its position. Cue and skeleton words have also been considered to calculate the sentence score. For single or multiple documents, K-means clustering algorithm has been applied to produce the final summary. The experimental result shows satisfactory outputs in comparison to the existing approaches possessing linear run time complexity.
{"title":"An extractive text summarization technique for Bengali document(s) using K-means clustering algorithm","authors":"Sumya Akter, Aysa Siddika Asa, Md. Palash Uddin, M. Hossain, Shikhor Kumer Roy, M. I. Afjal","doi":"10.1109/ICIVPR.2017.7890883","DOIUrl":"https://doi.org/10.1109/ICIVPR.2017.7890883","url":null,"abstract":"Text summarization, a field of data mining, is very important for developing various real-life applications. Many techniques have been developed for summarizing English text(s). But, a few attempts have been made for Bengali text because of its some multifaceted structure. This paper presents a method for text summarization which extracts important sentences from a single or multiple Bengali documents. The input document(s) should be pre-processed by tokenization, stemming operation etc. Then, word score is calculated by Term-Frequency/Inverse Document Frequency (TF/IDF) and sentence score is determined by summing up its constituent words' scores with its position. Cue and skeleton words have also been considered to calculate the sentence score. For single or multiple documents, K-means clustering algorithm has been applied to produce the final summary. The experimental result shows satisfactory outputs in comparison to the existing approaches possessing linear run time complexity.","PeriodicalId":126745,"journal":{"name":"2017 IEEE International Conference on Imaging, Vision & Pattern Recognition (icIVPR)","volume":"86 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126043935","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 : 1900-01-01DOI: 10.1109/ICIVPR.2017.7890870
G. Rahaman, J. Parkkinen, M. Hauta-Kasari, S. H. Amirshahi
Color is an effective communication media in the objects of Art and historical (A&H) significance. However, as age increases, the objects become prone to color change through weather conditions, handling, display or preservation tasks. Therefore, to monitor the overall color change or to detect discolored area, it is important to precisely visualize the colored surface. This paper shows that RGB values computed using surface reflectance in (400–1000) nm wavelength range are capable to automatcially highlight any subtle color defect. Classical carpets are chosen to exemplify the outputs in this study. The extended CIE color matching functions based visualization method is most effective to render each multivariate data point by a single color. The defective areas of the surface in the resulting images appear strong to be detected readily. However, the conventional RGB colors fail mostly to reveal these color defects. Since spectral imaging is non-destructive and wide-area resolved, presented technique offers a comprehensive understanding of the color conditions of the A&H objects. So the visualization method should help the conservators to make informative decisions about different conservation and restoration strategies.
{"title":"Enhanced color visualization by spectral imaging: An application in cultural heritage","authors":"G. Rahaman, J. Parkkinen, M. Hauta-Kasari, S. H. Amirshahi","doi":"10.1109/ICIVPR.2017.7890870","DOIUrl":"https://doi.org/10.1109/ICIVPR.2017.7890870","url":null,"abstract":"Color is an effective communication media in the objects of Art and historical (A&H) significance. However, as age increases, the objects become prone to color change through weather conditions, handling, display or preservation tasks. Therefore, to monitor the overall color change or to detect discolored area, it is important to precisely visualize the colored surface. This paper shows that RGB values computed using surface reflectance in (400–1000) nm wavelength range are capable to automatcially highlight any subtle color defect. Classical carpets are chosen to exemplify the outputs in this study. The extended CIE color matching functions based visualization method is most effective to render each multivariate data point by a single color. The defective areas of the surface in the resulting images appear strong to be detected readily. However, the conventional RGB colors fail mostly to reveal these color defects. Since spectral imaging is non-destructive and wide-area resolved, presented technique offers a comprehensive understanding of the color conditions of the A&H objects. So the visualization method should help the conservators to make informative decisions about different conservation and restoration strategies.","PeriodicalId":126745,"journal":{"name":"2017 IEEE International Conference on Imaging, Vision & Pattern Recognition (icIVPR)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131036109","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 : 1900-01-01DOI: 10.1109/ICIVPR.2017.7890872
G. Rahaman, J. Parkkinen, M. Hauta-Kasari, Syed Hossain Amirshahi
Identification of colorants of artworks is of paramount importance in the context of museums and art galleries. We present a technique to discriminate the fiber dyes into natural or synthetic class using principal component analysis (PCA). Spectral imaging is used to measure the reflectance spectra of a variety of dyed wools in visible to near infrared (Vis/NIR): 400–1000 nm and short wave infrared (SWIR): 1000–2500 nm wavelength range. The full spectral range is segmented into nine partitions, and eigen vectors are extracted for each segment of training data. The same eigen vectors are used to compute the principal components (PCs) of training and test data. To classify test data, we successively increase the number of PCs and apply k-NN classifier to associate class label to the most similar training data. Results show over 93% overall accuracy with high precision in the range (1500–2500) nm using six PCs. By this technique natural Madder dyes can be classified from synthetic dyes with more than 98% accuracy.
