Pub Date : 2017-05-05DOI: 10.1109/CCAA.2017.8229836
S. Shakya, Sandeep Sigdel
Anomaly detection involves way towards finding the example in the information that violates ordinary conduct. The choice of anomaly detection algorithm can to a great extent affect the undertaking of anomaly identification. The decision of abnormality revelation calculation can influence complexity and correctness of the process. The choice of anomaly recognition calculations may increase the occurrence of false alert rate, high resource usage, and may even lead to security vulnerabilities. In addition, one anomaly detection procedure can beat the other in same dataset. In this way, many anomaly detection systems can be used to merge the prediction from multiple system in order to improve the generalizability over a single estimator. In this research work, we show a weighted hybrid model utilizing Support Vector Machine and Naive Bayes for anomaly discovery, k-fold cross validation to figure the error related with corresponding model and accuracy based weight values to be used with the candidate model. The hybrid algorithm has been executed to join the result of expectation of SVM and Naive Bayes classifiers utilizing weight elements. The weights elements have been computed utilizing root mean square error of forecast as error metric. The classifier with high accuracy has been given higher weight and classifier with the lower precision has been given lower weight. The objective is to improve the performance of hybrid model than that of Support Vector Machine (SVM) and Naive Bayes.
{"title":"An approach to develop a hybrid algorithm based on support vector machine and Naive Bayes for anomaly detection","authors":"S. Shakya, Sandeep Sigdel","doi":"10.1109/CCAA.2017.8229836","DOIUrl":"https://doi.org/10.1109/CCAA.2017.8229836","url":null,"abstract":"Anomaly detection involves way towards finding the example in the information that violates ordinary conduct. The choice of anomaly detection algorithm can to a great extent affect the undertaking of anomaly identification. The decision of abnormality revelation calculation can influence complexity and correctness of the process. The choice of anomaly recognition calculations may increase the occurrence of false alert rate, high resource usage, and may even lead to security vulnerabilities. In addition, one anomaly detection procedure can beat the other in same dataset. In this way, many anomaly detection systems can be used to merge the prediction from multiple system in order to improve the generalizability over a single estimator. In this research work, we show a weighted hybrid model utilizing Support Vector Machine and Naive Bayes for anomaly discovery, k-fold cross validation to figure the error related with corresponding model and accuracy based weight values to be used with the candidate model. The hybrid algorithm has been executed to join the result of expectation of SVM and Naive Bayes classifiers utilizing weight elements. The weights elements have been computed utilizing root mean square error of forecast as error metric. The classifier with high accuracy has been given higher weight and classifier with the lower precision has been given lower weight. The objective is to improve the performance of hybrid model than that of Support Vector Machine (SVM) and Naive Bayes.","PeriodicalId":6627,"journal":{"name":"2017 International Conference on Computing, Communication and Automation (ICCCA)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2017-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89861706","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 : 2017-05-05DOI: 10.1109/CCAA.2017.8229774
Gaurav Goyal, Karanjit Singh, K. Ramkumar
JavaScript Object Notation (JSON) is a syntax for exchanging and storing data, the text data is converted in Object form and processed. The consistency and data integrity are the big challenges of payload delivery. In general, a message digest which is a cryptographic one way hash function containing a set of digits is used to protect the integrity of a data. The message digest is attached with the main data content and verified by the receiver, in turn it warns the receiver about the malfunctioning of payload. There are many standard algorithms exist to create the digest. This paper gives detailed review of the different algorithms suitable for XML and JSON documents and compares the performance of different algorithms.
{"title":"A detailed analysis of data consistency concepts in data exchange formats (JSON & XML)","authors":"Gaurav Goyal, Karanjit Singh, K. Ramkumar","doi":"10.1109/CCAA.2017.8229774","DOIUrl":"https://doi.org/10.1109/CCAA.2017.8229774","url":null,"abstract":"JavaScript Object Notation (JSON) is a syntax for exchanging and storing data, the text data is converted in Object form and processed. The consistency and data integrity are the big challenges of payload delivery. In general, a message digest which is a cryptographic one way hash function containing a set of digits is used to protect the integrity of a data. The message digest is attached with the main data content and verified by the receiver, in turn it warns the receiver about the malfunctioning of payload. There are many standard algorithms exist to create the digest. This paper gives detailed review of the different algorithms suitable for XML and JSON documents and compares the performance of different algorithms.","PeriodicalId":6627,"journal":{"name":"2017 International Conference on Computing, Communication and Automation (ICCCA)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2017-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78706276","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 : 2017-05-05DOI: 10.1109/CCAA.2017.8229778
Savita, Sandeep Jain, K. K. Paliwal
This paper investigates different methods of representing shape and texture in content-based image retrieval. We have combined five features set in our work and these are trained and classified with SVM (support vector machine) classifier which makes use of machine learning technology. We combined histogram features, texture features (GLCM features), wavelet features, Gabor features, and statistical features, which makes use of global and local features. A database of 1000 images (Wang database) of 10 different classes is used to extract all features vector for each image and stored in our database so that SVM can use it to classify the query image. By using these features set, we are able to reach up to 97.53% classification accuracy.
