Pub Date : 2022-06-24DOI: 10.1109/CONIT55038.2022.9847788
Kanimozhi. T, Sheeja K. Lalitha
In this paper., defected ground structure (DGS) implemented microstrip patch filtering antenna is presented. Here, slotted annular ring resonators along with strip which is capacitance loaded are used as a radiating element. To obtain the filtering characteristics., the presented patch antenna is incorporated with ring shaped DGS in the ground plane. The proposed filtenna resonates at 15.4GHz., which falls under Ku-band. The physical structural size of the proposed filtenna is 2.465AgX 1.667AgX 0.116Ag in terms of guided wavelength. The presented filtenna carries the bandwidth of 1580 MHz at 15.4GHz. The change in the width of the ring structure of the proposed DGS results in different resonating frequencies with different return losses. The presented filtenna structures are placed over FR4 substrate.
{"title":"Defected Ground Structure Implementation for Slotted Annular Ring Microstrip Filtenna","authors":"Kanimozhi. T, Sheeja K. Lalitha","doi":"10.1109/CONIT55038.2022.9847788","DOIUrl":"https://doi.org/10.1109/CONIT55038.2022.9847788","url":null,"abstract":"In this paper., defected ground structure (DGS) implemented microstrip patch filtering antenna is presented. Here, slotted annular ring resonators along with strip which is capacitance loaded are used as a radiating element. To obtain the filtering characteristics., the presented patch antenna is incorporated with ring shaped DGS in the ground plane. The proposed filtenna resonates at 15.4GHz., which falls under Ku-band. The physical structural size of the proposed filtenna is 2.465AgX 1.667AgX 0.116Ag in terms of guided wavelength. The presented filtenna carries the bandwidth of 1580 MHz at 15.4GHz. The change in the width of the ring structure of the proposed DGS results in different resonating frequencies with different return losses. The presented filtenna structures are placed over FR4 substrate.","PeriodicalId":270445,"journal":{"name":"2022 2nd International Conference on Intelligent Technologies (CONIT)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123564454","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 : 2022-06-24DOI: 10.1109/CONIT55038.2022.9847896
Swapnil V. Potdar, S. Kawar
Rechargeable batteries are the elements designed to hold the charge and produce the power when connected to the load. The batteries are manufactured using active materials like lead acid, nickel cadmium and various other materials. Such batteries when connected to the load, produces output power using electrochemical oxidation-reduction reaction process. The rechargeable batteries once connected to the load, discharges and then can be recharged again many times to hold the charge and use them in run time. In due course of time, to run the battery elements for longer duration of time, top notched researches are carried out. Through the present research paper, a detailed literature survey is carried out to demonstrate the diverse possibilities considered for prolonging the discharge of the rechargeable batteries.
{"title":"Synthesis and Analysis of Cathode Material for Lithium Batteries: An Eagle Eye","authors":"Swapnil V. Potdar, S. Kawar","doi":"10.1109/CONIT55038.2022.9847896","DOIUrl":"https://doi.org/10.1109/CONIT55038.2022.9847896","url":null,"abstract":"Rechargeable batteries are the elements designed to hold the charge and produce the power when connected to the load. The batteries are manufactured using active materials like lead acid, nickel cadmium and various other materials. Such batteries when connected to the load, produces output power using electrochemical oxidation-reduction reaction process. The rechargeable batteries once connected to the load, discharges and then can be recharged again many times to hold the charge and use them in run time. In due course of time, to run the battery elements for longer duration of time, top notched researches are carried out. Through the present research paper, a detailed literature survey is carried out to demonstrate the diverse possibilities considered for prolonging the discharge of the rechargeable batteries.","PeriodicalId":270445,"journal":{"name":"2022 2nd International Conference on Intelligent Technologies (CONIT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129769075","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 : 2022-06-24DOI: 10.1109/CONIT55038.2022.9847733
Hardik Pahuja, Jatinderkumar R. Saini, K. Kotecha, Rajnish M. Rakholia, Jinal Tailor
