Pub Date : 2017-05-01DOI: 10.1109/CCAA.2017.8230059
M. Mufti, M. Y. Zargar, S. A. Lone
This paper focuses on frequency control of standalone wind-diesel system using SMES. As the inertia is small, any disturbance in the load will disturb the frequency which will cause electromechanical oscillations. The system frequency which is used to control the SMES unit is estimated by centre of inertia COI technique. SMES being a fast acting storage system can handle the electromechanical oscillations quickly and help in reducing the frequency deviations under limit. In this paper active power control of SMES unit is modulated using an adaptive predictive control scheme. Predictive controller generates reference power for SMES and forces it to follow the power command. Results show that the frequency deviation of the standalone hybrid wind-diesel system is reduced considerably with the proposed predicatively controlled SMES without violating the converter limits.
{"title":"Predictive controlled SMES for frequency control of hybrid wind-diesel standalone system","authors":"M. Mufti, M. Y. Zargar, S. A. Lone","doi":"10.1109/CCAA.2017.8230059","DOIUrl":"https://doi.org/10.1109/CCAA.2017.8230059","url":null,"abstract":"This paper focuses on frequency control of standalone wind-diesel system using SMES. As the inertia is small, any disturbance in the load will disturb the frequency which will cause electromechanical oscillations. The system frequency which is used to control the SMES unit is estimated by centre of inertia COI technique. SMES being a fast acting storage system can handle the electromechanical oscillations quickly and help in reducing the frequency deviations under limit. In this paper active power control of SMES unit is modulated using an adaptive predictive control scheme. Predictive controller generates reference power for SMES and forces it to follow the power command. Results show that the frequency deviation of the standalone hybrid wind-diesel system is reduced considerably with the proposed predicatively controlled SMES without violating the converter limits.","PeriodicalId":6627,"journal":{"name":"2017 International Conference on Computing, Communication and Automation (ICCCA)","volume":"17 1","pages":"1395-1400"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89585789","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 : 2017-05-01DOI: 10.1109/CCAA.2017.8229871
Savita
One of the prominent problems of the Delay Tolerant Networks (DTNs) is the high delay occurring in the message delivery. As there is absence of complete path from source to destination in the network, these networks are often susceptible to high delays. In DTNs, one of the primary objective is to establish end-to-end communication path between the nodes in the heterogeneous environment e Factors such as discharge of batteries and link failure lead to frequent disconnection in these networks. The amount of energy dissipated in the network is highly dependent on the message routing and node mobility. Therefore, developing an energy efficient routing protocol is a key issue in DTNs. A plethora of routing algorithms for DTNs is developed, but only few of them take energy constraint into consideration. The challenge to maintain the high reliability of network in the presence of frequent topology changes in DTNs has garnered immense interest from the researchers to further explore the area. This article reviews the some of the state-of-the-art routing protocols of the DTNs. We have also compared the performance of these algorithms in the light of energy consumption.
{"title":"Energy efficient delay tolerant network routing protocols: A comparative study","authors":"Savita","doi":"10.1109/CCAA.2017.8229871","DOIUrl":"https://doi.org/10.1109/CCAA.2017.8229871","url":null,"abstract":"One of the prominent problems of the Delay Tolerant Networks (DTNs) is the high delay occurring in the message delivery. As there is absence of complete path from source to destination in the network, these networks are often susceptible to high delays. In DTNs, one of the primary objective is to establish end-to-end communication path between the nodes in the heterogeneous environment e Factors such as discharge of batteries and link failure lead to frequent disconnection in these networks. The amount of energy dissipated in the network is highly dependent on the message routing and node mobility. Therefore, developing an energy efficient routing protocol is a key issue in DTNs. A plethora of routing algorithms for DTNs is developed, but only few of them take energy constraint into consideration. The challenge to maintain the high reliability of network in the presence of frequent topology changes in DTNs has garnered immense interest from the researchers to further explore the area. This article reviews the some of the state-of-the-art routing protocols of the DTNs. We have also compared the performance of these algorithms in the light of energy consumption.","PeriodicalId":6627,"journal":{"name":"2017 International Conference on Computing, Communication and Automation (ICCCA)","volume":"1 1","pages":"596-600"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90388562","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}
Data Clustering in Data Mining is a domain which never gets out of focus. Clustering a data was always an easy task but achieving the required accuracy, precision and performance was never so easy. K means being an archaic clustering algorithm got tested and experimented thousands of times with variety of datasets and other combination of algorithm due to its robustness and simplicity but what this algorithm proposed was not suggested before. It used K means algorithm for the evaluation and validation purposes whereas optimization of the data is done with the help of Particle Swarm Optimization Algorithm. The drawbacks of K means mainly its local convergence property and initializing number of clusters at an early stage has aroused the process of working on this algorithm. So, for attaining the global convergence the Swarm Intelligence is preferred over Genetic Algorithm and many other techniques and for the latter one we combined two functions one of them helps in knowing the number of clusters which are optimal for the particular dataset and the other one validates the results using another function and compares the various metrics which will define the goodness and fitness of an algorithm. In one line the complete overview of the proposed algorithm can be described as ‘Evaluating the data using an Evalcluster Function, performing Validation with the help of an Evaluate Function of the K means and giving the final touch of Optimizing the data by K means PSO Algorithm’. The algorithm is tested for over 4 datasets available in UCI Repository and the results were unexpectedly great.
