Pub Date : 2019-04-01DOI: 10.1109/ICACCE46606.2019.9079958
K. P. Sampoornam, G. R. Darshini
MANET is a wireless mobile adhoc network which is infrastructure less connecting devices wirelessly. This paper analyze the performance of different routing protocols such as Bellman ford, AODV (Adhoc on-demand Distance Vector), DSR (Dynamic Source Routing), ZRP (Zone Routing Protocol) and DYMO (Dynamic MANET On-demand) without fault node and with fault node in a MANET network. The simulation is executed by using EXATA tool and it verifies the parameters such as Throughput, Average Delay, Average Jitter, Total number of packets enqueued, Total number of packets dequeued and Total number of packets dropped for fault node and normal node for these routing algorithm. Finally it will conclude the best routing protocol.
{"title":"Performance Analysis of Bellman Ford, AODV, DSR, ZRP and DYMO Routing Protocol in MANET using EXATA","authors":"K. P. Sampoornam, G. R. Darshini","doi":"10.1109/ICACCE46606.2019.9079958","DOIUrl":"https://doi.org/10.1109/ICACCE46606.2019.9079958","url":null,"abstract":"MANET is a wireless mobile adhoc network which is infrastructure less connecting devices wirelessly. This paper analyze the performance of different routing protocols such as Bellman ford, AODV (Adhoc on-demand Distance Vector), DSR (Dynamic Source Routing), ZRP (Zone Routing Protocol) and DYMO (Dynamic MANET On-demand) without fault node and with fault node in a MANET network. The simulation is executed by using EXATA tool and it verifies the parameters such as Throughput, Average Delay, Average Jitter, Total number of packets enqueued, Total number of packets dequeued and Total number of packets dropped for fault node and normal node for these routing algorithm. Finally it will conclude the best routing protocol.","PeriodicalId":317123,"journal":{"name":"2019 International Conference on Advances in Computing and Communication Engineering (ICACCE)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134478112","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 : 2019-04-01DOI: 10.1109/ICACCE46606.2019.9080012
K. Karthikeyan, A. Bharathi
Cloud Computing is a computing hypothesis, where a huge group of systems linked together in private, public or hybrid network, to offer dynamically amendable infrastructure for data storage, file storage and application. With this emerging technology, application hosting, delivery, content storage, and reduced computation cost, and it acts as an essential module for backbone of the Internet of Things (IOT). The efficiency of cloud Service providers (CSP) could be improved by considering significant factors such as availability, reliability, usability, security, responsiveness, and elasticity. Assessment of these factors leads to efficiency in designing scheduler for CSP. This metrics also improved the Quality of Service (QoS) in cloud. Many existing model and approaches evaluate this metrics. But these existing approaches doesn't offer efficient outcome. In this paper, a prominent performance model named as Spectral Expansion Method (SPM) evaluates cloud reliability. Spectral expansion Method (SPM) is a huge technique useful in reliability and performance modelling of computing system. This approach solves the Markov model of Cloud service Provider (CSP) to predict the reliability. The SPM is better compared to matrix geometric methods.
