Pub Date : 2020-09-05DOI: 10.1109/ICCE50343.2020.9290662
Pratick Ghosh, Devjyoti Saha, Diptangshu De, Sourish Sengupta, Tripti Majumdar
Gender is the most fundamental demographic feature of human beings. Human gender classification using computer vision has become a relevant aspect in a large variety of fields, extending from daily software applications to forensic science, specifically due to the certain surge in consumption of social media and social networking websites. In the past, many attempts have been made for gender classification using conventional models of Convolutional Neural Networks (CNNs) just by mere extraction of features (from the faces only) and classification (CNNs are capable of both). In this paper, we propose a method to classify genders using two different conventional 3-layered CNN models where one uses the facial features and the other uses the palm features of a human for gender classification. This method not only delivers better accuracy than the past single CNN model framework but also achieves the goal of a two-step verification process. We have trained the face model using one publicly available dataset that we have gathered from the online dataset repository Kaggle and we have trained the palm model using another dataset that was constructed by us in consideration of this model. On testing, the proposed framework has shown significant accuracy growth.
{"title":"Automatic Detection of Gender from Face and Palm Images using a 2-CNN Framework","authors":"Pratick Ghosh, Devjyoti Saha, Diptangshu De, Sourish Sengupta, Tripti Majumdar","doi":"10.1109/ICCE50343.2020.9290662","DOIUrl":"https://doi.org/10.1109/ICCE50343.2020.9290662","url":null,"abstract":"Gender is the most fundamental demographic feature of human beings. Human gender classification using computer vision has become a relevant aspect in a large variety of fields, extending from daily software applications to forensic science, specifically due to the certain surge in consumption of social media and social networking websites. In the past, many attempts have been made for gender classification using conventional models of Convolutional Neural Networks (CNNs) just by mere extraction of features (from the faces only) and classification (CNNs are capable of both). In this paper, we propose a method to classify genders using two different conventional 3-layered CNN models where one uses the facial features and the other uses the palm features of a human for gender classification. This method not only delivers better accuracy than the past single CNN model framework but also achieves the goal of a two-step verification process. We have trained the face model using one publicly available dataset that we have gathered from the online dataset repository Kaggle and we have trained the palm model using another dataset that was constructed by us in consideration of this model. On testing, the proposed framework has shown significant accuracy growth.","PeriodicalId":421963,"journal":{"name":"2020 IEEE 1st International Conference for Convergence in Engineering (ICCE)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124391959","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}
The process of image segmentation is very important in the context of image analysis. Segmentation makes it easier to analyze a portion of the image one has to deal with. The application of image segmentation is immense in the areas of machine vision, medical imaging, locating objects in satellite images, object detection, recognition tasks and various other fields of science and engineering. In recent times nature-inspired algorithms are being used for both bi-level and multilevel thresholding based image segmentation. In this paperthe performances of the Grasshopper Optimization Algorithm and the Whale Optimization Algorithm are evaluatedfor image segmentation.The performances of the proposed methods are compared with Cuckoo Search Algorithmalong with Kapur’s entropy criterion.The quality of segmentation is measured by variousimage quality metrices which indicates Whale Optimization as the best performing algorithm.
{"title":"Multilevel Thresholding based Image Segmentation using Optimization Algorithm","authors":"Pratikshan Malakar, Debasmita Ghosh, Kaushik Shaw, Puja Pandey, Shyandeep Das, Supriya Dhabal","doi":"10.1109/ICCE50343.2020.9290582","DOIUrl":"https://doi.org/10.1109/ICCE50343.2020.9290582","url":null,"abstract":"The process of image segmentation is very important in the context of image analysis. Segmentation makes it easier to analyze a portion of the image one has to deal with. The application of image segmentation is immense in the areas of machine vision, medical imaging, locating objects in satellite images, object detection, recognition tasks and various other fields of science and engineering. In recent times nature-inspired algorithms are being used for both bi-level and multilevel thresholding based image segmentation. In this paperthe performances of the Grasshopper Optimization Algorithm and the Whale Optimization Algorithm are evaluatedfor image segmentation.The performances of the proposed methods are compared with Cuckoo Search Algorithmalong with Kapur’s entropy criterion.The quality of segmentation is measured by variousimage quality metrices which indicates Whale Optimization as the best performing algorithm.","PeriodicalId":421963,"journal":{"name":"2020 IEEE 1st International Conference for Convergence in Engineering (ICCE)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125899106","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 : 2020-09-05DOI: 10.1109/ICCE50343.2020.9290597
Kaushik Sengupta, A. K. Mondal, D. Bose, Dilip K. Singh
The concept of Friction Stir Welding (FSW) technique was invented two decades ago, but its utilization has been restricted to low strength material because of the problems of tool wear, weld efficiency and sufficient heat required during the joining process in case of high strength material. Many secondary heat sources have been used for the addition of the heat to the joining process. In this paper, the study of the use of secondary heat sources to Friction Stir Welding has been used to join the high strength material like Mild Steel and Stainless Steel. Both MS and SS material have been joined with each other like MS to MS and MS to SS and the test sample has been tested and analyzed for the characterization of the material joined. The analysis has been done to resolve the problems rose during the joining of the high strength material and focused on the study on increase of the weld efficiency. Special focus on the variation of UTS and hardness has been done to find the effect of an addition of a secondary source of electric current on FSW for joining MS and SS material.