{"title":"Enhancing K means by unsupervised learning using PSO algorithm","authors":"Aishwarya Gupta, Vishwajeet Pattanaik, Mayank Singh","doi":"10.1109/CCAA.2017.8229805","DOIUrl":"https://doi.org/10.1109/CCAA.2017.8229805","url":null,"abstract":"Data Clustering in Data Mining is a domain which never gets out of focus. Clustering a data was always an easy task but achieving the required accuracy, precision and performance was never so easy. K means being an archaic clustering algorithm got tested and experimented thousands of times with variety of datasets and other combination of algorithm due to its robustness and simplicity but what this algorithm proposed was not suggested before. It used K means algorithm for the evaluation and validation purposes whereas optimization of the data is done with the help of Particle Swarm Optimization Algorithm. The drawbacks of K means mainly its local convergence property and initializing number of clusters at an early stage has aroused the process of working on this algorithm. So, for attaining the global convergence the Swarm Intelligence is preferred over Genetic Algorithm and many other techniques and for the latter one we combined two functions one of them helps in knowing the number of clusters which are optimal for the particular dataset and the other one validates the results using another function and compares the various metrics which will define the goodness and fitness of an algorithm. In one line the complete overview of the proposed algorithm can be described as ‘Evaluating the data using an Evalcluster Function, performing Validation with the help of an Evaluate Function of the K means and giving the final touch of Optimizing the data by K means PSO Algorithm’. The algorithm is tested for over 4 datasets available in UCI Repository and the results were unexpectedly great.","PeriodicalId":6627,"journal":{"name":"2017 International Conference on Computing, Communication and Automation (ICCCA)","volume":"17 6 Pt 1 1","pages":"228-233"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90405569","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 : 2017-05-01DOI: 10.1109/CCAA.2017.8229914
V. Singh, S. K. Peddoju
Cloud Environment allows enterprises to scale their application on demand. Microservice design is a new paradigm for cloud application development which is gaining popularity due to its granular approach and loosely coupled services unlike monolithic design with single code base. Applications developed using microservice design results in better scaling and gives extended flexibility to the developers with minimum cost. In this paper, first, different challenges in deployment and continuous integration of microservices are analyzed. To overcome these challenges, later, an automated system is proposed and designed which helps in deployment and continuous integration of microservices. Containers are recently heavily used in deploying the applications as they are easy to manage and lightweight when compared to traditional Virtual Machines (VMs). We have deployed the proposed microservices architecture on the docker containers and tested using a social networking application as case study. Finally, the results are presented and the performance of monolithic and microservice approach is compared using various parameters such as response time, throughput, deployment time etc. Results show that application developed using microservice approach and deployed using the proposed design reduce the time and effort for deployment and continuous integration of the application. Results also shows that microservice based application outperform monolithic design because of its low response time and high throughput.
