Pub Date : 2022-11-22DOI: 10.1109/ELECOM54934.2022.9965245
K. Sewraj, M. Botha
The use of large antenna arrays in radio-astronomy is of growing importance. Electromagnetic simulation is crucial during the design phase of such arrays. One of the preferred numerical method for antenna analysis is the integral-equation based Method of Moments (MoM). However, the MoM is computationally expensive, in terms of both memory and runtime scaling. The Macro Basis Function (MBF) technique can be used in MoM solvers to create MBFs by aggregating low-level basis functions with the aim of using fewer degrees of freedom. In this paper, two research avenues for efficient MBF solvers for array analysis are explored. Firstly, the use of Large-Domain MBFs. And secondly, using the Directional Cross Approximation (DCA) technique to rapidly compute the entries of the MBF reduced system.
{"title":"Overview of Macro Basis Function Research for Antenna Array Solvers","authors":"K. Sewraj, M. Botha","doi":"10.1109/ELECOM54934.2022.9965245","DOIUrl":"https://doi.org/10.1109/ELECOM54934.2022.9965245","url":null,"abstract":"The use of large antenna arrays in radio-astronomy is of growing importance. Electromagnetic simulation is crucial during the design phase of such arrays. One of the preferred numerical method for antenna analysis is the integral-equation based Method of Moments (MoM). However, the MoM is computationally expensive, in terms of both memory and runtime scaling. The Macro Basis Function (MBF) technique can be used in MoM solvers to create MBFs by aggregating low-level basis functions with the aim of using fewer degrees of freedom. In this paper, two research avenues for efficient MBF solvers for array analysis are explored. Firstly, the use of Large-Domain MBFs. And secondly, using the Directional Cross Approximation (DCA) technique to rapidly compute the entries of the MBF reduced system.","PeriodicalId":302869,"journal":{"name":"2022 4th International Conference on Emerging Trends in Electrical, Electronic and Communications Engineering (ELECOM)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128247354","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 : 2022-11-22DOI: 10.1109/ELECOM54934.2022.9965258
A. Murdan, I. Jahmeerbacus, S. Hassen
Reliable and efficient power systems operation requires voltage control as well as minimal reactive power flow between a load and the grid. To achieve this objective, reactive power compensating devices are typically utilized. In modern power systems, the synchronous static compensator (STATCOM) is primarily used for reactive power control, both in distribution and transmission lines. This study presents the modeling and simulation of a STATCOM based on a voltage source converter. Simulations are performed for both single phase and three phase power systems. Furthermore, two control techniques, utilizing Proportional Integral (PI) as well as Proportional Resonant (PR) controllers are explored. The PR controller presents several advantages compared to the PI controller. Simulation results show that in both cases, the STATCOM, connected in shunt with the load either provides reactive power to the load, or absorbs reactive power from the load. Thus, net reactive power transfer from the grid to the load is zero. The grid provides only active power, thus keeping the power factor to almost unity.
{"title":"Modeling and Simulation of a STATCOM for reactive power control","authors":"A. Murdan, I. Jahmeerbacus, S. Hassen","doi":"10.1109/ELECOM54934.2022.9965258","DOIUrl":"https://doi.org/10.1109/ELECOM54934.2022.9965258","url":null,"abstract":"Reliable and efficient power systems operation requires voltage control as well as minimal reactive power flow between a load and the grid. To achieve this objective, reactive power compensating devices are typically utilized. In modern power systems, the synchronous static compensator (STATCOM) is primarily used for reactive power control, both in distribution and transmission lines. This study presents the modeling and simulation of a STATCOM based on a voltage source converter. Simulations are performed for both single phase and three phase power systems. Furthermore, two control techniques, utilizing Proportional Integral (PI) as well as Proportional Resonant (PR) controllers are explored. The PR controller presents several advantages compared to the PI controller. Simulation results show that in both cases, the STATCOM, connected in shunt with the load either provides reactive power to the load, or absorbs reactive power from the load. Thus, net reactive power transfer from the grid to the load is zero. The grid provides only active power, thus keeping the power factor to almost unity.","PeriodicalId":302869,"journal":{"name":"2022 4th International Conference on Emerging Trends in Electrical, Electronic and Communications Engineering (ELECOM)","volume":"304 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129542581","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 : 2022-11-22DOI: 10.1109/ELECOM54934.2022.9965262
A. Falcon-Caro, Saeid Sanei
Air trackers such as AirTags and AirFinders have emerged as an alternative to image-and GPS-based positioning systems. On the other hand, adaptive cooperative networks have been found as powerful multi-agent adaptive systems which incorporate the information from the neighboring nodes (a.k. a. agents) in the adaptation or modelling process. Here, diffusion adaptation strategy is effectively used to exploit the positioning information from a group of blind people within a neighborhood in the crowd, collected by Air trackers, to best support them reaching their destinations.