e-learning has become an important part of the education system. This is more so in wake of the COVID-19 pandemic. There are a wide range of e-learning platforms available online and offering courses ranging from beginner to advanced levels. Such courses are accessible to nearly everyone around the world who has access to the internet. The readers and learners look for engaging content which will enhance their knowledge and skills in the respective field through e-learning. In order to provide the learners with effective learning, the content should be readable and easy to understand. The motives of the present study are multifold. The presented results will be helpful to the designers as well as creators of e-learning courses in maximizing the learner's attention span, content comprehension, ease of understanding and engagement with the e-course. To the best of our knowledge, this is first formal attempt for the analysis of the transcripts of the e-learning courses. Technically, we deploy five readability indices namely Flesch Readability Index (FRI), Gunning Fog Index (GFI), Flesch-Kincaid Grade Level (FKGL), Coleman-Liau Index (CLI), and Automated Readability Index (ARI) for the study. The calculations have been additionally fortified using Term Frequency-Inverse Document Frequency (TF-IDF). More than 1200 transcripts have been analyzed and vital statistics presented. It is concluded that the transcripts for the beginners should have a word range of 600- 900 while that for the intermediate and advanced learners should have an optimum word count value of around 1050.
{"title":"A Novel Analysis of Readability Indices of MOOC Transcripts for e-Learner Retainment","authors":"Hardik Pahuja, Jatinderkumar R. Saini, K. Kotecha, Rajnish M. Rakholia, Jinal Tailor","doi":"10.1109/CONIT55038.2022.9847733","DOIUrl":"https://doi.org/10.1109/CONIT55038.2022.9847733","url":null,"abstract":"e-learning has become an important part of the education system. This is more so in wake of the COVID-19 pandemic. There are a wide range of e-learning platforms available online and offering courses ranging from beginner to advanced levels. Such courses are accessible to nearly everyone around the world who has access to the internet. The readers and learners look for engaging content which will enhance their knowledge and skills in the respective field through e-learning. In order to provide the learners with effective learning, the content should be readable and easy to understand. The motives of the present study are multifold. The presented results will be helpful to the designers as well as creators of e-learning courses in maximizing the learner's attention span, content comprehension, ease of understanding and engagement with the e-course. To the best of our knowledge, this is first formal attempt for the analysis of the transcripts of the e-learning courses. Technically, we deploy five readability indices namely Flesch Readability Index (FRI), Gunning Fog Index (GFI), Flesch-Kincaid Grade Level (FKGL), Coleman-Liau Index (CLI), and Automated Readability Index (ARI) for the study. The calculations have been additionally fortified using Term Frequency-Inverse Document Frequency (TF-IDF). More than 1200 transcripts have been analyzed and vital statistics presented. It is concluded that the transcripts for the beginners should have a word range of 600- 900 while that for the intermediate and advanced learners should have an optimum word count value of around 1050.","PeriodicalId":270445,"journal":{"name":"2022 2nd International Conference on Intelligent Technologies (CONIT)","volume":"94 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127068822","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 : 2022-06-24DOI: 10.1109/CONIT55038.2022.9848410
K. Vennela, Balaji B, M. Chinnaiah, K. Srinivasarao
Grid based navigation is the simplest navigation methodology for unmanned ground vehicles (UGV) particularly for indoors. The grid map formation, grid cell occupancy, self-localization and avoiding obstacles in derived path are major considerations in navigation. This research work elaborate a new strategy of mobile robot navigation to goal point using an Adaptive Backpropagation tree based algorithm. For a confined stopping point like a charging station for an autonomous vehicles, this work provide minimal solution to reach that point. The path exploration begin from the stop point rather than the start point where robot is located. This backpropagation strategy implemented in real time scenario for its effectiveness. The simulation and experimental results gives the scope for robotic applications such as advance to stationary parking point or charging point.
