Pub Date : 2016-03-18DOI: 10.1109/ICCPCT.2016.7530365
T. Subetha, S. Chitrakala
Understanding the activities of human is a challenging task in Computer Vision. Identifying the activities of human from videos and predicting their activity class label is the key functionality of Human Activity Recognition system. In general the major issues of Human activity recognition system is to identify the activities with or without the concurrent movement of body parts, occlusion, incremental learning etc. Among these issues the major difficulty lies in detecting the activity of human performing the interactions with or without the concurrent movement of their body parts. This paper aims in resolving the aforementioned problem. Here, the frames are extracted from the videos using the conventional frame extraction techniques. A pixel-based Local Binary Similarity Pattern background subtraction algorithm is used to detect the foreground from the extracted frames. The features are extracted from the detected foreground using Histogram of oriented Gradients and pyramidal feature extraction technique. A 20-point Microsoft human kinematic model is constructed using the set of features present in the frame and supervised temporal-stochastic neighbor embedding is applied to transform a high dimensional data to a low dimensional data. K-means clustering is then applied to produce a bag of key poses. The classifier Constrained Weighted Dynamic Time Warping(CWDTW) is used for the final generation of activity class label. Experimental results show the higher recognition rate achieved for various interactions with the benchmarking datasets such as Kinect Interaction dataset and Gaming dataset.
{"title":"Recognition of human-human interaction using CWDTW","authors":"T. Subetha, S. Chitrakala","doi":"10.1109/ICCPCT.2016.7530365","DOIUrl":"https://doi.org/10.1109/ICCPCT.2016.7530365","url":null,"abstract":"Understanding the activities of human is a challenging task in Computer Vision. Identifying the activities of human from videos and predicting their activity class label is the key functionality of Human Activity Recognition system. In general the major issues of Human activity recognition system is to identify the activities with or without the concurrent movement of body parts, occlusion, incremental learning etc. Among these issues the major difficulty lies in detecting the activity of human performing the interactions with or without the concurrent movement of their body parts. This paper aims in resolving the aforementioned problem. Here, the frames are extracted from the videos using the conventional frame extraction techniques. A pixel-based Local Binary Similarity Pattern background subtraction algorithm is used to detect the foreground from the extracted frames. The features are extracted from the detected foreground using Histogram of oriented Gradients and pyramidal feature extraction technique. A 20-point Microsoft human kinematic model is constructed using the set of features present in the frame and supervised temporal-stochastic neighbor embedding is applied to transform a high dimensional data to a low dimensional data. K-means clustering is then applied to produce a bag of key poses. The classifier Constrained Weighted Dynamic Time Warping(CWDTW) is used for the final generation of activity class label. Experimental results show the higher recognition rate achieved for various interactions with the benchmarking datasets such as Kinect Interaction dataset and Gaming dataset.","PeriodicalId":431894,"journal":{"name":"2016 International Conference on Circuit, Power and Computing Technologies (ICCPCT)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133212250","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 : 2016-03-18DOI: 10.1109/ICCPCT.2016.7530256
T. Shanmuganantham, U. Gogoi, J. Gandhimohan
Accurate measurement of pressure is a matured application of MEMS pressure sensor. But the self powered sensor is desirable one without compromising the sensitivity and to enhance energy scavenging credibility at the same conditions. Now piezoelectric materials are being used to harvest ambient energy. In this paper the squared shaped diaphragm based sensor has been designed and simulated to explore the energy generation capability as well as the sensitivity of the sensor using finite element software INTELLISUITE. The analysis shows that the deflection of the diaphragm is in a linear relationship with pressure applied. Also variation of the thickness of the diaphragm as well as the piezoelectric layer is done to study its effect on performance of MEMS piezoelectric pressure sensor.
