Pub Date : 2022-09-01DOI: 10.37394/23201.2022.21.22
G. Fotis, V. Vita
The existing IEC Standard for Electrostatic Discharge (ESD) contains a general and simplified circuit for the generator that produces ESD discharges, without entering into details. The present work tries to fill this gap and proposes a circuit which will generate the ESD current in the limits that the current Standard defines. Two circuit models are examined through simulations with SPICE software, with the one to be the most suitable. This circuit model is also examined for various loads that simulate the Equipment under Test (EUT) and useful conclusions derive up to what type and size of equipment can be safely tested by ESD generators so that the test results are reliable.
{"title":"Circuit Modeling and Simulation of the ESD Generator for Various Tested Equipment According to the IEC 61000-4-2","authors":"G. Fotis, V. Vita","doi":"10.37394/23201.2022.21.22","DOIUrl":"https://doi.org/10.37394/23201.2022.21.22","url":null,"abstract":"The existing IEC Standard for Electrostatic Discharge (ESD) contains a general and simplified circuit for the generator that produces ESD discharges, without entering into details. The present work tries to fill this gap and proposes a circuit which will generate the ESD current in the limits that the current Standard defines. Two circuit models are examined through simulations with SPICE software, with the one to be the most suitable. This circuit model is also examined for various loads that simulate the Equipment under Test (EUT) and useful conclusions derive up to what type and size of equipment can be safely tested by ESD generators so that the test results are reliable.","PeriodicalId":376260,"journal":{"name":"WSEAS TRANSACTIONS ON CIRCUITS AND SYSTEMS","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133031538","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 : 2022-09-01DOI: 10.37394/23201.2022.21.23
V. Tuzlukov
In the present paper, a chip-level minimum mean-square-error (MMSE) decision-feedback equalizer for the downlink receiver of multicode wideband direct sequence code-division multiple access (DS-CDMA) wireless communication systems over frequency-selective channels is investigated. Firstly, the MMSE per sym-bol achievable by an optimal decision-feedback equalizer is derived, assuming that all interchip interference (ICI) of the desired user can be eliminated. The MMSE of the decision-feedback equalizer is always less than or at most equal to that of linear equalizers. When all the active codes belong to the desired user, the ideal deci-sion-feedback equalizer is able to eliminate multicode interference and approach the performance of the single-code case at high signal-to-noise ratio (SNR) range. Secondly, we apply the hypothesis-feedback equalizer or tentative-chip decision-feedback equalizer in the multicode scenario. The tentative-chip decision-feedback equ-alizer outperforms the chip-level linear equalizer and the decision-feedback equalizer that only feeds back the symbols already decided. The performance gain increases with SNR, but decreases with the number of active codes owned by the other users. When all the active codes are assigned to the desired user, the tentative-chip decision-feedback equalizer eliminates the multicode interference and achieves single-user performance at the high SNR, similarly, to the ideal decision-feedback equalizer. The asymptotic performance of the decision-feed-back equalizer is confirmed through the bit error rate (BER) simulation over various channels.
