Pub Date : 2021-11-19DOI: 10.1109/DISCOVER52564.2021.9663573
Harshavardhan Govulakonda, C. Venkatesh
Analysis of 17-level modified H-Bridge multilevel inverter is performed and presented in this paper. The number of components is limited to reduce the total number of components per levels factor, and DC sources are held in the circuit in such a way as to decrease the maximum voltage on the switches. In addition, PWM techniques such as level shifted carrier PWM and ANDed PWM is used to decrease the THD. Thus, parameters deciding the efficiency of the multilevel inverter are improved and simulation results are presented. Finally, analysis of a three-phase H-Bridge MLI connected to squirrel cage induction motor is performed to validate its performance for industrial applications. Parameters deciding the efficiency of multilevel inverter such as maximum voltage rating on the switches, THD, and total number of components per levels factor are addressed with a solution. Performance of the inverter are presented and compared with other topologies to justify 17-level modified Hbridge MLI performance.
本文对17电平改进型h桥多电平逆变器进行了分析。元件的数量受到限制，以减少每个电平因子的元件总数，并且直流电源以这样一种方式保持在电路中，以降低开关上的最大电压。此外，还采用了电平移位载波PWM和and - and PWM等PWM技术来降低THD。对决定多电平逆变器效率的参数进行了改进，并给出了仿真结果。最后，对连接鼠笼式感应电动机的三相h桥MLI进行了分析，以验证其在工业应用中的性能。给出了决定多电平逆变器效率的参数，如开关的最大额定电压、THD和每电平因子的总元件数。介绍了逆变器的性能，并与其他拓扑结构进行了比较，以验证17级改进Hbridge MLI的性能。
{"title":"A Comprehensive Analysis of 17-level Modified H-Bridge Multilevel Inverter","authors":"Harshavardhan Govulakonda, C. Venkatesh","doi":"10.1109/DISCOVER52564.2021.9663573","DOIUrl":"https://doi.org/10.1109/DISCOVER52564.2021.9663573","url":null,"abstract":"Analysis of 17-level modified H-Bridge multilevel inverter is performed and presented in this paper. The number of components is limited to reduce the total number of components per levels factor, and DC sources are held in the circuit in such a way as to decrease the maximum voltage on the switches. In addition, PWM techniques such as level shifted carrier PWM and ANDed PWM is used to decrease the THD. Thus, parameters deciding the efficiency of the multilevel inverter are improved and simulation results are presented. Finally, analysis of a three-phase H-Bridge MLI connected to squirrel cage induction motor is performed to validate its performance for industrial applications. Parameters deciding the efficiency of multilevel inverter such as maximum voltage rating on the switches, THD, and total number of components per levels factor are addressed with a solution. Performance of the inverter are presented and compared with other topologies to justify 17-level modified Hbridge MLI performance.","PeriodicalId":413789,"journal":{"name":"2021 IEEE International Conference on Distributed Computing, VLSI, Electrical Circuits and Robotics (DISCOVER)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128038086","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 : 2021-11-19DOI: 10.1109/DISCOVER52564.2021.9663708
Akshata, B. Deeksha, Mahima Dev, S. B. Rudraswamy, Varshitha L
Wearable devices have many applications in the healthcare sector. Various wearables like smart watch help to constantly monitor various parameters like body temperature, heart rate, calories burnt, etc. Recently, wearables are being integrated with a variety of sensors to monitor a wide range of parameters. One such wearable is a mask which can be embedded with various sensors for monitoring various parameters.. This paper aims to design a mask with sensors embedded in it which can help to monitor various parameters and be connected to an app on the user’s mobile. The app itself has various other features to monitor social distancing, detect face masks, track the number of steps, chatbot and many more.
