Pub Date : 2017-08-01DOI: 10.1109/IC3.2017.8284349
Sakshi Saxena, Priyanka Verma, D. Rajpoot
Data mining is a technique used to process information from a big dataset and converting it into a reasonable form for supplementary use. Clustering is a mining technique used in data mining. The goal of clustering is to discover the groupings of a set of points, patterns or objects. Minimum Spanning Tree (MST) based clustering algorithms are successfully used for detecting clusters. In this paper we have focused on minimizing the time complexity for constructing MST by using clustering. The proposed algorithm tries to minimize the time complexity by constructing a MST in two stages. In divide stage, the given dataset is divided in various clusters. In the conquer stage, for every cluster, local MSTs are created and then these MSTs are combined to obtain the final MST by using Midpoint MST algorithm. Experimental results show that the proposed MST algorithm is computationally efficient.
{"title":"Clustering based minimum spanning tree algorithm","authors":"Sakshi Saxena, Priyanka Verma, D. Rajpoot","doi":"10.1109/IC3.2017.8284349","DOIUrl":"https://doi.org/10.1109/IC3.2017.8284349","url":null,"abstract":"Data mining is a technique used to process information from a big dataset and converting it into a reasonable form for supplementary use. Clustering is a mining technique used in data mining. The goal of clustering is to discover the groupings of a set of points, patterns or objects. Minimum Spanning Tree (MST) based clustering algorithms are successfully used for detecting clusters. In this paper we have focused on minimizing the time complexity for constructing MST by using clustering. The proposed algorithm tries to minimize the time complexity by constructing a MST in two stages. In divide stage, the given dataset is divided in various clusters. In the conquer stage, for every cluster, local MSTs are created and then these MSTs are combined to obtain the final MST by using Midpoint MST algorithm. Experimental results show that the proposed MST algorithm is computationally efficient.","PeriodicalId":147099,"journal":{"name":"2017 Tenth International Conference on Contemporary Computing (IC3)","volume":"78 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":"114383254","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/IC3.2017.8284300
Vedasamhitha Abburu, Saumya Gupta, S. R. Rimitha, Manjunath Mulimani, S. Koolagudi
In this paper, we propose a system for automated currency recognition using image processing techniques. The proposed method can be used for recognizing both the country or origin as well as the denomination or value of a given banknote. Only paper currencies have been considered. This method works by first identifying the country of origin using certain predefined areas of interest, and then extracting the denomination value using characteristics such as size, color, or text on the note, depending on how much the notes within the same country differ. We have considered 20 of the most traded currencies, as well as their denominations. Our system is able to accurately and quickly identify test notes.
{"title":"Currency recognition system using image processing","authors":"Vedasamhitha Abburu, Saumya Gupta, S. R. Rimitha, Manjunath Mulimani, S. Koolagudi","doi":"10.1109/IC3.2017.8284300","DOIUrl":"https://doi.org/10.1109/IC3.2017.8284300","url":null,"abstract":"In this paper, we propose a system for automated currency recognition using image processing techniques. The proposed method can be used for recognizing both the country or origin as well as the denomination or value of a given banknote. Only paper currencies have been considered. This method works by first identifying the country of origin using certain predefined areas of interest, and then extracting the denomination value using characteristics such as size, color, or text on the note, depending on how much the notes within the same country differ. We have considered 20 of the most traded currencies, as well as their denominations. Our system is able to accurately and quickly identify test notes.","PeriodicalId":147099,"journal":{"name":"2017 Tenth International Conference on Contemporary Computing (IC3)","volume":"19 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":"117024880","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/IC3.2017.8284345
Suman Banerjee, M. Jenamani, D. K. Pratihar
Bipartite Graph or bipartite network (also known as two mode network) is often a general model of many real life complex networks and systems. However, due to the lack of analysis techniques, it is often converted into a unipartite network by one mode projection. Thus, performing faster one mode projection will lead to the faster analysis of input bipartite graph. In this paper, we have taken up the problem of one mode projection and presented three algorithms. All the algorithms have different working principles. The proposed algorithms have also been implemented on three benchmark datasets and execution times are reported.
