Pub Date : 1900-01-01DOI: 10.1109/CONFLUENCE.2016.7508152
H. S. Sandhu, K. Singh, D. S. Kapoor
With the advent of industrialization and rise of power generation plants, the cases of firing are on the rise. Besides other methods of fire detection, the technology today has touched every single aspect of human life in a way that are unimaginable. It is widely used for instant recognition and managing a rising fire. Edge detection is a significant ingredient in flame. Edge detection techniques can protect the significant structural property of the flame and also cut down the dispensation time. This technique can used to fragment a collection of flames as well. In this paper edge detection technique using morphological operation has been proposed which gives the satisfactory outcomes and is much faster than other traditional methods as demonstrated with the help od computer simulation.
{"title":"Automatic edge detection algorithm and area calculation for flame and fire images","authors":"H. S. Sandhu, K. Singh, D. S. Kapoor","doi":"10.1109/CONFLUENCE.2016.7508152","DOIUrl":"https://doi.org/10.1109/CONFLUENCE.2016.7508152","url":null,"abstract":"With the advent of industrialization and rise of power generation plants, the cases of firing are on the rise. Besides other methods of fire detection, the technology today has touched every single aspect of human life in a way that are unimaginable. It is widely used for instant recognition and managing a rising fire. Edge detection is a significant ingredient in flame. Edge detection techniques can protect the significant structural property of the flame and also cut down the dispensation time. This technique can used to fragment a collection of flames as well. In this paper edge detection technique using morphological operation has been proposed which gives the satisfactory outcomes and is much faster than other traditional methods as demonstrated with the help od computer simulation.","PeriodicalId":299044,"journal":{"name":"2016 6th International Conference - Cloud System and Big Data Engineering (Confluence)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116898371","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}
From time immemorial, Libraries have been the house of Illuminati. With the advancing world, new discoveries are being made creating new horizons of knowledge and with new and increasing researches being made there has been a proliferation of books, journals and transcripts. With this surplus production of books and journals in both existing and new areas managing them in library has become a tedious task. Looking up for a book seems like searching for a needle in a haystack. In this age of digitalization and automation we present an automated and innovative library management system which will not only automate the management process but will also ease the manual searching of books. The emphasis is on using the techniques of Optical Character Recognition to obtain a resulting system which can identify and locate books in a physical library by the use of searching algorithms.
{"title":"Global library innovative system: An image-search facilitated library system","authors":"Prashast Sahay, Ridhima Gupta, Rishi Kumar, Humera Zabin","doi":"10.1109/CONFLUENCE.2016.7508166","DOIUrl":"https://doi.org/10.1109/CONFLUENCE.2016.7508166","url":null,"abstract":"From time immemorial, Libraries have been the house of Illuminati. With the advancing world, new discoveries are being made creating new horizons of knowledge and with new and increasing researches being made there has been a proliferation of books, journals and transcripts. With this surplus production of books and journals in both existing and new areas managing them in library has become a tedious task. Looking up for a book seems like searching for a needle in a haystack. In this age of digitalization and automation we present an automated and innovative library management system which will not only automate the management process but will also ease the manual searching of books. The emphasis is on using the techniques of Optical Character Recognition to obtain a resulting system which can identify and locate books in a physical library by the use of searching algorithms.","PeriodicalId":299044,"journal":{"name":"2016 6th International Conference - Cloud System and Big Data Engineering (Confluence)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126564886","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1900-01-01DOI: 10.1109/CONFLUENCE.2016.7508049
Neelima Bhatia, Arunima Jaiswal
Text summarization is an incipient practice for verdict out the summary of the text article. Text summarization has grew so uses such as Due to the enormous aggregate of information getting augmented on internet; it is challenging for the user to verve through altogether the information accessible on web. The large availability of internet content partakes constrained a broad research area in the extent of automatic text summarization contained by the Natural Language Processing (NLP), especially statistical machine learning communal. Terminated the bygone half a century, the defaulting has been addressed from numerous diverse standpoints, in erratic domains and using innumerable archetypes. In this survey paper we investigate the popular and important work done in the field of single and multiple document summarizations, generous distinctive prominence towards pragmatic approaches and extractive techniques. Particular auspicious slants that quintessence on unambiguous minutiae of the summarization are also deliberated. Exceptional consideration is ardent to involuntary assessment of summarization classifications, as forthcoming investigation on summarization is sturdily reliant over evolvement in this problem space.
