Pub Date : 2020-06-01DOI: 10.1109/ecti-con49241.2020.9158297
{"title":"ECTI-CON 2020 Messages","authors":"","doi":"10.1109/ecti-con49241.2020.9158297","DOIUrl":"https://doi.org/10.1109/ecti-con49241.2020.9158297","url":null,"abstract":"","PeriodicalId":371552,"journal":{"name":"2020 17th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology (ECTI-CON)","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123803787","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 : 2020-06-01DOI: 10.1109/ECTI-CON49241.2020.9158277
K. Kanjanasit, Sutasinee Sanesaowarod, N. Homsup
In this paper we present the comparative study of an electromagnetically induced transparent (EIT) effect in a two-layer metamaterial (MM) for a high-gain planar antenna application. The proposed mechanism of a low-profile EIT-like MM is based on an identical resonant square ring arrays in a sandwich structure with a small dielectric thickness. The EIT-like effect was observed connected with a resonance condition in a narrow transmission window due to the near-field coupling of the identical ring resonators behaved as a unit-cell element in periodic arrangement. The simulation study shows that the property of electric conductivity in a perfect electric conductor (PEC) and copper influences on a resonant transmission peak. The EIT-like MM was utilized for a high-gain directive planar antenna design by applying a blank conductor surface at a planar line symmetry acting as an electromagnetic mirror. The narrow aperture fed by short-end coplanar waveguide (CPW) feed-line was incorporated into a conductor surface as a driven radiator. The EIT-like MM antenna can be operated close to the targeted resonant frequency of the EIT-like MM (~10 GHz). The proposed planar antenna provides a thickness of λ/60 (0.5 mm). The simulation of the proposed planar antenna design was performed and it reports the antenna gain of 14.45 dBi and 13.32 dBi in cases of using the PEC- and copper-based square ring resonator array respectively. The antenna-gain difference is due to the ohmic-loss absorption regarding to electric conductivity.
{"title":"EIT-Like Effect in Metamaterials based on Two-Layer Arrays for High-Gain Antennas","authors":"K. Kanjanasit, Sutasinee Sanesaowarod, N. Homsup","doi":"10.1109/ECTI-CON49241.2020.9158277","DOIUrl":"https://doi.org/10.1109/ECTI-CON49241.2020.9158277","url":null,"abstract":"In this paper we present the comparative study of an electromagnetically induced transparent (EIT) effect in a two-layer metamaterial (MM) for a high-gain planar antenna application. The proposed mechanism of a low-profile EIT-like MM is based on an identical resonant square ring arrays in a sandwich structure with a small dielectric thickness. The EIT-like effect was observed connected with a resonance condition in a narrow transmission window due to the near-field coupling of the identical ring resonators behaved as a unit-cell element in periodic arrangement. The simulation study shows that the property of electric conductivity in a perfect electric conductor (PEC) and copper influences on a resonant transmission peak. The EIT-like MM was utilized for a high-gain directive planar antenna design by applying a blank conductor surface at a planar line symmetry acting as an electromagnetic mirror. The narrow aperture fed by short-end coplanar waveguide (CPW) feed-line was incorporated into a conductor surface as a driven radiator. The EIT-like MM antenna can be operated close to the targeted resonant frequency of the EIT-like MM (~10 GHz). The proposed planar antenna provides a thickness of λ/60 (0.5 mm). The simulation of the proposed planar antenna design was performed and it reports the antenna gain of 14.45 dBi and 13.32 dBi in cases of using the PEC- and copper-based square ring resonator array respectively. The antenna-gain difference is due to the ohmic-loss absorption regarding to electric conductivity.","PeriodicalId":371552,"journal":{"name":"2020 17th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology (ECTI-CON)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121406117","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 : 2020-06-01DOI: 10.1109/ecti-con49241.2020.9158086
Aitthiphak Boonyakiat, P. Kamphikul, S. Kampeephat
Nowadays, a microstrip slot antenna is widely used in the modern wireless communication systems because it has more advantages such as compact, easy fabrication, low cost, and wide bandwidth. However, it also has the drawback such low gain, because of its resonant nature of microstrip. Therefore, this paper presents a method to increase and improve the gain of slot antenna, a bandwidth of 1,800 MHz to 6,000 MHz, to apply for a modern wireless communication system. The new technique of metamaterial utilized for improving the gain of slot antenna is presented. From this study, the proper metamaterial, the curved metallic holes structure, is competent to improve the performance of slot antenna by increasing it directivity, gain, and radiation efficiency. Moreover, a behavior of gain characteristic, reflection coefficient (S11), and radiation pattern of slot antenna with and without a metallic holes structure are examined in this paper. From simulated results by simulation software, it noted that the gains of all the operating frequencies of a slot antenna with a metallic holes structure have been increased around 1.7 dB of all operating frequencies when compared to a slot antenna without a metallic holes structure.