{"title":"Generalized Receiver with Decision-Feedback Equalizer for Multicode Wideband DS-CDMA","authors":"V. Tuzlukov","doi":"10.37394/23201.2022.21.23","DOIUrl":"https://doi.org/10.37394/23201.2022.21.23","url":null,"abstract":"In the present paper, a chip-level minimum mean-square-error (MMSE) decision-feedback equalizer for the downlink receiver of multicode wideband direct sequence code-division multiple access (DS-CDMA) wireless communication systems over frequency-selective channels is investigated. Firstly, the MMSE per sym-bol achievable by an optimal decision-feedback equalizer is derived, assuming that all interchip interference (ICI) of the desired user can be eliminated. The MMSE of the decision-feedback equalizer is always less than or at most equal to that of linear equalizers. When all the active codes belong to the desired user, the ideal deci-sion-feedback equalizer is able to eliminate multicode interference and approach the performance of the single-code case at high signal-to-noise ratio (SNR) range. Secondly, we apply the hypothesis-feedback equalizer or tentative-chip decision-feedback equalizer in the multicode scenario. The tentative-chip decision-feedback equ-alizer outperforms the chip-level linear equalizer and the decision-feedback equalizer that only feeds back the symbols already decided. The performance gain increases with SNR, but decreases with the number of active codes owned by the other users. When all the active codes are assigned to the desired user, the tentative-chip decision-feedback equalizer eliminates the multicode interference and achieves single-user performance at the high SNR, similarly, to the ideal decision-feedback equalizer. The asymptotic performance of the decision-feed-back equalizer is confirmed through the bit error rate (BER) simulation over various channels.","PeriodicalId":376260,"journal":{"name":"WSEAS TRANSACTIONS ON CIRCUITS AND SYSTEMS","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121561618","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 : 2022-08-02DOI: 10.37394/23201.2022.21.19
Karen J. Uribe-Murcia, Jorge A. Ortega-Contreras, Eli Pale-Ramon, Miguel Vazquez-Olguin, Y. Shmaliy
In this article, a comparison of the UFIR and Kalman filter to estimate a tracking vehicle system variables is developed considering two possible observation output models. The time stamp approach and the predictive compensation are used to analyze the problem from multiple perturbations, which produces random delayed data and losses during transmissions. For the estimation, a transformation model and a decorrelation covariance matrices are developed with the aim of assure optimal conditions and minimizing the estimation error. Finally, several real situations, miss modeling, uncertain noise covariances, and uncertain probabilities are proposed to demonstrate the effectiveness and robustness of the filter proposed.
{"title":"Comparison of the Kalman Filter and the Unbiased FIR Filter for Network Systems with Multiples Output Delays and Lost Data","authors":"Karen J. Uribe-Murcia, Jorge A. Ortega-Contreras, Eli Pale-Ramon, Miguel Vazquez-Olguin, Y. Shmaliy","doi":"10.37394/23201.2022.21.19","DOIUrl":"https://doi.org/10.37394/23201.2022.21.19","url":null,"abstract":"In this article, a comparison of the UFIR and Kalman filter to estimate a tracking vehicle system variables is developed considering two possible observation output models. The time stamp approach and the predictive compensation are used to analyze the problem from multiple perturbations, which produces random delayed data and losses during transmissions. For the estimation, a transformation model and a decorrelation covariance matrices are developed with the aim of assure optimal conditions and minimizing the estimation error. Finally, several real situations, miss modeling, uncertain noise covariances, and uncertain probabilities are proposed to demonstrate the effectiveness and robustness of the filter proposed.","PeriodicalId":376260,"journal":{"name":"WSEAS TRANSACTIONS ON CIRCUITS AND SYSTEMS","volume":"81 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129359868","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 : 2022-08-02DOI: 10.37394/23201.2022.21.20
Abdullah Altay, A. Yildiz
The modeling and analysis of permanent-magnet DC motor, whose attractiveness has increased with the availability of high-energy rare earth permanent magnet materials such as SmCo and NdFeB, is very important in recent years. The analysis of the established model is very important for researchers and engineers before siteworks. The most important features of the established model are that the equations are simple to obtain, the model can be set up using a simple platform, and ease of model analysis. Generally, for DC motor models, only the armature circuit model is given and only the equations of the mechanical system are given. In the armature circuit model, equations are obtained by switching to the s-domain, and analyzes are made on highly advanced platforms by using these equations. In this study, electrical equivalents of mechanical equations were obtained and both armature circuit and mechanical parameters of a DC motor were expressed as electrical circuit elements. Although the motor model includes mechanical parameters and variables, the whole model is expressed only with electrical elements and variables. Thus, a complete electrical equivalent circuit is proposed for the dynamic model of the permanent-magnet DC motor, in which both the armature and the mechanical part can be modeled as an electrical circuit. With the analyzes, the performance of the permanent magnet DC motor model was examined and it was seen that the system dynamics responses were compatible.