{"title":"CBIR by cascading features & SVM","authors":"Savita, Sandeep Jain, K. K. Paliwal","doi":"10.1109/CCAA.2017.8229778","DOIUrl":"https://doi.org/10.1109/CCAA.2017.8229778","url":null,"abstract":"This paper investigates different methods of representing shape and texture in content-based image retrieval. We have combined five features set in our work and these are trained and classified with SVM (support vector machine) classifier which makes use of machine learning technology. We combined histogram features, texture features (GLCM features), wavelet features, Gabor features, and statistical features, which makes use of global and local features. A database of 1000 images (Wang database) of 10 different classes is used to extract all features vector for each image and stored in our database so that SVM can use it to classify the query image. By using these features set, we are able to reach up to 97.53% classification accuracy.","PeriodicalId":6627,"journal":{"name":"2017 International Conference on Computing, Communication and Automation (ICCCA)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2017-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78926083","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 : 2017-05-05DOI: 10.1109/CCAA.2017.8229782
Prateek K. Gaddigoudar, T. R. Balihalli, Suprith S. Ijantkar, N. Iyer, Shruti Maralappanavar
Pedestrian detection is one of the significant task in any intelligent systems involving video surveillance, since it provides essential information regarding the semantic behavior of pedestrians from video footages. Pedestrian detection along with tracking serves as an obvious extension to automotive applications in design and improvement of safety systems. However, various challenges arise while designing a system for detection and tracking of pedestrians such as different styles of clothing, non-linear random motion of pedestrians, occlusions between pedestrians and surroundings. Particle filtering algorithm is best suited to overcome these types of difficulties. Existing approaches such as Kalman filtering technique are also being implemented in this paper in order to compare the results and further prove that the Particle filtering dominates over the existing approaches.
{"title":"Pedestrian detection and tracking using particle filtering","authors":"Prateek K. Gaddigoudar, T. R. Balihalli, Suprith S. Ijantkar, N. Iyer, Shruti Maralappanavar","doi":"10.1109/CCAA.2017.8229782","DOIUrl":"https://doi.org/10.1109/CCAA.2017.8229782","url":null,"abstract":"Pedestrian detection is one of the significant task in any intelligent systems involving video surveillance, since it provides essential information regarding the semantic behavior of pedestrians from video footages. Pedestrian detection along with tracking serves as an obvious extension to automotive applications in design and improvement of safety systems. However, various challenges arise while designing a system for detection and tracking of pedestrians such as different styles of clothing, non-linear random motion of pedestrians, occlusions between pedestrians and surroundings. Particle filtering algorithm is best suited to overcome these types of difficulties. Existing approaches such as Kalman filtering technique are also being implemented in this paper in order to compare the results and further prove that the Particle filtering dominates over the existing approaches.","PeriodicalId":6627,"journal":{"name":"2017 International Conference on Computing, Communication and Automation (ICCCA)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2017-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83629233","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 : 2017-05-01DOI: 10.1109/CCAA.2017.8229949
S. Z. N. Dar, M. Mufti
The present article describes the implementation of Battery energy storage system (BESS) for improved and better performance characteristics of load frequency control problem with a compact sized battery energy storage system (BESS) with respect to load frequency control (LFC) applications. It is observed there is significant reduction in the frequency deviations. Also tie-power variations get diminished by significant margin as seen by the extensive simulation carried out in Matlab Simulink Environment.
{"title":"Improved load frequency response in two area power system with battery energy storage","authors":"S. Z. N. Dar, M. Mufti","doi":"10.1109/CCAA.2017.8229949","DOIUrl":"https://doi.org/10.1109/CCAA.2017.8229949","url":null,"abstract":"The present article describes the implementation of Battery energy storage system (BESS) for improved and better performance characteristics of load frequency control problem with a compact sized battery energy storage system (BESS) with respect to load frequency control (LFC) applications. It is observed there is significant reduction in the frequency deviations. Also tie-power variations get diminished by significant margin as seen by the extensive simulation carried out in Matlab Simulink Environment.","PeriodicalId":6627,"journal":{"name":"2017 International Conference on Computing, Communication and Automation (ICCCA)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75223498","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 : 2017-05-01DOI: 10.1109/CCAA.2017.8229956
J. Kaur, Saurabh Upadhyay, Avinash Sharma
In this paper we describe a unique video database which consists of the real life moments of people and objects, captured under various illumination conditions and camera positions. We have classified all the videos of our database into six categories, out of which four categories are based on the movements of camera and objects (captured by the camera). The remaining categories of the database are daylight videos and night vision videos. The videos captured under the natural light source (such as sunlight) are covered in daylight videos category. The night vision videos category has the same setup and environment as in the daylight videos category but the videos are captured in low light condition and the camera is recording in night vision mode. Each category of this video database offers a good situation for the challenge of video authentication and to fathom the credibility of video authentication algorithms too. We have applied our own intelligent video authentication algorithm on each category of the video database and obtain the results with the overall accuracy of 94.85%, subjected to various tampering attacks.
