Pub Date : 2017-08-01DOI: 10.1109/IC3.2017.8284359
Ankur Kulhari, M. Saraswat
A robust subspace clustering assigns a label to each data point in a noisy and high dimensional dataset which has a collection of multiple linear subspaces of low dimension. To reduce the effect of noise in the dataset for subspace clustering, many methods have been proposed such as sparse representationbased, low rank representation-based, and thresholding ridge regression methods. These methods either reduce the noise in the input space (sparse representation and low rank representation) or in the projection space (thresholding ridge regression). However, reduction of noise in the projection space eliminates the constraints of spars errors and a prior knowledge of structure of errors. Further, thresholding ridge regression method uses k-means algorithm for clustering which is sensitive to initial centroids and may stuck into local optimum. Therefore, this paper introduces a modified thresholding ridge regression-based subspace clustering method which uses differential evolution and k-means algorithm. The proposed method has been compared with six different methods including thresholding ridge regression on facial image dataset. The experimental results show that the proposed method outperforms the existing algorithms in terms of accuracy and normalized mutual information.
{"title":"Differential evolution-based subspace clustering via thresholding ridge regression","authors":"Ankur Kulhari, M. Saraswat","doi":"10.1109/IC3.2017.8284359","DOIUrl":"https://doi.org/10.1109/IC3.2017.8284359","url":null,"abstract":"A robust subspace clustering assigns a label to each data point in a noisy and high dimensional dataset which has a collection of multiple linear subspaces of low dimension. To reduce the effect of noise in the dataset for subspace clustering, many methods have been proposed such as sparse representationbased, low rank representation-based, and thresholding ridge regression methods. These methods either reduce the noise in the input space (sparse representation and low rank representation) or in the projection space (thresholding ridge regression). However, reduction of noise in the projection space eliminates the constraints of spars errors and a prior knowledge of structure of errors. Further, thresholding ridge regression method uses k-means algorithm for clustering which is sensitive to initial centroids and may stuck into local optimum. Therefore, this paper introduces a modified thresholding ridge regression-based subspace clustering method which uses differential evolution and k-means algorithm. The proposed method has been compared with six different methods including thresholding ridge regression on facial image dataset. The experimental results show that the proposed method outperforms the existing algorithms in terms of accuracy and normalized mutual information.","PeriodicalId":147099,"journal":{"name":"2017 Tenth International Conference on Contemporary Computing (IC3)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127069818","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 : 2017-08-01DOI: 10.1109/IC3.2017.8284350
Jayant Yadav, M. Sharma, V. Saxena
Diabetic Retinopathy is an eye disorder which causes vision blurriness and blindness in diabetic patients. Currently, detection of Diabetic Retinopathy involves manual methods in which physical examination is done by a trained eye physician. This consumes a lot of time of the physician which could have been devoted to other patients. This paper tries to tackle this issue by using computer vision to not only detect this disease, but also automating this procedure using neural network to give results of many patients within a short time frame.
{"title":"Diabetic retinopathy detection using feedforward neural network","authors":"Jayant Yadav, M. Sharma, V. Saxena","doi":"10.1109/IC3.2017.8284350","DOIUrl":"https://doi.org/10.1109/IC3.2017.8284350","url":null,"abstract":"Diabetic Retinopathy is an eye disorder which causes vision blurriness and blindness in diabetic patients. Currently, detection of Diabetic Retinopathy involves manual methods in which physical examination is done by a trained eye physician. This consumes a lot of time of the physician which could have been devoted to other patients. This paper tries to tackle this issue by using computer vision to not only detect this disease, but also automating this procedure using neural network to give results of many patients within a short time frame.","PeriodicalId":147099,"journal":{"name":"2017 Tenth International Conference on Contemporary Computing (IC3)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131319767","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 : 2017-08-01DOI: 10.1109/IC3.2017.8284295
Tanvi Gandhi, Nitin, Taj Alam
Distributed systems are efficient means of realizing High-Performance Computing (HPC). They are used in meeting the demand of executing large-scale high-performance computational jobs. Scheduling the tasks on such computational resources is one of the prime concerns in the heterogeneous distributed systems. Scheduling jobs on such systems are NP-complete in nature. Scheduling requires either heuristic or metaheuristic approach for sub-optimal but acceptable solutions. An application can be divided into a number of tasks which can be represented as Direct Acyclic Graph (DAG). To accomplish high performance, it is important to efficiently schedule these dependent tasks on resources with the satisfaction of the constraints defined for schedule generation. Inspired by Quantum computing, this work proposes a Quantum Genetic Algorithm with Rotation Angle Refinement (QGARAR) for optimum schedule generation. In this paper, the proposed QGARAR is compared with its peers under various test conditions to account for minimization of the makespan value of dependent jobs submitted for execution on heterogeneous distributed systems.