{"title":"Container-based microservice architecture for cloud applications","authors":"V. Singh, S. K. Peddoju","doi":"10.1109/CCAA.2017.8229914","DOIUrl":"https://doi.org/10.1109/CCAA.2017.8229914","url":null,"abstract":"Cloud Environment allows enterprises to scale their application on demand. Microservice design is a new paradigm for cloud application development which is gaining popularity due to its granular approach and loosely coupled services unlike monolithic design with single code base. Applications developed using microservice design results in better scaling and gives extended flexibility to the developers with minimum cost. In this paper, first, different challenges in deployment and continuous integration of microservices are analyzed. To overcome these challenges, later, an automated system is proposed and designed which helps in deployment and continuous integration of microservices. Containers are recently heavily used in deploying the applications as they are easy to manage and lightweight when compared to traditional Virtual Machines (VMs). We have deployed the proposed microservices architecture on the docker containers and tested using a social networking application as case study. Finally, the results are presented and the performance of monolithic and microservice approach is compared using various parameters such as response time, throughput, deployment time etc. Results show that application developed using microservice approach and deployed using the proposed design reduce the time and effort for deployment and continuous integration of the application. Results also shows that microservice based application outperform monolithic design because of its low response time and high throughput.","PeriodicalId":6627,"journal":{"name":"2017 International Conference on Computing, Communication and Automation (ICCCA)","volume":"72 1","pages":"847-852"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73065072","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 : 2017-05-01DOI: 10.1109/CCAA.2017.8229892
Abhijeet Das, A. Swaroop
Efficient power use is the fundamental to think about tried and true operation of wireless or remote sensor frameworks. This applies correspondingly to direct or linear sensor masterminds as they create when sensors are sent along linear frameworks such as pipelines. In this work, a innovative approach to manage imperativeness capable controlling to a dual base station or control center in a straight or linear wireless sensor topology and on the basis of different attributes and calamities appears near pipelines, different sensor node senses these stimuli and immediately responds to base station presents at both the ends within certain range. Our informative show that a jump approach saves gigantic battery power in relation to MTE, MERR and other standard traditional systems and has close perfect execution.
{"title":"Energy efficient routing protocol for linear wireless sensor network","authors":"Abhijeet Das, A. Swaroop","doi":"10.1109/CCAA.2017.8229892","DOIUrl":"https://doi.org/10.1109/CCAA.2017.8229892","url":null,"abstract":"Efficient power use is the fundamental to think about tried and true operation of wireless or remote sensor frameworks. This applies correspondingly to direct or linear sensor masterminds as they create when sensors are sent along linear frameworks such as pipelines. In this work, a innovative approach to manage imperativeness capable controlling to a dual base station or control center in a straight or linear wireless sensor topology and on the basis of different attributes and calamities appears near pipelines, different sensor node senses these stimuli and immediately responds to base station presents at both the ends within certain range. Our informative show that a jump approach saves gigantic battery power in relation to MTE, MERR and other standard traditional systems and has close perfect execution.","PeriodicalId":6627,"journal":{"name":"2017 International Conference on Computing, Communication and Automation (ICCCA)","volume":"225 1","pages":"703-707"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75692252","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 : 2017-05-01DOI: 10.1109/CCAA.2017.8229980
Jatin Sokhal, B. Garg, S. Aggarwal, Rachna Jain
The electroencephalogram (EEG) signals are a sturdy tool for tracing brain variations during different periods of life, also it plays a prominent and considerable role in the diagnosis of various diseases. In our previously published papers [1-8] we have worked on diverse problems that can be analyzed by neural networks. In this paper, we have chosen EEG signals due to its increase its application in Motor Learning predicaments. EEG recordings complied and manifold over the duration of an elongated time frame encompasses an enormous quantum of EEG data. The study of signals and decomposition of these signals activity contribute a way to diminish the computational cost and emend the enforcement of the classifiers. We have proposed a unique classification of signals in which we have used empirical mode decomposition and variety of lifting wavelet transform schemes for the compression of signals. The procedure for making a resolution contains four stages: (a) extraction of the signals, (b) signal preprocessing and filtering,(c) compression using Empirical mode decomposition or lifting wavelet Transform schemes and (d) classification using artificial neural network enforcement. The outcomes contributed the fact that there exists ability in the proposed algorithm for the classification of EEG signals.
{"title":"Classification of EEG signals using empirical mode decomposition and lifting wavelet transforms","authors":"Jatin Sokhal, B. Garg, S. Aggarwal, Rachna Jain","doi":"10.1109/CCAA.2017.8229980","DOIUrl":"https://doi.org/10.1109/CCAA.2017.8229980","url":null,"abstract":"The electroencephalogram (EEG) signals are a sturdy tool for tracing brain variations during different periods of life, also it plays a prominent and considerable role in the diagnosis of various diseases. In our previously published papers [1-8] we have worked on diverse problems that can be analyzed by neural networks. In this paper, we have chosen EEG signals due to its increase its application in Motor Learning predicaments. EEG recordings complied and manifold over the duration of an elongated time frame encompasses an enormous quantum of EEG data. The study of signals and decomposition of these signals activity contribute a way to diminish the computational cost and emend the enforcement of the classifiers. We have proposed a unique classification of signals in which we have used empirical mode decomposition and variety of lifting wavelet transform schemes for the compression of signals. The procedure for making a resolution contains four stages: (a) extraction of the signals, (b) signal preprocessing and filtering,(c) compression using Empirical mode decomposition or lifting wavelet Transform schemes and (d) classification using artificial neural network enforcement. The outcomes contributed the fact that there exists ability in the proposed algorithm for the classification of EEG signals.","PeriodicalId":6627,"journal":{"name":"2017 International Conference on Computing, Communication and Automation (ICCCA)","volume":"8 1","pages":"1197-1202"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74717663","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 : 2017-05-01DOI: 10.1109/CCAA.2017.8229800
S. Pant, Y. S. Chauhan, K. Singh, J. N. Singh
We have discuss in the paper the stability results of tangent & inverse tangent functions using Jungck Ishikawa Iterative scheme. In previous year there have been research papers in which only mathematical explanation for trigonometric functions is discuss but in this paper we have generated Mandelbrot and Julia sets and discuss their characteristics using this iterative scheme.
