Pub Date : 2020-12-10DOI: 10.1109/ISRITI51436.2020.9315412
Muhammad Farin Akhsanta, S. Suyanto
The Speaker identification system is widely applied in various fields to detect the identity of a person by detecting the sound signal energy released by a person and not driven by a particular text. The challenges are how to differentiate the voices characteristic of the speaker, such as intonation style, rhythm, the pattern of pronunciation, accent, and vocabulary. In this paper, a speaker identification system using Principal Component Analysis (PCA) and Support Vector Machine (SVM) is developed. Besides, the Mel Frequency Cepstral Coefficient (MFCC) is used as the feature extraction. The system is then evaluated using unseen noisy utterances with various signal-noise ratio (SNR). The evaluation is performed using a confusion matrix to calculate the accuracy, precision, and recall to determine the relevance of the output results on the system. Experimental results show that the developed system is quite robust. It is capable of identifying speakers with high performance, an accuracy of 88.97%, a precision of 91,87%, and a recall of 94,39%, for a low noise level with SNR of 15dB. The performance slowly decreases as the noise level increases. For a high noise level with SNR of up to 0dB, it is still able to recognize the unseen speakers with an average accuracy of 70.93%, precision of 74.68%, and recall of 83.51%.
{"title":"Text-Independent Speaker Identification Using PCA-SVM Model","authors":"Muhammad Farin Akhsanta, S. Suyanto","doi":"10.1109/ISRITI51436.2020.9315412","DOIUrl":"https://doi.org/10.1109/ISRITI51436.2020.9315412","url":null,"abstract":"The Speaker identification system is widely applied in various fields to detect the identity of a person by detecting the sound signal energy released by a person and not driven by a particular text. The challenges are how to differentiate the voices characteristic of the speaker, such as intonation style, rhythm, the pattern of pronunciation, accent, and vocabulary. In this paper, a speaker identification system using Principal Component Analysis (PCA) and Support Vector Machine (SVM) is developed. Besides, the Mel Frequency Cepstral Coefficient (MFCC) is used as the feature extraction. The system is then evaluated using unseen noisy utterances with various signal-noise ratio (SNR). The evaluation is performed using a confusion matrix to calculate the accuracy, precision, and recall to determine the relevance of the output results on the system. Experimental results show that the developed system is quite robust. It is capable of identifying speakers with high performance, an accuracy of 88.97%, a precision of 91,87%, and a recall of 94,39%, for a low noise level with SNR of 15dB. The performance slowly decreases as the noise level increases. For a high noise level with SNR of up to 0dB, it is still able to recognize the unseen speakers with an average accuracy of 70.93%, precision of 74.68%, and recall of 83.51%.","PeriodicalId":325920,"journal":{"name":"2020 3rd International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":"99 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126035942","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 : 2020-12-10DOI: 10.1109/ISRITI51436.2020.9315353
Arif Sudaryanto, E. Purwanto, I. Ferdiansyah, Syechu Dwitya Nugraha, O. Qudsi, M. Rifadil, M. R. Rusli
The electric motor has replaced motor fuel as the main mover of the equipment. One of them is the use of a three-phase induction motor in the industrial sector. Equipment in an industry requires many speed controllers in operation. The induction motor speed can be changed by changing the number of poles, changing the stator voltage, and changing the frequency source. This method has many disadvantages, such as changes in motor dimensions and the occurrence of flux saturation. This paper provides method of controlling the speed of a three-phase induction motor with constant V/f. Speed regulation with constant V/f can prevent saturation flux when changing the input frequency and can maintain maximum motor torque along the speed regulation area. The speed regulation use an inverter Three-phase SVPWM by implementing PI control. The results of using constant V/f control show that motor speed response at 1300 rpm has a rise time of 0.13 second, a settling time of 0.164 second, an overshoot of 0%, and a THD of 19.26%.