{"title":"Complete Electrical Equivalent Circuit Based Modeling and Analysis of Permanent Magnet Direct Current (DC) Motors","authors":"Abdullah Altay, A. Yildiz","doi":"10.37394/23201.2022.21.20","DOIUrl":"https://doi.org/10.37394/23201.2022.21.20","url":null,"abstract":"The modeling and analysis of permanent-magnet DC motor, whose attractiveness has increased with the availability of high-energy rare earth permanent magnet materials such as SmCo and NdFeB, is very important in recent years. The analysis of the established model is very important for researchers and engineers before siteworks. The most important features of the established model are that the equations are simple to obtain, the model can be set up using a simple platform, and ease of model analysis. Generally, for DC motor models, only the armature circuit model is given and only the equations of the mechanical system are given. In the armature circuit model, equations are obtained by switching to the s-domain, and analyzes are made on highly advanced platforms by using these equations. In this study, electrical equivalents of mechanical equations were obtained and both armature circuit and mechanical parameters of a DC motor were expressed as electrical circuit elements. Although the motor model includes mechanical parameters and variables, the whole model is expressed only with electrical elements and variables. Thus, a complete electrical equivalent circuit is proposed for the dynamic model of the permanent-magnet DC motor, in which both the armature and the mechanical part can be modeled as an electrical circuit. With the analyzes, the performance of the permanent magnet DC motor model was examined and it was seen that the system dynamics responses were compatible.","PeriodicalId":376260,"journal":{"name":"WSEAS TRANSACTIONS ON CIRCUITS AND SYSTEMS","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133254501","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 : 2022-07-05DOI: 10.37394/23201.2022.21.17
A. Daud, S. Khader
The high static gain modified single ended primary coil (MSEPIC) converter is presented in this paper. The proposed converter presents low switch voltage and high efficiency for low input voltage and high output voltage applications. The configuration of MSEPIC converter is presented and analyzed. Closed loop feedback control with PID controller based on triggering system is developed for MSEPIC converter to maintain constant output voltage. Furthermore, the model is integrated with Photovoltaic generator where the input voltage and current depend on the solar irradiation rates. The proposed model is analyzed and simulated in Matlab/Simulink and m-file code. Simulation model is developed with a maximum power at full sun equal to 315 W, which presents efficiency equal to 99.03%. The PID controller works as intended, as the output voltage can approach the expected value. Furthermore, performance and robustness are tested by load variations and set point variations.
{"title":"Closed Loop Modified SEPIC Converter for Photovoltaic System","authors":"A. Daud, S. Khader","doi":"10.37394/23201.2022.21.17","DOIUrl":"https://doi.org/10.37394/23201.2022.21.17","url":null,"abstract":"The high static gain modified single ended primary coil (MSEPIC) converter is presented in this paper. The proposed converter presents low switch voltage and high efficiency for low input voltage and high output voltage applications. The configuration of MSEPIC converter is presented and analyzed. Closed loop feedback control with PID controller based on triggering system is developed for MSEPIC converter to maintain constant output voltage. Furthermore, the model is integrated with Photovoltaic generator where the input voltage and current depend on the solar irradiation rates. The proposed model is analyzed and simulated in Matlab/Simulink and m-file code. Simulation model is developed with a maximum power at full sun equal to 315 W, which presents efficiency equal to 99.03%. The PID controller works as intended, as the output voltage can approach the expected value. Furthermore, performance and robustness are tested by load variations and set point variations.","PeriodicalId":376260,"journal":{"name":"WSEAS TRANSACTIONS ON CIRCUITS AND SYSTEMS","volume":"96 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129106560","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 : 2022-07-05DOI: 10.37394/23201.2022.21.18
A. Zemliak
The formulation of the process of analog system design has been done on the basis of the control theory application as the problem of a special functional minimization. This approach generalizes the design process and produces the different design trajectories inside the same optimization procedure. Numerical examples show that the potential computer time gain of the optimal design strategy with respect to the traditional design strategy increases when the size and the complexity of the system increase. Some properties of an additional acceleration effect of the design process were analyzed. The special selection of the optimization process start point provides the acceleration effect with a great probability. The positions of the optimal switch points of the control vector were found on the basis of the analysis of the special Lyapunov function of the design process. The combination of the acceleration effect with the start point preliminary selection and the optimal switch points of the control vector serve as the principal ideas to the time-optimal design algorithm construction.