{"title":"Comparative study of rate of convergence & complex dynamics of trigonometric functions using Jungck Ishikawa iteration scheme","authors":"S. Pant, Y. S. Chauhan, K. Singh, J. N. Singh","doi":"10.1109/CCAA.2017.8229800","DOIUrl":"https://doi.org/10.1109/CCAA.2017.8229800","url":null,"abstract":"We have discuss in the paper the stability results of tangent & inverse tangent functions using Jungck Ishikawa Iterative scheme. In previous year there have been research papers in which only mathematical explanation for trigonometric functions is discuss but in this paper we have generated Mandelbrot and Julia sets and discuss their characteristics using this iterative scheme.","PeriodicalId":6627,"journal":{"name":"2017 International Conference on Computing, Communication and Automation (ICCCA)","volume":"15 1","pages":"202-209"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72923923","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 : 2017-05-01DOI: 10.1109/CCAA.2017.8229945
Reema Kalshaonkar, S. Kuwelkar
This paper focuses on detecting a pedestrian in an image. This real time application aims for high detection accuracy as well as faster computation. For higher accuracy and detection rate Histogram of Oriented Gradients (HOG) algorithm is used. Further, Linear Support Vector Machine (LSVM) classification is used for faster and reliable classification. Since the HOG algorithm is compute expensive several modifications have been made in order to get the best results for real time application. We have used bilinear interpolation and L2-normalisation for more reliable output. Further since the data is linearly separable a LSVM is designed in Matlab. The proposed algorithm provides an accuracy of 93.27% with a high true positive rate of 92.27% and a minor false positive rate of 4%.
本文主要研究图像中行人的检测问题。这个实时应用程序旨在提高检测精度和更快的计算速度。为了提高准确率和检出率，采用了直方图定向梯度(HOG)算法。进一步，采用线性支持向量机(Linear Support Vector Machine, LSVM)分类，实现更快、更可靠的分类。由于HOG算法计算量大，为了获得实时应用的最佳结果，对算法进行了一些修改。我们使用双线性插值和l2归一化来获得更可靠的输出。此外，由于数据是线性可分的，在Matlab中设计了一个LSVM。该算法的准确率为93.27%，其中真阳性率为92.27%，假阳性率为4%。
{"title":"Design of an accurate pedestrian detection system using modified HOG and LSVM","authors":"Reema Kalshaonkar, S. Kuwelkar","doi":"10.1109/CCAA.2017.8229945","DOIUrl":"https://doi.org/10.1109/CCAA.2017.8229945","url":null,"abstract":"This paper focuses on detecting a pedestrian in an image. This real time application aims for high detection accuracy as well as faster computation. For higher accuracy and detection rate Histogram of Oriented Gradients (HOG) algorithm is used. Further, Linear Support Vector Machine (LSVM) classification is used for faster and reliable classification. Since the HOG algorithm is compute expensive several modifications have been made in order to get the best results for real time application. We have used bilinear interpolation and L2-normalisation for more reliable output. Further since the data is linearly separable a LSVM is designed in Matlab. The proposed algorithm provides an accuracy of 93.27% with a high true positive rate of 92.27% and a minor false positive rate of 4%.","PeriodicalId":6627,"journal":{"name":"2017 International Conference on Computing, Communication and Automation (ICCCA)","volume":"1 1","pages":"957-962"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73249552","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 : 2017-05-01DOI: 10.1109/CCAA.2017.8230015
Komal Jaswal, T. Choudhury, Roshan lal Chhokar, Sooraj Randhir Singh
These days Internet of Things (Internet of things) has transformed into a serious ponder that has made progress in the practically every field we can imagine. The following research paper gives a review of Internet of things, its empowering innovations, developing applications and security issues in the remote advancements. There are colossal number of uses of Internet of things in practically every part of life i.e. medicinal services, coordinations and production network administration, shrewd environment and social application and so forth along these lines security is an essential worry of remote systems thus it is one of the principle issues in Internet of things. The following paper gives an outline of the many security worries in an Internet of things framework, dangers related to it, difficulties and techniques to avoid such security issues.