{"title":"Cooperative Networking Approach to Assisting Blinds in a Crowd Using Air Trackers","authors":"A. Falcon-Caro, Saeid Sanei","doi":"10.1109/ELECOM54934.2022.9965262","DOIUrl":"https://doi.org/10.1109/ELECOM54934.2022.9965262","url":null,"abstract":"Air trackers such as AirTags and AirFinders have emerged as an alternative to image-and GPS-based positioning systems. On the other hand, adaptive cooperative networks have been found as powerful multi-agent adaptive systems which incorporate the information from the neighboring nodes (a.k. a. agents) in the adaptation or modelling process. Here, diffusion adaptation strategy is effectively used to exploit the positioning information from a group of blind people within a neighborhood in the crowd, collected by Air trackers, to best support them reaching their destinations.","PeriodicalId":302869,"journal":{"name":"2022 4th International Conference on Emerging Trends in Electrical, Electronic and Communications Engineering (ELECOM)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130539880","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 : 2022-11-22DOI: 10.1109/ELECOM54934.2022.9965260
L. Butgereit
Online Dispute Resolution systems provide internet based platforms allowing parties to resolve their disputes at a distance. The first two people in the original dispute are known as the first and second party. The arbitrator or mediator is known as the third party. In the case of an online dispute resolution system, the technology platform becomes the Fourth Party in the dispute. The term Fourth Party was coined by Katsch and Rifkin. They also itemised a number of characteristics which should be present in the Fourth Party. This paper looks at various architectural decisions which need to be made in order to build a smart Fourth Party.
{"title":"Architectural Decisions in Designing a Cloud-Based Smart Fourth Party in an Online Dispute Resolution System","authors":"L. Butgereit","doi":"10.1109/ELECOM54934.2022.9965260","DOIUrl":"https://doi.org/10.1109/ELECOM54934.2022.9965260","url":null,"abstract":"Online Dispute Resolution systems provide internet based platforms allowing parties to resolve their disputes at a distance. The first two people in the original dispute are known as the first and second party. The arbitrator or mediator is known as the third party. In the case of an online dispute resolution system, the technology platform becomes the Fourth Party in the dispute. The term Fourth Party was coined by Katsch and Rifkin. They also itemised a number of characteristics which should be present in the Fourth Party. This paper looks at various architectural decisions which need to be made in order to build a smart Fourth Party.","PeriodicalId":302869,"journal":{"name":"2022 4th International Conference on Emerging Trends in Electrical, Electronic and Communications Engineering (ELECOM)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130420417","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 : 2022-11-22DOI: 10.1109/ELECOM54934.2022.9965255
B. Rajkumarsingh, Muhammad Husayn Edoo
The aim of this work is to improve the BER performance in the power line communication (PLC) channel. Impulsive noise is known to cause significant bit error in this channel. As an objective to decrease the bit error rate, adaptive filtering techniques based on the LMS and the RLS algorithms are employed for the mitigation of the impulsive noise in a MIMO PLC channel. To our best knowledge, adaptive filtering techniques employed for impulsive mitigation in MIIO PLC channels are few. Impulsive noise is represented by the Markov-Middleton and Middleton class A noise models. The Marloov-Middleton noise for a weakly and heavily disturbed MIMO PLC channel are simulated and their performances with noise mitigation are compared with that of the Middleton class A noise model. The performance of adaptive filtering techniques based on the LMS and RLS algorithms for mitigation of Markov-Middleton noise from the MIMO PLC system was remarkable. An average gain of 12.62 dB and 16.26 dB for LMS filtering, and 12.90 dB and 16.83 dB for RIS filtering were recorded in a weakly and heavily disturbed MIMO PLC channel respectively. It was concluded that for weakly disturbed MIDO PLC channels the performance of both algorithms is equally efficient while in heavily disturbed MIMO PLC channels the performance of RLS filtering slightly outperforms that of LMS filtering