{"title":"Design and Development of E-Care for Covid-19","authors":"Akshata, B. Deeksha, Mahima Dev, S. B. Rudraswamy, Varshitha L","doi":"10.1109/DISCOVER52564.2021.9663708","DOIUrl":"https://doi.org/10.1109/DISCOVER52564.2021.9663708","url":null,"abstract":"Wearable devices have many applications in the healthcare sector. Various wearables like smart watch help to constantly monitor various parameters like body temperature, heart rate, calories burnt, etc. Recently, wearables are being integrated with a variety of sensors to monitor a wide range of parameters. One such wearable is a mask which can be embedded with various sensors for monitoring various parameters.. This paper aims to design a mask with sensors embedded in it which can help to monitor various parameters and be connected to an app on the user’s mobile. The app itself has various other features to monitor social distancing, detect face masks, track the number of steps, chatbot and many more.","PeriodicalId":413789,"journal":{"name":"2021 IEEE International Conference on Distributed Computing, VLSI, Electrical Circuits and Robotics (DISCOVER)","volume":"68 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132759671","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 : 2021-11-19DOI: 10.1109/DISCOVER52564.2021.9663608
C. Sagana, P. Keerthika, R. Manjula Devi, M. Sangeetha, R. Abhilash, M. Dinesh Kumar, M. Hariharasudhan
One of the biggest problems that visually Impaired (VI) individuals face in their daily lives is object detection and recognition. A model is created for an object detector that can detect items for VI persons and other important uses by recognizing them at a specific distance. Existing object detection algorithms necessitate a huge amount of training data, which takes longer time, more complicated, and it is a difficult process. As a result, a computer vision notion for converting an object to text was developed using the Caffemodel framework by importing a pretrained dataset model. The Mobilenet SSD method is then used to translate the texts into speech. On a single screen, this system can detect many objects. It aids visually challenged people in detecting objects in real time. This technology can also be put into any portable gadget to assist visually impaired people to recognize items at a certain distance.
{"title":"Object Recognition System for Visually Impaired People","authors":"C. Sagana, P. Keerthika, R. Manjula Devi, M. Sangeetha, R. Abhilash, M. Dinesh Kumar, M. Hariharasudhan","doi":"10.1109/DISCOVER52564.2021.9663608","DOIUrl":"https://doi.org/10.1109/DISCOVER52564.2021.9663608","url":null,"abstract":"One of the biggest problems that visually Impaired (VI) individuals face in their daily lives is object detection and recognition. A model is created for an object detector that can detect items for VI persons and other important uses by recognizing them at a specific distance. Existing object detection algorithms necessitate a huge amount of training data, which takes longer time, more complicated, and it is a difficult process. As a result, a computer vision notion for converting an object to text was developed using the Caffemodel framework by importing a pretrained dataset model. The Mobilenet SSD method is then used to translate the texts into speech. On a single screen, this system can detect many objects. It aids visually challenged people in detecting objects in real time. This technology can also be put into any portable gadget to assist visually impaired people to recognize items at a certain distance.","PeriodicalId":413789,"journal":{"name":"2021 IEEE International Conference on Distributed Computing, VLSI, Electrical Circuits and Robotics (DISCOVER)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134117906","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 : 2021-11-19DOI: 10.1109/DISCOVER52564.2021.9663625
S. Thakur, R. K. Barai
Design of a controller for joint trajectory tracking for two-link flexible manipulator (TLFM) in presence of vibration, model uncertainty and external disturbance is a challenging task. To deal with these problems, in this work Sliding Mode Controller (SMC) has been designed. Equivalent viscous damping coefficient (EVDC) has been considered as model uncertainty. Mathematical model of TLFM has been derived using Lumped parameter method. Closed loop stability of the system has been verified using Lyapunov method. EVDC has been varied to show the robustness of the designed controller. Simulation results show that, the tracking performance of the designed controller is satisfactory and better than Proportional Derivative Controller (PDC).