{"title":"A video database for intelligent video authentication","authors":"J. Kaur, Saurabh Upadhyay, Avinash Sharma","doi":"10.1109/CCAA.2017.8229956","DOIUrl":"https://doi.org/10.1109/CCAA.2017.8229956","url":null,"abstract":"In this paper we describe a unique video database which consists of the real life moments of people and objects, captured under various illumination conditions and camera positions. We have classified all the videos of our database into six categories, out of which four categories are based on the movements of camera and objects (captured by the camera). The remaining categories of the database are daylight videos and night vision videos. The videos captured under the natural light source (such as sunlight) are covered in daylight videos category. The night vision videos category has the same setup and environment as in the daylight videos category but the videos are captured in low light condition and the camera is recording in night vision mode. Each category of this video database offers a good situation for the challenge of video authentication and to fathom the credibility of video authentication algorithms too. We have applied our own intelligent video authentication algorithm on each category of the video database and obtain the results with the overall accuracy of 94.85%, subjected to various tampering attacks.","PeriodicalId":6627,"journal":{"name":"2017 International Conference on Computing, Communication and Automation (ICCCA)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75880577","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 : 2017-05-01DOI: 10.1109/CCAA.2017.8229986
C. Mehrotra, Nayan Chitransh, A. Singh
The enormous amount of data being generated every day is a major issue for organisations. Analysing it and taking decisions from it is a major concern. Visual analytics can be a solution to visualize the data and draw better conclusions from data which was otherwise not possible. Instead of reports and written documents, graphics can play an important role in interpreting results. Visual analytics is a much researched topic nowadays. It is a very emerging field. This paper focuses on this field and the major building blocks of visual analytics on which the concept of visual analytics relies. The three building blocks are namely information visualization, interaction techniques and data analysis.
{"title":"Building blocks for visualanalytics","authors":"C. Mehrotra, Nayan Chitransh, A. Singh","doi":"10.1109/CCAA.2017.8229986","DOIUrl":"https://doi.org/10.1109/CCAA.2017.8229986","url":null,"abstract":"The enormous amount of data being generated every day is a major issue for organisations. Analysing it and taking decisions from it is a major concern. Visual analytics can be a solution to visualize the data and draw better conclusions from data which was otherwise not possible. Instead of reports and written documents, graphics can play an important role in interpreting results. Visual analytics is a much researched topic nowadays. It is a very emerging field. This paper focuses on this field and the major building blocks of visual analytics on which the concept of visual analytics relies. The three building blocks are namely information visualization, interaction techniques and data analysis.","PeriodicalId":6627,"journal":{"name":"2017 International Conference on Computing, Communication and Automation (ICCCA)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74649952","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 : 2017-05-01DOI: 10.1109/CCAA.2017.8230058
Anamika Rathore, D. K. Panda
Smart antenna system is very useful to increase the capacity, coverage and quality of communication system. Smart antenna combines the antenna array with digital signal processing capability which tracks the mobile user by focusing radiation in a specific desired user direction and at the same time forming null toward interference. This paper represents the performance analysis of Data reusing least mean square (DRLMS) and Least Mean Square (LMS) through beam steering ability and nullifying capability of algorithm and comparative analysis is done using MATLAB 7.14. The simulation result shows that DRLMS has better performance and interference suppression capability, beam steering ability and higher convergence rate than LMS by reusing current desired and input signal as repeatedly within each iteration for coefficients update.