{"title":"Quantum genetic algorithm with rotation angle refinement for dependent task scheduling on distributed systems","authors":"Tanvi Gandhi, Nitin, Taj Alam","doi":"10.1109/IC3.2017.8284295","DOIUrl":"https://doi.org/10.1109/IC3.2017.8284295","url":null,"abstract":"Distributed systems are efficient means of realizing High-Performance Computing (HPC). They are used in meeting the demand of executing large-scale high-performance computational jobs. Scheduling the tasks on such computational resources is one of the prime concerns in the heterogeneous distributed systems. Scheduling jobs on such systems are NP-complete in nature. Scheduling requires either heuristic or metaheuristic approach for sub-optimal but acceptable solutions. An application can be divided into a number of tasks which can be represented as Direct Acyclic Graph (DAG). To accomplish high performance, it is important to efficiently schedule these dependent tasks on resources with the satisfaction of the constraints defined for schedule generation. Inspired by Quantum computing, this work proposes a Quantum Genetic Algorithm with Rotation Angle Refinement (QGARAR) for optimum schedule generation. In this paper, the proposed QGARAR is compared with its peers under various test conditions to account for minimization of the makespan value of dependent jobs submitted for execution on heterogeneous distributed systems.","PeriodicalId":147099,"journal":{"name":"2017 Tenth International Conference on Contemporary Computing (IC3)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114586988","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 : 2017-08-01DOI: 10.1109/IC3.2017.8284353
C. B. Yuvaraj, M. Srikanth, V. S. Kumar, Vishnu Srinivasa Murthy Yarlagadda, S. Koolagudi
Nowadays, the research is growing towards the invention of new approaches. One such most attracted application is face recognition of image processing. There are several innovative technologies have been developed to take attendance. Some prominent ones are biometric, thumb impressions, access card, and fingerprints. The method proposed in this paper is to record the attendance through image using face detection and face recognition. The proposed approach has been implemented in four steps such as face detection, labelling the detected faces, training a classifier based on labelled dataset, and face recognition. The database has been constructed with the positive images and negative images. The complete database has been divided into training and testing set and further, processed by a classifier to recognize the faces in a classroom. The final step is to take the attendance using face recognition technique in which the input image of a classroom is given, and faces of the given image will be detected along with their IDs. The frames of a video taken for a minute is taken into consideration to avoid the missed ones due to rotational issues.
{"title":"An approach to maintain attendance using image processing techniques","authors":"C. B. Yuvaraj, M. Srikanth, V. S. Kumar, Vishnu Srinivasa Murthy Yarlagadda, S. Koolagudi","doi":"10.1109/IC3.2017.8284353","DOIUrl":"https://doi.org/10.1109/IC3.2017.8284353","url":null,"abstract":"Nowadays, the research is growing towards the invention of new approaches. One such most attracted application is face recognition of image processing. There are several innovative technologies have been developed to take attendance. Some prominent ones are biometric, thumb impressions, access card, and fingerprints. The method proposed in this paper is to record the attendance through image using face detection and face recognition. The proposed approach has been implemented in four steps such as face detection, labelling the detected faces, training a classifier based on labelled dataset, and face recognition. The database has been constructed with the positive images and negative images. The complete database has been divided into training and testing set and further, processed by a classifier to recognize the faces in a classroom. The final step is to take the attendance using face recognition technique in which the input image of a classroom is given, and faces of the given image will be detected along with their IDs. The frames of a video taken for a minute is taken into consideration to avoid the missed ones due to rotational issues.","PeriodicalId":147099,"journal":{"name":"2017 Tenth International Conference on Contemporary Computing (IC3)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114637899","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 : 2017-08-01DOI: 10.1109/IC3.2017.8284346
Mukta Mani
Unemployment and un-employability are some of most prevailing problems in our society. Entrepreneurship education has been viewed as a solution to the same. The aim of this study is to analyse different aspects of entrepreneurship education. The main aspects that have been studied here are-Entrepreneurship education programs, Teaching and assessment and Entrepreneurship education in non-business disciplines. It is found that the entrepreneurship education programs are gaining recognition in higher education institutes. But the programs need to be different from the conventional educational programs as entrepreneurship involves more of right brain thinking. Teaching of entrepreneurship has to be action oriented with focus on development of behavioural and attitudinal competencies. The learning can be enhanced through group discussions, workshops, presentations, solving cases studies, interacting with real entrepreneurs, developing business plan and implementation at later stages. The assessment techniques need to be different from the conventional system of examination as the learning outcomes are in the form of behavioural competencies and motivation. The study highlights the significance of entrepreneurship education for non-business disciplines. Non-business disciplines are able to give birth to more number of start-ups as they have many product ideas, which they can convert into business ideas if they are equipped with knowledge of entrepreneurship. This study is useful for policymakers and academicians as it provides an insight into different aspects of entrepreneurship education programs for universities and other higher education institutes.