{"title":"Design and Implementation of SVPWM Inverter to Reduce Total Harmonic Distortion (THD) on Three Phase Induction Motor Speed Regulation Using Constant V/F","authors":"Arif Sudaryanto, E. Purwanto, I. Ferdiansyah, Syechu Dwitya Nugraha, O. Qudsi, M. Rifadil, M. R. Rusli","doi":"10.1109/ISRITI51436.2020.9315353","DOIUrl":"https://doi.org/10.1109/ISRITI51436.2020.9315353","url":null,"abstract":"The electric motor has replaced motor fuel as the main mover of the equipment. One of them is the use of a three-phase induction motor in the industrial sector. Equipment in an industry requires many speed controllers in operation. The induction motor speed can be changed by changing the number of poles, changing the stator voltage, and changing the frequency source. This method has many disadvantages, such as changes in motor dimensions and the occurrence of flux saturation. This paper provides method of controlling the speed of a three-phase induction motor with constant V/f. Speed regulation with constant V/f can prevent saturation flux when changing the input frequency and can maintain maximum motor torque along the speed regulation area. The speed regulation use an inverter Three-phase SVPWM by implementing PI control. The results of using constant V/f control show that motor speed response at 1300 rpm has a rise time of 0.13 second, a settling time of 0.164 second, an overshoot of 0%, and a THD of 19.26%.","PeriodicalId":325920,"journal":{"name":"2020 3rd International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":"30 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128590005","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 : 2020-12-10DOI: 10.1109/ISRITI51436.2020.9315424
Farah Nur Alfi, M. Anggraeni, Rosiyah Faradisa
Indonesia established Analog Switch-Off (ASO) in 2018 and was not fully implemented. In this study, we assessed the quality of terrestrial digital TV from end-users, which was also complemented by field measurements of CNR, SNR, and BER values. Based on the results of the assessment, shown 59% of respondents still use analog TV. The TV migration process in Indonesia has not been widely known by the public, 78% of respondents are not aware of the ASO condition, and 74% of respondents claim to have never heard of digital terrestrial TV. More than 50% of respondents of terrestrial digital TV users stated that experienced broadcast dropouts and almost 50% experienced broadcast delays. This relates to the results of field measurements based on a technology-centered approach that shows a higher bit error rate than the simulation data, blank spots at two points, and are still points that classified as low signal categories.
{"title":"Quality Assessment of Digital Terrestrial Television Broadcast in Surabaya","authors":"Farah Nur Alfi, M. Anggraeni, Rosiyah Faradisa","doi":"10.1109/ISRITI51436.2020.9315424","DOIUrl":"https://doi.org/10.1109/ISRITI51436.2020.9315424","url":null,"abstract":"Indonesia established Analog Switch-Off (ASO) in 2018 and was not fully implemented. In this study, we assessed the quality of terrestrial digital TV from end-users, which was also complemented by field measurements of CNR, SNR, and BER values. Based on the results of the assessment, shown 59% of respondents still use analog TV. The TV migration process in Indonesia has not been widely known by the public, 78% of respondents are not aware of the ASO condition, and 74% of respondents claim to have never heard of digital terrestrial TV. More than 50% of respondents of terrestrial digital TV users stated that experienced broadcast dropouts and almost 50% experienced broadcast delays. This relates to the results of field measurements based on a technology-centered approach that shows a higher bit error rate than the simulation data, blank spots at two points, and are still points that classified as low signal categories.","PeriodicalId":325920,"journal":{"name":"2020 3rd International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132993610","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 : 2020-12-10DOI: 10.1109/ISRITI51436.2020.9315411
M. H. Ibrahim, A. Hanifa, S. Pramono, M. E. Sulistyo, I. Iftadi
Bit error rate (BER) is a fundamental performance measurement of data transmission and communication link. BER measures. Incorporating with digital baseband processing in transceiver, BER measurement can be integrated in a field programmable gate array (FPGA). A Cyclone IV E EP4CE115 is implemented as BER tester to measure performance of visible light communication (VLC) link. The flexibility of FPGA allows the proposed BER measurement system design to add features such as pseudo random bit sequence (PRBS) generator, burst error generator and delay control for synchronization. It shows that design capable to measure VLC link up to 2 Mbps due to limitation of VLC analog front end (AFE).
