Pub Date : 2015-08-20DOI: 10.1109/IC3.2015.7346657
Arko Banerjee
In this paper a novel approach to document clustering has been introduced by defining a representative-based document similarity model that performs probabilistic segmentation of documents into chunks. The frequently occuring chunks that are considered as representatives of the document set, may represent phrases or stem of true words. The representative based document similarity model, containing a term-document matrix with respect to the representatives, is a compact representation of the vector space model that improves quality of document clustering over traditional methods.
{"title":"Leveraging probabilistic segmentation to document clustering","authors":"Arko Banerjee","doi":"10.1109/IC3.2015.7346657","DOIUrl":"https://doi.org/10.1109/IC3.2015.7346657","url":null,"abstract":"In this paper a novel approach to document clustering has been introduced by defining a representative-based document similarity model that performs probabilistic segmentation of documents into chunks. The frequently occuring chunks that are considered as representatives of the document set, may represent phrases or stem of true words. The representative based document similarity model, containing a term-document matrix with respect to the representatives, is a compact representation of the vector space model that improves quality of document clustering over traditional methods.","PeriodicalId":217950,"journal":{"name":"2015 Eighth International Conference on Contemporary Computing (IC3)","volume":"98 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134552491","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 : 2015-08-20DOI: 10.1109/IC3.2015.7346702
Arpan Kumar Dubey, Adwitiya Sinha
Wireless sensor networks (WSNs) have inspired many research domains in recent years. Congestion is a major issue faced by such networks, which causes heavy loss in data transmissions. Congestion is caused due to several reasons, such as heavy traffic, link failure, node failure and many more. There are various techniques developed for combatting network congestion. In this paper, we have proposed a technique for prediction of the congestion before it happens and controlling the situation before it becomes worse. Congestion in the network is controlled by adjusting the traffic rate of sources. Source nodes change their transmission rate as soon as they receive the control signal. Our algorithm is developed especially for managing congestive situations created by self similar traffic. The self-similarty in network traffic is simulated Pareto distribution. Congestion in the network is detected by analyzing the buffer ratio of nodes. Further, the simulation results show that our algorithm outperforms other existing techniques in terms of packet delivery ratio and average number of packets dropped.
{"title":"Congestion control for self similar traffic in wireless sensor network","authors":"Arpan Kumar Dubey, Adwitiya Sinha","doi":"10.1109/IC3.2015.7346702","DOIUrl":"https://doi.org/10.1109/IC3.2015.7346702","url":null,"abstract":"Wireless sensor networks (WSNs) have inspired many research domains in recent years. Congestion is a major issue faced by such networks, which causes heavy loss in data transmissions. Congestion is caused due to several reasons, such as heavy traffic, link failure, node failure and many more. There are various techniques developed for combatting network congestion. In this paper, we have proposed a technique for prediction of the congestion before it happens and controlling the situation before it becomes worse. Congestion in the network is controlled by adjusting the traffic rate of sources. Source nodes change their transmission rate as soon as they receive the control signal. Our algorithm is developed especially for managing congestive situations created by self similar traffic. The self-similarty in network traffic is simulated Pareto distribution. Congestion in the network is detected by analyzing the buffer ratio of nodes. Further, the simulation results show that our algorithm outperforms other existing techniques in terms of packet delivery ratio and average number of packets dropped.","PeriodicalId":217950,"journal":{"name":"2015 Eighth International Conference on Contemporary Computing (IC3)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114665804","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 : 2015-08-20DOI: 10.1109/IC3.2015.7346665
Leo Pauly, Rahul D. Raj, B. Paul
In this paper a novel approach for recognition of handwritten digits for South Indian languages using artificial neural networks (ANN) and Histogram of Oriented Gradients (HOG) features is presented. The images of documents containing the hand written digits are optically scanned and are segmented into individual images of isolated digits. HOG features are then extracted from these images and applied to the ANN for recognition. The system recognises the digits with an overall accuracy of 83.4%.