{"title":"Algorithms for projecting a bipartite network","authors":"Suman Banerjee, M. Jenamani, D. K. Pratihar","doi":"10.1109/IC3.2017.8284345","DOIUrl":"https://doi.org/10.1109/IC3.2017.8284345","url":null,"abstract":"Bipartite Graph or bipartite network (also known as two mode network) is often a general model of many real life complex networks and systems. However, due to the lack of analysis techniques, it is often converted into a unipartite network by one mode projection. Thus, performing faster one mode projection will lead to the faster analysis of input bipartite graph. In this paper, we have taken up the problem of one mode projection and presented three algorithms. All the algorithms have different working principles. The proposed algorithms have also been implemented on three benchmark datasets and execution times are reported.","PeriodicalId":147099,"journal":{"name":"2017 Tenth International Conference on Contemporary Computing (IC3)","volume":"30 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":"128527679","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/IC3.2017.8284286
David Batista-Plaza, C. Travieso-González, M. Dutta, Anushikha Singh
This work presents a biometric approach for spider identification based on transform domain and Support Vector Machines as classifier. The dataset is composed by 185 images of spider web. The goal of this work is to use the structure of spider web for identifying the kind of spider. The experiments were done using two different of segmentation blocks and the analysis of the whole and center of the spider web. The best accuracy is reached after to run the different combinations.
{"title":"Biometric analysis for the recognition of spider species according to their webs","authors":"David Batista-Plaza, C. Travieso-González, M. Dutta, Anushikha Singh","doi":"10.1109/IC3.2017.8284286","DOIUrl":"https://doi.org/10.1109/IC3.2017.8284286","url":null,"abstract":"This work presents a biometric approach for spider identification based on transform domain and Support Vector Machines as classifier. The dataset is composed by 185 images of spider web. The goal of this work is to use the structure of spider web for identifying the kind of spider. The experiments were done using two different of segmentation blocks and the analysis of the whole and center of the spider web. The best accuracy is reached after to run the different combinations.","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":"129285178","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/IC3.2017.8284337
Manish Kumar, V. Ranga
Wireless sensor networks equipped with tiny and low powered nodes are susceptible to failures due to harsh surroundings. The operation of sensors becomes quite difficult when obstacles are present in the deployment area. Due to these obstacles, restoration of lost connectivity in WSN is a quite challenging task as well as computational intensive. Therefore, we proposed a meta-heuristic solution for restoration of lost connectivity. We use alpha shapes to detect boundary and shape of obstacles. Further, Grey Wolf Optimizer (GWO) is used to optimize the relay nodes placement. Our proposed solution, named as Meta-Heuristic Solution for Relay Node Placement in Constrained Environment (MH-RNPCE), implement convex hull approach to restrict the area for deployment of relay nodes. The simulation results show that the performance of MH-RNPCE.
{"title":"Meta-heuristic solution for relay nodes placement in constrained environment","authors":"Manish Kumar, V. Ranga","doi":"10.1109/IC3.2017.8284337","DOIUrl":"https://doi.org/10.1109/IC3.2017.8284337","url":null,"abstract":"Wireless sensor networks equipped with tiny and low powered nodes are susceptible to failures due to harsh surroundings. The operation of sensors becomes quite difficult when obstacles are present in the deployment area. Due to these obstacles, restoration of lost connectivity in WSN is a quite challenging task as well as computational intensive. Therefore, we proposed a meta-heuristic solution for restoration of lost connectivity. We use alpha shapes to detect boundary and shape of obstacles. Further, Grey Wolf Optimizer (GWO) is used to optimize the relay nodes placement. Our proposed solution, named as Meta-Heuristic Solution for Relay Node Placement in Constrained Environment (MH-RNPCE), implement convex hull approach to restrict the area for deployment of relay nodes. The simulation results show that the performance of MH-RNPCE.","PeriodicalId":147099,"journal":{"name":"2017 Tenth International Conference on Contemporary Computing (IC3)","volume":"12 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":"124202983","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/IC3.2017.8284296
Harika Abburi, K. R. Alluri, A. Vuppala, Manish Shrivastava, S. Gangashetty
Recent improvement in usage of digital media has led people to share their opinions about specific entity through audio. In this paper, an approach to detect the sentiment of an online spoken reviews based on relative prosody features is presented. Most of the existing systems for audio based sentiment analysis use conventional audio features, but they are not problem specific features to extract the sentiment. In this work, relative prosody features are extracted from normal and stressed regions of audio signal to detect the sentiment. Stressed regions are identified using the strength of excitation. Support Vector Machine (SVM) and Gaussian Mixture Model (GMM) classifiers are used to build the sentiment models. MOUD database is used for the proposed study. Experimental results show that, the rate of detecting the sentiment is improved with relative prosody features compared with the prosody and Mel Frequency Cepstral Coefficients (MFCC) because the relative prosody features has more sentiment specific discrimination compared to prosody features.