误码率是衡量数据传输和通信链路性能的基本指标。方方面面的措施。结合收发器中的数字基带处理，可以将误码率测量集成到现场可编程门阵列(FPGA)中。采用Cyclone IV E EP4CE115作为误码率测试仪，测量可见光通信(VLC)链路的性能。FPGA的灵活性允许所提出的误码率测量系统设计增加诸如伪随机比特序列(PRBS)发生器、突发错误发生器和同步延迟控制等功能。结果表明，由于VLC模拟前端(AFE)的限制，该设计只能测量高达2mbps的VLC链路。
{"title":"Design and Development of Bit Error Measurement using FPGA for Visible Light Communication","authors":"M. H. Ibrahim, A. Hanifa, S. Pramono, M. E. Sulistyo, I. Iftadi","doi":"10.1109/ISRITI51436.2020.9315411","DOIUrl":"https://doi.org/10.1109/ISRITI51436.2020.9315411","url":null,"abstract":"Bit error rate (BER) is a fundamental performance measurement of data transmission and communication link. BER measures. Incorporating with digital baseband processing in transceiver, BER measurement can be integrated in a field programmable gate array (FPGA). A Cyclone IV E EP4CE115 is implemented as BER tester to measure performance of visible light communication (VLC) link. The flexibility of FPGA allows the proposed BER measurement system design to add features such as pseudo random bit sequence (PRBS) generator, burst error generator and delay control for synchronization. It shows that design capable to measure VLC link up to 2 Mbps due to limitation of VLC analog front end (AFE).","PeriodicalId":325920,"journal":{"name":"2020 3rd International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133438444","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 : 2020-12-10DOI: 10.1109/ISRITI51436.2020.9315465
S. Zahara, Sugianto
Multivariate time series forecasting affords an opportunity to forecast future recent trends or possibility incident based on historical observations. Forecasting in economic world becomes global interest particularly for researchers seeking for best accuracy result using several methods. Consumer Price Index is the primary instrument used by central banks to set inflation targets. However, most of previous studies commonly only used univariate factor to forecast Consumer Price Index. Furthermore, mostly model development of forecasting system is done by personal and physical server facing the problem of impractical yet time consuming. Since measuring method of Consumer Price Index commonly is pick an average of the period-to-period price move for the different products, we conducted multivariate Consumer Price Index forecasting based Cloud Computing utilizing 28 types of Surabaya daily food price from 2014 to 2018 using Multilayer Perceptron and Long Short Term Memory (LSTM) of deep learning. Furthermore, we implement architectural variations of the number of neurons, epoch, and hidden layers. The whole development of forecasting system is built in Amazon Web Service (AWS) Cloud. The result indicated the best accuracy value was obtained from the Multilayer Perceptron with 3.380 of RMSE consist of a configuration of 2 hidden layers, 10 neurons of first hidden layer, 10 neurons of second hidden layer also 1000 of epoch.
{"title":"Multivariate Time Series Forecasting Based Cloud Computing For Consumer Price Index Using Deep Learning Algorithms","authors":"S. Zahara, Sugianto","doi":"10.1109/ISRITI51436.2020.9315465","DOIUrl":"https://doi.org/10.1109/ISRITI51436.2020.9315465","url":null,"abstract":"Multivariate time series forecasting affords an opportunity to forecast future recent trends or possibility incident based on historical observations. Forecasting in economic world becomes global interest particularly for researchers seeking for best accuracy result using several methods. Consumer Price Index is the primary instrument used by central banks to set inflation targets. However, most of previous studies commonly only used univariate factor to forecast Consumer Price Index. Furthermore, mostly model development of forecasting system is done by personal and physical server facing the problem of impractical yet time consuming. Since measuring method of Consumer Price Index commonly is pick an average of the period-to-period price move for the different products, we conducted multivariate Consumer Price Index forecasting based Cloud Computing utilizing 28 types of Surabaya daily food price from 2014 to 2018 using Multilayer Perceptron and Long Short Term Memory (LSTM) of deep learning. Furthermore, we implement architectural variations of the number of neurons, epoch, and hidden layers. The whole development of forecasting system is built in Amazon Web Service (AWS) Cloud. The result indicated the best accuracy value was obtained from the Multilayer Perceptron with 3.380 of RMSE consist of a configuration of 2 hidden layers, 10 neurons of first hidden layer, 10 neurons of second hidden layer also 1000 of epoch.","PeriodicalId":325920,"journal":{"name":"2020 3rd International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130520228","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 : 2020-12-10DOI: 10.1109/ISRITI51436.2020.9315435
A. Lagunov, A. Ladvishchenko
The Arctic attracts the attention of many countries around the world because it is rich in hydrocarbons. To conduct exploration for hydrocarbons, researchers need electricity. Traditionally, diesel or gasoline generators are used to generate electricity in the circumpolar region. Fuel delivery is costly, and environmental pollution occurs during the operation of electric generators. Wind generators and solar power plants can be used as alternative sources of electricity. In adverse conditions in the Arctic, wind turbines quickly fail. This work is devoted to choosing the type of solar cells that can operate efficiently at low temperatures.