{"title":"Adaptive Backpropagation Algorithm for Clustered Indoor Motion Planning","authors":"K. Vennela, Balaji B, M. Chinnaiah, K. Srinivasarao","doi":"10.1109/CONIT55038.2022.9848410","DOIUrl":"https://doi.org/10.1109/CONIT55038.2022.9848410","url":null,"abstract":"Grid based navigation is the simplest navigation methodology for unmanned ground vehicles (UGV) particularly for indoors. The grid map formation, grid cell occupancy, self-localization and avoiding obstacles in derived path are major considerations in navigation. This research work elaborate a new strategy of mobile robot navigation to goal point using an Adaptive Backpropagation tree based algorithm. For a confined stopping point like a charging station for an autonomous vehicles, this work provide minimal solution to reach that point. The path exploration begin from the stop point rather than the start point where robot is located. This backpropagation strategy implemented in real time scenario for its effectiveness. The simulation and experimental results gives the scope for robotic applications such as advance to stationary parking point or charging point.","PeriodicalId":270445,"journal":{"name":"2022 2nd International Conference on Intelligent Technologies (CONIT)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127315917","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 : 2022-06-24DOI: 10.1109/CONIT55038.2022.9848198
Akshata Baloolad, R. Manjunath, Prince Kumar, S. Kareemulla, K. Sreelakshmi
RF (Radio frequency) Filters realized, based on printed circuit techniques are becoming more popular, due to their simplicity, compactness, ease of fabrication and low cost. However they have their own limitations with respect to the performance, like high insertion loss and low attenuation figures. In this paper a practical methodology for the design, simulation and analysis of a stepped impedance low pass filter, realized based on printed circuit technology for X band operation (10GHz) is presented. Higher stop band attenuation values warrants higher order filter (more number of sections). With the increase in frequency band more and more problems are encountered with regarded optimization of the frequency response of the filters. Many simulation iterations are required to achieve the desired results by striking a balance between the numbers of sections, pass band insertion loss, pass band ripple and stop band attenuation figures. This article presents different aspects to be considered for the realization of an X band stepped impedance Low pass filter (LPF) at 10 GHz band.
{"title":"Design, Simulation and Analysis of Stepped Impedance Micro-Strip Low Pass Filter for 10GHz band","authors":"Akshata Baloolad, R. Manjunath, Prince Kumar, S. Kareemulla, K. Sreelakshmi","doi":"10.1109/CONIT55038.2022.9848198","DOIUrl":"https://doi.org/10.1109/CONIT55038.2022.9848198","url":null,"abstract":"RF (Radio frequency) Filters realized, based on printed circuit techniques are becoming more popular, due to their simplicity, compactness, ease of fabrication and low cost. However they have their own limitations with respect to the performance, like high insertion loss and low attenuation figures. In this paper a practical methodology for the design, simulation and analysis of a stepped impedance low pass filter, realized based on printed circuit technology for X band operation (10GHz) is presented. Higher stop band attenuation values warrants higher order filter (more number of sections). With the increase in frequency band more and more problems are encountered with regarded optimization of the frequency response of the filters. Many simulation iterations are required to achieve the desired results by striking a balance between the numbers of sections, pass band insertion loss, pass band ripple and stop band attenuation figures. This article presents different aspects to be considered for the realization of an X band stepped impedance Low pass filter (LPF) at 10 GHz band.","PeriodicalId":270445,"journal":{"name":"2022 2nd International Conference on Intelligent Technologies (CONIT)","volume":"2012 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127399943","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 : 2022-06-24DOI: 10.1109/CONIT55038.2022.9848390
Angela Infanta Ramesh, Ayush Raghuwanshi, Eshan Goel, Dakshayani G
One of the greatest emerging sectors in marketing which has expanded rapidly over the last decade is the E-Commerce platform that makes the process of purchasing products online quite convenient and easy for the end-users. Especially when it comes to the farmers who at times have to travel long distances to buy seeds and agricultural products in a traditional market scene only to be exploited and being taken advantage of by their unawareness about the actual seed/crop prices. With an E-Commerce site stepping up in this scenario, it not only reduces the time and efforts spent but also entrusts the crop/seed quality. Therefore, we aim to build a fully-fledged Electronic Commerce website for the farmers based on a Direct-to-Consumer marketing strategy where we aim to eliminate the need for retailers and have direct interaction with the customers without services being warped by the intermediaries. This would help the manufacturers to directly address the ‘pain points' of the farmers as well as reduce the prices of products as per their needs. This project also aims in building an aesthetic web application, specially designed for farmers by embedding customized recommendations for purchasing seeds and other customer services for easier communication with the manufacturers.
