Pub Date : 2016-06-04DOI: 10.1109/ICCSN.2016.7586623
Xu Huang, Raul Fernandez-Rojas, K. Ou, A. C. Madoc
Signal processing of brain activity is becoming challenging to various researchers from different areas, including medical, biomedical, and engineering researchers. In this paper, investigations of brain activity are made from experimental works, with optical flow based on spatiotemporal analysis and wavelet over the equipment of Near Infrared Spectroscopy (NIRS). Ant Colony Optimization (ACO) algorithm is employed for obtaining the distributions of the intensity of the targeted image. The major outcomes of this paper from our research are the following items: (a) optical flow can be a proper technology for the investigation of brain activity based on NIRS; (b) the analyses of the temporal domain, the spatial domain, and the wavelet domain underpinned coherently to our experimental results; (c) our wavelet analysis can define the most brain activity image, denoted as targeted image; (d) the details of the intensity distributions on the targeted image show the most significant brain activity via ACO algorithm; (e) we can clearly observe, via our algorithm technology, the existence of the so-called Dominant Channel (DC) based on spatiotemporal analysis and it plays a critical role in brain activity. The spatial distribution of the origin of cortical activity can be described by hemodynamic response in the cerebral cortex after evoked stimulation using near infrared spectroscopy. Further application of this research is expected in the next step research outcomes.
{"title":"Novel signal processing of brain activity based on Ant Colony Optimization and wavelet analysis with near infrared spectroscopy","authors":"Xu Huang, Raul Fernandez-Rojas, K. Ou, A. C. Madoc","doi":"10.1109/ICCSN.2016.7586623","DOIUrl":"https://doi.org/10.1109/ICCSN.2016.7586623","url":null,"abstract":"Signal processing of brain activity is becoming challenging to various researchers from different areas, including medical, biomedical, and engineering researchers. In this paper, investigations of brain activity are made from experimental works, with optical flow based on spatiotemporal analysis and wavelet over the equipment of Near Infrared Spectroscopy (NIRS). Ant Colony Optimization (ACO) algorithm is employed for obtaining the distributions of the intensity of the targeted image. The major outcomes of this paper from our research are the following items: (a) optical flow can be a proper technology for the investigation of brain activity based on NIRS; (b) the analyses of the temporal domain, the spatial domain, and the wavelet domain underpinned coherently to our experimental results; (c) our wavelet analysis can define the most brain activity image, denoted as targeted image; (d) the details of the intensity distributions on the targeted image show the most significant brain activity via ACO algorithm; (e) we can clearly observe, via our algorithm technology, the existence of the so-called Dominant Channel (DC) based on spatiotemporal analysis and it plays a critical role in brain activity. The spatial distribution of the origin of cortical activity can be described by hemodynamic response in the cerebral cortex after evoked stimulation using near infrared spectroscopy. Further application of this research is expected in the next step research outcomes.","PeriodicalId":158877,"journal":{"name":"2016 8th IEEE International Conference on Communication Software and Networks (ICCSN)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116621331","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 : 2016-06-04DOI: 10.1109/ICCSN.2016.7586583
Yonghong Chen, Xin Chen, H. Tian, Tian Wang, Yiqiao Cai
With the rapid growth of the Internet, the impact of attacks becomes more serious. IP spoofing makes hosts hard to defend against DDoS attacks. In this paper, we propose a blind detection method for tracing the real source of DDoS attack packets. Tracing the real source of a single-packet is difficult, so we trace-back a cluster of similar packets rather than a single-packet by cluster matching. We choose K-harmonic means clustering method to preprocess the packets according to our proposed quantitative model, at the same time, we propose an approach to determine the best number of clusters. In addition, we propose a novel detection algorithm about cluster matching for tracing the real source of packet clusters based on K-harmonic means and our improved silhouette. Experimental results show that our method can detect the real source of packets with up to 92.54% accuracy.
