Pub Date : 2017-09-01DOI: 10.1109/ICSIPA.2017.8120594
M. Mustaffa, Wong San San
Many animal species exist in this world and there are always new species being discovered each year. Therefore, it is very important that these valuable species be documented properly to be referred to in future. Numerous information retrieval systems for managing and documenting animal species today only allow users to search animal images and descriptions online via text-based input. Therefore, people without knowledge on the animal species or without Internet access are not able to search using the systems. Motivated by these issues, the focus of this work is to construct a colour-shape content-based image representation for fauna. Two orders of the Colour Moment are used to represent the colour feature while the i-means approach is used to represent the shape feature. Based on the conducted quantitative and qualitative studies, the proposed fusion method together with the Content-based Image Retrieval (CBIR) system are found to be very effective in retrieving animal images similar to the given query, able to provide reliable and useful information on animal species, an easy system to interact with, and has easy to understand and user-friendly interfaces.
{"title":"Content-based fauna image retrieval system","authors":"M. Mustaffa, Wong San San","doi":"10.1109/ICSIPA.2017.8120594","DOIUrl":"https://doi.org/10.1109/ICSIPA.2017.8120594","url":null,"abstract":"Many animal species exist in this world and there are always new species being discovered each year. Therefore, it is very important that these valuable species be documented properly to be referred to in future. Numerous information retrieval systems for managing and documenting animal species today only allow users to search animal images and descriptions online via text-based input. Therefore, people without knowledge on the animal species or without Internet access are not able to search using the systems. Motivated by these issues, the focus of this work is to construct a colour-shape content-based image representation for fauna. Two orders of the Colour Moment are used to represent the colour feature while the i-means approach is used to represent the shape feature. Based on the conducted quantitative and qualitative studies, the proposed fusion method together with the Content-based Image Retrieval (CBIR) system are found to be very effective in retrieving animal images similar to the given query, able to provide reliable and useful information on animal species, an easy system to interact with, and has easy to understand and user-friendly interfaces.","PeriodicalId":268112,"journal":{"name":"2017 IEEE International Conference on Signal and Image Processing Applications (ICSIPA)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115079839","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 : 2017-09-01DOI: 10.1109/ICSIPA.2017.8120658
Hanif Bhuiyan, Jinat Ara, Rajon Bardhan, Md. Rashedul Islam
YouTube is one of the comprehensive video information source on the web where video is uploading continuously in real time. It is one of the most popular site in social media, where users interact with sharing, commenting and rating (like/views) videos. Generally the quality, relevancy and popularity of the video is maintained based on this rating. Sometimes irrelevant and low quality videos ranked higher in the search result due to the number of views or likes, which seems untenable. To minimize this issue, we present a Natural Language processing (NLP) based sentiment analysis approach on user comments. This analysis helps to find out the most relevant and popular video of YouTube according to the search. The effectiveness of the proposed scheme has been proved by a data driven experiment in terms of accuracy of finding relevant, popular and high quality video.
{"title":"Retrieving YouTube video by sentiment analysis on user comment","authors":"Hanif Bhuiyan, Jinat Ara, Rajon Bardhan, Md. Rashedul Islam","doi":"10.1109/ICSIPA.2017.8120658","DOIUrl":"https://doi.org/10.1109/ICSIPA.2017.8120658","url":null,"abstract":"YouTube is one of the comprehensive video information source on the web where video is uploading continuously in real time. It is one of the most popular site in social media, where users interact with sharing, commenting and rating (like/views) videos. Generally the quality, relevancy and popularity of the video is maintained based on this rating. Sometimes irrelevant and low quality videos ranked higher in the search result due to the number of views or likes, which seems untenable. To minimize this issue, we present a Natural Language processing (NLP) based sentiment analysis approach on user comments. This analysis helps to find out the most relevant and popular video of YouTube according to the search. The effectiveness of the proposed scheme has been proved by a data driven experiment in terms of accuracy of finding relevant, popular and high quality video.","PeriodicalId":268112,"journal":{"name":"2017 IEEE International Conference on Signal and Image Processing Applications (ICSIPA)","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122483346","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 : 2017-09-01DOI: 10.1109/ICSIPA.2017.8120631
S. N. M. Usak, S. Sugiman, N. Sha'ari, Mugunthan Kaneson, H. Abdullah, N. Noor, C. Patti, Chamila Dissanayaka, D. Cvetkovic
Sleep Apnoea Syndromes (SAS) is a sleep disorder which caused breathing pauses during sleep at night. There is various method of analyzing sleep EEG signals can be found in the literature. In this paper both linear; Discrete Wavelet Transform (DWT) and non-linear; Approximate Entropy (ApEn) extraction methods were performed to differentiate features of each sleep stages between apnoea and healthy person. The efficiency of both extraction methods was compared by using ANOVA. In our study, we observed the non-linear feature of ApEn improves the ability to discriminate healthy and sleep apnoea at different sleep stages.