{"title":"Characterization of Electrical Assisted Friction Stir Welded for Joining Similar and Dissimilar Material Plates of Mild Steel and Stainless Steel","authors":"Kaushik Sengupta, A. K. Mondal, D. Bose, Dilip K. Singh","doi":"10.1109/ICCE50343.2020.9290597","DOIUrl":"https://doi.org/10.1109/ICCE50343.2020.9290597","url":null,"abstract":"The concept of Friction Stir Welding (FSW) technique was invented two decades ago, but its utilization has been restricted to low strength material because of the problems of tool wear, weld efficiency and sufficient heat required during the joining process in case of high strength material. Many secondary heat sources have been used for the addition of the heat to the joining process. In this paper, the study of the use of secondary heat sources to Friction Stir Welding has been used to join the high strength material like Mild Steel and Stainless Steel. Both MS and SS material have been joined with each other like MS to MS and MS to SS and the test sample has been tested and analyzed for the characterization of the material joined. The analysis has been done to resolve the problems rose during the joining of the high strength material and focused on the study on increase of the weld efficiency. Special focus on the variation of UTS and hardness has been done to find the effect of an addition of a secondary source of electric current on FSW for joining MS and SS material.","PeriodicalId":421963,"journal":{"name":"2020 IEEE 1st International Conference for Convergence in Engineering (ICCE)","volume":"103 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128396311","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 : 2020-09-05DOI: 10.1109/ICCE50343.2020.9290538
S. Deb, Subir Datta, Ksh. Robert Singh, Ramesh Kumar
Deregulation of electricity market brought several complexities and challenges for Independent System Operator (ISO). The growing electricity demands creates pressure on both generation and transmission sectors to generate and transfer electricity in a more efficient and reliable manner. Due to this load growth, the power transfer through transmission lines reaches beyond of its thermal limit, results in transmission line congestion. Therefore, a necessary step needs to be taken by ISO in order to avoid transmission line congestion. Various methods are available to manage transmission congestion. In this paper, the method generator rescheduling is considered in order to manage transmission line congestion. Firstly, all the generators in the system are chosen to reschedule real power outputs. Secondly, a newly developed population based heuristic algorithm, namely Atom Search Optimization (ASO) is used in order to manage transmission line congestion by formulating proposed optimization problem. The proposed method is tested on IEEE 30 bus test system and rigorous analysis is established to show the efficiency of the proposed work.
{"title":"Real Power Rescheduling of Generator for Transmission Line Congestion Management using Atom Search Algorithm","authors":"S. Deb, Subir Datta, Ksh. Robert Singh, Ramesh Kumar","doi":"10.1109/ICCE50343.2020.9290538","DOIUrl":"https://doi.org/10.1109/ICCE50343.2020.9290538","url":null,"abstract":"Deregulation of electricity market brought several complexities and challenges for Independent System Operator (ISO). The growing electricity demands creates pressure on both generation and transmission sectors to generate and transfer electricity in a more efficient and reliable manner. Due to this load growth, the power transfer through transmission lines reaches beyond of its thermal limit, results in transmission line congestion. Therefore, a necessary step needs to be taken by ISO in order to avoid transmission line congestion. Various methods are available to manage transmission congestion. In this paper, the method generator rescheduling is considered in order to manage transmission line congestion. Firstly, all the generators in the system are chosen to reschedule real power outputs. Secondly, a newly developed population based heuristic algorithm, namely Atom Search Optimization (ASO) is used in order to manage transmission line congestion by formulating proposed optimization problem. The proposed method is tested on IEEE 30 bus test system and rigorous analysis is established to show the efficiency of the proposed work.","PeriodicalId":421963,"journal":{"name":"2020 IEEE 1st International Conference for Convergence in Engineering (ICCE)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132906578","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 : 2020-09-05DOI: 10.1109/icce50343.2020.9290545
{"title":"ICCE 2020 Cover Page","authors":"","doi":"10.1109/icce50343.2020.9290545","DOIUrl":"https://doi.org/10.1109/icce50343.2020.9290545","url":null,"abstract":"","PeriodicalId":421963,"journal":{"name":"2020 IEEE 1st International Conference for Convergence in Engineering (ICCE)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131595404","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 : 2020-09-05DOI: 10.1109/ICCE50343.2020.9290577
Jayanta Ghosh
In today's world, Networking is root of the corporate data communication, it is an extremely necessary thing for connecting the world virtually via e-mail, chat and others services with telnet services. With the evolution, computer networks play very important role to connect, communicate, administrate and provide the information or data from one node to other nodes. Therefore networking is treated as the key of proper functionally in most of the corporate sector. Proper design of network with simulation is essential thing for a network project of company. This paper looks at several real-life interconnection between routers, switches and other components in communication network and provides securities to protect company networks in proper way with better advantages.