{"title":"A blind detection method for tracing the real source of DDoS attack packets by cluster matching","authors":"Yonghong Chen, Xin Chen, H. Tian, Tian Wang, Yiqiao Cai","doi":"10.1109/ICCSN.2016.7586583","DOIUrl":"https://doi.org/10.1109/ICCSN.2016.7586583","url":null,"abstract":"With the rapid growth of the Internet, the impact of attacks becomes more serious. IP spoofing makes hosts hard to defend against DDoS attacks. In this paper, we propose a blind detection method for tracing the real source of DDoS attack packets. Tracing the real source of a single-packet is difficult, so we trace-back a cluster of similar packets rather than a single-packet by cluster matching. We choose K-harmonic means clustering method to preprocess the packets according to our proposed quantitative model, at the same time, we propose an approach to determine the best number of clusters. In addition, we propose a novel detection algorithm about cluster matching for tracing the real source of packet clusters based on K-harmonic means and our improved silhouette. Experimental results show that our method can detect the real source of packets with up to 92.54% accuracy.","PeriodicalId":158877,"journal":{"name":"2016 8th IEEE International Conference on Communication Software and Networks (ICCSN)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132040191","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 : 2016-06-04DOI: 10.1109/ICCSN.2016.7586644
Feiyu Hou, Kun Xiao
In this paper, we investigate the impact of the outdated Channel State Information (CSI) and the Co-Channel Interference (CCI) on the performance of Transmit Antenna Selection with Selective Combining (TAS/SC) in a dual-hop amplify-and-forward (AF) Multiple-Input Multiple-Output (MIMO) relay network. We derive the exact closed-form and asymptotic expressions for the outage probability in the cases of perfect and outdated CSI, respectively. The simulation results match the theoretical analysis well. The findings suggest that the outdated CSI and CCI have significant impacts on the outage probability of an AF MIMO relay system with TAS/SC.
{"title":"Performance analysis of TAS/SC in MIMO relay systems with outdated CSI in the presence of co-channel interference","authors":"Feiyu Hou, Kun Xiao","doi":"10.1109/ICCSN.2016.7586644","DOIUrl":"https://doi.org/10.1109/ICCSN.2016.7586644","url":null,"abstract":"In this paper, we investigate the impact of the outdated Channel State Information (CSI) and the Co-Channel Interference (CCI) on the performance of Transmit Antenna Selection with Selective Combining (TAS/SC) in a dual-hop amplify-and-forward (AF) Multiple-Input Multiple-Output (MIMO) relay network. We derive the exact closed-form and asymptotic expressions for the outage probability in the cases of perfect and outdated CSI, respectively. The simulation results match the theoretical analysis well. The findings suggest that the outdated CSI and CCI have significant impacts on the outage probability of an AF MIMO relay system with TAS/SC.","PeriodicalId":158877,"journal":{"name":"2016 8th IEEE International Conference on Communication Software and Networks (ICCSN)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130052957","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 : 2016-06-04DOI: 10.1109/ICCSN.2016.7586607
Huan Jiang, Yu Wang, Changchun Zhang, X. Zhu
The quality of the fluorescence microscopic image is greatly degraded because of the physical limitation and human disturbance during the course of the optical imaging. Many image restoration and reconstruction algorithms were proposed to solve this problem. In this paper, an image display and analysis system for fluorescence microscopic sample was designed based on two-dimensional restoration and three-dimensional reconstruction algorithms. Our system aims to integrate those algorithms into one display interface. In this case, it is more convenient and ocular to process the images of fluorescence microscopic sample, and the results are more impressive. Users can obtain different restoration results by choosing different algorithms, and observe different restoration effects by setting different parameters.
{"title":"An image display and analysis system for fluorescence microscopic sample","authors":"Huan Jiang, Yu Wang, Changchun Zhang, X. Zhu","doi":"10.1109/ICCSN.2016.7586607","DOIUrl":"https://doi.org/10.1109/ICCSN.2016.7586607","url":null,"abstract":"The quality of the fluorescence microscopic image is greatly degraded because of the physical limitation and human disturbance during the course of the optical imaging. Many image restoration and reconstruction algorithms were proposed to solve this problem. In this paper, an image display and analysis system for fluorescence microscopic sample was designed based on two-dimensional restoration and three-dimensional reconstruction algorithms. Our system aims to integrate those algorithms into one display interface. In this case, it is more convenient and ocular to process the images of fluorescence microscopic sample, and the results are more impressive. Users can obtain different restoration results by choosing different algorithms, and observe different restoration effects by setting different parameters.","PeriodicalId":158877,"journal":{"name":"2016 8th IEEE International Conference on Communication Software and Networks (ICCSN)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116366759","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 : 2016-06-04DOI: 10.1109/ICCSN.2016.7586577
Meng Qingmin, Pang Fengmei, Zou Yulong
The requirement of high data rate and energy efficiency for a new generation of wireless network should reshape the designs of wireless heterogeneous network architecture including wireless relaying. For two-top bi-directional information exchange in wireless networks, we consider a wireless transmission design, which adopts the bi-directional relaying channel and the physical broadcasting. The bi-directional relaying channel is roughly divided into Decode and Forward (DF) strategy and Amplify and Forward (AF) strategy. This work focuses on a power control scheme of the DF-based bi-directional relaying in the configuration of a limited and a non-limited buffer. This scheme assumes that the transmitters of two source nodes have the channel gain information of the bi-directional relaying channel. The numerical results show that: the size of buffer at the relay node will not affect average end-to-end capacity over the Rayleigh fading channel while the size of maximum buffer is set as to an appropriate value. In addition, optimal power control will significantly improve the average end-to-end capacity of the transmission strategy compared to that of the equal power control scheme.