{"title":"A study scheme of energy harvesting process of MEMS piezoelectric pressure sensor","authors":"T. Shanmuganantham, U. Gogoi, J. Gandhimohan","doi":"10.1109/ICCPCT.2016.7530256","DOIUrl":"https://doi.org/10.1109/ICCPCT.2016.7530256","url":null,"abstract":"Accurate measurement of pressure is a matured application of MEMS pressure sensor. But the self powered sensor is desirable one without compromising the sensitivity and to enhance energy scavenging credibility at the same conditions. Now piezoelectric materials are being used to harvest ambient energy. In this paper the squared shaped diaphragm based sensor has been designed and simulated to explore the energy generation capability as well as the sensitivity of the sensor using finite element software INTELLISUITE. The analysis shows that the deflection of the diaphragm is in a linear relationship with pressure applied. Also variation of the thickness of the diaphragm as well as the piezoelectric layer is done to study its effect on performance of MEMS piezoelectric pressure sensor.","PeriodicalId":431894,"journal":{"name":"2016 International Conference on Circuit, Power and Computing Technologies (ICCPCT)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132692077","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 : 2016-03-18DOI: 10.1109/ICCPCT.2016.7530287
Jijo Balakrishnan, A. Krishnan, P. Krishnan, J. Joy, K. Nibin, Reshma Chandran, H. SreeVishnu
Any organization which is a large consumer of electrical energy should adopt suitable scheme of energy conservation to minimize the energy utility. Energy auditing, both the thermal energy auditing and electrical energy auditing is a usual procedure in an educational institution. Most of the commercial building in India, were not constructed by following the standard energy conservation code. Recent studies in the field shows that, commercial building in India have an energy saving potential of 25% to 35%. The energy consumption survey investigates the major consuming energy source. The energy audit is used to investigate the weak points of the institute energy-usage system and to build up energy-saving responsibility. The energy audit reveals that the institute consumes a monthly average electrical energy of 10MWh and having a energy saving potential of 10%. This paper outlines some of the options that energy auditor can consider while conducting an audit in an institute. This paper set forth some energy saving methods in a methodological approach, experienced during an energy audit in an institution.
{"title":"Energy footprint evaluation of an educational institution in Kerala","authors":"Jijo Balakrishnan, A. Krishnan, P. Krishnan, J. Joy, K. Nibin, Reshma Chandran, H. SreeVishnu","doi":"10.1109/ICCPCT.2016.7530287","DOIUrl":"https://doi.org/10.1109/ICCPCT.2016.7530287","url":null,"abstract":"Any organization which is a large consumer of electrical energy should adopt suitable scheme of energy conservation to minimize the energy utility. Energy auditing, both the thermal energy auditing and electrical energy auditing is a usual procedure in an educational institution. Most of the commercial building in India, were not constructed by following the standard energy conservation code. Recent studies in the field shows that, commercial building in India have an energy saving potential of 25% to 35%. The energy consumption survey investigates the major consuming energy source. The energy audit is used to investigate the weak points of the institute energy-usage system and to build up energy-saving responsibility. The energy audit reveals that the institute consumes a monthly average electrical energy of 10MWh and having a energy saving potential of 10%. This paper outlines some of the options that energy auditor can consider while conducting an audit in an institute. This paper set forth some energy saving methods in a methodological approach, experienced during an energy audit in an institution.","PeriodicalId":431894,"journal":{"name":"2016 International Conference on Circuit, Power and Computing Technologies (ICCPCT)","volume":"2014 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132783401","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 : 2016-03-18DOI: 10.1109/ICCPCT.2016.7530298
Vijayakumar Gali, P. Amrutha
In this paper, a SEPIC converter designed for Photovoltaic water pumping system. This type of model avoids use of extra converter and use of battery which reduces the cost of whole system. The Solar water pumping system has becoming more popular in recent years. Photovoltaic (PV) cell having non linear P-V characteristics, it varies with changing solar radiation. Maximum power point tracking (MPPT) algorithms are used to track the peak power point, which helps to improve the efficiency of the system. The MPPT algorithms are incorporated with DC-DC converter which helps to track the MPP of PV cell. The Advantage of SEPIC converter is reduce the ripple at the output stage and also gives the same polarity as input polarity, which feeds the DC motor, so that the motor runs smoothly without any jerking moments, therefore life the DC motor will be increased. The proposed system is tested with different insolation conditions by changing the solar radiation and observed the DC motor characteristics. The P&O algorithm is used to track the MPP point according to changes in solar insolation and tested using MATLAB SIMULINK model and observed all the results.