{"title":"Hand written digit recognition system for South Indian languages using artificial neural networks","authors":"Leo Pauly, Rahul D. Raj, B. Paul","doi":"10.1109/IC3.2015.7346665","DOIUrl":"https://doi.org/10.1109/IC3.2015.7346665","url":null,"abstract":"In this paper a novel approach for recognition of handwritten digits for South Indian languages using artificial neural networks (ANN) and Histogram of Oriented Gradients (HOG) features is presented. The images of documents containing the hand written digits are optically scanned and are segmented into individual images of isolated digits. HOG features are then extracted from these images and applied to the ANN for recognition. The system recognises the digits with an overall accuracy of 83.4%.","PeriodicalId":217950,"journal":{"name":"2015 Eighth International Conference on Contemporary Computing (IC3)","volume":"45 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114121201","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 : 2015-08-20DOI: 10.1109/IC3.2015.7346698
Palki Gupta, Lasit Pratap Singh, A. Khandelwal, Kavita Pandey
In this current scenario, vehicular ad-hoc networks are expected to provide support to a large range of distributed applications which ranges from traffic management, dynamic route planning to location based services. Traffic jams on the roads is a very serious issue that needs immediate attention. Various algorithms and solutions have been suggested in the field of VANETs to remove the problem of traffic congestion and waiting time. At initial level, it is not feasible to implement the proposed solution in the real world so a small area of Noida was taken up for real time simulations. The traffic simulation was created and observed using SUMO and NS2. This was in done in order to note the behavior of traffic light and congestion at the junctions and the results were further calculated and verified using AODV and GPSR protocol.
{"title":"Reduction of congestion and signal waiting time","authors":"Palki Gupta, Lasit Pratap Singh, A. Khandelwal, Kavita Pandey","doi":"10.1109/IC3.2015.7346698","DOIUrl":"https://doi.org/10.1109/IC3.2015.7346698","url":null,"abstract":"In this current scenario, vehicular ad-hoc networks are expected to provide support to a large range of distributed applications which ranges from traffic management, dynamic route planning to location based services. Traffic jams on the roads is a very serious issue that needs immediate attention. Various algorithms and solutions have been suggested in the field of VANETs to remove the problem of traffic congestion and waiting time. At initial level, it is not feasible to implement the proposed solution in the real world so a small area of Noida was taken up for real time simulations. The traffic simulation was created and observed using SUMO and NS2. This was in done in order to note the behavior of traffic light and congestion at the junctions and the results were further calculated and verified using AODV and GPSR protocol.","PeriodicalId":217950,"journal":{"name":"2015 Eighth International Conference on Contemporary Computing (IC3)","volume":"152 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127013979","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 : 2015-08-20DOI: 10.1109/IC3.2015.7346654
Kanika Mehta, S. P. Ghrera
With rapid technological development and growth of sequencing data, an umpteen gamut of biological data has been generated. As an alternative, Data Compression is employed to reduce the size of data. In this direction, this paper proposes a new reference-based compression approach, which is employed as a solution. Firstly, a reference has been constructed from the common sub strings of randomly selected input sequences. Reference set is a pair of key and value, where key is a fingerprint (or a unique id) and value is a sequence of characters. Next, these given sequences are compressed using referential compression algorithm. This is attained by matching the input with the reference and hence, replacing the match found in input by its fingerprints contained in the reference, thereby achieving better compression. The experimental results of this paper show that the approach proposed herein, outperforms the existing approaches and methodologies applied so far.
{"title":"DNA compression using referential compression algorithm","authors":"Kanika Mehta, S. P. Ghrera","doi":"10.1109/IC3.2015.7346654","DOIUrl":"https://doi.org/10.1109/IC3.2015.7346654","url":null,"abstract":"With rapid technological development and growth of sequencing data, an umpteen gamut of biological data has been generated. As an alternative, Data Compression is employed to reduce the size of data. In this direction, this paper proposes a new reference-based compression approach, which is employed as a solution. Firstly, a reference has been constructed from the common sub strings of randomly selected input sequences. Reference set is a pair of key and value, where key is a fingerprint (or a unique id) and value is a sequence of characters. Next, these given sequences are compressed using referential compression algorithm. This is attained by matching the input with the reference and hence, replacing the match found in input by its fingerprints contained in the reference, thereby achieving better compression. The experimental results of this paper show that the approach proposed herein, outperforms the existing approaches and methodologies applied so far.","PeriodicalId":217950,"journal":{"name":"2015 Eighth International Conference on Contemporary Computing (IC3)","volume":"407 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129216883","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 : 2015-08-20DOI: 10.1109/IC3.2015.7346728
K. K. Jha
Understanding Operating System behavior is very critical for any embedded designer to make informed design decision. We present a new logging method which can capture the high granular details of the kernel activity. It reduces the logging latency by 95-97% & logging memory usage by 70% compared to conventional “printk”. We utilize the string literal pool of the Linux kernel to reconstruct the log offline, and store only the parameter values passed to a printk function, instead of current method putting the log as string after printk formatting.