{"title":"Sentiment analysis using relative prosody features","authors":"Harika Abburi, K. R. Alluri, A. Vuppala, Manish Shrivastava, S. Gangashetty","doi":"10.1109/IC3.2017.8284296","DOIUrl":"https://doi.org/10.1109/IC3.2017.8284296","url":null,"abstract":"Recent improvement in usage of digital media has led people to share their opinions about specific entity through audio. In this paper, an approach to detect the sentiment of an online spoken reviews based on relative prosody features is presented. Most of the existing systems for audio based sentiment analysis use conventional audio features, but they are not problem specific features to extract the sentiment. In this work, relative prosody features are extracted from normal and stressed regions of audio signal to detect the sentiment. Stressed regions are identified using the strength of excitation. Support Vector Machine (SVM) and Gaussian Mixture Model (GMM) classifiers are used to build the sentiment models. MOUD database is used for the proposed study. Experimental results show that, the rate of detecting the sentiment is improved with relative prosody features compared with the prosody and Mel Frequency Cepstral Coefficients (MFCC) because the relative prosody features has more sentiment specific discrimination compared to prosody features.","PeriodicalId":147099,"journal":{"name":"2017 Tenth International Conference on Contemporary Computing (IC3)","volume":"3 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":"121929936","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/IC3.2017.8284327
Anmol Chachra, Pulkit Mehndiratta, Mohit Gupta
Sentiment analysis has been one of the most researched topics in Machine learning. The roots of sentiment analysis are in studies on public opinion analysis at the start of 20th century, but the outbreak of computer-based sentiment analysis only occurred with the availability of subjective text in Web. The task of generating effective sentence model that captures both syntactic and semantic relations has been the primary goal to make better sentiment analyzers. In this paper, we harness the power of deep convolution neural networks (DCNN) to model sentences and perform sentiment analysis. This approach automates the whole process otherwise done using advance NLP techniques. It is a modular approach analyzing syntactic and context based relation from word level to phrase level to sentence level and then to document level. Such approach not only stands outs in terms of better classification, it also fits the concept of transfer learning. We have achieved an accuracy of 80.69% using this technique and further working on the enhancement and refinement of this approach.
{"title":"Sentiment analysis of text using deep convolution neural networks","authors":"Anmol Chachra, Pulkit Mehndiratta, Mohit Gupta","doi":"10.1109/IC3.2017.8284327","DOIUrl":"https://doi.org/10.1109/IC3.2017.8284327","url":null,"abstract":"Sentiment analysis has been one of the most researched topics in Machine learning. The roots of sentiment analysis are in studies on public opinion analysis at the start of 20th century, but the outbreak of computer-based sentiment analysis only occurred with the availability of subjective text in Web. The task of generating effective sentence model that captures both syntactic and semantic relations has been the primary goal to make better sentiment analyzers. In this paper, we harness the power of deep convolution neural networks (DCNN) to model sentences and perform sentiment analysis. This approach automates the whole process otherwise done using advance NLP techniques. It is a modular approach analyzing syntactic and context based relation from word level to phrase level to sentence level and then to document level. Such approach not only stands outs in terms of better classification, it also fits the concept of transfer learning. We have achieved an accuracy of 80.69% using this technique and further working on the enhancement and refinement of this approach.","PeriodicalId":147099,"journal":{"name":"2017 Tenth International Conference on Contemporary Computing (IC3)","volume":"26 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":"134205367","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/IC3.2017.8284322
Abhinav Saini, S. Suregaonkar, Neena Gupta, V. Karar, Shashi Poddar
Intelligent traffic monitoring using video surveillance is one of the most important aspects in administering a modern smart city. A recent growth towards machine learning and computer vision techniques has provided an added impetus towards this growth. In this paper, an image processing based vehicle tracking technique is developed that does not require background subtraction process to be applied for extracting the region of interest. Instead, a hybrid of feature detection and region matching approach is suggested in this article, which helps in estimating vehicle trajectory over consequent frames. Later, the tracked path is monitored for the occurrence of any specific event while the vehicle passes through an intersection. The proposed scheme is found to work promisingly on the real world dataset and is able to detect the occurrence of an accident between two vehicles.