{"title":"Automatic text summarization and it's methods - a review","authors":"Neelima Bhatia, Arunima Jaiswal","doi":"10.1109/CONFLUENCE.2016.7508049","DOIUrl":"https://doi.org/10.1109/CONFLUENCE.2016.7508049","url":null,"abstract":"Text summarization is an incipient practice for verdict out the summary of the text article. Text summarization has grew so uses such as Due to the enormous aggregate of information getting augmented on internet; it is challenging for the user to verve through altogether the information accessible on web. The large availability of internet content partakes constrained a broad research area in the extent of automatic text summarization contained by the Natural Language Processing (NLP), especially statistical machine learning communal. Terminated the bygone half a century, the defaulting has been addressed from numerous diverse standpoints, in erratic domains and using innumerable archetypes. In this survey paper we investigate the popular and important work done in the field of single and multiple document summarizations, generous distinctive prominence towards pragmatic approaches and extractive techniques. Particular auspicious slants that quintessence on unambiguous minutiae of the summarization are also deliberated. Exceptional consideration is ardent to involuntary assessment of summarization classifications, as forthcoming investigation on summarization is sturdily reliant over evolvement in this problem space.","PeriodicalId":299044,"journal":{"name":"2016 6th International Conference - Cloud System and Big Data Engineering (Confluence)","volume":"86 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134473299","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1900-01-01DOI: 10.1109/CONFLUENCE.2016.7508214
Vicky Chawla, Sumit Sharma
From the past two decades, the research area of nearest neighbor search in high dimensional data sets has always been in the limelight. Content-based multimedia indexing has been an active area of research as multimedia content is mapped into high-dimensional vectors of numbers, which are then stored in a high-dimensional index. For large collections, high-performance environments and large amount of main memory have been used. This paper reviews the NV-Tree (Nearest Vector Tree), a disk based data structure, which addresses the specific problem of locating the k-nearest neighbors within a collection of high dimensional data sets. The NV-tree is already used in industry to index more than 150 thousand hours of video for (very effective) near-duplicate detection. We present a critical summary of published research literature pertinent to NV-Tree under contemplation for research. The purpose is to create familiarity with existing thinking and research on a particular topic, which may justify future research into a previously overlooked or understudied area.
{"title":"A study on Nearest-Vector Tree","authors":"Vicky Chawla, Sumit Sharma","doi":"10.1109/CONFLUENCE.2016.7508214","DOIUrl":"https://doi.org/10.1109/CONFLUENCE.2016.7508214","url":null,"abstract":"From the past two decades, the research area of nearest neighbor search in high dimensional data sets has always been in the limelight. Content-based multimedia indexing has been an active area of research as multimedia content is mapped into high-dimensional vectors of numbers, which are then stored in a high-dimensional index. For large collections, high-performance environments and large amount of main memory have been used. This paper reviews the NV-Tree (Nearest Vector Tree), a disk based data structure, which addresses the specific problem of locating the k-nearest neighbors within a collection of high dimensional data sets. The NV-tree is already used in industry to index more than 150 thousand hours of video for (very effective) near-duplicate detection. We present a critical summary of published research literature pertinent to NV-Tree under contemplation for research. The purpose is to create familiarity with existing thinking and research on a particular topic, which may justify future research into a previously overlooked or understudied area.","PeriodicalId":299044,"journal":{"name":"2016 6th International Conference - Cloud System and Big Data Engineering (Confluence)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131720254","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1900-01-01DOI: 10.1109/CONFLUENCE.2016.7508040
A. Agrawal, Arvinder Kaur
Metaheuristic algorithms are applied in various fields to solve realistic problems. In many situations, a researcher moves in perplexed situation when it comes to selection of an appropriate metaheuristic algorithm for any specific problem. To overcome from such situation a comparative study is must. Considering this view we have done the performance evaluations of three popular metaheuristic algorithms: Evolution Strategy, Tabu Search and Variable Neighborhood Search. We framed three research questions to evaluate our hypothesis. Extensive experiments are conducted and results are collected. It was observed that Variable Neighborhood Search approach performed far better than other approaches. But this result seems insufficient in presenting some conclusion. Therefore, various statistical tests such as F-test, Post-hoc tests were performed. An obvious outcome of this study is that there is an interaction effect between the problem sizes and the metaheuristic used and no clear superiority of one metaheuristic over the other.