{"title":"Fiber dye classification by spectral imaging","authors":"G. Rahaman, J. Parkkinen, M. Hauta-Kasari, Syed Hossain Amirshahi","doi":"10.1109/ICIVPR.2017.7890872","DOIUrl":"https://doi.org/10.1109/ICIVPR.2017.7890872","url":null,"abstract":"Identification of colorants of artworks is of paramount importance in the context of museums and art galleries. We present a technique to discriminate the fiber dyes into natural or synthetic class using principal component analysis (PCA). Spectral imaging is used to measure the reflectance spectra of a variety of dyed wools in visible to near infrared (Vis/NIR): 400–1000 nm and short wave infrared (SWIR): 1000–2500 nm wavelength range. The full spectral range is segmented into nine partitions, and eigen vectors are extracted for each segment of training data. The same eigen vectors are used to compute the principal components (PCs) of training and test data. To classify test data, we successively increase the number of PCs and apply k-NN classifier to associate class label to the most similar training data. Results show over 93% overall accuracy with high precision in the range (1500–2500) nm using six PCs. By this technique natural Madder dyes can be classified from synthetic dyes with more than 98% accuracy.","PeriodicalId":126745,"journal":{"name":"2017 IEEE International Conference on Imaging, Vision & Pattern Recognition (icIVPR)","volume":"74 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130629812","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 : 1900-01-01DOI: 10.1109/ICIVPR.2017.7890861
Md.Ibrahim Khalil, M. Hossain, Md.Japirul Haque, M. Hasan
Event-driven based traffic consideration in Wireless Sensor network (WSN) is a new area of research in the field of WSN. A few media access control (MAC) protocol has been proposed to handle the variety of both light and heavy traffic load situation such as RC-MAC which allows switching of modes to handle different traffic loads. In RC-MAC, nodes consume extra energy to stay awake like Receiver Initiated (RI-MAC) MAC, create energy hole in the network at later stages and nodes take large contention window to send data after receiving a beacon. Energy efficiency of sensor nodes should also take into consideration for the better network lifetime. In this paper, we improve energy hole problem of Receiver-Centric MAC(RC-MAC), entitled as EERC-MAC, which has better energy conservation and better throughput than RC-MAC. It uses a beacon technique that lets nodes to get sleep appropriately between data transmission and change the data routing path to avoid energy hole.
{"title":"EERC-MAC: Energy efficient Receiver Centric MAC protocol for Wireless Sensor network","authors":"Md.Ibrahim Khalil, M. Hossain, Md.Japirul Haque, M. Hasan","doi":"10.1109/ICIVPR.2017.7890861","DOIUrl":"https://doi.org/10.1109/ICIVPR.2017.7890861","url":null,"abstract":"Event-driven based traffic consideration in Wireless Sensor network (WSN) is a new area of research in the field of WSN. A few media access control (MAC) protocol has been proposed to handle the variety of both light and heavy traffic load situation such as RC-MAC which allows switching of modes to handle different traffic loads. In RC-MAC, nodes consume extra energy to stay awake like Receiver Initiated (RI-MAC) MAC, create energy hole in the network at later stages and nodes take large contention window to send data after receiving a beacon. Energy efficiency of sensor nodes should also take into consideration for the better network lifetime. In this paper, we improve energy hole problem of Receiver-Centric MAC(RC-MAC), entitled as EERC-MAC, which has better energy conservation and better throughput than RC-MAC. It uses a beacon technique that lets nodes to get sleep appropriately between data transmission and change the data routing path to avoid energy hole.","PeriodicalId":126745,"journal":{"name":"2017 IEEE International Conference on Imaging, Vision & Pattern Recognition (icIVPR)","volume":"113 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126302823","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：