{"title":"A Study of Gain Improvement of a Slot Antenna Using Curved Metallic Holes Structure","authors":"Aitthiphak Boonyakiat, P. Kamphikul, S. Kampeephat","doi":"10.1109/ecti-con49241.2020.9158086","DOIUrl":"https://doi.org/10.1109/ecti-con49241.2020.9158086","url":null,"abstract":"Nowadays, a microstrip slot antenna is widely used in the modern wireless communication systems because it has more advantages such as compact, easy fabrication, low cost, and wide bandwidth. However, it also has the drawback such low gain, because of its resonant nature of microstrip. Therefore, this paper presents a method to increase and improve the gain of slot antenna, a bandwidth of 1,800 MHz to 6,000 MHz, to apply for a modern wireless communication system. The new technique of metamaterial utilized for improving the gain of slot antenna is presented. From this study, the proper metamaterial, the curved metallic holes structure, is competent to improve the performance of slot antenna by increasing it directivity, gain, and radiation efficiency. Moreover, a behavior of gain characteristic, reflection coefficient (S11), and radiation pattern of slot antenna with and without a metallic holes structure are examined in this paper. From simulated results by simulation software, it noted that the gains of all the operating frequencies of a slot antenna with a metallic holes structure have been increased around 1.7 dB of all operating frequencies when compared to a slot antenna without a metallic holes structure.","PeriodicalId":371552,"journal":{"name":"2020 17th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology (ECTI-CON)","volume":"159 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124456380","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 : 2020-06-01DOI: 10.1109/ecti-con49241.2020.9158230
A. Kyaw, May Zin Oo, C. Khin
Due to centralized control and programmable capability of the SDN architecture, network administrators can easily manage and control the whole network through the centralized controller. According to the SDN architecture, the SDN controller is vulnerable to distributed denial of service (DDOS) attacks. Thus, a failure of SDN controller is a major leak for security concern. The objectives of paper is therefore to detect the DDOS attacks and classify the normal or attack traffic in SDN network using machine learning algorithms. In this proposed system, polynomial SVM is applied to compare to existing linear SVM by using scapy, which is packet generation tool and RYU SDN controller. According to the experimental result, polynomial SVM achieves 3% better accuracy and 34% lower false alarm rate compared to Linear SVM.