{"title":"Corporate Networking With Advance Routing, Switching and Security","authors":"Jayanta Ghosh","doi":"10.1109/ICCE50343.2020.9290577","DOIUrl":"https://doi.org/10.1109/ICCE50343.2020.9290577","url":null,"abstract":"In today's world, Networking is root of the corporate data communication, it is an extremely necessary thing for connecting the world virtually via e-mail, chat and others services with telnet services. With the evolution, computer networks play very important role to connect, communicate, administrate and provide the information or data from one node to other nodes. Therefore networking is treated as the key of proper functionally in most of the corporate sector. Proper design of network with simulation is essential thing for a network project of company. This paper looks at several real-life interconnection between routers, switches and other components in communication network and provides securities to protect company networks in proper way with better advantages.","PeriodicalId":421963,"journal":{"name":"2020 IEEE 1st International Conference for Convergence in Engineering (ICCE)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115408735","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 : 2020-09-05DOI: 10.1109/ICCE50343.2020.9290570
S. Poornima, H. Gajera, S. Chandramma, Koushik Dutta
Rectangular microstrip patch has been designed with defected microstrip surface for the suppression of cross polarized radiations. Very simple linear slot defects have been created over the patch surface without any deviation in resonance frequency. The proposed technique is so simple and easily adapted to any working microstrip patch antenna using standard etching process. Results have been validated experimentally using a set of antenna prototype. Measured results are very close to the simulated data.
{"title":"Design of Rectangular Microstrip Antenna with Defected Patch Surface for Improved Cross-Polarized Radiations","authors":"S. Poornima, H. Gajera, S. Chandramma, Koushik Dutta","doi":"10.1109/ICCE50343.2020.9290570","DOIUrl":"https://doi.org/10.1109/ICCE50343.2020.9290570","url":null,"abstract":"Rectangular microstrip patch has been designed with defected microstrip surface for the suppression of cross polarized radiations. Very simple linear slot defects have been created over the patch surface without any deviation in resonance frequency. The proposed technique is so simple and easily adapted to any working microstrip patch antenna using standard etching process. Results have been validated experimentally using a set of antenna prototype. Measured results are very close to the simulated data.","PeriodicalId":421963,"journal":{"name":"2020 IEEE 1st International Conference for Convergence in Engineering (ICCE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123163862","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 : 2020-09-05DOI: 10.1109/ICCE50343.2020.9290637
S. Patnaik, Saloni Kumari, S. Das Mahapatra
Handwritten Optical Character Recognition is a lush area of research and is used in various real time applications. This research is based on comparative analysis of handwritten OCR by using Deep CNN and ResNet for Devanagari script, a regional language. Devanagari character contains two elements, diacritics and the main grapheme. Key challenge associated with Devanagari script is many a time different characters look similar. Secondly some characters are written differently by different individuals. Proposed ResNet manages vanishing gradient issue and improves capability of traditional Deep CNN. It uses dynamic flow of activation. ResNet identity blocks help in to overcome vanishing gradient issues. Proposed architecture scored close to 99% accuracy for the DHCD, which is better than other state-of-art results. Training phase of proposed model is reasonably less than many other variants of deep CNN.