{"title":"Features of the Use of Solar Panels at Low Temperatures in the Arctic","authors":"A. Lagunov, A. Ladvishchenko","doi":"10.1109/ISRITI51436.2020.9315435","DOIUrl":"https://doi.org/10.1109/ISRITI51436.2020.9315435","url":null,"abstract":"The Arctic attracts the attention of many countries around the world because it is rich in hydrocarbons. To conduct exploration for hydrocarbons, researchers need electricity. Traditionally, diesel or gasoline generators are used to generate electricity in the circumpolar region. Fuel delivery is costly, and environmental pollution occurs during the operation of electric generators. Wind generators and solar power plants can be used as alternative sources of electricity. In adverse conditions in the Arctic, wind turbines quickly fail. This work is devoted to choosing the type of solar cells that can operate efficiently at low temperatures.","PeriodicalId":325920,"journal":{"name":"2020 3rd International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":"649 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115831756","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}
Recommendation systems have become a staple feature for any e-commerce sites. The ability to predict whether a customer likes an unseen product forms the very foundation of a recommendation system. In this paper, we concern the issue of explicit rating prediction over cosmetic products. Given a dataset of cosmetic product ratings, we analyze the characteristics of the dataset and implement a wide range of algorithms, such as KNN and matrix factorization, to predict such ratings. We evaluate the performance of these algorithms using MAE and RMSE measures, and discuss factors that may contribute to their performance results. Our experiments have shown that the SVD++ technique performs the best among all with an MAE of 0.7699 and an RMSE of 0.9696. We hope that our paper can shed new light on the selection of explicit rating prediction algorithms not only in the domain of beauty products, but also in wider scenarios.
{"title":"Benchmarking Explicit Rating Prediction Algorithms for Cosmetic Products","authors":"Raditya Nurfadillah, Fariz Darari, Radityo Eko Prasojo, Yasmin Amalia","doi":"10.1109/isriti51436.2020.9315512","DOIUrl":"https://doi.org/10.1109/isriti51436.2020.9315512","url":null,"abstract":"Recommendation systems have become a staple feature for any e-commerce sites. The ability to predict whether a customer likes an unseen product forms the very foundation of a recommendation system. In this paper, we concern the issue of explicit rating prediction over cosmetic products. Given a dataset of cosmetic product ratings, we analyze the characteristics of the dataset and implement a wide range of algorithms, such as KNN and matrix factorization, to predict such ratings. We evaluate the performance of these algorithms using MAE and RMSE measures, and discuss factors that may contribute to their performance results. Our experiments have shown that the SVD++ technique performs the best among all with an MAE of 0.7699 and an RMSE of 0.9696. We hope that our paper can shed new light on the selection of explicit rating prediction algorithms not only in the domain of beauty products, but also in wider scenarios.","PeriodicalId":325920,"journal":{"name":"2020 3rd International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117214354","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 : 2020-12-10DOI: 10.1109/ISRITI51436.2020.9315347
B. L. Widjiantoro, K. Indriawati, Egy Josua Simbolon
In this research, speed sensorless control design for induction motors is done by using the Particle Filter algorithm (PF) as a speed estimator and Direct Torque Control (DTC) as a control scheme used to control the speed of an induction motor. For testing with a close loop control system, the test range is at speeds of 50 to 500 rpm, with a steady state error obtained less than 5%. Based on the value of the error obtained it can be said that the design of the speed sensorless control for the induction motor is running well, however at high speeds such as 350 and 500 rpm the results obtained have a high overshoot value and a long settling time.