{"title":"An E-store for Farmers Buying Seeds","authors":"Angela Infanta Ramesh, Ayush Raghuwanshi, Eshan Goel, Dakshayani G","doi":"10.1109/CONIT55038.2022.9848390","DOIUrl":"https://doi.org/10.1109/CONIT55038.2022.9848390","url":null,"abstract":"One of the greatest emerging sectors in marketing which has expanded rapidly over the last decade is the E-Commerce platform that makes the process of purchasing products online quite convenient and easy for the end-users. Especially when it comes to the farmers who at times have to travel long distances to buy seeds and agricultural products in a traditional market scene only to be exploited and being taken advantage of by their unawareness about the actual seed/crop prices. With an E-Commerce site stepping up in this scenario, it not only reduces the time and efforts spent but also entrusts the crop/seed quality. Therefore, we aim to build a fully-fledged Electronic Commerce website for the farmers based on a Direct-to-Consumer marketing strategy where we aim to eliminate the need for retailers and have direct interaction with the customers without services being warped by the intermediaries. This would help the manufacturers to directly address the ‘pain points' of the farmers as well as reduce the prices of products as per their needs. This project also aims in building an aesthetic web application, specially designed for farmers by embedding customized recommendations for purchasing seeds and other customer services for easier communication with the manufacturers.","PeriodicalId":270445,"journal":{"name":"2022 2nd International Conference on Intelligent Technologies (CONIT)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127193240","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 : 2022-06-24DOI: 10.1109/CONIT55038.2022.9848326
S. Sasikumar, S. Prabha, V. Adithya Sai, K.V. Mohan Reddy
Now a days Machine Learning Methods are doing an excellent job at analysing and preventing damage before it occurs., however the models developed are only intended to be used in the applications for which they were designed. We are attempting to build an application in order to tackle this issue by combining several models to work together. This is an application that seems to have forecasts about a disease based on symptoms., weather., and admission analysis by utilising a chatbot. To analyse and process user instructions NLP Techniques are used so that the given commands may provide the necessary result. The main goal is to combine multiple machine Learning models and develop a Chatbot that can access the properties of the combined model. We conducted a thorough review of recent literature in this work. We looked at a lot of papers over the previous years that were about chatbots. Then we discussed many relevant efforts as well as the AI ideas required to create an intelligent conversational agent based on Machine Learning and deep learning models. Finally., we provided a functional architecture for developing an intelligent chatbot for Personal Assistance.