{"title":"Power control for buffer limited physical layer network coding","authors":"Meng Qingmin, Pang Fengmei, Zou Yulong","doi":"10.1109/ICCSN.2016.7586577","DOIUrl":"https://doi.org/10.1109/ICCSN.2016.7586577","url":null,"abstract":"The requirement of high data rate and energy efficiency for a new generation of wireless network should reshape the designs of wireless heterogeneous network architecture including wireless relaying. For two-top bi-directional information exchange in wireless networks, we consider a wireless transmission design, which adopts the bi-directional relaying channel and the physical broadcasting. The bi-directional relaying channel is roughly divided into Decode and Forward (DF) strategy and Amplify and Forward (AF) strategy. This work focuses on a power control scheme of the DF-based bi-directional relaying in the configuration of a limited and a non-limited buffer. This scheme assumes that the transmitters of two source nodes have the channel gain information of the bi-directional relaying channel. The numerical results show that: the size of buffer at the relay node will not affect average end-to-end capacity over the Rayleigh fading channel while the size of maximum buffer is set as to an appropriate value. In addition, optimal power control will significantly improve the average end-to-end capacity of the transmission strategy compared to that of the equal power control scheme.","PeriodicalId":158877,"journal":{"name":"2016 8th IEEE International Conference on Communication Software and Networks (ICCSN)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133602191","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 : 2016-06-04DOI: 10.1109/ICCSN.2016.7587202
R. Pei, Zulin Wang, Qiang Xiao, Li Quan
Blind identification for channel codes are essential in adaptive modulation and coding (AMC) systems. Since Turbo codes are popular in AMC systems, it's necessary to identify its parameters. In this paper, we focus on the identification for Turbo codes from a closed-set. The proposed approach firstly identifies the first component code by accumulating Log-Likelihood Ratio (LLR) for syndrome a posteriori probability, then the interleaver and the other component code are identified by decoding based on zero insertion and LLR accumulation. This approach is robust to noise due to LLR. Moreover, it applies to both symmetric Turbo codes with two same component codes and asymmetric Turbo codes with two different component codes. Simulation results demonstrate that the proposed blind identification scheme is able to identify Turbo codes at signal-to-noise ratio (SNR) larger than 3.5dB.
{"title":"Blind identification for Turbo codes in AMC systems","authors":"R. Pei, Zulin Wang, Qiang Xiao, Li Quan","doi":"10.1109/ICCSN.2016.7587202","DOIUrl":"https://doi.org/10.1109/ICCSN.2016.7587202","url":null,"abstract":"Blind identification for channel codes are essential in adaptive modulation and coding (AMC) systems. Since Turbo codes are popular in AMC systems, it's necessary to identify its parameters. In this paper, we focus on the identification for Turbo codes from a closed-set. The proposed approach firstly identifies the first component code by accumulating Log-Likelihood Ratio (LLR) for syndrome a posteriori probability, then the interleaver and the other component code are identified by decoding based on zero insertion and LLR accumulation. This approach is robust to noise due to LLR. Moreover, it applies to both symmetric Turbo codes with two same component codes and asymmetric Turbo codes with two different component codes. Simulation results demonstrate that the proposed blind identification scheme is able to identify Turbo codes at signal-to-noise ratio (SNR) larger than 3.5dB.","PeriodicalId":158877,"journal":{"name":"2016 8th IEEE International Conference on Communication Software and Networks (ICCSN)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125724674","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 : 2016-06-04DOI: 10.1109/ICCSN.2016.7586608
Rafaqat Hussain, Hui-xian Gao, R. Shaikh, S. Soomro
Text based CAPTCHA (Completely Automated Public Turing test to tell Computers and Humans Apart) is the most widely used mechanism adopted by numerous popular web sites in order to differentiate between machines and humans, however due to extensive research carried out by computer vision researchers, it is now a days vulnerable against automated attacks. Segmentation is the most difficult task in automatic recognition of CAPTCHAs, therefore contemporary Text based CAPTCHAs try to combine the characters together in order to make them as segmentation resistant against these attacks as possible. In this research, we have found vulnerabilities in such CAPTCHAs, a novel mechanism, i.e. the recognition based segmentation is applied to crop such connected characters, a sliding window based neural network classifier is used to recognize and segment the connected characters. Experimental results have proved 95.5% recognition success rate and 58.25% segmentation success rate on our dataset of tmall CAPTCHAs, this algorithm is further tested on two other datasets of slightly different implementations and promising results were achieved.