{"title":"Spectral Expansion Method for Cloud Reliability Analysis","authors":"K. Karthikeyan, A. Bharathi","doi":"10.1109/ICACCE46606.2019.9080012","DOIUrl":"https://doi.org/10.1109/ICACCE46606.2019.9080012","url":null,"abstract":"Cloud Computing is a computing hypothesis, where a huge group of systems linked together in private, public or hybrid network, to offer dynamically amendable infrastructure for data storage, file storage and application. With this emerging technology, application hosting, delivery, content storage, and reduced computation cost, and it acts as an essential module for backbone of the Internet of Things (IOT). The efficiency of cloud Service providers (CSP) could be improved by considering significant factors such as availability, reliability, usability, security, responsiveness, and elasticity. Assessment of these factors leads to efficiency in designing scheduler for CSP. This metrics also improved the Quality of Service (QoS) in cloud. Many existing model and approaches evaluate this metrics. But these existing approaches doesn't offer efficient outcome. In this paper, a prominent performance model named as Spectral Expansion Method (SPM) evaluates cloud reliability. Spectral expansion Method (SPM) is a huge technique useful in reliability and performance modelling of computing system. This approach solves the Markov model of Cloud service Provider (CSP) to predict the reliability. The SPM is better compared to matrix geometric methods.","PeriodicalId":317123,"journal":{"name":"2019 International Conference on Advances in Computing and Communication Engineering (ICACCE)","volume":"172 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133584895","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 : 2019-04-01DOI: 10.1109/ICACCE46606.2019.9079964
N. Gayathiri, D. D. Jaspher, A. Natarajan
As the size of the data grows enormous day by day, there are challenges in storing, sorting and quick accessibility of the data. In order to overcome these challenges indexing of Big Data were made predominant so that these data can be ordered, addressed and located easily. Though there are lot of techniques to index data and map them, each has its own advantages and issues over its performance across various kinds of data. Two different techniques for Big Data retrieval namely MapReduce, a way of simplifying a huge collection into some useful aggregation values and Hash indexing, which is a method of generating key and storing the value of the tuples so that the data are addressed by the generated key on its tuples is compared using NoSQL database. An analysis is made to examine the retrieval efficiency of the data which are of varying size from the whole dataset and limiting the data to be retrieved using predicates through search queries is performed. The comparison is made using both singleton and distributed NoSQL MongoDB.
{"title":"Big Data retrieval techniques based on Hash Indexing and MapReduce approach with NoSQL Database","authors":"N. Gayathiri, D. D. Jaspher, A. Natarajan","doi":"10.1109/ICACCE46606.2019.9079964","DOIUrl":"https://doi.org/10.1109/ICACCE46606.2019.9079964","url":null,"abstract":"As the size of the data grows enormous day by day, there are challenges in storing, sorting and quick accessibility of the data. In order to overcome these challenges indexing of Big Data were made predominant so that these data can be ordered, addressed and located easily. Though there are lot of techniques to index data and map them, each has its own advantages and issues over its performance across various kinds of data. Two different techniques for Big Data retrieval namely MapReduce, a way of simplifying a huge collection into some useful aggregation values and Hash indexing, which is a method of generating key and storing the value of the tuples so that the data are addressed by the generated key on its tuples is compared using NoSQL database. An analysis is made to examine the retrieval efficiency of the data which are of varying size from the whole dataset and limiting the data to be retrieved using predicates through search queries is performed. The comparison is made using both singleton and distributed NoSQL MongoDB.","PeriodicalId":317123,"journal":{"name":"2019 International Conference on Advances in Computing and Communication Engineering (ICACCE)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132744144","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 : 2019-04-01DOI: 10.1109/ICACCE46606.2019.9079998
V. Divya, R. Deepika, C. Yamini, P. Sobiyaa
In data mining has a lot of technique for knowledge discovery. In this Clustering method is very well technique for unsupervised learning. It's important objective is to find a high-quality cluster where the distance between clusters are maximal and the distance in the cluster is minimal. K-means algorithm is applied in this paper for its simplicity. It has been widely discussed and applied in pattern recognition and machine learning. However, the K-means algorithm could not guarantee unique clustering results for the same dataset because its initial cluster centers are select randomly. To avoid such issues a new initialization method is proposed in the Improved K-means algorithm with Cuckoo Search algorithm. The proposed method uses different numerical datasets like iris, wine and solar datasets (Ames, Chariton stations). The K-means clustering solutions are comparable with cuckoo search initialization methods using different measures such as Accuracy, Precision and Recall, F1-score, Silhouette value and MSE (Mean Square Error). The experimental solution represents the effectiveness of the proposed method.