{"title":"Joint Trajectory Tracking of Two- link Flexible Manipulator in Presence of Matched Uncertainty","authors":"S. Thakur, R. K. Barai","doi":"10.1109/DISCOVER52564.2021.9663625","DOIUrl":"https://doi.org/10.1109/DISCOVER52564.2021.9663625","url":null,"abstract":"Design of a controller for joint trajectory tracking for two-link flexible manipulator (TLFM) in presence of vibration, model uncertainty and external disturbance is a challenging task. To deal with these problems, in this work Sliding Mode Controller (SMC) has been designed. Equivalent viscous damping coefficient (EVDC) has been considered as model uncertainty. Mathematical model of TLFM has been derived using Lumped parameter method. Closed loop stability of the system has been verified using Lyapunov method. EVDC has been varied to show the robustness of the designed controller. Simulation results show that, the tracking performance of the designed controller is satisfactory and better than Proportional Derivative Controller (PDC).","PeriodicalId":413789,"journal":{"name":"2021 IEEE International Conference on Distributed Computing, VLSI, Electrical Circuits and Robotics (DISCOVER)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115443510","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 : 2021-11-19DOI: 10.1109/DISCOVER52564.2021.9663628
S. Anusha, Bommidi Shivanath Nikhil, K. Manoj, Kirti S. Pande
The semiconductor industry is expanding swiftly and the demand for memory and faster access of memory is increasing. The data stability and energy usage are the basic requirements of cache memory in embedded processors that uses SRAM. The SRAM cell parameters that require scrutiny at lower supply voltages are data stability, leakage current and delay. In order to ameliorate the stability further and lower the substrate (junction) leakage current in comparison to the existing SRAM cells, the MTCMOS ST SRAM cell is introduced in this paper. The proposed MTCMOS ST SRAM cell uses HVT and LVT MOSFETs that helps in reduction of the average power consumption by subsiding the leakage current. The proposed MTCMOS ST SRAM cell is implemented, analysed, verified and compared to the existing SRAM cells using Cadence Virtuoso with a channel length of 45 nm at a power supply of 500 mV. In proposed MTCMOS ST SRAM cell, i) read stability RSVNM is increased by 5.89%, 5.72% and 4.74% ii) write stability WTV is increased by 4.16%, 4.16% and 5.05% iii) hold stability HSNM is increased by 0.24% iv) power consumption is decreased by 58.87%, 3.164% and 66.49% in comparison to conventional 6T, existing 8T and existing 9T SRAM cell respectively v) overall read path leakage current is reduced by 94.83% and 87.420%, when compared with existing 8T and existing 9T SRAM cell respectively.
半导体产业正在迅速发展，对存储器和更快存取存储器的需求也在增加。数据稳定性和能耗是采用SRAM的嵌入式处理器对高速缓存的基本要求。在较低的电源电压下，需要仔细检查的SRAM单元参数是数据稳定性、泄漏电流和延迟。为了进一步提高SRAM电池的稳定性，降低衬底(结)漏电流，本文介绍了MTCMOS ST SRAM电池。所提出的MTCMOS ST SRAM单元使用HVT和LVT mosfet，通过降低泄漏电流有助于降低平均功耗。使用Cadence Virtuoso实现、分析、验证了所提出的MTCMOS ST SRAM单元，并将其与现有的SRAM单元进行了比较，该SRAM单元的通道长度为45 nm，电源为500 mV。在提出MTCMOS圣SRAM单元,我)读稳定RSVNM是增长了5.89%,5.72%和4.74%(二)写稳定WTV是增长了4.16%,4.16%和5.05% iii)持有稳定HSNM增加了0.24%(四)能耗下降了58.87%,3.164%和66.49%相比传统6 t,现有8 t和现有9 SRAM t细胞分别v)整体阅读路径漏电流降低94.83%和87.420%,相比与现有8 t和现有9分别SRAM t细胞。
{"title":"MTCMOS 8T SRAM Cell with Improved Stability and Reduced Power Consumption","authors":"S. Anusha, Bommidi Shivanath Nikhil, K. Manoj, Kirti S. Pande","doi":"10.1109/DISCOVER52564.2021.9663628","DOIUrl":"https://doi.org/10.1109/DISCOVER52564.2021.9663628","url":null,"abstract":"The semiconductor industry is expanding swiftly and the demand for memory and faster access of memory is increasing. The data stability and energy usage are the basic requirements of cache memory in embedded processors that uses SRAM. The SRAM cell parameters that require scrutiny at lower supply voltages are data stability, leakage current and delay. In order to ameliorate the stability further and lower the substrate (junction) leakage current in comparison to the existing SRAM cells, the MTCMOS ST SRAM cell is introduced in this paper. The proposed MTCMOS ST SRAM cell uses HVT and LVT MOSFETs that helps in reduction of the average power consumption by subsiding the leakage current. The proposed MTCMOS ST SRAM cell is implemented, analysed, verified and compared to the existing SRAM cells using Cadence Virtuoso with a channel length of 45 nm at a power supply of 500 mV. In proposed MTCMOS ST SRAM cell, i) read stability RSVNM is increased by 5.89%, 5.72% and 4.74% ii) write stability WTV is increased by 4.16%, 4.16% and 5.05% iii) hold stability HSNM is increased by 0.24% iv) power consumption is decreased by 58.87%, 3.164% and 66.49% in comparison to conventional 6T, existing 8T and existing 9T SRAM cell respectively v) overall read path leakage current is reduced by 94.83% and 87.420%, when compared with existing 8T and existing 9T SRAM cell respectively.","PeriodicalId":413789,"journal":{"name":"2021 IEEE International Conference on Distributed Computing, VLSI, Electrical Circuits and Robotics (DISCOVER)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126107978","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 : 2021-11-19DOI: 10.1109/DISCOVER52564.2021.9663619