{"title":"Recognition based segmentation of connected characters in text based CAPTCHAs","authors":"Rafaqat Hussain, Hui-xian Gao, R. Shaikh, S. Soomro","doi":"10.1109/ICCSN.2016.7586608","DOIUrl":"https://doi.org/10.1109/ICCSN.2016.7586608","url":null,"abstract":"Text based CAPTCHA (Completely Automated Public Turing test to tell Computers and Humans Apart) is the most widely used mechanism adopted by numerous popular web sites in order to differentiate between machines and humans, however due to extensive research carried out by computer vision researchers, it is now a days vulnerable against automated attacks. Segmentation is the most difficult task in automatic recognition of CAPTCHAs, therefore contemporary Text based CAPTCHAs try to combine the characters together in order to make them as segmentation resistant against these attacks as possible. In this research, we have found vulnerabilities in such CAPTCHAs, a novel mechanism, i.e. the recognition based segmentation is applied to crop such connected characters, a sliding window based neural network classifier is used to recognize and segment the connected characters. Experimental results have proved 95.5% recognition success rate and 58.25% segmentation success rate on our dataset of tmall CAPTCHAs, this algorithm is further tested on two other datasets of slightly different implementations and promising results were achieved.","PeriodicalId":158877,"journal":{"name":"2016 8th IEEE International Conference on Communication Software and Networks (ICCSN)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124792162","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 : 2016-06-04DOI: 10.1109/ICCSN.2016.7586586
Hong Zhang, Changzhen Hu, Xiaojun Wang
Outlier detection is drawing more attention in recent years. It has a wide variety of applications, including network intrusion detection and event detection. A great deal of research has been done in this area, using spectrum or MDL (Minimum Description Length) as important tools to find some outliers. In this paper, we bring the k-shell into the outlier detection in complex networks, using the structural entropy as a way to measure the feature of the whole complex network. Through the experiment both on a synthetic network and a real world network, we give the importance of k-shell in discovering outliers in complex networks.
{"title":"The importance of k-shell in discovering key nodes in complex networks","authors":"Hong Zhang, Changzhen Hu, Xiaojun Wang","doi":"10.1109/ICCSN.2016.7586586","DOIUrl":"https://doi.org/10.1109/ICCSN.2016.7586586","url":null,"abstract":"Outlier detection is drawing more attention in recent years. It has a wide variety of applications, including network intrusion detection and event detection. A great deal of research has been done in this area, using spectrum or MDL (Minimum Description Length) as important tools to find some outliers. In this paper, we bring the k-shell into the outlier detection in complex networks, using the structural entropy as a way to measure the feature of the whole complex network. Through the experiment both on a synthetic network and a real world network, we give the importance of k-shell in discovering outliers in complex networks.","PeriodicalId":158877,"journal":{"name":"2016 8th IEEE International Conference on Communication Software and Networks (ICCSN)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129074204","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 : 2016-06-04DOI: 10.1109/ICCSN.2016.7586664
T. An, B. Lao, Junyi Wang, Yang Lu, Yanheng Wei, Xiaocong Wu
The Strategic Priority Research Program on Space Science of the Chinese Academy of Sciences, “Space Millimeter-wavelength VLBI Array (SMVA)”, aims to build the first space millimeter-wavelength Very Long Baseline Interferometry (VLBI) array in the world. The SMVA, which has the ultra-high spatial resolution with a best of 20 micro-arcsecond that a ground-based VLBI array can not attain, is a powerful tool in imaging the hyperfine emission structure surrounding the black holes and other compact celestial objects. The simulations, such as UV coverage simulation, numerical simulation and image simulation, play a crucial role in all phases of the project, so a space VLBI simulation software was designed and implemented. This software has all the necessary and auxiliary simulation functions. And it has many advantages compared to other similar software packages: its interface is more friendly, the software package is robust and independent of operation system, the code is much easier to expand and scalable.