{"title":"EEG biomarker of Sleep Apnoea using discrete wavelet transform and approximate entropy","authors":"S. N. M. Usak, S. Sugiman, N. Sha'ari, Mugunthan Kaneson, H. Abdullah, N. Noor, C. Patti, Chamila Dissanayaka, D. Cvetkovic","doi":"10.1109/ICSIPA.2017.8120631","DOIUrl":"https://doi.org/10.1109/ICSIPA.2017.8120631","url":null,"abstract":"Sleep Apnoea Syndromes (SAS) is a sleep disorder which caused breathing pauses during sleep at night. There is various method of analyzing sleep EEG signals can be found in the literature. In this paper both linear; Discrete Wavelet Transform (DWT) and non-linear; Approximate Entropy (ApEn) extraction methods were performed to differentiate features of each sleep stages between apnoea and healthy person. The efficiency of both extraction methods was compared by using ANOVA. In our study, we observed the non-linear feature of ApEn improves the ability to discriminate healthy and sleep apnoea at different sleep stages.","PeriodicalId":268112,"journal":{"name":"2017 IEEE International Conference on Signal and Image Processing Applications (ICSIPA)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123059948","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 : 2017-09-01DOI: 10.1109/ICSIPA.2017.8120578
Niloofar Ghasemi Roochi, H. Ghassemian, F. Mirzapour
Remote sensing is the acquisition of information about an object or phenomenon without making physical contact with the object. Remote sensing is used in numerous fields, including geography, land surveying and most Earth Science disciplines. In supervised classification, all of the feature extraction methods try to increase the accuracy of classification and simultaneously time of computation. At the present work, we use the moments and Attribute Morphology Profiles (APs) to extract texture information from satellite panchromatic images. We use four conventional moments in pattern recognition such as Geometric, Chebyshev, Legendre and Zernike moments and APs to extract features from remote sensing image. An MP is constructed based on the repeated use of openings and closings by reconstruction of a structuring elements (SE) of an increasing size, applied to a scalar image. Then, we use those two set of features together. The well-known support vector machine (SVM) is used for supervised classification. We compare our proposed method with moments and APs. Different criteria such as average accuracy, overall accuracy, κ statistic and computation time are used for assessment of classification performance.
{"title":"Remote sensing images classification using moment features and attribute profiles","authors":"Niloofar Ghasemi Roochi, H. Ghassemian, F. Mirzapour","doi":"10.1109/ICSIPA.2017.8120578","DOIUrl":"https://doi.org/10.1109/ICSIPA.2017.8120578","url":null,"abstract":"Remote sensing is the acquisition of information about an object or phenomenon without making physical contact with the object. Remote sensing is used in numerous fields, including geography, land surveying and most Earth Science disciplines. In supervised classification, all of the feature extraction methods try to increase the accuracy of classification and simultaneously time of computation. At the present work, we use the moments and Attribute Morphology Profiles (APs) to extract texture information from satellite panchromatic images. We use four conventional moments in pattern recognition such as Geometric, Chebyshev, Legendre and Zernike moments and APs to extract features from remote sensing image. An MP is constructed based on the repeated use of openings and closings by reconstruction of a structuring elements (SE) of an increasing size, applied to a scalar image. Then, we use those two set of features together. The well-known support vector machine (SVM) is used for supervised classification. We compare our proposed method with moments and APs. Different criteria such as average accuracy, overall accuracy, κ statistic and computation time are used for assessment of classification performance.","PeriodicalId":268112,"journal":{"name":"2017 IEEE International Conference on Signal and Image Processing Applications (ICSIPA)","volume":"180 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133706239","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 : 2017-09-01DOI: 10.1109/ICSIPA.2017.8120621
Riady Siswoyo Jo, H. S. Jo, Almon Chai
Falling sphere viscometer is one of the most commonly used techniques in experimentally determining fluid viscosity. This method requires the measurement of the terminal velocity of a falling sphere inside the fluid, which remains a challenging and costly task, especially if high precision is required. This paper presents the development of a low-cost visionbased falling sphere viscometer. The velocity measurement is performed by incorporating two linear image sensors which allow faster frame rate. A specific object detection algorithm based on background subtraction is developed to analyze the image data in real-time. The experimental setup and implementation are also presented.
