The focus of this research effort is to build Web Services based on open standards and monitor their requestresponse exchanges with a ASP.NET based application that stores performance information of the calls made to the web services, built in Microsoft Visual Studio for the purpose of generating performance data in the form of QoS quantifying quantities of Successes (similar to throughput), Failures (Total attemptssuccesses*) , Datasize or length and the Time taken (Response Time) measured from the service calls of web services for usage in research efforts for the selection and/or recommendation of these services to Web Service consumers. An approach for web service selection has been suggested as well as implemented using data mining techniques included in the selection algorithm.
{"title":"QoWS Analysis for Web Service Selection Using WS Monitoring Tool","authors":"G. Raj, Dheerendra Singh, Triveni Mishra","doi":"10.1109/CINE.2017.15","DOIUrl":"https://doi.org/10.1109/CINE.2017.15","url":null,"abstract":"The focus of this research effort is to build Web Services based on open standards and monitor their requestresponse exchanges with a ASP.NET based application that stores performance information of the calls made to the web services, built in Microsoft Visual Studio for the purpose of generating performance data in the form of QoS quantifying quantities of Successes (similar to throughput), Failures (Total attemptssuccesses*) , Datasize or length and the Time taken (Response Time) measured from the service calls of web services for usage in research efforts for the selection and/or recommendation of these services to Web Service consumers. An approach for web service selection has been suggested as well as implemented using data mining techniques included in the selection algorithm.","PeriodicalId":236972,"journal":{"name":"2017 3rd International Conference on Computational Intelligence and Networks (CINE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130091737","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}
Identity Crime is considered as crimes which involve masquerading one's identity and steal confidential information with respect to the concerned person's identity. This paper mainly deals with identity crime related to credit card application, which nowadays is quite prevalent and costly even. The existing non data-mining techniques for eliminating identity theft have some flaws and to combat them a new data-mining layer of defence has been proposed. This novel layer makes use of two algorithms-Communal Detection and Spike Detection for detecting frauds in applications.
{"title":"Identity Crime Detection Using Data Mining","authors":"Sharmistha Dutta, Ankit Gupta, Neetu Narayan","doi":"10.1109/CINE.2017.18","DOIUrl":"https://doi.org/10.1109/CINE.2017.18","url":null,"abstract":"Identity Crime is considered as crimes which involve masquerading one's identity and steal confidential information with respect to the concerned person's identity. This paper mainly deals with identity crime related to credit card application, which nowadays is quite prevalent and costly even. The existing non data-mining techniques for eliminating identity theft have some flaws and to combat them a new data-mining layer of defence has been proposed. This novel layer makes use of two algorithms-Communal Detection and Spike Detection for detecting frauds in applications.","PeriodicalId":236972,"journal":{"name":"2017 3rd International Conference on Computational Intelligence and Networks (CINE)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134394090","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}
J. Dhamija, T. Choudhury, Praveen Kumar, Y. Rathore
Image based or live video feed based face recognition is a very interesting field in research and applications. Various face recognition methods have been devised and applied over the past several years of technological development. Fields like security and surveillance have widely used face recognition over the years as people are very concerned as to identifying and catching criminals or people with mal intentions. Catching them without being able to promptly recognize and their faces has been a major problem. A person's facial features are dynamic and have variable appearances, which makes it a problem to be very accurate and fast in identification of a person. Not only this, security access controls through face recognizers makes it highly difficult for hackers and crackers to use a person's identity or data. The basic objective of this paper hence is to understand several pre-existing face detection and recognition algorithms and then provide a viable solution for live video based facial recognition with better accuracy, higher speed and efficiency so as to help develop a technology such which can help catch criminals promptly and as well as protect people's privacy and identity from hackers. Many facial databases have been considered so as to differentiate them in conditions of changes in poses, illuminations and emotions. Various other conditions to obstruct identification of faces are discussed later.