D. Bharadwaj, P. Anirvinnan, B. S. Premanada
Cryptographic key generation is an important part of the secured communication system where the key that is generated has a major role to play in the strength of the security of the data that is transferred. To enhance the necessary strength of the key, the random number generated has to be highly secure. This is enhanced by the use of a True Random Number Generation. Diffused Bit Generator (DBG) is an entropy source which is used to produce a sequence of random bits. It is composed of a Linear Feedback Shift Register (LFSR) and a Cellular Automata in order to increase the randomness emanating from the DBG. The proposed LFSR has been designed using TSPC based D flip-flops and the XOR gates consisting of 6 transistors, which has enabled to fulfil the objective of low power. The circuit implementation has been done in Cadence Virtuoso in the CMOS 180 nm technology and simulated in Cadence Spectre. The supply voltage used was 1.8 V and the circuits were simulated for the frequencies ranging from 100 MHz to 1 GHz and the proposed DBG was found to consume lesser power when compared to the existing architectures.
{"title":"A Low Power Diffused Bit Generator as a TRNG for Cryptographic Key Generation","authors":"D. Bharadwaj, P. Anirvinnan, B. S. Premanada","doi":"10.1109/DISCOVER52564.2021.9663619","DOIUrl":"https://doi.org/10.1109/DISCOVER52564.2021.9663619","url":null,"abstract":"Cryptographic key generation is an important part of the secured communication system where the key that is generated has a major role to play in the strength of the security of the data that is transferred. To enhance the necessary strength of the key, the random number generated has to be highly secure. This is enhanced by the use of a True Random Number Generation. Diffused Bit Generator (DBG) is an entropy source which is used to produce a sequence of random bits. It is composed of a Linear Feedback Shift Register (LFSR) and a Cellular Automata in order to increase the randomness emanating from the DBG. The proposed LFSR has been designed using TSPC based D flip-flops and the XOR gates consisting of 6 transistors, which has enabled to fulfil the objective of low power. The circuit implementation has been done in Cadence Virtuoso in the CMOS 180 nm technology and simulated in Cadence Spectre. The supply voltage used was 1.8 V and the circuits were simulated for the frequencies ranging from 100 MHz to 1 GHz and the proposed DBG was found to consume lesser power when compared to the existing architectures.","PeriodicalId":413789,"journal":{"name":"2021 IEEE International Conference on Distributed Computing, VLSI, Electrical Circuits and Robotics (DISCOVER)","volume":"100 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133789809","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 : 2021-11-19DOI: 10.1109/DISCOVER52564.2021.9663710
Keerthi Shetty, CV Aravinda
Clustering of data is a standard way used for analyzing the data in several applications such as, data mining, image analysis, pattern recognition, etc. The weighted K-means clustering is one amongst the various data mining techniques used for clustering of the data. The key advantages of weighted k-means clustering are efficient in managing huge amount of data, easy to implement, scalable, simple and easily modifiable. In contrast, the major disadvantage of weighted K-means clustering is the problem with choosing the initial centroids. This clustering technique chooses the initial centroids randomly that leads to a local optimum solution. To address this concern, an effective naturally-inspired optimization algorithm: fire-fly optimization is combined with weighted k-means clustering for obtaining the global optimum solution. In this research paper, weighted k-means clustering along with fire-fly optimization algorithm was developed for enhancing the performance of information sharing and searching efficiency among the population. Here, the proposed system was experimented on dissimilar medical datasets such as, heart disease (original), heart disease (stat-log), liver disease and Indian liver patients. In the practical study, the proposed method enhances the performance up to 0.02-0.4 (label value) as compared to the existing systems by using the concept of precision, recall, and FB-cubed.