{"title":"Fast dynamic response of SEPIC converter based photovoltaic DC motor drive for water pumping system","authors":"Vijayakumar Gali, P. Amrutha","doi":"10.1109/ICCPCT.2016.7530298","DOIUrl":"https://doi.org/10.1109/ICCPCT.2016.7530298","url":null,"abstract":"In this paper, a SEPIC converter designed for Photovoltaic water pumping system. This type of model avoids use of extra converter and use of battery which reduces the cost of whole system. The Solar water pumping system has becoming more popular in recent years. Photovoltaic (PV) cell having non linear P-V characteristics, it varies with changing solar radiation. Maximum power point tracking (MPPT) algorithms are used to track the peak power point, which helps to improve the efficiency of the system. The MPPT algorithms are incorporated with DC-DC converter which helps to track the MPP of PV cell. The Advantage of SEPIC converter is reduce the ripple at the output stage and also gives the same polarity as input polarity, which feeds the DC motor, so that the motor runs smoothly without any jerking moments, therefore life the DC motor will be increased. The proposed system is tested with different insolation conditions by changing the solar radiation and observed the DC motor characteristics. The P&O algorithm is used to track the MPP point according to changes in solar insolation and tested using MATLAB SIMULINK model and observed all the results.","PeriodicalId":431894,"journal":{"name":"2016 International Conference on Circuit, Power and Computing Technologies (ICCPCT)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117334499","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 : 2016-03-18DOI: 10.1109/ICCPCT.2016.7530240
S. Ahmed, K. Patil
Medical images are complicated to analyze in terms of digitalization. Breast cancer detection technique for telemedical approach in telemammography services for rural Indian women is been proposed in this paper. The output of the technique is to dynamically generate the report on input samples, the algorithm involves segmentation, and image enhancement of the samples for better processing followed by image analyzer for generating a summarized value of the input samples and thus is compared with threshold value for estimation of breast cancer level and report generation.
{"title":"Novel breast cancer detection technique for TMS-India with dynamic analysis approach","authors":"S. Ahmed, K. Patil","doi":"10.1109/ICCPCT.2016.7530240","DOIUrl":"https://doi.org/10.1109/ICCPCT.2016.7530240","url":null,"abstract":"Medical images are complicated to analyze in terms of digitalization. Breast cancer detection technique for telemedical approach in telemammography services for rural Indian women is been proposed in this paper. The output of the technique is to dynamically generate the report on input samples, the algorithm involves segmentation, and image enhancement of the samples for better processing followed by image analyzer for generating a summarized value of the input samples and thus is compared with threshold value for estimation of breast cancer level and report generation.","PeriodicalId":431894,"journal":{"name":"2016 International Conference on Circuit, Power and Computing Technologies (ICCPCT)","volume":"142 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116327145","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 : 2016-03-18DOI: 10.1109/ICCPCT.2016.7530352
L. Balaji, V. Raj, R. Raghavendran, S. Raj, G. Akash
High Efficiency Video Coding (HEVC) is an ongoing standard, which is an extension of H.264/AVC which is the latest coding standard. In HEVC encoder an exhaustive search method is employed to select the best mode for each macro block which consumes more encoding time. Rate and Distortion tradeoff attained for encoding each macroblock introduces more computation complexity. Although, HEVC has better coding efficiency, in regard to AVC it has more number of macroblock modes to identify the best mode. In this paper, a fast mode intra prediction algorithm to predict the best mode for each macro block based on distortion variance is proposed. The distortion variance finds the integer pixel difference between the current macroblock and the reference macroblock. The experimental result shows that the proposed algorithm achieves better encoding time when compared with HM reference model without a drastic increment in bit rate and PSNR or degradation.
高效视频编码(High Efficiency Video Coding, HEVC)是一个正在发展的标准，它是对H.264/AVC这一最新编码标准的扩展。HEVC编码器采用穷举搜索方法为每个宏块选择最优模式，节省了大量的编码时间。为编码每个宏块而获得的速率和失真权衡引入了更多的计算复杂度。虽然HEVC具有更好的编码效率，但相对于AVC而言，HEVC有更多的宏块模式来识别最佳模式。本文提出了一种基于失真方差预测宏块最佳模式的快速模式内预测算法。畸变方差查找当前宏块和参考宏块之间的整数像素差。实验结果表明，与HM参考模型相比，该算法的编码时间更长，且比特率和PSNR没有显著增加或下降。
{"title":"Fast intra mode prediction for HEVC based on distortion variance","authors":"L. Balaji, V. Raj, R. Raghavendran, S. Raj, G. Akash","doi":"10.1109/ICCPCT.2016.7530352","DOIUrl":"https://doi.org/10.1109/ICCPCT.2016.7530352","url":null,"abstract":"High Efficiency Video Coding (HEVC) is an ongoing standard, which is an extension of H.264/AVC which is the latest coding standard. In HEVC encoder an exhaustive search method is employed to select the best mode for each macro block which consumes more encoding time. Rate and Distortion tradeoff attained for encoding each macroblock introduces more computation complexity. Although, HEVC has better coding efficiency, in regard to AVC it has more number of macroblock modes to identify the best mode. In this paper, a fast mode intra prediction algorithm to predict the best mode for each macro block based on distortion variance is proposed. The distortion variance finds the integer pixel difference between the current macroblock and the reference macroblock. The experimental result shows that the proposed algorithm achieves better encoding time when compared with HM reference model without a drastic increment in bit rate and PSNR or degradation.","PeriodicalId":431894,"journal":{"name":"2016 International Conference on Circuit, Power and Computing Technologies (ICCPCT)","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114719259","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 : 2016-03-18DOI: 10.1109/ICCPCT.2016.7530285
C. Sai, V. Datta, Sudheera
This paper describes a design and implementation of a smart infrared (IR) remote control which can be used for various home appliances. The entire system is based on microcontroller that makes the control system smarter and easy to modify. It enables the user to operate a T.V, Air Conditioner and other Home appliances from about 10 meters away. This Smart remote control can incorporate all infrared remote controls in the room or office into ones smart phone based on Android Platform. By downloading the android app one can configure their remotes into the smart remote app and control them from his/her smart phone to eliminate the need to have half a dozen controllers spread out across their home or office.
