Pub Date : 2018-07-01DOI: 10.1109/ICSCAN.2018.8541208
P. Saha
A moderatley doped pocket is implemented in the substrate of an N-MOSFET. Three dimensional simulation modelling of the device has been carried out such that the W/L ratio can be varied. Input output characteristics of the device is obtianed from the simulation which follows the characteristics of the conventional MOSFET. In order to perfrom analysis and comparison the device designed with different channel length ranging from 20nm to 40nm, width of the device is varied from 22nm to 2um. Device characteristics are also obtained for the device with different dimension by keeping the W/L ratio constant and variable. It has been observed that for constant W/L ratio the drain current remains almost constant and for different W/L ratio the drain current changes with the same fraction as that of W/L ratio. On Being comparing the results with the conventional one this modified MOSFET gives better results in terms of both input and output characteristics. Leakage current analysis signifies that modified drain characteristics has a narrower slope.
{"title":"Three Dimensional Design and Implementation of Doped-Pocket Substrate in N-MOSFET","authors":"P. Saha","doi":"10.1109/ICSCAN.2018.8541208","DOIUrl":"https://doi.org/10.1109/ICSCAN.2018.8541208","url":null,"abstract":"A moderatley doped pocket is implemented in the substrate of an N-MOSFET. Three dimensional simulation modelling of the device has been carried out such that the W/L ratio can be varied. Input output characteristics of the device is obtianed from the simulation which follows the characteristics of the conventional MOSFET. In order to perfrom analysis and comparison the device designed with different channel length ranging from 20nm to 40nm, width of the device is varied from 22nm to 2um. Device characteristics are also obtained for the device with different dimension by keeping the W/L ratio constant and variable. It has been observed that for constant W/L ratio the drain current remains almost constant and for different W/L ratio the drain current changes with the same fraction as that of W/L ratio. On Being comparing the results with the conventional one this modified MOSFET gives better results in terms of both input and output characteristics. Leakage current analysis signifies that modified drain characteristics has a narrower slope.","PeriodicalId":378798,"journal":{"name":"2018 IEEE International Conference on System, Computation, Automation and Networking (ICSCA)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122998192","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 : 2018-07-01DOI: 10.1109/ICSCAN.2018.8541177
P. Mallikarjun, Dr. Y. S. Kumarswamy
Power transfer is expected to be major physical design concern in Three Dimension ICs due to higher energy density and package asymmetries. Three Dimension integrated circuits promise high bandwidth, low latency energy and a small form factor. To improve Three Dimension energy transfer different methods have been used in this paper. Analyzed the influence such as ThSV granularity, ThSV size, and spacing of controlled collapse chip connection (C4) and also dedicated energy transfer ThSVs. Investigated typical cylindrical or square metal filled ThSVs (Core ThSVs) for energy transfer. Three Dimension evaluation system is composed of quad internal chip multiprocessor, a memory cast and ACCL and it is evaluated using representative some SPEC bench marks traces. It is the detailed architectural level study of for Three Dimension energy transfer. Also this paper focuses on low energy and low skew timer interconnected points design and study of for ThSV based Three Dimension stacked silicon chip’s. Developed Three Dimension abstract tree generation based on the 3Dimensional method of means and medians (Three Dimension-MnM) method to determine the optimal count of ThSV’s to be used in the Three Dimension timer tree so that the overall energy dissipation is minimized. Provided the set of rules for Three Dimension energy transfer design and also the mathematical and statistical study of for energy transfer interconnected points of Three Dimension ICs.