{"title":"An Effective Data Clustering System using Weighted K-Means and Firefly Optimization Algorithms","authors":"Keerthi Shetty, CV Aravinda","doi":"10.1109/DISCOVER52564.2021.9663710","DOIUrl":"https://doi.org/10.1109/DISCOVER52564.2021.9663710","url":null,"abstract":"Clustering of data is a standard way used for analyzing the data in several applications such as, data mining, image analysis, pattern recognition, etc. The weighted K-means clustering is one amongst the various data mining techniques used for clustering of the data. The key advantages of weighted k-means clustering are efficient in managing huge amount of data, easy to implement, scalable, simple and easily modifiable. In contrast, the major disadvantage of weighted K-means clustering is the problem with choosing the initial centroids. This clustering technique chooses the initial centroids randomly that leads to a local optimum solution. To address this concern, an effective naturally-inspired optimization algorithm: fire-fly optimization is combined with weighted k-means clustering for obtaining the global optimum solution. In this research paper, weighted k-means clustering along with fire-fly optimization algorithm was developed for enhancing the performance of information sharing and searching efficiency among the population. Here, the proposed system was experimented on dissimilar medical datasets such as, heart disease (original), heart disease (stat-log), liver disease and Indian liver patients. In the practical study, the proposed method enhances the performance up to 0.02-0.4 (label value) as compared to the existing systems by using the concept of precision, recall, and FB-cubed.","PeriodicalId":413789,"journal":{"name":"2021 IEEE International Conference on Distributed Computing, VLSI, Electrical Circuits and Robotics (DISCOVER)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116987322","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 : 2021-11-19DOI: 10.1109/DISCOVER52564.2021.9663651
Praatibh Surana, Mirza Yusuf, Sanjay Singh
The use of social media has drastically gone up over the last decade. With this comes more opportunity and also more problems. There is a rise in the number of mental health-related issues, and it is to some extent possible to detect such cases via user posts and tweets (in our case). Previous research has focused on classifying mental health diseases such as depression, bipolar disorder, schizophrenia, etc., from already filtered data. However, not much has been done to filter out tweets that might be sarcastic, which are generally misclassified, or tweets that might not be intended in a harmful way and, in general, classify tweets based on their severity with regards to mental health. This paper uses multiple models to classify tweets based on their severity and classify them into three classes that help determine whether they help people with mental conditions or sarcasm. We use famous neural network architectures such as Bidirectional LSTMs, GRUs, and a custom HYBRID model to carry out the classification. The models could detect sarcasm in tweets and identify tweets that were helpful despite having words like “depression” and “anxiety.” We obtained F1 scores of 74% on completely unseen data, which is a good starting point considering the limited available data. This paper should serve as a utility for future research in this area and act as a primary data collection and segregation filter.