{"title":"Logging method for high execution frequency paths of Linux kernel","authors":"K. K. Jha","doi":"10.1109/IC3.2015.7346728","DOIUrl":"https://doi.org/10.1109/IC3.2015.7346728","url":null,"abstract":"Understanding Operating System behavior is very critical for any embedded designer to make informed design decision. We present a new logging method which can capture the high granular details of the kernel activity. It reduces the logging latency by 95-97% & logging memory usage by 70% compared to conventional “printk”. We utilize the string literal pool of the Linux kernel to reconstruct the log offline, and store only the parameter values passed to a printk function, instead of current method putting the log as string after printk formatting.","PeriodicalId":217950,"journal":{"name":"2015 Eighth International Conference on Contemporary Computing (IC3)","volume":"41 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127989671","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 : 2015-08-20DOI: 10.1109/IC3.2015.7346711
V. VarshaM., P. Vinod, A. DhanyaK.
In this paper, a broad static analysis system to classify the android malware application is been proposed. The features like hardware components, permissions, application components, filtered intents, opcodes and number of smali files per application are used to generate the vector space model. Significant features are selected using Entropy based Category Coverage Difference criterion. The performance of the system was evaluated using classifiers like SVM, Rotation Forest and Random Forest. An accuracy of 98.14% with F-measure 0.976 was obtained for the Meta feature space model containing malware features using Random Forest classifier. An overall analysis concluded that the malware model outperforms benign model.
{"title":"Heterogeneous feature space for Android malware detection","authors":"V. VarshaM., P. Vinod, A. DhanyaK.","doi":"10.1109/IC3.2015.7346711","DOIUrl":"https://doi.org/10.1109/IC3.2015.7346711","url":null,"abstract":"In this paper, a broad static analysis system to classify the android malware application is been proposed. The features like hardware components, permissions, application components, filtered intents, opcodes and number of smali files per application are used to generate the vector space model. Significant features are selected using Entropy based Category Coverage Difference criterion. The performance of the system was evaluated using classifiers like SVM, Rotation Forest and Random Forest. An accuracy of 98.14% with F-measure 0.976 was obtained for the Meta feature space model containing malware features using Random Forest classifier. An overall analysis concluded that the malware model outperforms benign model.","PeriodicalId":217950,"journal":{"name":"2015 Eighth International Conference on Contemporary Computing (IC3)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126822380","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 : 2015-08-20DOI: 10.1109/IC3.2015.7346688
A. Dutta, K. S. Rao
The present work investigates the robustness of Power Normalized Cepstral Coefficients (PNCC) for Language identification (LID) from noisy speech. Though the state of the art vocal tract features like mel frequency cepstral coefficients (MFCC) give good recognition accuracy in clean environments, the performance degrades drastically when the signal to noise ratio decreases. In this work, experiments have been carried out on IITKGP-MLILSC speech database. Gaussian mixture model (GMM) is used to building the language models. We have used NOISEX-92 database to add synthetic noise at different SNR levels. We have also compared the recognition accuracy of two systems, one developed using MFCCs and and the other using PNCCs. Finally, we have shown that PNCC features are more robust to noise.