{"title":"An Efficient K-Means Clustering Initialization Using Optimization Algorithm","authors":"V. Divya, R. Deepika, C. Yamini, P. Sobiyaa","doi":"10.1109/ICACCE46606.2019.9079998","DOIUrl":"https://doi.org/10.1109/ICACCE46606.2019.9079998","url":null,"abstract":"In data mining has a lot of technique for knowledge discovery. In this Clustering method is very well technique for unsupervised learning. It's important objective is to find a high-quality cluster where the distance between clusters are maximal and the distance in the cluster is minimal. K-means algorithm is applied in this paper for its simplicity. It has been widely discussed and applied in pattern recognition and machine learning. However, the K-means algorithm could not guarantee unique clustering results for the same dataset because its initial cluster centers are select randomly. To avoid such issues a new initialization method is proposed in the Improved K-means algorithm with Cuckoo Search algorithm. The proposed method uses different numerical datasets like iris, wine and solar datasets (Ames, Chariton stations). The K-means clustering solutions are comparable with cuckoo search initialization methods using different measures such as Accuracy, Precision and Recall, F1-score, Silhouette value and MSE (Mean Square Error). The experimental solution represents the effectiveness of the proposed method.","PeriodicalId":317123,"journal":{"name":"2019 International Conference on Advances in Computing and Communication Engineering (ICACCE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126064407","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 : 2019-04-01DOI: 10.1109/ICACCE46606.2019.9079992
Priyanka Dalal, S. Dhull
Electromagnetic Band Gap (EBG) Structures are of great interest among RF and microwave engineers since their development. Because of their unique characteristics like zero phase reflection and surface wave suppression, they have been used for design of efficient antennas and numerous other applications. This article briefs a review of the three state of the art applications where EBG structures have been utilized namely: Ground Bounce Noise (GBN) suppression or Simultaneous Switching Noise (SSN) suppression, Radar Cross Section (RCS) reduction and Specific Absorption Rate (SAR) reduction. SSN reduction up to −60 dB is achieved by printing EBG structures on power plane of mixed signal system. By embedding the EBG structures with patch antenna up to 20 dB reduction in RCS is realized. Up to 84% reduction in the SAR of a mobile phone antenna is obtained as compared to same antenna without any EBG loading. Substantial reduction in the SAR of a Wireless Body Area Network (WBAN) antenna is also observed when integrated with EBG structures.
{"title":"Electromagnetic Band Gap Structure Applications in Modern Wireless Perspective: A Review","authors":"Priyanka Dalal, S. Dhull","doi":"10.1109/ICACCE46606.2019.9079992","DOIUrl":"https://doi.org/10.1109/ICACCE46606.2019.9079992","url":null,"abstract":"Electromagnetic Band Gap (EBG) Structures are of great interest among RF and microwave engineers since their development. Because of their unique characteristics like zero phase reflection and surface wave suppression, they have been used for design of efficient antennas and numerous other applications. This article briefs a review of the three state of the art applications where EBG structures have been utilized namely: Ground Bounce Noise (GBN) suppression or Simultaneous Switching Noise (SSN) suppression, Radar Cross Section (RCS) reduction and Specific Absorption Rate (SAR) reduction. SSN reduction up to −60 dB is achieved by printing EBG structures on power plane of mixed signal system. By embedding the EBG structures with patch antenna up to 20 dB reduction in RCS is realized. Up to 84% reduction in the SAR of a mobile phone antenna is obtained as compared to same antenna without any EBG loading. Substantial reduction in the SAR of a Wireless Body Area Network (WBAN) antenna is also observed when integrated with EBG structures.","PeriodicalId":317123,"journal":{"name":"2019 International Conference on Advances in Computing and Communication Engineering (ICACCE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126348566","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 : 2019-04-01DOI: 10.1109/ICACCE46606.2019.9079962
Priyank Bhandia, R. S. Anupindi, Pavan Yekbote, N. Singh, H. L. Phalachandra, D. Sitaram
Explosion of digital content has resulted in large amounts of resources being provisioned and managed for various applications in cloud Data Centers. Energy consumption in these large Cloud Data Centers is a rising concern, accounting for 1.3% of the worlds electricity consumption [1]. Data Center cooling accounts for 40% of this energy consumption [2]. Of the various mechanisms available for studying the energy consumption in Data Centers, a simulation based approach is quite popular. In this paper, we propose DCSim, a configurable extension to CloudSim, a popularly used cloud infrastructure and simulation framework. CloudSim provides coarse power models to calculate total energy consumption in a Data Center for a given workload, but has no provision to factor in the Data Center topology and current cooled area into this power model. This makes building intelligent cooling energy aware allocation policies in CloudSim difficult. In DCSim, we introduce a novel Data Center model that addresses the shortcomings of CloudSim by encapsulating concepts of Racks, Aisles, Sectors and Zones (collectively referred to as DCObjects). We also provide the capability to model the cooling of these DCObjects. This makes the study of cooling aware resource provisioning for workloads easier. The DCObjects and the Data Center model presented are designed to be fully extensible to support future developments in this area. In this work we also implement a Cooling aware VM allocation policy, and demonstrate using multiple algorithms, that this VM allocation policy will effectively reduce the total Data Center power consumption by 18.18% over an algorithm which does not factor in the cooled DCObjects.