{"title":"An Advancement towards Efficient Face Recognition Using Live Video Feed: \"For the Future\"","authors":"J. Dhamija, T. Choudhury, Praveen Kumar, Y. Rathore","doi":"10.1109/CINE.2017.21","DOIUrl":"https://doi.org/10.1109/CINE.2017.21","url":null,"abstract":"Image based or live video feed based face recognition is a very interesting field in research and applications. Various face recognition methods have been devised and applied over the past several years of technological development. Fields like security and surveillance have widely used face recognition over the years as people are very concerned as to identifying and catching criminals or people with mal intentions. Catching them without being able to promptly recognize and their faces has been a major problem. A person's facial features are dynamic and have variable appearances, which makes it a problem to be very accurate and fast in identification of a person. Not only this, security access controls through face recognizers makes it highly difficult for hackers and crackers to use a person's identity or data. The basic objective of this paper hence is to understand several pre-existing face detection and recognition algorithms and then provide a viable solution for live video based facial recognition with better accuracy, higher speed and efficiency so as to help develop a technology such which can help catch criminals promptly and as well as protect people's privacy and identity from hackers. Many facial databases have been considered so as to differentiate them in conditions of changes in poses, illuminations and emotions. Various other conditions to obstruct identification of faces are discussed later.","PeriodicalId":236972,"journal":{"name":"2017 3rd International Conference on Computational Intelligence and Networks (CINE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131207485","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}
This paper demonstrates a comparative analysis of two binarization techniques- Niblack and Sauvola algorithm in context with their applications to retinal vessel segmentation. Preprocessed images are applied with Niblack’s binarization. Sauvola’s binarization is also applied as modification to Niblack’s algorithm. Drawbacks of Sauvola algorithm are addressed by incorporating some changes in the original algorithm and by setting experimentally the value of its Dynamic Range and the constant k in an application oriented way. Some post processing steps are needed to get rid of background noise pixels, The result is compared with the ground truth images of DRIVE database. The method achieves 93.23% accuracy in case of Niblack’s algorithm application and 93.31% (without post processing) and 94.34% (with post processing) accuracy in case of Sauvola algorithm. The accuracy obtained is very encouraging as far as the simplicity of the method is concerned.
{"title":"A Comparative Analysis of Application of Niblack and Sauvola Binarization to Retinal Vessel Segmentation","authors":"M. Nandy, M. Banerjee","doi":"10.1109/CINE.2017.19","DOIUrl":"https://doi.org/10.1109/CINE.2017.19","url":null,"abstract":"This paper demonstrates a comparative analysis of two binarization techniques- Niblack and Sauvola algorithm in context with their applications to retinal vessel segmentation. Preprocessed images are applied with Niblack’s binarization. Sauvola’s binarization is also applied as modification to Niblack’s algorithm. Drawbacks of Sauvola algorithm are addressed by incorporating some changes in the original algorithm and by setting experimentally the value of its Dynamic Range and the constant k in an application oriented way. Some post processing steps are needed to get rid of background noise pixels, The result is compared with the ground truth images of DRIVE database. The method achieves 93.23% accuracy in case of Niblack’s algorithm application and 93.31% (without post processing) and 94.34% (with post processing) accuracy in case of Sauvola algorithm. The accuracy obtained is very encouraging as far as the simplicity of the method is concerned.","PeriodicalId":236972,"journal":{"name":"2017 3rd International Conference on Computational Intelligence and Networks (CINE)","volume":"60 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126105835","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}
Sensors these days are ubiquitous. They are in homes, factories, farms and just about everywhere. For distributed sensing requirements, several sensors are deployed and connected on a wireless media forming a Wireless Sensor Network (WSN). Sensor nodes communicate with each other and with a base station (BS). In this paper we first review recent work which is focused on cross-layer WSN design techniques based on the Open System Interconnection (OSI) model. Sensor nodes are often clustered and cluster heads (CH) are used to route data to the BS. We have also reviewed constraints-based routing algorithms which select a routing path satisfying administrative-oriented or Quality of Service-oriented (QoS-oriented) constraints. The algorithms minimize costs, balance network load, or increase security. Previous works of cross-layer design for malicious node identification, diagonal data aggregation and route adjustments were deficient to support WSN. The major problem was higher energy consumption and congestion during data aggregation. To overcome all the limitations and the problems that exist in cross layer design of WSN, we have proposed a novel design in this paper.
{"title":"A Review of and a Proposal for Cross-Layer Design for Efficient Routing and Secure Data Aggregation over WSN","authors":"Mukesh Mishra, G. S. Gupta, X. Gui","doi":"10.1109/CINE.2017.30","DOIUrl":"https://doi.org/10.1109/CINE.2017.30","url":null,"abstract":"Sensors these days are ubiquitous. They are in homes, factories, farms and just about everywhere. For distributed sensing requirements, several sensors are deployed and connected on a wireless media forming a Wireless Sensor Network (WSN). Sensor nodes communicate with each other and with a base station (BS). In this paper we first review recent work which is focused on cross-layer WSN design techniques based on the Open System Interconnection (OSI) model. Sensor nodes are often clustered and cluster heads (CH) are used to route data to the BS. We have also reviewed constraints-based routing algorithms which select a routing path satisfying administrative-oriented or Quality of Service-oriented (QoS-oriented) constraints. The algorithms minimize costs, balance network load, or increase security. Previous works of cross-layer design for malicious node identification, diagonal data aggregation and route adjustments were deficient to support WSN. The major problem was higher energy consumption and congestion during data aggregation. To overcome all the limitations and the problems that exist in cross layer design of WSN, we have proposed a novel design in this paper.","PeriodicalId":236972,"journal":{"name":"2017 3rd International Conference on Computational Intelligence and Networks (CINE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129113706","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}
Analysis of crime is essential for providing safety and security to the civilian population. Using data mining, we can discover critical information which can help local authorities detect crime and areas of importance. The main purpose of this paper is to analyze the crime which entails theft, homicide and various drug offences which also include suspicious activities, noise complaints and burglar alarm by using qualitative and quantitative approach. Using K-means clustering data mining approach on a crime dataset from New South Wales region of Australia, crime rates of each type of crimes and cities with high crime rates have been found.