{"title":"Analysis of Power Transfer Modeling for Three Dimension silicon chip’s using ThSV Technologies","authors":"P. Mallikarjun, Dr. Y. S. Kumarswamy","doi":"10.1109/ICSCAN.2018.8541177","DOIUrl":"https://doi.org/10.1109/ICSCAN.2018.8541177","url":null,"abstract":"Power transfer is expected to be major physical design concern in Three Dimension ICs due to higher energy density and package asymmetries. Three Dimension integrated circuits promise high bandwidth, low latency energy and a small form factor. To improve Three Dimension energy transfer different methods have been used in this paper. Analyzed the influence such as ThSV granularity, ThSV size, and spacing of controlled collapse chip connection (C4) and also dedicated energy transfer ThSVs. Investigated typical cylindrical or square metal filled ThSVs (Core ThSVs) for energy transfer. Three Dimension evaluation system is composed of quad internal chip multiprocessor, a memory cast and ACCL and it is evaluated using representative some SPEC bench marks traces. It is the detailed architectural level study of for Three Dimension energy transfer. Also this paper focuses on low energy and low skew timer interconnected points design and study of for ThSV based Three Dimension stacked silicon chip’s. Developed Three Dimension abstract tree generation based on the 3Dimensional method of means and medians (Three Dimension-MnM) method to determine the optimal count of ThSV’s to be used in the Three Dimension timer tree so that the overall energy dissipation is minimized. Provided the set of rules for Three Dimension energy transfer design and also the mathematical and statistical study of for energy transfer interconnected points of Three Dimension ICs.","PeriodicalId":378798,"journal":{"name":"2018 IEEE International Conference on System, Computation, Automation and Networking (ICSCA)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128689522","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 : 2018-07-01DOI: 10.1109/ICSCAN.2018.8541187
K. Joshitha, T. Jayalakshmi, R. Bhavani, S. Preethibala
The fastening of the communication is due to the blessing of electronic gadgets like smartphones and evolving data connectivity. The challenge that is faced is the energy drain of these gadgets that makes it mandatory to charge them multiple times a day. Any system that is capable of performing this task without the user’s knowledge and effort would really be a boon to the society. The proposed work aims at charging the gadgets using light beam. A new approach called auto-charge is used. The Auto-charge approach is based on two steps. First, we leverage solar charging technique but use it in indoor spaces, to remotely charge a smartphone using a light beam without a wire. Second, we employ an image processing based technique to detect and track smartphones on a desk for automatic smartphone charging. The auto-charge consists of a controller, rotator, light and camera. The prototype is able to detect the presence of smartphone within seconds and charge it as fast as existing wired chargers. Auto-charge is able to largely reduce the user’s efforts in smartphone charging and keeps the process absolutely user unaware.
{"title":"Automatic Charging of Multiple Smartphones Using Light Beam","authors":"K. Joshitha, T. Jayalakshmi, R. Bhavani, S. Preethibala","doi":"10.1109/ICSCAN.2018.8541187","DOIUrl":"https://doi.org/10.1109/ICSCAN.2018.8541187","url":null,"abstract":"The fastening of the communication is due to the blessing of electronic gadgets like smartphones and evolving data connectivity. The challenge that is faced is the energy drain of these gadgets that makes it mandatory to charge them multiple times a day. Any system that is capable of performing this task without the user’s knowledge and effort would really be a boon to the society. The proposed work aims at charging the gadgets using light beam. A new approach called auto-charge is used. The Auto-charge approach is based on two steps. First, we leverage solar charging technique but use it in indoor spaces, to remotely charge a smartphone using a light beam without a wire. Second, we employ an image processing based technique to detect and track smartphones on a desk for automatic smartphone charging. The auto-charge consists of a controller, rotator, light and camera. The prototype is able to detect the presence of smartphone within seconds and charge it as fast as existing wired chargers. Auto-charge is able to largely reduce the user’s efforts in smartphone charging and keeps the process absolutely user unaware.","PeriodicalId":378798,"journal":{"name":"2018 IEEE International Conference on System, Computation, Automation and Networking (ICSCA)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117019525","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 : 2018-07-01DOI: 10.1109/ICSCAN.2018.8541239
G. Shanmugasundaram, S. Balaji, R. Saravanan, V. Malarselvam, S. Yazhini
Breast cancer is a major public health contention and currently the second leading cause of cancer death in women. Every year more than a million women are diagnosed with breast cancer that results in the demise of more than half of them, due to the delay in diagnosis of the disease. High veracity in cancer prediction is important to revamp the treatment aspect and the survivability standard of patients. Cites from the top ten leading sites of cancer in the human body, in women, breast cancer tops the list with a relative proportion of 32%. Screening involved for breast cancer are Breast Self-Examination and Mammography. The preeminent intent of this survey in medical diagnostics is to comprehend the attributes based on the acceptance level for more accurate prediction. Further the study concentrates on existing approaches or mechanisms used in predicting breast cancer. This article concluded with the various challenges which are not yet addressed.