{"title":"On the Structure of a Quasi-Optimal Algorithm for Circuit Designing","authors":"A. Zemliak","doi":"10.37394/23201.2022.21.18","DOIUrl":"https://doi.org/10.37394/23201.2022.21.18","url":null,"abstract":"The formulation of the process of analog system design has been done on the basis of the control theory application as the problem of a special functional minimization. This approach generalizes the design process and produces the different design trajectories inside the same optimization procedure. Numerical examples show that the potential computer time gain of the optimal design strategy with respect to the traditional design strategy increases when the size and the complexity of the system increase. Some properties of an additional acceleration effect of the design process were analyzed. The special selection of the optimization process start point provides the acceleration effect with a great probability. The positions of the optimal switch points of the control vector were found on the basis of the analysis of the special Lyapunov function of the design process. The combination of the acceleration effect with the start point preliminary selection and the optimal switch points of the control vector serve as the principal ideas to the time-optimal design algorithm construction.","PeriodicalId":376260,"journal":{"name":"WSEAS TRANSACTIONS ON CIRCUITS AND SYSTEMS","volume":"142 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116321451","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 : 2022-07-04DOI: 10.37394/23201.2022.21.16
N. Nehaoua, I. Ami, F. Mebtouche, H. Meziani, S. Abaidia
Photovoltaics, which convert directly solar energy into electricity, provide a practical and sustainable solution to the challenge of meeting the increasing global energy demand. Computer simulation is an important tool for investigating solar cell device’s behavior and optimizing their performance. This work develops a new approach to retrieve the five parameters of the single diode equivalent solar cell/module model using the measured current-voltage data and its derivative (G=dI/dV). A nonlinear least-square technique based on the Newton-Raphson method under MATLAB Program is applied to determine the five parameters of the hybrid solar cell including under different temperature.
{"title":"Theoretical Study of Hybrid Solar Cell Parameters Evaluation From I-V Characteristics","authors":"N. Nehaoua, I. Ami, F. Mebtouche, H. Meziani, S. Abaidia","doi":"10.37394/23201.2022.21.16","DOIUrl":"https://doi.org/10.37394/23201.2022.21.16","url":null,"abstract":"Photovoltaics, which convert directly solar energy into electricity, provide a practical and sustainable solution to the challenge of meeting the increasing global energy demand. Computer simulation is an important tool for investigating solar cell device’s behavior and optimizing their performance. This work develops a new approach to retrieve the five parameters of the single diode equivalent solar cell/module model using the measured current-voltage data and its derivative (G=dI/dV). A nonlinear least-square technique based on the Newton-Raphson method under MATLAB Program is applied to determine the five parameters of the hybrid solar cell including under different temperature.","PeriodicalId":376260,"journal":{"name":"WSEAS TRANSACTIONS ON CIRCUITS AND SYSTEMS","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126359431","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 : 2022-07-01DOI: 10.37394/23201.2022.21.14
A. Kostadinov, G. Kouzaev
A variable predicate logic processor (VPLP) is proposed for artificial intelligence (AI), robotics, computer-aided medicine, electronic security, and other applications. The development is realized as an accelerating unit in AI computing machines. The difference from known designs, the datapath of this processor consists of universal gates changing on-the-fly their logical styles-subsets of predicate logic according to the data type and implemented instructions. In this paper, the processor’s reconfigurable gates and the main units are proposed, designed, modeled, and verified using a Field-Programmable Gate Array (FPGA) board and corresponding computer-aided design (CAD) tool. The implemented processor confirmed its reconfigurability on-the-fly performing testing codes. This processor is interesting in accelerating AI computing, molecular and quantum calculations in science, cryptography, computer-aided medicine, robotics, etc.
{"title":"A Novel Processor for Artificial Intelligence Acceleration","authors":"A. Kostadinov, G. Kouzaev","doi":"10.37394/23201.2022.21.14","DOIUrl":"https://doi.org/10.37394/23201.2022.21.14","url":null,"abstract":"A variable predicate logic processor (VPLP) is proposed for artificial intelligence (AI), robotics, computer-aided medicine, electronic security, and other applications. The development is realized as an accelerating unit in AI computing machines. The difference from known designs, the datapath of this processor consists of universal gates changing on-the-fly their logical styles-subsets of predicate logic according to the data type and implemented instructions. In this paper, the processor’s reconfigurable gates and the main units are proposed, designed, modeled, and verified using a Field-Programmable Gate Array (FPGA) board and corresponding computer-aided design (CAD) tool. The implemented processor confirmed its reconfigurability on-the-fly performing testing codes. This processor is interesting in accelerating AI computing, molecular and quantum calculations in science, cryptography, computer-aided medicine, robotics, etc.","PeriodicalId":376260,"journal":{"name":"WSEAS TRANSACTIONS ON CIRCUITS AND SYSTEMS","volume":"335 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127574416","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 : 2022-06-03DOI: 10.37394/23201.2022.21.13
Neha Khurana
Inspite of so universally accepted, control performance by NN depends on many of the varying factors such as output weights. To ensure the functional accuracy of the NN, it is required to have an defined value of these performance effecting factors. Control scheme proposed in this paper uses an emerging optimization technique naming, PSO to get the optimal value of the parameters, naming spread factor and weights of output layer in RBNN. Thus, this hybrid controller possesses the advantageous qualities of RBNN and PSO both. For the further improvement in the basic PSO algorithm, inertia weight factor of PSO is made adaptive.This projected controller has been verified by comparing it with a basic PSO and the basic RBNN controller for the trajectory tracking control of a 2-DOF remotely driven robotic manipulator. To check the robustness of the controller its performance has been checked by incorporating uncertainties naming payload masses and friction. Appropriate conclusions have been drawn in last.