{"title":"Severity Classification of Mental Health Related Tweets","authors":"Praatibh Surana, Mirza Yusuf, Sanjay Singh","doi":"10.1109/DISCOVER52564.2021.9663651","DOIUrl":"https://doi.org/10.1109/DISCOVER52564.2021.9663651","url":null,"abstract":"The use of social media has drastically gone up over the last decade. With this comes more opportunity and also more problems. There is a rise in the number of mental health-related issues, and it is to some extent possible to detect such cases via user posts and tweets (in our case). Previous research has focused on classifying mental health diseases such as depression, bipolar disorder, schizophrenia, etc., from already filtered data. However, not much has been done to filter out tweets that might be sarcastic, which are generally misclassified, or tweets that might not be intended in a harmful way and, in general, classify tweets based on their severity with regards to mental health. This paper uses multiple models to classify tweets based on their severity and classify them into three classes that help determine whether they help people with mental conditions or sarcasm. We use famous neural network architectures such as Bidirectional LSTMs, GRUs, and a custom HYBRID model to carry out the classification. The models could detect sarcasm in tweets and identify tweets that were helpful despite having words like “depression” and “anxiety.” We obtained F1 scores of 74% on completely unseen data, which is a good starting point considering the limited available data. This paper should serve as a utility for future research in this area and act as a primary data collection and segregation filter.","PeriodicalId":413789,"journal":{"name":"2021 IEEE International Conference on Distributed Computing, VLSI, Electrical Circuits and Robotics (DISCOVER)","volume":"504 1-2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131931777","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 : 2021-11-19DOI: 10.1109/DISCOVER52564.2021.9663662
B. Spoorthi, Shwetha S. Kumar, Anisha P. Rodrigues, Roshan Fernandes, N. Balaji
Nowadays, there are numerous risks identified with the banking sector regarding giving loans to the clients and for the individuals who get the loan. The examination of risk in bank credits needs to understand what is the reason for this risk. Likewise, the quantity of exchanges in the financial area is quickly developing and information volumes are accessible which address the client’s conduct, and the risk of giving loans are expanded. The objective of this paper is to discover the nature or details of the clients who are applying for the loan. This paper proposes a comparative study of three machine learning models, namely, Random Forest, Naive Bayes (Gaussian model, Multinomial model, and Bernoulli Model), and Support Vector Machine (Linear kernel, Gaussian RBF kernel, and Polynomial kernel), to predict whether a customer may get a loan or not. In this paper, we analyze the evaluation parameters, namely, classification accuracy, precision, recall, and F1-Score for these machine learning models to foresee which model is best suitable for predicting a loan.
{"title":"Comparative Analysis of Bank Loan Defaulter Prediction Using Machine Learning Techniques","authors":"B. Spoorthi, Shwetha S. Kumar, Anisha P. Rodrigues, Roshan Fernandes, N. Balaji","doi":"10.1109/DISCOVER52564.2021.9663662","DOIUrl":"https://doi.org/10.1109/DISCOVER52564.2021.9663662","url":null,"abstract":"Nowadays, there are numerous risks identified with the banking sector regarding giving loans to the clients and for the individuals who get the loan. The examination of risk in bank credits needs to understand what is the reason for this risk. Likewise, the quantity of exchanges in the financial area is quickly developing and information volumes are accessible which address the client’s conduct, and the risk of giving loans are expanded. The objective of this paper is to discover the nature or details of the clients who are applying for the loan. This paper proposes a comparative study of three machine learning models, namely, Random Forest, Naive Bayes (Gaussian model, Multinomial model, and Bernoulli Model), and Support Vector Machine (Linear kernel, Gaussian RBF kernel, and Polynomial kernel), to predict whether a customer may get a loan or not. In this paper, we analyze the evaluation parameters, namely, classification accuracy, precision, recall, and F1-Score for these machine learning models to foresee which model is best suitable for predicting a loan.","PeriodicalId":413789,"journal":{"name":"2021 IEEE International Conference on Distributed Computing, VLSI, Electrical Circuits and Robotics (DISCOVER)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132153325","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：