{"title":"Particle Filter Based Speed Estimator for Speed Sensorless Control in Induction Motor","authors":"B. L. Widjiantoro, K. Indriawati, Egy Josua Simbolon","doi":"10.1109/ISRITI51436.2020.9315347","DOIUrl":"https://doi.org/10.1109/ISRITI51436.2020.9315347","url":null,"abstract":"In this research, speed sensorless control design for induction motors is done by using the Particle Filter algorithm (PF) as a speed estimator and Direct Torque Control (DTC) as a control scheme used to control the speed of an induction motor. For testing with a close loop control system, the test range is at speeds of 50 to 500 rpm, with a steady state error obtained less than 5%. Based on the value of the error obtained it can be said that the design of the speed sensorless control for the induction motor is running well, however at high speeds such as 350 and 500 rpm the results obtained have a high overshoot value and a long settling time.","PeriodicalId":325920,"journal":{"name":"2020 3rd International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121819269","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 : 2020-12-10DOI: 10.1109/ISRITI51436.2020.9315527
Muhammad Rizal Fanani, I. Sudiharto, I. Ferdiansyah
Implementation of Solar thermal energy as a source of renewable electricity is currently being developed. The main problem with photovoltaic systems is the result of power efficiency is low. The maximum power point tracking (MPPT) method can increase the efficiency of photovoltaic output power. This research will use the MPPT method with an artificial bee colony (ABC) algorithm. MPPT design will be simulated using Power Simulation (PSIM) software. Simulation results will be compared with no MPPT and MPPT human psychology optimization (HPO) algorithm. The results show MPPT ABC gets the best average accuracy from the average accuracy without MPPT and MPPT HPO, which is 99.95%. And the MPPT ABC has a response time of MPP tracking faster than MPPT HPO, during irradiation 800 W/m2, 900 W/m2, 1000 W/m2.
{"title":"Implementation of Maximum Power Point Tracking on PV System using Artificial Bee Colony Algorithm","authors":"Muhammad Rizal Fanani, I. Sudiharto, I. Ferdiansyah","doi":"10.1109/ISRITI51436.2020.9315527","DOIUrl":"https://doi.org/10.1109/ISRITI51436.2020.9315527","url":null,"abstract":"Implementation of Solar thermal energy as a source of renewable electricity is currently being developed. The main problem with photovoltaic systems is the result of power efficiency is low. The maximum power point tracking (MPPT) method can increase the efficiency of photovoltaic output power. This research will use the MPPT method with an artificial bee colony (ABC) algorithm. MPPT design will be simulated using Power Simulation (PSIM) software. Simulation results will be compared with no MPPT and MPPT human psychology optimization (HPO) algorithm. The results show MPPT ABC gets the best average accuracy from the average accuracy without MPPT and MPPT HPO, which is 99.95%. And the MPPT ABC has a response time of MPP tracking faster than MPPT HPO, during irradiation 800 W/m2, 900 W/m2, 1000 W/m2.","PeriodicalId":325920,"journal":{"name":"2020 3rd International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126519074","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 : 2020-12-10DOI: 10.1109/ISRITI51436.2020.9315344
S. Sa'adah, Melati Suci Pratiwi
Development of technology have influenced all aspect, especially in financial sector in this pandemic situation, where most people tend to use digital money to conduct daily financial transactions. In one side, there is security point that need to be concern much. Like several disadvantages using credit cards by undue owners, social engineering, and transactions to commit fraud. In this paper, PaySim Mobile Money Simulator data is used with a machine learning algorithm called probabilistic neural network (PNN) to classify whether the customer's actions are normal or fraudulent actions. This PNN approach combined using binary classification to prevent fraudulent actions in transactions that have been or are being used by customers. And the result indicated that this system able to classify class 0 (as a normal class customer) and 1 (as a fraudulent class customer). Based on this result, maybe it would help many sectors that involved as a tool to classify a genuine customer. Especially in this pandemic covid-19, the fraud needs to detect often, to mitigate the fraud early.
{"title":"Classification of Customer Actions on Digital Money Transactions on PaySim Mobile Money Simulator using Probabilistic Neural Network (PNN) Algorithm","authors":"S. Sa'adah, Melati Suci Pratiwi","doi":"10.1109/ISRITI51436.2020.9315344","DOIUrl":"https://doi.org/10.1109/ISRITI51436.2020.9315344","url":null,"abstract":"Development of technology have influenced all aspect, especially in financial sector in this pandemic situation, where most people tend to use digital money to conduct daily financial transactions. In one side, there is security point that need to be concern much. Like several disadvantages using credit cards by undue owners, social engineering, and transactions to commit fraud. In this paper, PaySim Mobile Money Simulator data is used with a machine learning algorithm called probabilistic neural network (PNN) to classify whether the customer's actions are normal or fraudulent actions. This PNN approach combined using binary classification to prevent fraudulent actions in transactions that have been or are being used by customers. And the result indicated that this system able to classify class 0 (as a normal class customer) and 1 (as a fraudulent class customer). Based on this result, maybe it would help many sectors that involved as a tool to classify a genuine customer. Especially in this pandemic covid-19, the fraud needs to detect often, to mitigate the fraud early.","PeriodicalId":325920,"journal":{"name":"2020 3rd International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":"79 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126182577","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：