{"title":"PSO-RBNN Based Control Design for Trajectory Tracking","authors":"Neha Khurana","doi":"10.37394/23201.2022.21.13","DOIUrl":"https://doi.org/10.37394/23201.2022.21.13","url":null,"abstract":"Inspite of so universally accepted, control performance by NN depends on many of the varying factors such as output weights. To ensure the functional accuracy of the NN, it is required to have an defined value of these performance effecting factors. Control scheme proposed in this paper uses an emerging optimization technique naming, PSO to get the optimal value of the parameters, naming spread factor and weights of output layer in RBNN. Thus, this hybrid controller possesses the advantageous qualities of RBNN and PSO both. For the further improvement in the basic PSO algorithm, inertia weight factor of PSO is made adaptive.This projected controller has been verified by comparing it with a basic PSO and the basic RBNN controller for the trajectory tracking control of a 2-DOF remotely driven robotic manipulator. To check the robustness of the controller its performance has been checked by incorporating uncertainties naming payload masses and friction. Appropriate conclusions have been drawn in last.","PeriodicalId":376260,"journal":{"name":"WSEAS TRANSACTIONS ON CIRCUITS AND SYSTEMS","volume":"79 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116003857","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 : 2022-05-20DOI: 10.37394/23201.2022.21.12
Zaynab Hjouji, M. M’hamdi
We present in this article a new approach to predict the creditworthiness of borrowers that we call “Method of separating the learning set into two regions”. The goal of this approach is to build two regions from a training set. Thus, to predict the solvency of borrowers, it suffices to identify which of the two regions has its characteristic vectors; if it does not correspond to any region, credit decision-making requires further analysis. To test our approach, a large set of real and recent credit data obtained from the UCI repository is used, we trained also on a real credit database of a Moroccan bank and the creditworthiness of borrowers is analyzed at using two performance measurement indicators such as classification accuracy and AUC of the ROC curve as a robustness measurement criterion. The proposed model was compared with three traditional machine learning algorithms: LR, RBF-NN and MLP-NN. The experimental results show the superiority of the proposed approach.
{"title":"A New Machine Learning Method for Bank Credit Risk Analysis","authors":"Zaynab Hjouji, M. M’hamdi","doi":"10.37394/23201.2022.21.12","DOIUrl":"https://doi.org/10.37394/23201.2022.21.12","url":null,"abstract":"We present in this article a new approach to predict the creditworthiness of borrowers that we call “Method of separating the learning set into two regions”. The goal of this approach is to build two regions from a training set. Thus, to predict the solvency of borrowers, it suffices to identify which of the two regions has its characteristic vectors; if it does not correspond to any region, credit decision-making requires further analysis. To test our approach, a large set of real and recent credit data obtained from the UCI repository is used, we trained also on a real credit database of a Moroccan bank and the creditworthiness of borrowers is analyzed at using two performance measurement indicators such as classification accuracy and AUC of the ROC curve as a robustness measurement criterion. The proposed model was compared with three traditional machine learning algorithms: LR, RBF-NN and MLP-NN. The experimental results show the superiority of the proposed approach.","PeriodicalId":376260,"journal":{"name":"WSEAS TRANSACTIONS ON CIRCUITS AND SYSTEMS","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130735777","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：