{"title":"Markov-Middleton Impulsive Noise Mitigation in the MIMO Power Line Communication Channel","authors":"B. Rajkumarsingh, Muhammad Husayn Edoo","doi":"10.1109/ELECOM54934.2022.9965255","DOIUrl":"https://doi.org/10.1109/ELECOM54934.2022.9965255","url":null,"abstract":"The aim of this work is to improve the BER performance in the power line communication (PLC) channel. Impulsive noise is known to cause significant bit error in this channel. As an objective to decrease the bit error rate, adaptive filtering techniques based on the LMS and the RLS algorithms are employed for the mitigation of the impulsive noise in a MIMO PLC channel. To our best knowledge, adaptive filtering techniques employed for impulsive mitigation in MIIO PLC channels are few. Impulsive noise is represented by the Markov-Middleton and Middleton class A noise models. The Marloov-Middleton noise for a weakly and heavily disturbed MIMO PLC channel are simulated and their performances with noise mitigation are compared with that of the Middleton class A noise model. The performance of adaptive filtering techniques based on the LMS and RLS algorithms for mitigation of Markov-Middleton noise from the MIMO PLC system was remarkable. An average gain of 12.62 dB and 16.26 dB for LMS filtering, and 12.90 dB and 16.83 dB for RIS filtering were recorded in a weakly and heavily disturbed MIMO PLC channel respectively. It was concluded that for weakly disturbed MIDO PLC channels the performance of both algorithms is equally efficient while in heavily disturbed MIMO PLC channels the performance of RLS filtering slightly outperforms that of LMS filtering","PeriodicalId":302869,"journal":{"name":"2022 4th International Conference on Emerging Trends in Electrical, Electronic and Communications Engineering (ELECOM)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131730304","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 : 2022-11-22DOI: 10.1109/elecom54934.2022.9965254
{"title":"ELECOM 2022 Cover Page","authors":"","doi":"10.1109/elecom54934.2022.9965254","DOIUrl":"https://doi.org/10.1109/elecom54934.2022.9965254","url":null,"abstract":"","PeriodicalId":302869,"journal":{"name":"2022 4th International Conference on Emerging Trends in Electrical, Electronic and Communications Engineering (ELECOM)","volume":"125 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121154298","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 : 2022-11-22DOI: 10.1109/ELECOM54934.2022.9965243
Lavesh Babooram, T. P. Fowdur
Web browsing has become a very common and almost indispensable activity for the ever-increasing number of internet users. However, with the increase in network traffic, the Quality of Service (QoS) of users is also impacted especially during peak utilization periods. It is therefore important to predict network traffic parameters such as bandwidth, and upload and download speeds which directly impact QoS. In this paper, a network analytics application is proposed whereby a browser extension is developed to analyse network traffic and perform prediction and classification. The extension sends requests to a Node.js server which provides real-time network traffic information to users and an indication of the QoS based on the parameters such as the latency, jitter, and upload and download speeds. The application can seamlessly be integrated in a Chrome browser and results show that it can effectively provide important network traffic data and classify the application type run in the browser.