{"title":"Comparison of deep CNN and ResNet for Handwritten Devanagari Character Recognition","authors":"S. Patnaik, Saloni Kumari, S. Das Mahapatra","doi":"10.1109/ICCE50343.2020.9290637","DOIUrl":"https://doi.org/10.1109/ICCE50343.2020.9290637","url":null,"abstract":"Handwritten Optical Character Recognition is a lush area of research and is used in various real time applications. This research is based on comparative analysis of handwritten OCR by using Deep CNN and ResNet for Devanagari script, a regional language. Devanagari character contains two elements, diacritics and the main grapheme. Key challenge associated with Devanagari script is many a time different characters look similar. Secondly some characters are written differently by different individuals. Proposed ResNet manages vanishing gradient issue and improves capability of traditional Deep CNN. It uses dynamic flow of activation. ResNet identity blocks help in to overcome vanishing gradient issues. Proposed architecture scored close to 99% accuracy for the DHCD, which is better than other state-of-art results. Training phase of proposed model is reasonably less than many other variants of deep CNN.","PeriodicalId":421963,"journal":{"name":"2020 IEEE 1st International Conference for Convergence in Engineering (ICCE)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121433683","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 : 2020-09-05DOI: 10.1109/ICCE50343.2020.9290625
B. Chakraborty, Arijit Mondal, S. Maur, B. Chatterjee, S. Dalai
In this paper mineral oil and vegetable oil have been blended in a certain ratio for preparingfive types of liquid dielectrics in laboratory to investigate their performance as liquid insulation. Then those mixed dielectrics were subjected to time domain dielectric response analysis through PDC measurement. Further from the recorded PDC data, conductivity of each sample has been calculated and compared with the pure mineral oil and vegetable oil. Moreover to realize the temperature effect, PDC data has been recorded in three distinct temperatures. From these data at 25°C, 50°C and 70°C the temperature conductivity dependency of the prepared samples has been investigated. After that activation energy of the prepared samples has been analyzed through PDC measurement using Arrhenius equation.
{"title":"Investigation on Activation Energy and Temperature Conductivity Dependency of Laboratory prepared Mixed Insulation Samples","authors":"B. Chakraborty, Arijit Mondal, S. Maur, B. Chatterjee, S. Dalai","doi":"10.1109/ICCE50343.2020.9290625","DOIUrl":"https://doi.org/10.1109/ICCE50343.2020.9290625","url":null,"abstract":"In this paper mineral oil and vegetable oil have been blended in a certain ratio for preparingfive types of liquid dielectrics in laboratory to investigate their performance as liquid insulation. Then those mixed dielectrics were subjected to time domain dielectric response analysis through PDC measurement. Further from the recorded PDC data, conductivity of each sample has been calculated and compared with the pure mineral oil and vegetable oil. Moreover to realize the temperature effect, PDC data has been recorded in three distinct temperatures. From these data at 25°C, 50°C and 70°C the temperature conductivity dependency of the prepared samples has been investigated. After that activation energy of the prepared samples has been analyzed through PDC measurement using Arrhenius equation.","PeriodicalId":421963,"journal":{"name":"2020 IEEE 1st International Conference for Convergence in Engineering (ICCE)","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134366184","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 : 2020-09-05DOI: 10.1109/ICCE50343.2020.9290502
Biplab Bag, S. Biswas, S. Sarkar, P. Sarkar
A multiband moderate gain monopole antenna with parasitic element has been presented in this paper. Two U-shape strips (radiating patch and parasitic element) are situated in face to face. The volume of the proposed antenna is taken about 50x40x1.6mm3. The length of the U-shaped radiating element and parasitic element together excite multiple modes, which produce multiple resonance frequencies. The resonance frequencies are 1.59GHz, 2.41GHz, 4.29GHz, 5.13GHz, and 7.41GHz. The corresponding -10dB bandwidths are 160MHz, 640MHz, and 5090MHz. The peak gains of the proposed antenna are obtained about 5dBi at 2.4GHz, 4.75dBi at 4.3GHz, 4.6dBi at 5.2GHz, and 7dBi at 7.2GHz. The evolution strategy of the proposed antenna structure is explained in the consecutive section. The measured results are experimentally tested and found good in agreement with simulated results.
{"title":"Multiband Monopole Antenna with Moderate Gain","authors":"Biplab Bag, S. Biswas, S. Sarkar, P. Sarkar","doi":"10.1109/ICCE50343.2020.9290502","DOIUrl":"https://doi.org/10.1109/ICCE50343.2020.9290502","url":null,"abstract":"A multiband moderate gain monopole antenna with parasitic element has been presented in this paper. Two U-shape strips (radiating patch and parasitic element) are situated in face to face. The volume of the proposed antenna is taken about 50x40x1.6mm3. The length of the U-shaped radiating element and parasitic element together excite multiple modes, which produce multiple resonance frequencies. The resonance frequencies are 1.59GHz, 2.41GHz, 4.29GHz, 5.13GHz, and 7.41GHz. The corresponding -10dB bandwidths are 160MHz, 640MHz, and 5090MHz. The peak gains of the proposed antenna are obtained about 5dBi at 2.4GHz, 4.75dBi at 4.3GHz, 4.6dBi at 5.2GHz, and 7dBi at 7.2GHz. The evolution strategy of the proposed antenna structure is explained in the consecutive section. The measured results are experimentally tested and found good in agreement with simulated results.","PeriodicalId":421963,"journal":{"name":"2020 IEEE 1st International Conference for Convergence in Engineering (ICCE)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133662308","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：