如今，物联网(Internet of Things)已经转变为一个严肃的思考，几乎在我们能想象到的每个领域都取得了进展。下面的研究报告给出了物联网的回顾，它的授权创新，开发应用和安全问题在远程推进。物联网几乎在生活的各个方面都有大量的应用，例如医疗服务、协调和生产网络管理、精明的环境和社会应用等等，这些方面的安全是远程系统的基本担忧，因此它是物联网的主要问题之一。下面的文章概述了物联网框架中存在的诸多安全隐患、与之相关的危险、难点以及避免这些安全问题的技术。
{"title":"Securing the Internet of Things: A proposed framework","authors":"Komal Jaswal, T. Choudhury, Roshan lal Chhokar, Sooraj Randhir Singh","doi":"10.1109/CCAA.2017.8230015","DOIUrl":"https://doi.org/10.1109/CCAA.2017.8230015","url":null,"abstract":"These days Internet of Things (Internet of things) has transformed into a serious ponder that has made progress in the practically every field we can imagine. The following research paper gives a review of Internet of things, its empowering innovations, developing applications and security issues in the remote advancements. There are colossal number of uses of Internet of things in practically every part of life i.e. medicinal services, coordinations and production network administration, shrewd environment and social application and so forth along these lines security is an essential worry of remote systems thus it is one of the principle issues in Internet of things. The following paper gives an outline of the many security worries in an Internet of things framework, dangers related to it, difficulties and techniques to avoid such security issues.","PeriodicalId":6627,"journal":{"name":"2017 International Conference on Computing, Communication and Automation (ICCCA)","volume":"12 1","pages":"1277-1281"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74465327","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 : 2017-05-01DOI: 10.1109/CCAA.2017.8229972
Surender Singh, A. Prasad, Kingshuk Srivastava, Suman Bhattacharya
Edge detection is one of the basic methods for various image processing functions such as image analysis, image segmentation, pattern recognition etc. This is a process to find out discontinuity of intensity in image. If some or all neighboring pixels form a convex region of same gray level intensity, then there exists an edge. In order to distinguish between different level of intensities in edge detection, a threshold is required which is usually different for different type of images due to variation in level of intensities. This paper proposes and compares two methods namely global and local thresholding to model the value of threshold through quantitative empirical method for cellular logic array processing based edge detection method. The performance of the modeled algorithms is measured by F1-score, recall-precision break-even-points and performance ratio. Experimental results show that the local thresholding approach gives slightly better F1-score and performance ratio for all scenarios of six Berkeley Segmentation Database images and respective ground truths. It has also been found that best percentage of threshold value can be determined in a better way by break-even-point rather than by best F1-score. The proposed approach reduces false edge detection and make threshold selection automatic for every scenario.
{"title":"Threshold modeling for cellular logic array processing based edge detection algorithm","authors":"Surender Singh, A. Prasad, Kingshuk Srivastava, Suman Bhattacharya","doi":"10.1109/CCAA.2017.8229972","DOIUrl":"https://doi.org/10.1109/CCAA.2017.8229972","url":null,"abstract":"Edge detection is one of the basic methods for various image processing functions such as image analysis, image segmentation, pattern recognition etc. This is a process to find out discontinuity of intensity in image. If some or all neighboring pixels form a convex region of same gray level intensity, then there exists an edge. In order to distinguish between different level of intensities in edge detection, a threshold is required which is usually different for different type of images due to variation in level of intensities. This paper proposes and compares two methods namely global and local thresholding to model the value of threshold through quantitative empirical method for cellular logic array processing based edge detection method. The performance of the modeled algorithms is measured by F1-score, recall-precision break-even-points and performance ratio. Experimental results show that the local thresholding approach gives slightly better F1-score and performance ratio for all scenarios of six Berkeley Segmentation Database images and respective ground truths. It has also been found that best percentage of threshold value can be determined in a better way by break-even-point rather than by best F1-score. The proposed approach reduces false edge detection and make threshold selection automatic for every scenario.","PeriodicalId":6627,"journal":{"name":"2017 International Conference on Computing, Communication and Automation (ICCCA)","volume":"236 1","pages":"1158-1162"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74393821","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：