{"title":"An empirical evaluation of three popular meta-heuristics for solving Travelling Salesman Problem","authors":"A. Agrawal, Arvinder Kaur","doi":"10.1109/CONFLUENCE.2016.7508040","DOIUrl":"https://doi.org/10.1109/CONFLUENCE.2016.7508040","url":null,"abstract":"Metaheuristic algorithms are applied in various fields to solve realistic problems. In many situations, a researcher moves in perplexed situation when it comes to selection of an appropriate metaheuristic algorithm for any specific problem. To overcome from such situation a comparative study is must. Considering this view we have done the performance evaluations of three popular metaheuristic algorithms: Evolution Strategy, Tabu Search and Variable Neighborhood Search. We framed three research questions to evaluate our hypothesis. Extensive experiments are conducted and results are collected. It was observed that Variable Neighborhood Search approach performed far better than other approaches. But this result seems insufficient in presenting some conclusion. Therefore, various statistical tests such as F-test, Post-hoc tests were performed. An obvious outcome of this study is that there is an interaction effect between the problem sizes and the metaheuristic used and no clear superiority of one metaheuristic over the other.","PeriodicalId":299044,"journal":{"name":"2016 6th International Conference - Cloud System and Big Data Engineering (Confluence)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134411888","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1900-01-01DOI: 10.1109/CONFLUENCE.2016.7508051
Bhat Jasra, Aniqa Yaqoob, S. Dubey
In this paper an efficient yet simple approach of salt and pepper noise removal based on back propagation neural network and adaptive median filtering has been suggested. The proposed method uses supervised learning capability of back-propagation neural network to remove the salt and pepper noise in first phase and adaptive median filter is used to enhance the image quality in second phase. It overcomes all drawbacks of conventional median filtering by preserving the fine details. Experimental results show that the algorithm performs better than neural network based model & other conventional filtering mechanisms. Performance is exceptionally good even for high density noised images.
{"title":"Removal of high density salt and pepper noise using BPANN-modified median filter technique","authors":"Bhat Jasra, Aniqa Yaqoob, S. Dubey","doi":"10.1109/CONFLUENCE.2016.7508051","DOIUrl":"https://doi.org/10.1109/CONFLUENCE.2016.7508051","url":null,"abstract":"In this paper an efficient yet simple approach of salt and pepper noise removal based on back propagation neural network and adaptive median filtering has been suggested. The proposed method uses supervised learning capability of back-propagation neural network to remove the salt and pepper noise in first phase and adaptive median filter is used to enhance the image quality in second phase. It overcomes all drawbacks of conventional median filtering by preserving the fine details. Experimental results show that the algorithm performs better than neural network based model & other conventional filtering mechanisms. Performance is exceptionally good even for high density noised images.","PeriodicalId":299044,"journal":{"name":"2016 6th International Conference - Cloud System and Big Data Engineering (Confluence)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133308251","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1900-01-01DOI: 10.1109/CONFLUENCE.2016.7508039
Getachew Mamo Wegari, M. Melucci, S. Teferra
Morphological models are used in many natural language processing tasks including machine translation and speech recognition. We investigated probabilistic and grouping methods to develop a morphological root identification model for Afaan Oromo. In this paper, we have experimentally shown that the proposed methods can improve the morphological root identification performance of some state-of-the-art methods.
{"title":"Probabilistic and grouping methods for morphological root identification for Afaan Oromo","authors":"Getachew Mamo Wegari, M. Melucci, S. Teferra","doi":"10.1109/CONFLUENCE.2016.7508039","DOIUrl":"https://doi.org/10.1109/CONFLUENCE.2016.7508039","url":null,"abstract":"Morphological models are used in many natural language processing tasks including machine translation and speech recognition. We investigated probabilistic and grouping methods to develop a morphological root identification model for Afaan Oromo. In this paper, we have experimentally shown that the proposed methods can improve the morphological root identification performance of some state-of-the-art methods.","PeriodicalId":299044,"journal":{"name":"2016 6th International Conference - Cloud System and Big Data Engineering (Confluence)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122229557","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1900-01-01DOI: 10.1109/CONFLUENCE.2016.7508041
Shweta Taneja, Bhawna Suri, Himanshu Narwal, A. Jain, Akshay Kathuria, Sachin Gupta
Data mining is a process of discovering useful patterns from a large set of data. It is mostly used in large information processing applications. As we know, classification technique of data mining classifies the data into a set of classes based on some attributes for further processing. We have developed a new algorithm to handle the classification by using fuzzy rules on the real world data set. Our proposed algorithm caters in handling admission of students to various universities by classifying them into three clusters- admitted, rejected and those who probably would get the admission. To handle the third cluster, fuzzy logic based approach is appropriate. Our algorithm makes prediction for getting admission on the basis of ranking and fuzzy rules generated from the numerical data and gives output in linguistic terms. We have compared our algorithm with the state of art algorithms- KNN, Fuzzy C- means etc. Our algorithm has proved to be more efficient than others in terms of performance.