{"title":"Crime Analysis Using K-Means Clustering","authors":"Anant Joshi, A. Sabitha, T. Choudhury","doi":"10.1109/CINE.2017.23","DOIUrl":"https://doi.org/10.1109/CINE.2017.23","url":null,"abstract":"Analysis of crime is essential for providing safety and security to the civilian population. Using data mining, we can discover critical information which can help local authorities detect crime and areas of importance. The main purpose of this paper is to analyze the crime which entails theft, homicide and various drug offences which also include suspicious activities, noise complaints and burglar alarm by using qualitative and quantitative approach. Using K-means clustering data mining approach on a crime dataset from New South Wales region of Australia, crime rates of each type of crimes and cities with high crime rates have been found.","PeriodicalId":236972,"journal":{"name":"2017 3rd International Conference on Computational Intelligence and Networks (CINE)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126510400","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}
A Blockchain is basically a decentralized, distributed ledger of all the transactions or events which takes place only after involving multiple parties. It ensures high level of security as the transactions which takes place are entirely anonymous. Each transactions or digital events taking place in a Blockchain network is verified, only if it is agreed upon by the consensus of the majority party of the users participating in this process. Blockchain is one of the emerging technologies in today's world and a lot of revolution and research has just began regarding this distributed technology. Bitcoin has been the most popular cryptographic currency since it was invented and it is the best example that uses the Blockchain technology. In this paper, we will discuss about the research being done on this new domain of Computer Science. We will outline the underlining concepts about this new technology. We will try to peek a bit into its applications in the financial and non financial sector. It is not only the most popular topic to discuss about, but is the most technological breakthrough, that is all set to revolutionize the entire world.
{"title":"An Overview of the Emerging Technology: Blockchain","authors":"Rishav Chatterjee, Rajdeep Chatterjee","doi":"10.1109/CINE.2017.33","DOIUrl":"https://doi.org/10.1109/CINE.2017.33","url":null,"abstract":"A Blockchain is basically a decentralized, distributed ledger of all the transactions or events which takes place only after involving multiple parties. It ensures high level of security as the transactions which takes place are entirely anonymous. Each transactions or digital events taking place in a Blockchain network is verified, only if it is agreed upon by the consensus of the majority party of the users participating in this process. Blockchain is one of the emerging technologies in today's world and a lot of revolution and research has just began regarding this distributed technology. Bitcoin has been the most popular cryptographic currency since it was invented and it is the best example that uses the Blockchain technology. In this paper, we will discuss about the research being done on this new domain of Computer Science. We will outline the underlining concepts about this new technology. We will try to peek a bit into its applications in the financial and non financial sector. It is not only the most popular topic to discuss about, but is the most technological breakthrough, that is all set to revolutionize the entire world.","PeriodicalId":236972,"journal":{"name":"2017 3rd International Conference on Computational Intelligence and Networks (CINE)","volume":"327 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123311580","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}
M. Debnath, J. Padhi, Priyambada Satapathy, R. Mallick
Fuzzy-PID controller with derivative filter (Fuzzy-PIDF) is suggested in this article for automatic generation control in a two area multi-unit hydro-thermal system. The controller scaling coefficients are tuned with a simple and a new powerful optimization technique called JAYA algorithm. Integral time absolute error (ITAE) is used as a fitness function to achieve the optimal parameters of the Fuzzy-PIDF controller with an abrupt load disturbance of 0.01p.u. applied in area 1. Further, this controller is scrutinized for robustness by increasing the loading in the system. The dynamic responses of this implemented controller being optimized by JAYA algorithm are evaluated and compared with the results of previously published article such as hybrid firefly algorithm and pattern search technique based PID controller in terms of peak undershoot, overshoot and settling time and supremacy is proved.