{"title":"Personal Aide Application Using A.I Techniques … !","authors":"S. Sasikumar, S. Prabha, V. Adithya Sai, K.V. Mohan Reddy","doi":"10.1109/CONIT55038.2022.9848326","DOIUrl":"https://doi.org/10.1109/CONIT55038.2022.9848326","url":null,"abstract":"Now a days Machine Learning Methods are doing an excellent job at analysing and preventing damage before it occurs., however the models developed are only intended to be used in the applications for which they were designed. We are attempting to build an application in order to tackle this issue by combining several models to work together. This is an application that seems to have forecasts about a disease based on symptoms., weather., and admission analysis by utilising a chatbot. To analyse and process user instructions NLP Techniques are used so that the given commands may provide the necessary result. The main goal is to combine multiple machine Learning models and develop a Chatbot that can access the properties of the combined model. We conducted a thorough review of recent literature in this work. We looked at a lot of papers over the previous years that were about chatbots. Then we discussed many relevant efforts as well as the AI ideas required to create an intelligent conversational agent based on Machine Learning and deep learning models. Finally., we provided a functional architecture for developing an intelligent chatbot for Personal Assistance.","PeriodicalId":270445,"journal":{"name":"2022 2nd International Conference on Intelligent Technologies (CONIT)","volume":"136 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131951474","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 : 2022-06-24DOI: 10.1109/CONIT55038.2022.9848294
T. Keerthi, Apurva Kumari, M. Chinnaiah, P. Asharani, D. Nikitha, C. Manojkumar
In these modern days many techniques have been developed to save agricultural fields, but the present scenario is mainly focusing on organic food products for a healthier life, so it is a challenging task to detect the pests for cultivating organic crops as well as inorganic crops. In this paper two approaches have been developed for detecting the pest, one approach is using thresholding and edge detection through image processing techniques, by utilizing thresholding the presence of pest is identified. It gives the range of pixels for the clear identification of the image. In our work we have considered an average value of 100 pixels. Using the technique of edge Detection, the outline of the pest is determined. The other approach is convolution neural network (CNN) which provides pest detection by three steps, firstly direct wavelet transform (DWT) next neural network detection last is area detection. By using these techniques pest detection is developed.
{"title":"Efficient Detection and Classification of PEST Using Image Thresholding and Edge Detection Technique","authors":"T. Keerthi, Apurva Kumari, M. Chinnaiah, P. Asharani, D. Nikitha, C. Manojkumar","doi":"10.1109/CONIT55038.2022.9848294","DOIUrl":"https://doi.org/10.1109/CONIT55038.2022.9848294","url":null,"abstract":"In these modern days many techniques have been developed to save agricultural fields, but the present scenario is mainly focusing on organic food products for a healthier life, so it is a challenging task to detect the pests for cultivating organic crops as well as inorganic crops. In this paper two approaches have been developed for detecting the pest, one approach is using thresholding and edge detection through image processing techniques, by utilizing thresholding the presence of pest is identified. It gives the range of pixels for the clear identification of the image. In our work we have considered an average value of 100 pixels. Using the technique of edge Detection, the outline of the pest is determined. The other approach is convolution neural network (CNN) which provides pest detection by three steps, firstly direct wavelet transform (DWT) next neural network detection last is area detection. By using these techniques pest detection is developed.","PeriodicalId":270445,"journal":{"name":"2022 2nd International Conference on Intelligent Technologies (CONIT)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130906366","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 : 2022-06-24DOI: 10.1109/CONIT55038.2022.9847886
Pradip Dhal, Chandrashekhar Azad
In Information Retrieval (IR), Text Mining (TM), and web search, Multi-label Text Classification (MTC) plays an essential role. A document can fall into more than one category in MTC. Text documents frequently include High Dimensional (HD) non-discriminative (noisy and irrelevant) phrases, resulting in high computing costs and impoverish learning performance of Text Classification (TC). The Feature Selection (FS) procedure is complicated by three issues caused by small samples and HD datasets. First, given limited samples and HD, FS is unstable. Second, with HD, FS takes longer. Third, a particular FS approach may not provide enough Classification Accuracy (CA). In this paper, we have developed a two-stage FS approach based Meta-heuristics Algorithm (MA) for MTC. The first stage work on the filter-based FS approach, while the second stage is based on the multi-objective Grey Wolf Optimization (GWO) algorithm. The first objective is to diminish the Hamming Loss (HL), and the second objective is to decrease the Selected Features (SF). We have used the Multi-Layer Perceptron (MLP) model for the classification task. The experimental findings show that the suggested FS scheme achieves superior HL with a less number of features.