{"title":"DCSim: Cooling Energy Aware VM Allocation Framework for a Cloud Data Center","authors":"Priyank Bhandia, R. S. Anupindi, Pavan Yekbote, N. Singh, H. L. Phalachandra, D. Sitaram","doi":"10.1109/ICACCE46606.2019.9079962","DOIUrl":"https://doi.org/10.1109/ICACCE46606.2019.9079962","url":null,"abstract":"Explosion of digital content has resulted in large amounts of resources being provisioned and managed for various applications in cloud Data Centers. Energy consumption in these large Cloud Data Centers is a rising concern, accounting for 1.3% of the worlds electricity consumption [1]. Data Center cooling accounts for 40% of this energy consumption [2]. Of the various mechanisms available for studying the energy consumption in Data Centers, a simulation based approach is quite popular. In this paper, we propose DCSim, a configurable extension to CloudSim, a popularly used cloud infrastructure and simulation framework. CloudSim provides coarse power models to calculate total energy consumption in a Data Center for a given workload, but has no provision to factor in the Data Center topology and current cooled area into this power model. This makes building intelligent cooling energy aware allocation policies in CloudSim difficult. In DCSim, we introduce a novel Data Center model that addresses the shortcomings of CloudSim by encapsulating concepts of Racks, Aisles, Sectors and Zones (collectively referred to as DCObjects). We also provide the capability to model the cooling of these DCObjects. This makes the study of cooling aware resource provisioning for workloads easier. The DCObjects and the Data Center model presented are designed to be fully extensible to support future developments in this area. In this work we also implement a Cooling aware VM allocation policy, and demonstrate using multiple algorithms, that this VM allocation policy will effectively reduce the total Data Center power consumption by 18.18% over an algorithm which does not factor in the cooled DCObjects.","PeriodicalId":317123,"journal":{"name":"2019 International Conference on Advances in Computing and Communication Engineering (ICACCE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131375110","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 : 2019-04-01DOI: 10.1109/ICACCE46606.2019.9079990
S. Chakravarthy, H. Rajaguru
The noise removal is being a substantial phase for the computer-assisted detection (CAD) based breast cancer diagnosis using mammogram medical images. A proficient method for the salt-and-pepper or impulse noise eradication in digital mammograms is implemented. The approach depends on the statistical measures like mean, median and standard deviation quantities. This calculates the new intensity which is to be substituted in the impulse area by determining those measures in neighbour points of the taken mammogram images. The proposed is simply an iterative method that aims to take away the salt and pepper otherwise impulse noise devoid of affecting the boundaries and other major significant portions of the image. The approach is compared with several existing methods and it provides enhanced noise removal performance over others.