{"title":"Design of a Smart remote","authors":"C. Sai, V. Datta, Sudheera","doi":"10.1109/ICCPCT.2016.7530285","DOIUrl":"https://doi.org/10.1109/ICCPCT.2016.7530285","url":null,"abstract":"This paper describes a design and implementation of a smart infrared (IR) remote control which can be used for various home appliances. The entire system is based on microcontroller that makes the control system smarter and easy to modify. It enables the user to operate a T.V, Air Conditioner and other Home appliances from about 10 meters away. This Smart remote control can incorporate all infrared remote controls in the room or office into ones smart phone based on Android Platform. By downloading the android app one can configure their remotes into the smart remote app and control them from his/her smart phone to eliminate the need to have half a dozen controllers spread out across their home or office.","PeriodicalId":431894,"journal":{"name":"2016 International Conference on Circuit, Power and Computing Technologies (ICCPCT)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115074481","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 : 2016-03-18DOI: 10.1109/ICCPCT.2016.7530326
M. Manoj, L. Suresh
The acquisition of Positron Emission Tomography (PET) images for tumor and lesion detection has emerged as one of the most powerful tools for medical image analysis in recent years. In this paper, a novel technique to obtain multimodality aspect of tumor and lesion detection in PET images through Automated Multimodal Spectral Cluster based Segmentation (AMSCS) is proposed, aiming at improving the tumor detection accuracy. The Spectral Contours with Constrained Threshold (SCCT) technique in AMSCS is carried out to various spectral features of the PET image without any deformation, improving the true positive rate. The SCCT technique utilize user defined seed point in the region of interest in PET images and generate spectral contours (i.e.,) shape, size, location and intensity. A Multi-Spectral Contour Cluster (MSCC) mechanism is introduced that organizes the spectral contour features of shape, size, location and intensity into multi-spectral clusters for quicker segmentation of PET Image regions of interest. Experimental analysis is conducted using Primary Tumor Data Set from UCI repository PET Images on parametric such as, Multi-spectral cluster size, ROI segmentation time, tumor and lesion detection time, tumor detection accuracy.
近年来，获取用于肿瘤和病变检测的正电子发射断层扫描(PET)图像已成为医学图像分析最强大的工具之一。为了提高PET图像的肿瘤检测精度，提出了一种基于自动多模态谱聚类分割(Automated Multimodal Spectral Cluster based Segmentation, AMSCS)的肿瘤多模态检测方法。AMSCS中的约束阈值光谱轮廓(SCCT)技术对PET图像的各种光谱特征进行不变形处理，提高了真阳性率。SCCT技术利用用户在PET图像中感兴趣的区域定义的种子点，并生成光谱轮廓(即)形状、大小、位置和强度。介绍了一种多光谱轮廓聚类(MSCC)机制，该机制将光谱轮廓的形状、大小、位置和强度等特征组织成多光谱聚类，以更快地分割PET图像感兴趣的区域。利用UCI存储库PET图像中的原发肿瘤数据集，对多光谱聚类大小、ROI分割时间、肿瘤及病变检测时间、肿瘤检测准确率等参数进行实验分析。
{"title":"An automated multimodal spectral cluster based segmentation for tumor and lesion detection in PET images","authors":"M. Manoj, L. Suresh","doi":"10.1109/ICCPCT.2016.7530326","DOIUrl":"https://doi.org/10.1109/ICCPCT.2016.7530326","url":null,"abstract":"The acquisition of Positron Emission Tomography (PET) images for tumor and lesion detection has emerged as one of the most powerful tools for medical image analysis in recent years. In this paper, a novel technique to obtain multimodality aspect of tumor and lesion detection in PET images through Automated Multimodal Spectral Cluster based Segmentation (AMSCS) is proposed, aiming at improving the tumor detection accuracy. The Spectral Contours with Constrained Threshold (SCCT) technique in AMSCS is carried out to various spectral features of the PET image without any deformation, improving the true positive rate. The SCCT technique utilize user defined seed point in the region of interest in PET images and generate spectral contours (i.e.,) shape, size, location and intensity. A Multi-Spectral Contour Cluster (MSCC) mechanism is introduced that organizes the spectral contour features of shape, size, location and intensity into multi-spectral clusters for quicker segmentation of PET Image regions of interest. Experimental analysis is conducted using Primary Tumor Data Set from UCI repository PET Images on parametric such as, Multi-spectral cluster size, ROI segmentation time, tumor and lesion detection time, tumor detection accuracy.","PeriodicalId":431894,"journal":{"name":"2016 International Conference on Circuit, Power and Computing Technologies (ICCPCT)","volume":"97 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114777256","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 : 2016-03-18DOI: 10.1109/ICCPCT.2016.7530156
D. A. A. G. Singh, A. Fernando, E. Leavline