{"title":"Development of low-cost vision-based falling sphere viscometer","authors":"Riady Siswoyo Jo, H. S. Jo, Almon Chai","doi":"10.1109/ICSIPA.2017.8120621","DOIUrl":"https://doi.org/10.1109/ICSIPA.2017.8120621","url":null,"abstract":"Falling sphere viscometer is one of the most commonly used techniques in experimentally determining fluid viscosity. This method requires the measurement of the terminal velocity of a falling sphere inside the fluid, which remains a challenging and costly task, especially if high precision is required. This paper presents the development of a low-cost visionbased falling sphere viscometer. The velocity measurement is performed by incorporating two linear image sensors which allow faster frame rate. A specific object detection algorithm based on background subtraction is developed to analyze the image data in real-time. The experimental setup and implementation are also presented.","PeriodicalId":268112,"journal":{"name":"2017 IEEE International Conference on Signal and Image Processing Applications (ICSIPA)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134087673","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 : 2017-09-01DOI: 10.1109/ICSIPA.2017.8120589
M. Malek, P. Sebastian, M. Drieberg
This paper presents an alternative navigation tool that can be used in indoor environment. This is due to restrictions on GPS signals that cannot be detected in indoor locations. The work presented here shows the development of an interactive indoor localization system that uses live input video capture and can identify location markers to indicate its current location. In addition, augmented reality is also used to superimpose augmented reality objects above the location markers to indicate the direction to be taken by the user, which assists the user in navigating to the chosen destination. The developed system was implemented on a Raspberry Pi, an embedded computing platform, with a USB camera and display glasses for the live video capture and display devices respectively. It was tested in Universiti Teknologi PETRONAS' Information Resource Center, across multiple locations and different floors of the center.
本文提出了一种可用于室内环境的替代导航工具。这是由于GPS信号的限制，无法在室内位置检测到。这里展示的工作展示了一种交互式室内定位系统的发展，该系统使用实时输入视频捕获，并可以识别位置标记以指示其当前位置。此外，增强现实还用于将增强现实对象叠加在位置标记之上，以指示用户要走的方向，从而帮助用户导航到选择的目的地。所开发的系统在嵌入式计算平台Raspberry Pi上实现，其中USB摄像头和显示眼镜分别用于实时视频捕获和显示设备。它在Universiti Teknologi PETRONAS的信息资源中心进行了测试，横跨多个地点和中心的不同楼层。
{"title":"Augmented reality assisted localization for indoor navigation on embedded computing platform","authors":"M. Malek, P. Sebastian, M. Drieberg","doi":"10.1109/ICSIPA.2017.8120589","DOIUrl":"https://doi.org/10.1109/ICSIPA.2017.8120589","url":null,"abstract":"This paper presents an alternative navigation tool that can be used in indoor environment. This is due to restrictions on GPS signals that cannot be detected in indoor locations. The work presented here shows the development of an interactive indoor localization system that uses live input video capture and can identify location markers to indicate its current location. In addition, augmented reality is also used to superimpose augmented reality objects above the location markers to indicate the direction to be taken by the user, which assists the user in navigating to the chosen destination. The developed system was implemented on a Raspberry Pi, an embedded computing platform, with a USB camera and display glasses for the live video capture and display devices respectively. It was tested in Universiti Teknologi PETRONAS' Information Resource Center, across multiple locations and different floors of the center.","PeriodicalId":268112,"journal":{"name":"2017 IEEE International Conference on Signal and Image Processing Applications (ICSIPA)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131803204","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 : 2017-09-01DOI: 10.1109/ICSIPA.2017.8120672
Jarle Urdal, K. Engan, T. Eftestøl, H. Kidanto, L. Yarrot, J. Eilevstjønn, H. Ersdal
Neonatal mortality is a global challenge. One million newborns die each year within their first 24 hours as a result of complications during labour and birth asphyxia. Most of these deaths happen in low resource settings. However, basic resuscitation at birth can increase newborn survival. Identification of initial factors and simple therapeutic strategies determinant for neonatal outcome can aid health care workers provide the best follow-up during resuscitation. In this work, the initial condition of the newborn, the treatment given, and early heart rate response from manual bag mask ventilation are parameterized. The features are investigated in a machine learning framework to identify which features are determinant for the different outcomes. Using a selection of the defined features, an identification rate of 89% for newborns in the normal group, and an identification rate of 74% for episodes ending in death was found. This points to the direction of identifying the important factors of newborn survival.