{"title":"SYSTEMATIC ANALYSIS ON BREAST CANCER PREDICTION","authors":"G. Shanmugasundaram, S. Balaji, R. Saravanan, V. Malarselvam, S. Yazhini","doi":"10.1109/ICSCAN.2018.8541239","DOIUrl":"https://doi.org/10.1109/ICSCAN.2018.8541239","url":null,"abstract":"Breast cancer is a major public health contention and currently the second leading cause of cancer death in women. Every year more than a million women are diagnosed with breast cancer that results in the demise of more than half of them, due to the delay in diagnosis of the disease. High veracity in cancer prediction is important to revamp the treatment aspect and the survivability standard of patients. Cites from the top ten leading sites of cancer in the human body, in women, breast cancer tops the list with a relative proportion of 32%. Screening involved for breast cancer are Breast Self-Examination and Mammography. The preeminent intent of this survey in medical diagnostics is to comprehend the attributes based on the acceptance level for more accurate prediction. Further the study concentrates on existing approaches or mechanisms used in predicting breast cancer. This article concluded with the various challenges which are not yet addressed.","PeriodicalId":378798,"journal":{"name":"2018 IEEE International Conference on System, Computation, Automation and Networking (ICSCA)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117335808","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 : 2018-07-01DOI: 10.1109/ICSCAN.2018.8541142
Pooja Gupta, Dr. Avleen Kaur Malhi
Head and neck cancer detection is performed by collecting 26019 CT scan images from Cancer Imaging Archive (TCIA) as this cancer rapidly increases now a days. This paper mainly focuses on classifier Deep learning framework in h2o that gives better accuracy. At first CT scan image of head and neck cancer is given as input to the system and processed through the image processing technique called weiner filter. Then process the image through the segmentation technique called fuzzy c means algorithm. After that feature extraction technique Gray Level Co-Occurrence Matrix (GLCM) is used to extract the features. These features are given to classifier to train the model and finally it obtains the satisfactory results with 98.8% accuracy.
{"title":"Using deep learning to enhance head and neck cancer diagnosis and classification","authors":"Pooja Gupta, Dr. Avleen Kaur Malhi","doi":"10.1109/ICSCAN.2018.8541142","DOIUrl":"https://doi.org/10.1109/ICSCAN.2018.8541142","url":null,"abstract":"Head and neck cancer detection is performed by collecting 26019 CT scan images from Cancer Imaging Archive (TCIA) as this cancer rapidly increases now a days. This paper mainly focuses on classifier Deep learning framework in h2o that gives better accuracy. At first CT scan image of head and neck cancer is given as input to the system and processed through the image processing technique called weiner filter. Then process the image through the segmentation technique called fuzzy c means algorithm. After that feature extraction technique Gray Level Co-Occurrence Matrix (GLCM) is used to extract the features. These features are given to classifier to train the model and finally it obtains the satisfactory results with 98.8% accuracy.","PeriodicalId":378798,"journal":{"name":"2018 IEEE International Conference on System, Computation, Automation and Networking (ICSCA)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127425041","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 : 2018-07-01DOI: 10.1109/ICSCAN.2018.8541243
S. Shri, S. Jothilakshmi
The Government of India develops the road and transport facilities to reduce traffic congestion in mass gatherings at rush time. Based on the public needs, the video scene detection system provides a video classification technique to analyze the video sequences from various crowd and traffic congestion excellently. This classification technique is most significant in many applications such as video surveillance, traffic control analysis and crowd monitoring. A number of applications for detecting and classifying videos have been proposed in the literature. Scene analysis in the video is a big challenge in many Crowd monitoring and Traffic controlling system. The proposed system presents an automatic video scene detection and analysis method for detecting and classifying crowd and traffic video scenes. Histogram Oriented Gradients (HOG) feature descriptor is extracted features from the video scenes. K Nearest Neighbour (KNN) and Support Vector Machine (SVM) classifiers are used to classify the video scenes. The video scenes are collected from various crowd videos of Tamil Nadu. The experimental results show that KNN with HOG features performs well with 97% accuracy.