{"title":"A Novel Noise Removal in Digital Mammograms based on Statistical Algorithms","authors":"S. Chakravarthy, H. Rajaguru","doi":"10.1109/ICACCE46606.2019.9079990","DOIUrl":"https://doi.org/10.1109/ICACCE46606.2019.9079990","url":null,"abstract":"The noise removal is being a substantial phase for the computer-assisted detection (CAD) based breast cancer diagnosis using mammogram medical images. A proficient method for the salt-and-pepper or impulse noise eradication in digital mammograms is implemented. The approach depends on the statistical measures like mean, median and standard deviation quantities. This calculates the new intensity which is to be substituted in the impulse area by determining those measures in neighbour points of the taken mammogram images. The proposed is simply an iterative method that aims to take away the salt and pepper otherwise impulse noise devoid of affecting the boundaries and other major significant portions of the image. The approach is compared with several existing methods and it provides enhanced noise removal performance over others.","PeriodicalId":317123,"journal":{"name":"2019 International Conference on Advances in Computing and Communication Engineering (ICACCE)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114448567","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 : 2019-04-01DOI: 10.1109/ICACCE46606.2019.9079987
Mike Mikailov, N. Petrick, Yasameen Azarbaijani, Fu-Jyh Luo, Lohit Valleru, Stephen Whitney, Yelizaveta Torosyan
Big data analysis can exhibit significant scaling problems when migrated to High Performance Computing (HPC) clusters and/or cloud computing platforms if traditional software parallelization techniques such as POSIX multi-threading and Message Passing Interface (MPI) are used. This paper introduces a novel scaling technique based on a-well-known array job mechanism to enable a team of FDA researchers to validate a method for identifying evidence of possible adverse events in very large sets of patient medical records. The analysis employed the widely-used basic Statistical Analysis Software (SAS) package, and the proposed parallelization approach dramatically increased the scaling and thus the speed of job completion for this application and is applicable to any similar software written in any other programming language. The new scaling technique offers O(T) theoretical speedup in comparison to multi-threading and MPI techniques. Here T is the number of array job tasks. The basis of the new approach is the segmentation of both (a) the big data set being analyzed and (b) the large number of SAS analysis types applied to each data segment. The large number of unique pairs of data set segment and analysis type segment are then each processed by a separate computing node (core) in pseudo-parallel manner. As a result, a SAS big data analysis which required more than 10 days to complete and consumed more than a terabyte of RAM on a single multi-core computing node completed in less than an hour parallelized over a large number of nodes, none of which needed more than 50 GB of RAM. The massive increase in the number of tasks when running an analysis job with this degree of segmentation reduces the size, scope and execution time of each task. Besides the significant speed improvement, additional benefits include fine-grained checkpointing and increased flexibility of job submission.
{"title":"Scaling and Parallelization of Big Data Analysis on HPC and Cloud Systems","authors":"Mike Mikailov, N. Petrick, Yasameen Azarbaijani, Fu-Jyh Luo, Lohit Valleru, Stephen Whitney, Yelizaveta Torosyan","doi":"10.1109/ICACCE46606.2019.9079987","DOIUrl":"https://doi.org/10.1109/ICACCE46606.2019.9079987","url":null,"abstract":"Big data analysis can exhibit significant scaling problems when migrated to High Performance Computing (HPC) clusters and/or cloud computing platforms if traditional software parallelization techniques such as POSIX multi-threading and Message Passing Interface (MPI) are used. This paper introduces a novel scaling technique based on a-well-known array job mechanism to enable a team of FDA researchers to validate a method for identifying evidence of possible adverse events in very large sets of patient medical records. The analysis employed the widely-used basic Statistical Analysis Software (SAS) package, and the proposed parallelization approach dramatically increased the scaling and thus the speed of job completion for this application and is applicable to any similar software written in any other programming language. The new scaling technique offers O(T) theoretical speedup in comparison to multi-threading and MPI techniques. Here T is the number of array job tasks. The basis of the new approach is the segmentation of both (a) the big data set being analyzed and (b) the large number of SAS analysis types applied to each data segment. The large number of unique pairs of data set segment and analysis type segment are then each processed by a separate computing node (core) in pseudo-parallel manner. As a result, a SAS big data analysis which required more than 10 days to complete and consumed more than a terabyte of RAM on a single multi-core computing node completed in less than an hour parallelized over a large number of nodes, none of which needed more than 50 GB of RAM. The massive increase in the number of tasks when running an analysis job with this degree of segmentation reduces the size, scope and execution time of each task. Besides the significant speed improvement, additional benefits include fine-grained checkpointing and increased flexibility of job submission.","PeriodicalId":317123,"journal":{"name":"2019 International Conference on Advances in Computing and Communication Engineering (ICACCE)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114745920","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 : 2019-04-01DOI: 10.1109/ICACCE46606.2019.9079965
R. Deepa, E. Tamilselvan, ES Abrar, Shrinivas Sampath
This paper describes a systemic approach that analyses tennis videos to estimate its trajectory when the ball is tossed by the player. This system will reconstruct the trajectory of the ball by combining various image processing techniques to interpret the video frames using Action Decision networks. The project estimates the ball location using multiple-view geometry and state estimation filtering. Image processing concepts like image segmentation, morphological image processing are employed. We will perform the project using three different algorithms namely YOLO, SSD and Faster RCNN. A comparison is done using the three different algorithms and the performance of the different algorithms will be determined for the detection of a tennis ball. Software has been developed to compare the algorithms and to find the algorithm that is more efficient and has less computational power.