{"title":"Signal processing and classification for identification of clinically important parameters during neonatal resuscitation","authors":"Jarle Urdal, K. Engan, T. Eftestøl, H. Kidanto, L. Yarrot, J. Eilevstjønn, H. Ersdal","doi":"10.1109/ICSIPA.2017.8120672","DOIUrl":"https://doi.org/10.1109/ICSIPA.2017.8120672","url":null,"abstract":"Neonatal mortality is a global challenge. One million newborns die each year within their first 24 hours as a result of complications during labour and birth asphyxia. Most of these deaths happen in low resource settings. However, basic resuscitation at birth can increase newborn survival. Identification of initial factors and simple therapeutic strategies determinant for neonatal outcome can aid health care workers provide the best follow-up during resuscitation. In this work, the initial condition of the newborn, the treatment given, and early heart rate response from manual bag mask ventilation are parameterized. The features are investigated in a machine learning framework to identify which features are determinant for the different outcomes. Using a selection of the defined features, an identification rate of 89% for newborns in the normal group, and an identification rate of 74% for episodes ending in death was found. This points to the direction of identifying the important factors of newborn survival.","PeriodicalId":268112,"journal":{"name":"2017 IEEE International Conference on Signal and Image Processing Applications (ICSIPA)","volume":"34 23","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120853888","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 : 2017-09-01DOI: 10.1109/ICSIPA.2017.8120670
Shermon S. Mathulamuthu, V. Asirvadam, S. Dass, B. Gill
Recently, Malaysia has been reported with dengue epidemic, that could rise up to 120, 000 cases recorded per year. This serious issue needs a vital look to prevent the dengue occurrences as it has no medicine yet to be found. Therefore, studies need to be done in order to prevent the dengue occurrences. This paper presents a high accuracy dengue occurrences prediction model which could forecast the dengue occurrences accurately. Manifold learning theorem has been performed to reduce the dimension into one by maintaining the geodesic distances between all points. Next machine learning theorem such as clustering (K-means technique) and linear regression has been done to model the data. Averaged silhouette width method was used to determine the number of K for K-means technique. Each cluster the regression model is built and SSE was shown in table. Overall, it's shown that there is low SSE achieved after applying dimension reduction and cluster based regression. The regression fit is improved and bring out better fit.