{"title":"Space millimeter-wavelength very long baseline interferometry simulation software","authors":"T. An, B. Lao, Junyi Wang, Yang Lu, Yanheng Wei, Xiaocong Wu","doi":"10.1109/ICCSN.2016.7586664","DOIUrl":"https://doi.org/10.1109/ICCSN.2016.7586664","url":null,"abstract":"The Strategic Priority Research Program on Space Science of the Chinese Academy of Sciences, “Space Millimeter-wavelength VLBI Array (SMVA)”, aims to build the first space millimeter-wavelength Very Long Baseline Interferometry (VLBI) array in the world. The SMVA, which has the ultra-high spatial resolution with a best of 20 micro-arcsecond that a ground-based VLBI array can not attain, is a powerful tool in imaging the hyperfine emission structure surrounding the black holes and other compact celestial objects. The simulations, such as UV coverage simulation, numerical simulation and image simulation, play a crucial role in all phases of the project, so a space VLBI simulation software was designed and implemented. This software has all the necessary and auxiliary simulation functions. And it has many advantages compared to other similar software packages: its interface is more friendly, the software package is robust and independent of operation system, the code is much easier to expand and scalable.","PeriodicalId":158877,"journal":{"name":"2016 8th IEEE International Conference on Communication Software and Networks (ICCSN)","volume":"2006 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121079263","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 : 2016-06-04DOI: 10.1109/ICCSN.2016.7586601
V. Raman, P. Then, P. Sumari
Diabetes occurs when the pancreas fails to secrete enough insulin, slowly affecting the retina of the human eye, leading to diabetic retinopathy. The blood vessels in the retina get altered and have abnormality. Exudates are secreted, micro-aneurysms and haemorrhages occur in the retina. The appearance of these features represents the degree of severity of the disease. Early detection of diabetic retinopathy plays a major role in the success of such disease treatment. The main challenge is to extract exudates which are similar in colour property and size of the optic disk, and then micro-aneurysms are similar in colour and proximity with blood vessels. The main objective of the paper is to develop a computer aided detection system to find the abnormality of retinal imaging and detects the presence of abnormality features from retinal fundus images. There is few existing research works have been undergone by applying machine learning techniques, but existing approaches have not achieved a good accuracy of detection and they have not yielded successful performance in different datasets. The proposed methodology is to enhance the image and filter the noise, detect blood vessel and identify the optic disc, extract the exudates and micro aneurysms, extract the features and classify different stages of diabetic retinopathy into mild, moderate, severe non-proliferative diabetic retinopathy (NPDR) and proliferative Diabetic retinopathy (PDR) by using proposed machine learning methods. The expected output of proposed work in this paper will be a preliminary design and pilot prototype development.
{"title":"Proposed retinal abnormality detection and classification approach: Computer aided detection for diabetic retinopathy by machine learning approaches","authors":"V. Raman, P. Then, P. Sumari","doi":"10.1109/ICCSN.2016.7586601","DOIUrl":"https://doi.org/10.1109/ICCSN.2016.7586601","url":null,"abstract":"Diabetes occurs when the pancreas fails to secrete enough insulin, slowly affecting the retina of the human eye, leading to diabetic retinopathy. The blood vessels in the retina get altered and have abnormality. Exudates are secreted, micro-aneurysms and haemorrhages occur in the retina. The appearance of these features represents the degree of severity of the disease. Early detection of diabetic retinopathy plays a major role in the success of such disease treatment. The main challenge is to extract exudates which are similar in colour property and size of the optic disk, and then micro-aneurysms are similar in colour and proximity with blood vessels. The main objective of the paper is to develop a computer aided detection system to find the abnormality of retinal imaging and detects the presence of abnormality features from retinal fundus images. There is few existing research works have been undergone by applying machine learning techniques, but existing approaches have not achieved a good accuracy of detection and they have not yielded successful performance in different datasets. The proposed methodology is to enhance the image and filter the noise, detect blood vessel and identify the optic disc, extract the exudates and micro aneurysms, extract the features and classify different stages of diabetic retinopathy into mild, moderate, severe non-proliferative diabetic retinopathy (NPDR) and proliferative Diabetic retinopathy (PDR) by using proposed machine learning methods. The expected output of proposed work in this paper will be a preliminary design and pilot prototype development.","PeriodicalId":158877,"journal":{"name":"2016 8th IEEE International Conference on Communication Software and Networks (ICCSN)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115111828","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：