{"title":"Performance analysis of data reusing least mean square algorithm for smart antenna system","authors":"Anamika Rathore, D. K. Panda","doi":"10.1109/CCAA.2017.8230058","DOIUrl":"https://doi.org/10.1109/CCAA.2017.8230058","url":null,"abstract":"Smart antenna system is very useful to increase the capacity, coverage and quality of communication system. Smart antenna combines the antenna array with digital signal processing capability which tracks the mobile user by focusing radiation in a specific desired user direction and at the same time forming null toward interference. This paper represents the performance analysis of Data reusing least mean square (DRLMS) and Least Mean Square (LMS) through beam steering ability and nullifying capability of algorithm and comparative analysis is done using MATLAB 7.14. The simulation result shows that DRLMS has better performance and interference suppression capability, beam steering ability and higher convergence rate than LMS by reusing current desired and input signal as repeatedly within each iteration for coefficients update.","PeriodicalId":6627,"journal":{"name":"2017 International Conference on Computing, Communication and Automation (ICCCA)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75359930","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 : 2017-05-01DOI: 10.1109/CCAA.2017.8229867
Awadhesh Kumar, N. Tyagi
The role of energy in wireless sensor networks (WSN) becomes very important when network is unattended and it is not possible to recharge sensor node's battery in the sensing region many times. Due to this limited battery energy of sensor nodes it becomes a challenge for WSN to maintain proper functioning for a long time. So for the enhancement in network lifetime of the WSN, here we propose a modified diagonal first (bypass) forwarding scheme. In our proposed bypass forwarding scheme, the sensing region is partitioned into a grid based virtual infrastructure and in each grid the sensors elect a grid_leader on the basis of their residual energy and the grid_leaders are responsible for data dissemination to the sink node in three ways (a) horizontal (b) vertical and (c) diagonal. In this paper, we propose a modified data dissemination algorithm for wireless sensor networks that reduces the number of intermediate nodes involved during the communication between source and sink. This eventually extends the lifetime of sensor network. Simulation results show that the proposed algorithm can extend the network lifetime up to 30 percent.
{"title":"Grid based forwarding and routing scheme for extending lifetime of wireless sensor networks","authors":"Awadhesh Kumar, N. Tyagi","doi":"10.1109/CCAA.2017.8229867","DOIUrl":"https://doi.org/10.1109/CCAA.2017.8229867","url":null,"abstract":"The role of energy in wireless sensor networks (WSN) becomes very important when network is unattended and it is not possible to recharge sensor node's battery in the sensing region many times. Due to this limited battery energy of sensor nodes it becomes a challenge for WSN to maintain proper functioning for a long time. So for the enhancement in network lifetime of the WSN, here we propose a modified diagonal first (bypass) forwarding scheme. In our proposed bypass forwarding scheme, the sensing region is partitioned into a grid based virtual infrastructure and in each grid the sensors elect a grid_leader on the basis of their residual energy and the grid_leaders are responsible for data dissemination to the sink node in three ways (a) horizontal (b) vertical and (c) diagonal. In this paper, we propose a modified data dissemination algorithm for wireless sensor networks that reduces the number of intermediate nodes involved during the communication between source and sink. This eventually extends the lifetime of sensor network. Simulation results show that the proposed algorithm can extend the network lifetime up to 30 percent.","PeriodicalId":6627,"journal":{"name":"2017 International Conference on Computing, Communication and Automation (ICCCA)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75719523","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 : 2017-05-01DOI: 10.1109/CCAA.2017.8229898
Nitin Tandon, B. Suman, Nisha Agarwal, V. Bhatia
Software Defined Radio (SDR) is an emergent technology for future network centric operations as it can support dynamism of Mobile Adhoc Networking (MANET) waveforms through its inherent benefits of re configurability, portability and reusability. Unlike conventional radio, designing Physical layer for MANET waveform over SDR platform demands a new design approach and consequently must be tested thoroughly for basic radio transceiver functions as well as MANET configurations. In this paper, testability aspects of MANET waveform are discussed along with its design, development and testing in context of SDR. The test methodology has been developed considering various aspects of waveform design and system integration components. The testing results of baseband and RF subsystem of physical layer have also been presented in this paper.
{"title":"Design and testability aspects of mobile adhoc networking waveform physical layer for software defined radio","authors":"Nitin Tandon, B. Suman, Nisha Agarwal, V. Bhatia","doi":"10.1109/CCAA.2017.8229898","DOIUrl":"https://doi.org/10.1109/CCAA.2017.8229898","url":null,"abstract":"Software Defined Radio (SDR) is an emergent technology for future network centric operations as it can support dynamism of Mobile Adhoc Networking (MANET) waveforms through its inherent benefits of re configurability, portability and reusability. Unlike conventional radio, designing Physical layer for MANET waveform over SDR platform demands a new design approach and consequently must be tested thoroughly for basic radio transceiver functions as well as MANET configurations. In this paper, testability aspects of MANET waveform are discussed along with its design, development and testing in context of SDR. The test methodology has been developed considering various aspects of waveform design and system integration components. The testing results of baseband and RF subsystem of physical layer have also been presented in this paper.","PeriodicalId":6627,"journal":{"name":"2017 International Conference on Computing, Communication and Automation (ICCCA)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80151103","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：