{"title":"Region and feature matching based vehicle tracking for accident detection","authors":"Abhinav Saini, S. Suregaonkar, Neena Gupta, V. Karar, Shashi Poddar","doi":"10.1109/IC3.2017.8284322","DOIUrl":"https://doi.org/10.1109/IC3.2017.8284322","url":null,"abstract":"Intelligent traffic monitoring using video surveillance is one of the most important aspects in administering a modern smart city. A recent growth towards machine learning and computer vision techniques has provided an added impetus towards this growth. In this paper, an image processing based vehicle tracking technique is developed that does not require background subtraction process to be applied for extracting the region of interest. Instead, a hybrid of feature detection and region matching approach is suggested in this article, which helps in estimating vehicle trajectory over consequent frames. Later, the tracked path is monitored for the occurrence of any specific event while the vehicle passes through an intersection. The proposed scheme is found to work promisingly on the real world dataset and is able to detect the occurrence of an accident between two vehicles.","PeriodicalId":147099,"journal":{"name":"2017 Tenth International Conference on Contemporary Computing (IC3)","volume":"40 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":"132908015","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/IC3.2017.8284311
Ritu Banga, Pulkit Mehndiratta
Authorship Attribution, (AA) is a process of determining a particular document is written by which author among a list of suspected authors. Authorship attribution has been the problem from last six decades; when there were handwritten documents needed to be identified for the genuine author. Due to the technology advancement and increase in cybercrime and unlawful activities, this problem of AA becomes forth most important to trace out the author behind online messages. Over the past, many years research has been conducted to attribute the authorship of an author on the basis of their writing style as all authors possess different distinctiveness while writing a piece of document. This paper presents a comparative study of various machine learning approaches on different feature sets for authorship attribution on short text. The Twitter dataset has been used for comparison with varying sample size of a dataset of 10 prolific authors with various combinations of feature sets. The significance and impact of combinations of features while inferring different stylometric features has been reflected. The results of different approaches are compared based on their accuracy and precision values.
{"title":"Authorship attribution for textual data on online social networks","authors":"Ritu Banga, Pulkit Mehndiratta","doi":"10.1109/IC3.2017.8284311","DOIUrl":"https://doi.org/10.1109/IC3.2017.8284311","url":null,"abstract":"Authorship Attribution, (AA) is a process of determining a particular document is written by which author among a list of suspected authors. Authorship attribution has been the problem from last six decades; when there were handwritten documents needed to be identified for the genuine author. Due to the technology advancement and increase in cybercrime and unlawful activities, this problem of AA becomes forth most important to trace out the author behind online messages. Over the past, many years research has been conducted to attribute the authorship of an author on the basis of their writing style as all authors possess different distinctiveness while writing a piece of document. This paper presents a comparative study of various machine learning approaches on different feature sets for authorship attribution on short text. The Twitter dataset has been used for comparison with varying sample size of a dataset of 10 prolific authors with various combinations of feature sets. The significance and impact of combinations of features while inferring different stylometric features has been reflected. The results of different approaches are compared based on their accuracy and precision values.","PeriodicalId":147099,"journal":{"name":"2017 Tenth International Conference on Contemporary Computing (IC3)","volume":"71 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":"133618849","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/IC3.2017.8284313
Shikha Jain, Parmeet Kaur, M. Goyal, G. Dhanalekshmi
Source code plagiarism in an academic environment is a serious concern of faculties. The paper presents an efficient plagiarism detection tool, CPLAG, for C programming language codes. The tool assesses the structure of the C programs based on a set of attributes and performs a binary encoding of the C code statements. Subsequently, it utilizes computationally inexpensive bitwise operations to detect similarity between the given C programs. The design of CPLAG considers the commonly used techniques to avoid detection of plagiarism for delivering an efficient performance. Moreover, it avoids the extensive computations as used by existing tools for plagiarism detection. Experiment results indicate that CPLAG can detect plagiarism with accuracy. The tool finds application in academic institutions for fair and efficient automatic evaluation and grading of programming assignments.
{"title":"CPLAG: Efficient plagiarism detection using bitwise operations","authors":"Shikha Jain, Parmeet Kaur, M. Goyal, G. Dhanalekshmi","doi":"10.1109/IC3.2017.8284313","DOIUrl":"https://doi.org/10.1109/IC3.2017.8284313","url":null,"abstract":"Source code plagiarism in an academic environment is a serious concern of faculties. The paper presents an efficient plagiarism detection tool, CPLAG, for C programming language codes. The tool assesses the structure of the C programs based on a set of attributes and performs a binary encoding of the C code statements. Subsequently, it utilizes computationally inexpensive bitwise operations to detect similarity between the given C programs. The design of CPLAG considers the commonly used techniques to avoid detection of plagiarism for delivering an efficient performance. Moreover, it avoids the extensive computations as used by existing tools for plagiarism detection. Experiment results indicate that CPLAG can detect plagiarism with accuracy. The tool finds application in academic institutions for fair and efficient automatic evaluation and grading of programming assignments.","PeriodicalId":147099,"journal":{"name":"2017 Tenth International Conference on Contemporary Computing (IC3)","volume":"48 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":"127241034","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：