{"title":"A Web-Based Network Traffic Prediction and Classification Application using Machine Learning","authors":"Lavesh Babooram, T. P. Fowdur","doi":"10.1109/ELECOM54934.2022.9965243","DOIUrl":"https://doi.org/10.1109/ELECOM54934.2022.9965243","url":null,"abstract":"Web browsing has become a very common and almost indispensable activity for the ever-increasing number of internet users. However, with the increase in network traffic, the Quality of Service (QoS) of users is also impacted especially during peak utilization periods. It is therefore important to predict network traffic parameters such as bandwidth, and upload and download speeds which directly impact QoS. In this paper, a network analytics application is proposed whereby a browser extension is developed to analyse network traffic and perform prediction and classification. The extension sends requests to a Node.js server which provides real-time network traffic information to users and an indication of the QoS based on the parameters such as the latency, jitter, and upload and download speeds. The application can seamlessly be integrated in a Chrome browser and results show that it can effectively provide important network traffic data and classify the application type run in the browser.","PeriodicalId":302869,"journal":{"name":"2022 4th International Conference on Emerging Trends in Electrical, Electronic and Communications Engineering (ELECOM)","volume":"135 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115302158","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 : 2022-11-22DOI: 10.1109/ELECOM54934.2022.9965234
M. Z. Ahmed, Hosni Mokhtar Ali, Rida Emhammed Khamiss
In latest years, the Weibull distribution was a widely used, acceptable, and suggested distribution for expressing the wind speed frequency distribution in literatures. In this paper, the excel solver tool (EST) was used to improve the estimation of the Weibull distribution coefficients for the wind speed data used in the paper presented by Hosni Mokhtar, et al. [1], which studies the assessment of seven methods for calculating the Weibull distribution parameters for Al-Aziziyah city, Libya, with the results indicating that the Modified Maximum Likelihood Method (MML), Maximum Likelihood Method (MLM) and Empirical method of Justus (EMJ) are the most appropriate methods. Various goodness of fit tests at different heights at site are used to evaluate the applicability of these methods. A comparing of relative inaccuracy of power density estimate findings from earlier and current investigations is also carried out to illustrate the accuracy of employing a solver excel tool. The findings of this study show that using solver excel to estimate Weibull parameters is a viable option, and that it may be more suitable than other approaches. A most significant benefit of EST is that it does not need the formulation of complicated mathematical equations that require the use of difficult numerical techniques to solve. It’s relatively simple to estimate the Weibull parameters if simply the wind speed distribution is known.
{"title":"Estimation of Weibull Distribution Parameters by Using Excel Solver Tool for Wind Speed Data at Al-Aziziyah, Libya","authors":"M. Z. Ahmed, Hosni Mokhtar Ali, Rida Emhammed Khamiss","doi":"10.1109/ELECOM54934.2022.9965234","DOIUrl":"https://doi.org/10.1109/ELECOM54934.2022.9965234","url":null,"abstract":"In latest years, the Weibull distribution was a widely used, acceptable, and suggested distribution for expressing the wind speed frequency distribution in literatures. In this paper, the excel solver tool (EST) was used to improve the estimation of the Weibull distribution coefficients for the wind speed data used in the paper presented by Hosni Mokhtar, et al. [1], which studies the assessment of seven methods for calculating the Weibull distribution parameters for Al-Aziziyah city, Libya, with the results indicating that the Modified Maximum Likelihood Method (MML), Maximum Likelihood Method (MLM) and Empirical method of Justus (EMJ) are the most appropriate methods. Various goodness of fit tests at different heights at site are used to evaluate the applicability of these methods. A comparing of relative inaccuracy of power density estimate findings from earlier and current investigations is also carried out to illustrate the accuracy of employing a solver excel tool. The findings of this study show that using solver excel to estimate Weibull parameters is a viable option, and that it may be more suitable than other approaches. A most significant benefit of EST is that it does not need the formulation of complicated mathematical equations that require the use of difficult numerical techniques to solve. It’s relatively simple to estimate the Weibull parameters if simply the wind speed distribution is known.","PeriodicalId":302869,"journal":{"name":"2022 4th International Conference on Emerging Trends in Electrical, Electronic and Communications Engineering (ELECOM)","volume":"94 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120993854","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 : 2022-11-22DOI: 10.1109/ELECOM54934.2022.9965266
Teodora Spasić, D. Kljajić, K. Kasas-Lazetic, G. Mijatović, M. Milutinov, M. Prsa
With the advancement of technology, it is becoming increasingly necessary to protect electrical devices from electromagnetic fields. For this reason, it is important to analyze how an electromagnetic field can be reduced. This paper examines shielding as a way of reducing magnetic fields. The reduction can be achieved by various shield geometry, placed coaxially with a long current carrying wire, in order to decrease the magnetic field outside the shield. DC and low-frequency AC fields (50 Hz) shielding are investigated. For the DC fields, a shield made of a high permeability ferromagnetic material was applied, while for the AC fields, a copper layer of different thicknesses was added to the ferromagnetic material to reduce the magnetic field more effectively by the currents induced in it. Shielding effectiveness as a parameter applied to quantify the shielding quality was calculated for different combinations of shading material thickness and arc length. The most significant increase in shielding effectiveness occurs at the thickest copper layer, between the shield angles 180 and 270 degrees. At the distance of 565 mm from the system axis, the shielding effectiveness will increase 2.4 times for the specified angle increase. The obtained results show that partial shielding can provide good protection in many practical cases and additionally reduce the amount of used material.