{"title":"Robust language identification using Power Normalized Cepstral Coefficients","authors":"A. Dutta, K. S. Rao","doi":"10.1109/IC3.2015.7346688","DOIUrl":"https://doi.org/10.1109/IC3.2015.7346688","url":null,"abstract":"The present work investigates the robustness of Power Normalized Cepstral Coefficients (PNCC) for Language identification (LID) from noisy speech. Though the state of the art vocal tract features like mel frequency cepstral coefficients (MFCC) give good recognition accuracy in clean environments, the performance degrades drastically when the signal to noise ratio decreases. In this work, experiments have been carried out on IITKGP-MLILSC speech database. Gaussian mixture model (GMM) is used to building the language models. We have used NOISEX-92 database to add synthetic noise at different SNR levels. We have also compared the recognition accuracy of two systems, one developed using MFCCs and and the other using PNCCs. Finally, we have shown that PNCC features are more robust to noise.","PeriodicalId":217950,"journal":{"name":"2015 Eighth International Conference on Contemporary Computing (IC3)","volume":"94 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128392523","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 : 2015-08-20DOI: 10.1109/IC3.2015.7346703
Rakhi Joon, A. Singhal
Adverbs are one of the main aspects of grammar in almost all the languages as they play a vital role in formation of a sentence. The identification and extraction of Multi Word Expressions (MWEs) in Hindi is done by various researchers but this new category of adverbs in Hindi MWEs is not known so far. A lot of research is going on adverbs in many other languages but in Hindi MWEs, adverbs have not gained proper place. There are various combinations of adverbs which could be used as Multi words. The main focus of this paper is to extract those Adverbs combination or compound adverbs which act as MWEs in Hindi text. Further classification of these adverb is also proposed on the basis of type of adverbs. The system is developed and tested with the dataset obtained from CFILT Hindi corpus. Results are evaluated using the evaluation measures precision, recall and F-measure.
{"title":"A system for compound adverbs MWEs extraction in Hindi","authors":"Rakhi Joon, A. Singhal","doi":"10.1109/IC3.2015.7346703","DOIUrl":"https://doi.org/10.1109/IC3.2015.7346703","url":null,"abstract":"Adverbs are one of the main aspects of grammar in almost all the languages as they play a vital role in formation of a sentence. The identification and extraction of Multi Word Expressions (MWEs) in Hindi is done by various researchers but this new category of adverbs in Hindi MWEs is not known so far. A lot of research is going on adverbs in many other languages but in Hindi MWEs, adverbs have not gained proper place. There are various combinations of adverbs which could be used as Multi words. The main focus of this paper is to extract those Adverbs combination or compound adverbs which act as MWEs in Hindi text. Further classification of these adverb is also proposed on the basis of type of adverbs. The system is developed and tested with the dataset obtained from CFILT Hindi corpus. Results are evaluated using the evaluation measures precision, recall and F-measure.","PeriodicalId":217950,"journal":{"name":"2015 Eighth International Conference on Contemporary Computing (IC3)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133348001","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 : 2015-08-20DOI: 10.1109/IC3.2015.7346714
S. Goel, Suma Dawn, G. Dhanalekshmi, N. Hema, S. Singh, Sanchika Gupta, Taj Alam, Prashant Kaushik, Kashav Ajmera
Collaborative teaching was applied by eight teachers for teaching nearly 700 students in four different sections of three different computer science courses with section strength varying from 120-240. Different forms of collaborative teaching were tried. Collaborative teaching at JIIT, Noida has turned out to be successful for large classes of the strength of 100 and above.
{"title":"Collaborative teaching in large classes of computer science courses","authors":"S. Goel, Suma Dawn, G. Dhanalekshmi, N. Hema, S. Singh, Sanchika Gupta, Taj Alam, Prashant Kaushik, Kashav Ajmera","doi":"10.1109/IC3.2015.7346714","DOIUrl":"https://doi.org/10.1109/IC3.2015.7346714","url":null,"abstract":"Collaborative teaching was applied by eight teachers for teaching nearly 700 students in four different sections of three different computer science courses with section strength varying from 120-240. Different forms of collaborative teaching were tried. Collaborative teaching at JIIT, Noida has turned out to be successful for large classes of the strength of 100 and above.","PeriodicalId":217950,"journal":{"name":"2015 Eighth International Conference on Contemporary Computing (IC3)","volume":"260 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131659061","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：