{"title":"Application of JAYA Algorithm to Tune Fuzzy-PIDF Controller for Automatic Generation Control","authors":"M. Debnath, J. Padhi, Priyambada Satapathy, R. Mallick","doi":"10.1109/CINE.2017.13","DOIUrl":"https://doi.org/10.1109/CINE.2017.13","url":null,"abstract":"Fuzzy-PID controller with derivative filter (Fuzzy-PIDF) is suggested in this article for automatic generation control in a two area multi-unit hydro-thermal system. The controller scaling coefficients are tuned with a simple and a new powerful optimization technique called JAYA algorithm. Integral time absolute error (ITAE) is used as a fitness function to achieve the optimal parameters of the Fuzzy-PIDF controller with an abrupt load disturbance of 0.01p.u. applied in area 1. Further, this controller is scrutinized for robustness by increasing the loading in the system. The dynamic responses of this implemented controller being optimized by JAYA algorithm are evaluated and compared with the results of previously published article such as hybrid firefly algorithm and pattern search technique based PID controller in terms of peak undershoot, overshoot and settling time and supremacy is proved.","PeriodicalId":236972,"journal":{"name":"2017 3rd International Conference on Computational Intelligence and Networks (CINE)","volume":"183 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121102328","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}
Since the GridSim toolkit is used to simulate the Grid computing environment, it has been widely used in the study of Grid. In this paper, the proposed work presents a load balancing scheme called LBLC for GridSim. Here, the load balancing is performed by providing an effective selection method for scheduling of Gridlets among heterogeneous resources with load consideration which maximizes the utilization of the resources and increases the efficiency of the Grid system. The performance is evaluated under various cases by using GridSim. From the simulation results, our load balancing scheme is shown to be quite efficient in maximizing the finished Gridlets and minimizing the execution time, unfinished Gridlets.
{"title":"An Effective Selection Method for Scheduling of Gridlets among Heterogeneous Resources with Load Balancing on GridSim","authors":"D. Patel, C. Tripathy","doi":"10.1109/CINE.2017.17","DOIUrl":"https://doi.org/10.1109/CINE.2017.17","url":null,"abstract":"Since the GridSim toolkit is used to simulate the Grid computing environment, it has been widely used in the study of Grid. In this paper, the proposed work presents a load balancing scheme called LBLC for GridSim. Here, the load balancing is performed by providing an effective selection method for scheduling of Gridlets among heterogeneous resources with load consideration which maximizes the utilization of the resources and increases the efficiency of the Grid system. The performance is evaluated under various cases by using GridSim. From the simulation results, our load balancing scheme is shown to be quite efficient in maximizing the finished Gridlets and minimizing the execution time, unfinished Gridlets.","PeriodicalId":236972,"journal":{"name":"2017 3rd International Conference on Computational Intelligence and Networks (CINE)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129709061","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}
P. K. Mohanty, Arun Kumar Sah, Vikash Kumar, S. Kundu
Autonomous mobile robot has tremendous application in various environment due to the fact that they work without human intervention. Path planning and obstacle avoidance are challenging problem for autonomous mobile robot. This paper explores--- the obstacle avoidance technique for wheeled mobile robot based on Deep-Q-Learning. In this paper, we introduce a log-based reward value field function which is the reward receives by agent based on relative positions of agent, obstacles and goal. We perform the experiment in simulated environment and physical environment. Finally, we measure the accuracy of the performance of the obstacle avoidance ability of the robot based of hit rate metrices. Our presented method achieves high success rate to avoid collisions.
{"title":"Application of Deep Q-Learning for Wheel Mobile Robot Navigation","authors":"P. K. Mohanty, Arun Kumar Sah, Vikash Kumar, S. Kundu","doi":"10.1109/CINE.2017.11","DOIUrl":"https://doi.org/10.1109/CINE.2017.11","url":null,"abstract":"Autonomous mobile robot has tremendous application in various environment due to the fact that they work without human intervention. Path planning and obstacle avoidance are challenging problem for autonomous mobile robot. This paper explores--- the obstacle avoidance technique for wheeled mobile robot based on Deep-Q-Learning. In this paper, we introduce a log-based reward value field function which is the reward receives by agent based on relative positions of agent, obstacles and goal. We perform the experiment in simulated environment and physical environment. Finally, we measure the accuracy of the performance of the obstacle avoidance ability of the robot based of hit rate metrices. Our presented method achieves high success rate to avoid collisions.","PeriodicalId":236972,"journal":{"name":"2017 3rd International Conference on Computational Intelligence and Networks (CINE)","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127396108","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：