{"title":"Protection Against Exposure to DC or AC Magnetic Field Based on Partial Shielding","authors":"Teodora Spasić, D. Kljajić, K. Kasas-Lazetic, G. Mijatović, M. Milutinov, M. Prsa","doi":"10.1109/ELECOM54934.2022.9965266","DOIUrl":"https://doi.org/10.1109/ELECOM54934.2022.9965266","url":null,"abstract":"With the advancement of technology, it is becoming increasingly necessary to protect electrical devices from electromagnetic fields. For this reason, it is important to analyze how an electromagnetic field can be reduced. This paper examines shielding as a way of reducing magnetic fields. The reduction can be achieved by various shield geometry, placed coaxially with a long current carrying wire, in order to decrease the magnetic field outside the shield. DC and low-frequency AC fields (50 Hz) shielding are investigated. For the DC fields, a shield made of a high permeability ferromagnetic material was applied, while for the AC fields, a copper layer of different thicknesses was added to the ferromagnetic material to reduce the magnetic field more effectively by the currents induced in it. Shielding effectiveness as a parameter applied to quantify the shielding quality was calculated for different combinations of shading material thickness and arc length. The most significant increase in shielding effectiveness occurs at the thickest copper layer, between the shield angles 180 and 270 degrees. At the distance of 565 mm from the system axis, the shielding effectiveness will increase 2.4 times for the specified angle increase. The obtained results show that partial shielding can provide good protection in many practical cases and additionally reduce the amount of used material.","PeriodicalId":302869,"journal":{"name":"2022 4th International Conference on Emerging Trends in Electrical, Electronic and Communications Engineering (ELECOM)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131983531","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 : 2022-11-22DOI: 10.1109/ELECOM54934.2022.9965212
Khalid M. B. A. Joolfoo, R. Jugurnauth, Muhammad B. A. Joolfoo
Call drop in the cellular networking decides the top players of the industry where the most rated cellular network could sustain in the market and the least rated could face even bankruptcy. Customer satisfaction towards call quality is an important factor that any telecom organization must focus in order to survive successfully in the market in the long run. This research has demonstrated on how machine learning can be applied to predict customer satisfaction towards call drop quality of various telecom service providers. The dataset was acquired from Kaggle and the developed machine learning model has been trained and tested using the dataset. The research uses Random Forest Classifier for classification. The parameters under focus are the call rating, call drop, and the number of subscribers. The study focused on three months of data samples as the timeline (September to November) to predict and estimate customer satisfaction of cellular networking through developing a machine learning model that examined the call quality during a call, with the rating provided by the customers (call rating) at the call termination. The developed model was measured for its performance through recall, precision, accuracy and F1-score. The results obtained had rendered 91% accuracy in terms of predicting the customer satisfaction of call quality.
{"title":"Application of Machine Learning in Predicting Customer Satisfaction of Telecom Service Providers","authors":"Khalid M. B. A. Joolfoo, R. Jugurnauth, Muhammad B. A. Joolfoo","doi":"10.1109/ELECOM54934.2022.9965212","DOIUrl":"https://doi.org/10.1109/ELECOM54934.2022.9965212","url":null,"abstract":"Call drop in the cellular networking decides the top players of the industry where the most rated cellular network could sustain in the market and the least rated could face even bankruptcy. Customer satisfaction towards call quality is an important factor that any telecom organization must focus in order to survive successfully in the market in the long run. This research has demonstrated on how machine learning can be applied to predict customer satisfaction towards call drop quality of various telecom service providers. The dataset was acquired from Kaggle and the developed machine learning model has been trained and tested using the dataset. The research uses Random Forest Classifier for classification. The parameters under focus are the call rating, call drop, and the number of subscribers. The study focused on three months of data samples as the timeline (September to November) to predict and estimate customer satisfaction of cellular networking through developing a machine learning model that examined the call quality during a call, with the rating provided by the customers (call rating) at the call termination. The developed model was measured for its performance through recall, precision, accuracy and F1-score. The results obtained had rendered 91% accuracy in terms of predicting the customer satisfaction of call quality.","PeriodicalId":302869,"journal":{"name":"2022 4th International Conference on Emerging Trends in Electrical, Electronic and Communications Engineering (ELECOM)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131077187","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：