Software fault detection is the process of analyzing the software for identifying the errors before it is being deployed to the customer. The classifier is employed to perform the software fault detection. Therefore, the accuracy of the software fault detection highly depends on the classifier which is employed in fault detection. Developing the classifier with irrelevant and redundant features of the error-prone data deteriorates the accuracy in software fault detect. Therefore, the feature selection process is employed to remove the redundant and irrelevant features from the error-prone data to improve the accuracy in the software fault detection. Hence, this paper presents an experimental study on the performance of the feature selection methods namely gain ratio (GR), Info gain (IG), OneR, ReliefF, and symmetric uncertainty (SU) to develop the highly accurate classifier for improving the accuracy in software fault detection.
{"title":"Experimental study on feature selection methods for software fault detection","authors":"D. A. A. G. Singh, A. Fernando, E. Leavline","doi":"10.1109/ICCPCT.2016.7530156","DOIUrl":"https://doi.org/10.1109/ICCPCT.2016.7530156","url":null,"abstract":"Software fault detection is the process of analyzing the software for identifying the errors before it is being deployed to the customer. The classifier is employed to perform the software fault detection. Therefore, the accuracy of the software fault detection highly depends on the classifier which is employed in fault detection. Developing the classifier with irrelevant and redundant features of the error-prone data deteriorates the accuracy in software fault detect. Therefore, the feature selection process is employed to remove the redundant and irrelevant features from the error-prone data to improve the accuracy in the software fault detection. Hence, this paper presents an experimental study on the performance of the feature selection methods namely gain ratio (GR), Info gain (IG), OneR, ReliefF, and symmetric uncertainty (SU) to develop the highly accurate classifier for improving the accuracy in software fault detection.","PeriodicalId":431894,"journal":{"name":"2016 International Conference on Circuit, Power and Computing Technologies (ICCPCT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123696082","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 : 2016-03-18DOI: 10.1109/ICCPCT.2016.7530282
A. George, V. J. Pillai
Vehicle number plate recognition (VNPR) is a technique used to extract the license plate from a sequence of images. The extracted information in the database can be used in the applications like electronic payment systems such as toll payment, parking lots etc. An effective VNPR can be implemented based on the quality of the acquired images. It is used for real time application and it has to recognize the number plates of all types under different environmental conditions. Different algorithms has been used which depends on the features present in the images. It should be generalised to extract different types of license plate from the images. In this paper we propose a new method which is robust enough to recognize the characters from the number plates with help of artificial neural network. This algorithm is practical for the front view and rear view of orientation of the vehicle.
{"title":"VNPR system using artificial neural network","authors":"A. George, V. J. Pillai","doi":"10.1109/ICCPCT.2016.7530282","DOIUrl":"https://doi.org/10.1109/ICCPCT.2016.7530282","url":null,"abstract":"Vehicle number plate recognition (VNPR) is a technique used to extract the license plate from a sequence of images. The extracted information in the database can be used in the applications like electronic payment systems such as toll payment, parking lots etc. An effective VNPR can be implemented based on the quality of the acquired images. It is used for real time application and it has to recognize the number plates of all types under different environmental conditions. Different algorithms has been used which depends on the features present in the images. It should be generalised to extract different types of license plate from the images. In this paper we propose a new method which is robust enough to recognize the characters from the number plates with help of artificial neural network. This algorithm is practical for the front view and rear view of orientation of the vehicle.","PeriodicalId":431894,"journal":{"name":"2016 International Conference on Circuit, Power and Computing Technologies (ICCPCT)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114680874","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：