{"title":"Comparison of Yolo, SSD, Faster RCNN for Real Time Tennis Ball Tracking for Action Decision Networks","authors":"R. Deepa, E. Tamilselvan, ES Abrar, Shrinivas Sampath","doi":"10.1109/ICACCE46606.2019.9079965","DOIUrl":"https://doi.org/10.1109/ICACCE46606.2019.9079965","url":null,"abstract":"This paper describes a systemic approach that analyses tennis videos to estimate its trajectory when the ball is tossed by the player. This system will reconstruct the trajectory of the ball by combining various image processing techniques to interpret the video frames using Action Decision networks. The project estimates the ball location using multiple-view geometry and state estimation filtering. Image processing concepts like image segmentation, morphological image processing are employed. We will perform the project using three different algorithms namely YOLO, SSD and Faster RCNN. A comparison is done using the three different algorithms and the performance of the different algorithms will be determined for the detection of a tennis ball. Software has been developed to compare the algorithms and to find the algorithm that is more efficient and has less computational power.","PeriodicalId":317123,"journal":{"name":"2019 International Conference on Advances in Computing and Communication Engineering (ICACCE)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128268862","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 : 2019-04-01DOI: 10.1109/ICACCE46606.2019.9080008
Subham Shaw, M. Prakash
Solar energy is the most predominant renewable energy resource available to humankind. To remain depend on it in future, forecasting of solar energy is essential. In this paper, solar potential is forecasted with the help of Support vector regression (SVR) depending on other easily measurable parameters. The parameters like pressure, temperature, humidity are exploited in the prediction of daily global solar radiation. The data used for the study is taken for a period of two year for the location of New Alipore, Kolkata. Two models where developed using RBF kernel and Polynomial kernel function of SVR. The performance of this two models are evaluated with the statistical measures viz, Coefficient of Determination (R2) and Root Mean Square Error (RMSE). The result obtained are R2 of 0.7976 and RMSE of 1.0564 for training while R2 of 0.7845 and RMSE of 1.0532 for testing with RBF kernel. While polynomial kernel gives R2 of 0.9393 and RMSE of 1.1975 for training while R2 of 0.9060 and RMSE of 1.1594 for testing.
{"title":"Solar Radiation Forecasting Using Support Vector Regression","authors":"Subham Shaw, M. Prakash","doi":"10.1109/ICACCE46606.2019.9080008","DOIUrl":"https://doi.org/10.1109/ICACCE46606.2019.9080008","url":null,"abstract":"Solar energy is the most predominant renewable energy resource available to humankind. To remain depend on it in future, forecasting of solar energy is essential. In this paper, solar potential is forecasted with the help of Support vector regression (SVR) depending on other easily measurable parameters. The parameters like pressure, temperature, humidity are exploited in the prediction of daily global solar radiation. The data used for the study is taken for a period of two year for the location of New Alipore, Kolkata. Two models where developed using RBF kernel and Polynomial kernel function of SVR. The performance of this two models are evaluated with the statistical measures viz, Coefficient of Determination (R2) and Root Mean Square Error (RMSE). The result obtained are R2 of 0.7976 and RMSE of 1.0564 for training while R2 of 0.7845 and RMSE of 1.0532 for testing with RBF kernel. While polynomial kernel gives R2 of 0.9393 and RMSE of 1.1975 for training while R2 of 0.9060 and RMSE of 1.1594 for testing.","PeriodicalId":317123,"journal":{"name":"2019 International Conference on Advances in Computing and Communication Engineering (ICACCE)","volume":"226 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131447857","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：