在信息检索(IR)、文本挖掘(TM)和web搜索中,多标签文本分类(MTC)起着至关重要的作用。在MTC中,一个文档可以属于多个类别。文本文档中经常包含高维(HD)非判别(有噪声和不相关)短语,导致文本分类(TC)的计算成本高,学习性能差。特征选择(FS)过程由于小样本和高清数据集导致的三个问题而复杂化。首先,考虑到有限的样本和HD, FS是不稳定的。其次,使用HD, FS需要更长的时间。第三,特定的FS方法可能无法提供足够的分类精度(CA)。在本文中,我们开发了一个基于两阶段FS方法的MTC元启发式算法(MA)。第一阶段采用基于滤波器的FS方法,第二阶段采用多目标灰狼优化算法。第一个目标是减少Hamming Loss (HL),第二个目标是减少Selected Features (SF)。我们使用多层感知器(MLP)模型进行分类任务。实验结果表明,所提出的FS方案以较少的特征数达到了较好的HL。
{"title":"A multi-stage multi-objective GWO based feature selection approach for multi-label text classification","authors":"Pradip Dhal, Chandrashekhar Azad","doi":"10.1109/CONIT55038.2022.9847886","DOIUrl":"https://doi.org/10.1109/CONIT55038.2022.9847886","url":null,"abstract":"In Information Retrieval (IR), Text Mining (TM), and web search, Multi-label Text Classification (MTC) plays an essential role. A document can fall into more than one category in MTC. Text documents frequently include High Dimensional (HD) non-discriminative (noisy and irrelevant) phrases, resulting in high computing costs and impoverish learning performance of Text Classification (TC). The Feature Selection (FS) procedure is complicated by three issues caused by small samples and HD datasets. First, given limited samples and HD, FS is unstable. Second, with HD, FS takes longer. Third, a particular FS approach may not provide enough Classification Accuracy (CA). In this paper, we have developed a two-stage FS approach based Meta-heuristics Algorithm (MA) for MTC. The first stage work on the filter-based FS approach, while the second stage is based on the multi-objective Grey Wolf Optimization (GWO) algorithm. The first objective is to diminish the Hamming Loss (HL), and the second objective is to decrease the Selected Features (SF). We have used the Multi-Layer Perceptron (MLP) model for the classification task. The experimental findings show that the suggested FS scheme achieves superior HL with a less number of features.","PeriodicalId":270445,"journal":{"name":"2022 2nd International Conference on Intelligent Technologies (CONIT)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126846133","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 : 2022-06-24DOI: 10.1109/CONIT55038.2022.9847980
Pranay Dhongade, Kunwar Singh, Shalini
The discovery of the memristor, also known as the fourth missing element after resistor, inductor and capacitor, has shown emerging growth in nanoscale devices. The properties of non-volatility, small size and low power will be a significant advantage in the upcoming generation of chip design. Flip-Flops are sequential circuits with applications like registers, counters, frequency dividers etc. They can be generated by cascading latch in a master-slave configuration. This paper proposes a design of a D latch cascaded in master-slave configuration for designing a D flip-flop. This paper also compares various methods for designing D latch using the memristor-CMOS hybrid technique and Memristor ratioed logic (MRL). All the simulations were performed on Cadence Virtuoso, VTEAM model for memristor and CMOS 90nm technological file were used.
{"title":"Design and Analysis of Memristor-CMOS Based Hybrid D Latch","authors":"Pranay Dhongade, Kunwar Singh, Shalini","doi":"10.1109/CONIT55038.2022.9847980","DOIUrl":"https://doi.org/10.1109/CONIT55038.2022.9847980","url":null,"abstract":"The discovery of the memristor, also known as the fourth missing element after resistor, inductor and capacitor, has shown emerging growth in nanoscale devices. The properties of non-volatility, small size and low power will be a significant advantage in the upcoming generation of chip design. Flip-Flops are sequential circuits with applications like registers, counters, frequency dividers etc. They can be generated by cascading latch in a master-slave configuration. This paper proposes a design of a D latch cascaded in master-slave configuration for designing a D flip-flop. This paper also compares various methods for designing D latch using the memristor-CMOS hybrid technique and Memristor ratioed logic (MRL). All the simulations were performed on Cadence Virtuoso, VTEAM model for memristor and CMOS 90nm technological file were used.","PeriodicalId":270445,"journal":{"name":"2022 2nd International Conference on Intelligent Technologies (CONIT)","volume":"211 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123242189","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}