{"title":"Predicting dengue cases by aggregation of climate variable using manifold learning","authors":"Shermon S. Mathulamuthu, V. Asirvadam, S. Dass, B. Gill","doi":"10.1109/ICSIPA.2017.8120670","DOIUrl":"https://doi.org/10.1109/ICSIPA.2017.8120670","url":null,"abstract":"Recently, Malaysia has been reported with dengue epidemic, that could rise up to 120, 000 cases recorded per year. This serious issue needs a vital look to prevent the dengue occurrences as it has no medicine yet to be found. Therefore, studies need to be done in order to prevent the dengue occurrences. This paper presents a high accuracy dengue occurrences prediction model which could forecast the dengue occurrences accurately. Manifold learning theorem has been performed to reduce the dimension into one by maintaining the geodesic distances between all points. Next machine learning theorem such as clustering (K-means technique) and linear regression has been done to model the data. Averaged silhouette width method was used to determine the number of K for K-means technique. Each cluster the regression model is built and SSE was shown in table. Overall, it's shown that there is low SSE achieved after applying dimension reduction and cluster based regression. The regression fit is improved and bring out better fit.","PeriodicalId":268112,"journal":{"name":"2017 IEEE International Conference on Signal and Image Processing Applications (ICSIPA)","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127532863","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 : 2017-09-01DOI: 10.1109/ICSIPA.2017.8120602
Maisam Jalilian, M. Nouri, A. Ahmadi, Nabeeh Kandalaft
This paper proposes a digital construction of Pulse Width Modulation (PWM) signals based on the Izhikevich neuron model using a Field Programmable Gate Array (FPGA) platform. The signals are intended for use in diverse electronics applications such as robotics and power converters. A spiking pattern was used to generate the input data and produce the PWM signals. A comparator was used to compare between the spiking pattern data and DC level parameters. The results validate that the proposed hardware can reproduce PWM signals with duty cycles from 0% to 100%.
{"title":"Pulse width modulation (PWM) signals using spiking neuronal networks","authors":"Maisam Jalilian, M. Nouri, A. Ahmadi, Nabeeh Kandalaft","doi":"10.1109/ICSIPA.2017.8120602","DOIUrl":"https://doi.org/10.1109/ICSIPA.2017.8120602","url":null,"abstract":"This paper proposes a digital construction of Pulse Width Modulation (PWM) signals based on the Izhikevich neuron model using a Field Programmable Gate Array (FPGA) platform. The signals are intended for use in diverse electronics applications such as robotics and power converters. A spiking pattern was used to generate the input data and produce the PWM signals. A comparator was used to compare between the spiking pattern data and DC level parameters. The results validate that the proposed hardware can reproduce PWM signals with duty cycles from 0% to 100%.","PeriodicalId":268112,"journal":{"name":"2017 IEEE International Conference on Signal and Image Processing Applications (ICSIPA)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133962044","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 : 2017-09-01DOI: 10.1109/ICSIPA.2017.8120627
S. S. M. Radzi, V. Asirvadam, S. Dass, Duma Kristina Yanti Hutapea
This paper investigates the influences of noise power and signals length towards the fractal dimension (FD) of a short and non-complex visual evoked potential (VEP). Higuchi and Katz's algorithms have been used to estimate the fractal dimension of the simulated VEPs with the various parameter. To examine the performance of both algorithms, the parameter of colored noise and window length of the signal were varied. Weierstrass cosine function was generated with a known FD for validation. Katz's FD of the VEPs are linearly proportional to the noise power, as it measures the roughness of the signal. Higuchi's algorithm is highly affected by noise. The FD decreases as noise power increased until it reaches the plateau when the noise power equals to 0.05. It was found that Katz's FD has no significant effect of window length, meanwhile, Higuchi's FD increases as window length increases.
{"title":"Evaluation of simulated VEP signals on basis of Higuchi and Katz's algorithm","authors":"S. S. M. Radzi, V. Asirvadam, S. Dass, Duma Kristina Yanti Hutapea","doi":"10.1109/ICSIPA.2017.8120627","DOIUrl":"https://doi.org/10.1109/ICSIPA.2017.8120627","url":null,"abstract":"This paper investigates the influences of noise power and signals length towards the fractal dimension (FD) of a short and non-complex visual evoked potential (VEP). Higuchi and Katz's algorithms have been used to estimate the fractal dimension of the simulated VEPs with the various parameter. To examine the performance of both algorithms, the parameter of colored noise and window length of the signal were varied. Weierstrass cosine function was generated with a known FD for validation. Katz's FD of the VEPs are linearly proportional to the noise power, as it measures the roughness of the signal. Higuchi's algorithm is highly affected by noise. The FD decreases as noise power increased until it reaches the plateau when the noise power equals to 0.05. It was found that Katz's FD has no significant effect of window length, meanwhile, Higuchi's FD increases as window length increases.","PeriodicalId":268112,"journal":{"name":"2017 IEEE International Conference on Signal and Image Processing Applications (ICSIPA)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134069836","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：