{"title":"Aspects of entrepreneurship education in higher education institutes","authors":"Mukta Mani","doi":"10.1109/IC3.2017.8284346","DOIUrl":"https://doi.org/10.1109/IC3.2017.8284346","url":null,"abstract":"Unemployment and un-employability are some of most prevailing problems in our society. Entrepreneurship education has been viewed as a solution to the same. The aim of this study is to analyse different aspects of entrepreneurship education. The main aspects that have been studied here are-Entrepreneurship education programs, Teaching and assessment and Entrepreneurship education in non-business disciplines. It is found that the entrepreneurship education programs are gaining recognition in higher education institutes. But the programs need to be different from the conventional educational programs as entrepreneurship involves more of right brain thinking. Teaching of entrepreneurship has to be action oriented with focus on development of behavioural and attitudinal competencies. The learning can be enhanced through group discussions, workshops, presentations, solving cases studies, interacting with real entrepreneurs, developing business plan and implementation at later stages. The assessment techniques need to be different from the conventional system of examination as the learning outcomes are in the form of behavioural competencies and motivation. The study highlights the significance of entrepreneurship education for non-business disciplines. Non-business disciplines are able to give birth to more number of start-ups as they have many product ideas, which they can convert into business ideas if they are equipped with knowledge of entrepreneurship. This study is useful for policymakers and academicians as it provides an insight into different aspects of entrepreneurship education programs for universities and other higher education institutes.","PeriodicalId":147099,"journal":{"name":"2017 Tenth International Conference on Contemporary Computing (IC3)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129048506","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 : 2017-08-01DOI: 10.1109/IC3.2017.8284321
Taranpreet Kaur, Manvjeet Kaur
The encryption techniques, biometrics and cryptography integrate to form biometric cryptosystems. These are designed either to bind a cryptographic key or to generate cryptographic key using biometric features. The deployment of bio-cryptosystem technique, namely fuzzy extractor in multimodal biometric system leads to increase in user privacy and system security. This paper provides with a framework where feature level fusion of iris and dual fingerprint forms a multimodal template and key is generated using fuzzy extractors, in order to provide reliability and good recognition performance. The hash function is used to protect the key generated from biometric traits. Since fuzzy extractor operates only on ordered dataset. However the minutiae points of fingerprint are unordered, so an algorithm is designed for conversion of unordered minutiae points to ordered minutiae dataset to make it consistent for key generation methods.
{"title":"Cryptographic key generation from multimodal template using fuzzy extractor","authors":"Taranpreet Kaur, Manvjeet Kaur","doi":"10.1109/IC3.2017.8284321","DOIUrl":"https://doi.org/10.1109/IC3.2017.8284321","url":null,"abstract":"The encryption techniques, biometrics and cryptography integrate to form biometric cryptosystems. These are designed either to bind a cryptographic key or to generate cryptographic key using biometric features. The deployment of bio-cryptosystem technique, namely fuzzy extractor in multimodal biometric system leads to increase in user privacy and system security. This paper provides with a framework where feature level fusion of iris and dual fingerprint forms a multimodal template and key is generated using fuzzy extractors, in order to provide reliability and good recognition performance. The hash function is used to protect the key generated from biometric traits. Since fuzzy extractor operates only on ordered dataset. However the minutiae points of fingerprint are unordered, so an algorithm is designed for conversion of unordered minutiae points to ordered minutiae dataset to make it consistent for key generation methods.","PeriodicalId":147099,"journal":{"name":"2017 Tenth International Conference on Contemporary Computing (IC3)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126568960","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 : 2017-08-01DOI: 10.1109/IC3.2017.8284318
Sharad Verma, Mayank Saini, Aditi Sharan
Sentiment Analysis of review data is becoming an important task to understand the needs and expectations of customers. The challenges that lie in review sentiment analysis is capturing the long term dependencies and intricacies to model the interrelationship between the sentences of the review. In this work, we address the problem of review sentiment analysis using deep sequential model viz. Long short term memory (LSTM) and Gated Recurrent Neural Network (GRNN). LSTM, a variant of RNN is used to process the sentences to a fixed length vector. GRNN is used to capture the interdependencies that exist between the sentences of a review. The combination of LSTM and GRNN shows good performance on Amazon Electronics dataset.
{"title":"Deep sequential model for review rating prediction","authors":"Sharad Verma, Mayank Saini, Aditi Sharan","doi":"10.1109/IC3.2017.8284318","DOIUrl":"https://doi.org/10.1109/IC3.2017.8284318","url":null,"abstract":"Sentiment Analysis of review data is becoming an important task to understand the needs and expectations of customers. The challenges that lie in review sentiment analysis is capturing the long term dependencies and intricacies to model the interrelationship between the sentences of the review. In this work, we address the problem of review sentiment analysis using deep sequential model viz. Long short term memory (LSTM) and Gated Recurrent Neural Network (GRNN). LSTM, a variant of RNN is used to process the sentences to a fixed length vector. GRNN is used to capture the interdependencies that exist between the sentences of a review. The combination of LSTM and GRNN shows good performance on Amazon Electronics dataset.","PeriodicalId":147099,"journal":{"name":"2017 Tenth International Conference on Contemporary Computing (IC3)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126175600","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：