{"title":"A new approach for data classification using Fuzzy logic","authors":"Shweta Taneja, Bhawna Suri, Himanshu Narwal, A. Jain, Akshay Kathuria, Sachin Gupta","doi":"10.1109/CONFLUENCE.2016.7508041","DOIUrl":"https://doi.org/10.1109/CONFLUENCE.2016.7508041","url":null,"abstract":"Data mining is a process of discovering useful patterns from a large set of data. It is mostly used in large information processing applications. As we know, classification technique of data mining classifies the data into a set of classes based on some attributes for further processing. We have developed a new algorithm to handle the classification by using fuzzy rules on the real world data set. Our proposed algorithm caters in handling admission of students to various universities by classifying them into three clusters- admitted, rejected and those who probably would get the admission. To handle the third cluster, fuzzy logic based approach is appropriate. Our algorithm makes prediction for getting admission on the basis of ranking and fuzzy rules generated from the numerical data and gives output in linguistic terms. We have compared our algorithm with the state of art algorithms- KNN, Fuzzy C- means etc. Our algorithm has proved to be more efficient than others in terms of performance.","PeriodicalId":299044,"journal":{"name":"2016 6th International Conference - Cloud System and Big Data Engineering (Confluence)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114137700","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1900-01-01DOI: 10.1109/CONFLUENCE.2016.7508119
Roohi Arora, A. Garg, Mukesh Sareen
Terrorist threats and narcotics are the major security concerns in India. The ease with which the terrorists and smugglers travel inter and intra countries using fake identifications, visas, falsely generated immigration documents and tampered passports is a scenario that is a huge challenge to various countries and they are finding a solution to combat the same. The present checks at the airports are reliable but not autonomously reliable. There are still reports of security breaches, plane hijacking and smuggling, etc. The obnoxious fact is that we cannot just depend on the existing security system as we solely trust the optikos of a human being that can be deceived. Hence, there is need for the airport authorities to reengineer their security system to restrict the infiltrators. Identifying individuals before they board the plane is crucial to ensure safety of passengers and therefore high security at airports has become apparent. The objective of the paper is to establish a security framework that would not be swindled under any circumstances and one that performs unequivocal identification of passengers.
{"title":"Framework for augmenting security systems at airports","authors":"Roohi Arora, A. Garg, Mukesh Sareen","doi":"10.1109/CONFLUENCE.2016.7508119","DOIUrl":"https://doi.org/10.1109/CONFLUENCE.2016.7508119","url":null,"abstract":"Terrorist threats and narcotics are the major security concerns in India. The ease with which the terrorists and smugglers travel inter and intra countries using fake identifications, visas, falsely generated immigration documents and tampered passports is a scenario that is a huge challenge to various countries and they are finding a solution to combat the same. The present checks at the airports are reliable but not autonomously reliable. There are still reports of security breaches, plane hijacking and smuggling, etc. The obnoxious fact is that we cannot just depend on the existing security system as we solely trust the optikos of a human being that can be deceived. Hence, there is need for the airport authorities to reengineer their security system to restrict the infiltrators. Identifying individuals before they board the plane is crucial to ensure safety of passengers and therefore high security at airports has become apparent. The objective of the paper is to establish a security framework that would not be swindled under any circumstances and one that performs unequivocal identification of passengers.","PeriodicalId":299044,"journal":{"name":"2016 6th International Conference - Cloud System and Big Data Engineering (Confluence)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127431496","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1900-01-01DOI: 10.1109/CONFLUENCE.2016.7508048
Meera Ramadas, Sushil Kumar
Evolutionary algorithm is a field of great interest to many researchers. Many new algorithms are being developed based on the biological processes in nature. Many variants of the existing algorithms are also being developed and the most optimal method is being researched. This paper gives a brief introduction to flower pollination algorithm (FPA) and an introduction to differential evolution (DE). Further, a description on the hybrid algorithm developed with DE and FPA is introduced and the subsequent results under process are also stated.
{"title":"An efficient hybrid approach using differential evolution and flower pollination algorithm","authors":"Meera Ramadas, Sushil Kumar","doi":"10.1109/CONFLUENCE.2016.7508048","DOIUrl":"https://doi.org/10.1109/CONFLUENCE.2016.7508048","url":null,"abstract":"Evolutionary algorithm is a field of great interest to many researchers. Many new algorithms are being developed based on the biological processes in nature. Many variants of the existing algorithms are also being developed and the most optimal method is being researched. This paper gives a brief introduction to flower pollination algorithm (FPA) and an introduction to differential evolution (DE). Further, a description on the hybrid algorithm developed with DE and FPA is introduced and the subsequent results under process are also stated.","PeriodicalId":299044,"journal":{"name":"2016 6th International Conference - Cloud System and Big Data Engineering (Confluence)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116745126","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：