{"title":"Video Analysis for Crowd and Traffic Management","authors":"S. Shri, S. Jothilakshmi","doi":"10.1109/ICSCAN.2018.8541243","DOIUrl":"https://doi.org/10.1109/ICSCAN.2018.8541243","url":null,"abstract":"The Government of India develops the road and transport facilities to reduce traffic congestion in mass gatherings at rush time. Based on the public needs, the video scene detection system provides a video classification technique to analyze the video sequences from various crowd and traffic congestion excellently. This classification technique is most significant in many applications such as video surveillance, traffic control analysis and crowd monitoring. A number of applications for detecting and classifying videos have been proposed in the literature. Scene analysis in the video is a big challenge in many Crowd monitoring and Traffic controlling system. The proposed system presents an automatic video scene detection and analysis method for detecting and classifying crowd and traffic video scenes. Histogram Oriented Gradients (HOG) feature descriptor is extracted features from the video scenes. K Nearest Neighbour (KNN) and Support Vector Machine (SVM) classifiers are used to classify the video scenes. The video scenes are collected from various crowd videos of Tamil Nadu. The experimental results show that KNN with HOG features performs well with 97% accuracy.","PeriodicalId":378798,"journal":{"name":"2018 IEEE International Conference on System, Computation, Automation and Networking (ICSCA)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125588963","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 : 2018-07-01DOI: 10.1109/ICSCAN.2018.8541225
Mai Diab, M. El-Habrouk, T. H. Abdelhamid, S. Deghedie
The rapid growth in nonlinear appliances over the past years has increased the power quality problems along the grid. This has called up a continuous research to develop the active power filters. The persistent development has produced numerous applications that have helped in improving the power quality. Although many publications were dedicated to reviewing active power filters, this survey organizes and evaluates the existing reviews to identify the patterns and the new trends in this field. This paper seeks to assemble the existing approaches concerning different aspects of active power filters and their control techniques. This review should be quite beneficial for engineers and researchers who are interested in solving power quality issues using active filters to be able to select the most adequate and preferable technique for their applications.
{"title":"Survey of Active Power Filters Configurations","authors":"Mai Diab, M. El-Habrouk, T. H. Abdelhamid, S. Deghedie","doi":"10.1109/ICSCAN.2018.8541225","DOIUrl":"https://doi.org/10.1109/ICSCAN.2018.8541225","url":null,"abstract":"The rapid growth in nonlinear appliances over the past years has increased the power quality problems along the grid. This has called up a continuous research to develop the active power filters. The persistent development has produced numerous applications that have helped in improving the power quality. Although many publications were dedicated to reviewing active power filters, this survey organizes and evaluates the existing reviews to identify the patterns and the new trends in this field. This paper seeks to assemble the existing approaches concerning different aspects of active power filters and their control techniques. This review should be quite beneficial for engineers and researchers who are interested in solving power quality issues using active filters to be able to select the most adequate and preferable technique for their applications.","PeriodicalId":378798,"journal":{"name":"2018 IEEE International Conference on System, Computation, Automation and Networking (ICSCA)","volume":"34 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123362194","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 : 2018-07-01DOI: 10.1109/ICSCAN.2018.8541262
S. Varsha, V. Rajinikanth, G. A. Prabhu
Image processing field is widely adopted in a variety of domains to examine and extract the vital features. Image multi-thresholding is an essential pre-processing field, widely implemented to pre-process the classical and medical images. In this paper, pre-processing of benchmark gray scale is implemented using the Chaotic Cuckoo Search (CCS) algorithm using the Tsallis entropy value. The experimental investigation is implemented with the Matlab7 software using test images of 512x512 pixels. The performance of CCS is confirmed with the other heuristic methods, such as FA, BA and PSO. The experimental results of this study verify that, implemented CCS tenders enhanced outcome with improved image quality measures and the run time compared with other algorithms adopted in this paper. This work confirms that, chaotic algorithms are better than the conventional approaches.
{"title":"Gray Scale Image Multi-Thresholding with Chaotic Cuckoo Search","authors":"S. Varsha, V. Rajinikanth, G. A. Prabhu","doi":"10.1109/ICSCAN.2018.8541262","DOIUrl":"https://doi.org/10.1109/ICSCAN.2018.8541262","url":null,"abstract":"Image processing field is widely adopted in a variety of domains to examine and extract the vital features. Image multi-thresholding is an essential pre-processing field, widely implemented to pre-process the classical and medical images. In this paper, pre-processing of benchmark gray scale is implemented using the Chaotic Cuckoo Search (CCS) algorithm using the Tsallis entropy value. The experimental investigation is implemented with the Matlab7 software using test images of 512x512 pixels. The performance of CCS is confirmed with the other heuristic methods, such as FA, BA and PSO. The experimental results of this study verify that, implemented CCS tenders enhanced outcome with improved image quality measures and the run time compared with other algorithms adopted in this paper. This work confirms that, chaotic algorithms are better than the conventional approaches.","PeriodicalId":378798,"journal":{"name":"2018 IEEE International Conference on System, Computation, Automation and Networking (ICSCA)","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124412129","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}
Wireless system characterized by multipath fading can be disregarded by Massive multiple input multiple output (MIMO) a promising candidate for enhancing energy efficiency in wireless network. The energy efficiency can be realized by zero forcing (ZF) linear processing scheme for fixed power consumption in the massive MIMO network. The channel is estimated in imperfect channel state information (CSI) with K user equipment and M base station in a symmetric multicell scenario with different reuse pattern across cells. The simulation results prove that ZF inheritance performs optimally and it is compared to that of conventional ZF system.
{"title":"Energy Efficiency in Multicell Massive MIMO network using Zero Forcing technique","authors":"Surender Ragunathan, Sathian Dananjayan, Dananjayan Perumal","doi":"10.1109/ICSCAN.2018.8541250","DOIUrl":"https://doi.org/10.1109/ICSCAN.2018.8541250","url":null,"abstract":"Wireless system characterized by multipath fading can be disregarded by Massive multiple input multiple output (MIMO) a promising candidate for enhancing energy efficiency in wireless network. The energy efficiency can be realized by zero forcing (ZF) linear processing scheme for fixed power consumption in the massive MIMO network. The channel is estimated in imperfect channel state information (CSI) with K user equipment and M base station in a symmetric multicell scenario with different reuse pattern across cells. The simulation results prove that ZF inheritance performs optimally and it is compared to that of conventional ZF system.","PeriodicalId":378798,"journal":{"name":"2018 IEEE International Conference on System, Computation, Automation and Networking (ICSCA)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123677839","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 : 2018-07-01DOI: 10.1109/ICSCAN.2018.8541228
Vijayalakshmi Ramasamy, Urvashi Desai, Hakam W. Alomari, J. Kiper
Clustering similar entities in relational tables is an open challenge to the research community due to the representation of transactional data as tables where the relationships between two or more entities are difficult to represent. This paper uses a graph-based modeling approach called Transaction Pattern Graph Miner (TP-GraphMiner) to identify clusters based on the similarities of the attributes in the transactions. It explores a socio-centric analysis that aims at educational decision-making processes such as identifying the relative engagement of female and male students in the coursework, the similarities of their interaction patterns, similar clusters of entities base on the attributes in the transactions, and the outliers - the entities with divergent interests. The empirical results of this initial investigation have revealed the following: while the rate of enrollment of female students in STEM courses is much lower than that of male students, the clustering results reveals greater active participation of the female students in computer programming courses and their prominent engagement in knowledge sharing and answering their peers’ questions.
{"title":"TP-GraphMiner: A Clustering Framework for Task-Based Information Networks","authors":"Vijayalakshmi Ramasamy, Urvashi Desai, Hakam W. Alomari, J. Kiper","doi":"10.1109/ICSCAN.2018.8541228","DOIUrl":"https://doi.org/10.1109/ICSCAN.2018.8541228","url":null,"abstract":"Clustering similar entities in relational tables is an open challenge to the research community due to the representation of transactional data as tables where the relationships between two or more entities are difficult to represent. This paper uses a graph-based modeling approach called Transaction Pattern Graph Miner (TP-GraphMiner) to identify clusters based on the similarities of the attributes in the transactions. It explores a socio-centric analysis that aims at educational decision-making processes such as identifying the relative engagement of female and male students in the coursework, the similarities of their interaction patterns, similar clusters of entities base on the attributes in the transactions, and the outliers - the entities with divergent interests. The empirical results of this initial investigation have revealed the following: while the rate of enrollment of female students in STEM courses is much lower than that of male students, the clustering results reveals greater active participation of the female students in computer programming courses and their prominent engagement in knowledge sharing and answering their peers’ questions.","PeriodicalId":378798,"journal":{"name":"2018 IEEE International Conference on System, Computation, Automation and Networking (ICSCA)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123708361","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：