由于SDN架构的集中控制和可编程能力，网络管理员可以通过集中控制器方便地管理和控制整个网络。在SDN架构下，SDN控制器容易受到DDOS (distributed denial of service)攻击。因此，SDN控制器的故障是安全问题的主要泄漏。因此，本文的目标是使用机器学习算法检测DDOS攻击并对SDN网络中的正常或攻击流量进行分类。在该系统中，利用数据包生成工具scapy和RYU SDN控制器，将多项式支持向量机与现有的线性支持向量机进行比较。实验结果表明，与线性支持向量机相比，多项式支持向量机的准确率提高3%，虚警率降低34%。
{"title":"Machine-Learning Based DDOS Attack Classifier in Software Defined Network","authors":"A. Kyaw, May Zin Oo, C. Khin","doi":"10.1109/ecti-con49241.2020.9158230","DOIUrl":"https://doi.org/10.1109/ecti-con49241.2020.9158230","url":null,"abstract":"Due to centralized control and programmable capability of the SDN architecture, network administrators can easily manage and control the whole network through the centralized controller. According to the SDN architecture, the SDN controller is vulnerable to distributed denial of service (DDOS) attacks. Thus, a failure of SDN controller is a major leak for security concern. The objectives of paper is therefore to detect the DDOS attacks and classify the normal or attack traffic in SDN network using machine learning algorithms. In this proposed system, polynomial SVM is applied to compare to existing linear SVM by using scapy, which is packet generation tool and RYU SDN controller. According to the experimental result, polynomial SVM achieves 3% better accuracy and 34% lower false alarm rate compared to Linear SVM.","PeriodicalId":371552,"journal":{"name":"2020 17th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology (ECTI-CON)","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125143553","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 : 2020-06-01DOI: 10.1109/ecti-con49241.2020.9158116
P. Thongdit, Surachai Chunchay, K. Angkeaw
This paper presents a scheme of pinched hysteresis loop behavior of a proposed meminductor emulator circuit at frequency of 5 kHz, 10 kHz, and 20 kHz. The mathematical model with flux-controlled concept was chosen to apply for meminductor equation and used for creating a proposed emulator. The proposed meminductor emulator was created based on the device called Field Programmable Analog Arrays (FPAAs). The AnadigmDesigner2 software was used to simulate in order to verify the performance of proposed meminductor emulator. Moreover, the variation of phase diagram of time integral of the flux and charge were computed to determine the meminductance.
{"title":"A Meminductor Emulator Based on Flux-controlled Model Using Field Programmable Analog Array","authors":"P. Thongdit, Surachai Chunchay, K. Angkeaw","doi":"10.1109/ecti-con49241.2020.9158116","DOIUrl":"https://doi.org/10.1109/ecti-con49241.2020.9158116","url":null,"abstract":"This paper presents a scheme of pinched hysteresis loop behavior of a proposed meminductor emulator circuit at frequency of 5 kHz, 10 kHz, and 20 kHz. The mathematical model with flux-controlled concept was chosen to apply for meminductor equation and used for creating a proposed emulator. The proposed meminductor emulator was created based on the device called Field Programmable Analog Arrays (FPAAs). The AnadigmDesigner2 software was used to simulate in order to verify the performance of proposed meminductor emulator. Moreover, the variation of phase diagram of time integral of the flux and charge were computed to determine the meminductance.","PeriodicalId":371552,"journal":{"name":"2020 17th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology (ECTI-CON)","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128889769","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 : 2020-06-01DOI: 10.1109/ecti-con49241.2020.9158103
Piyapat Leeraksakiat, W. Pora
Neural networks can be used as a forecasting tool in several fields such as medicine, agriculture, and entertainment. Accurate forecasting of human habit such as the entry/exit behavior of a person may be exploited to control electrical appliances in order to reduce energy consumption while maintaining comfort. However, the neural network has a problem that is it can be trained to forecast behavior of only one person. If the neural network is used to predict another person, It will decrease accuracy. Although new data will be collected to re-train the neural network, data collection might take long time. This paper proposes to use transfer learning on a Long Short-Term Memory (LSTM) network in order to improve the performance of the network after a specific person uses the room, the person changes his/her behavior, or a new person occupies the room. After a network is trained by a norm dataset, then new batches of sampling data can be applied to update the network, in other words, to transfer the new knowledge on top of the existing one. The results show that transfer learning helps the LSTM network to be able to track the behavior change continually. Its forecast becomes more and more accurate, when compared to that of the norm one.
{"title":"Occupancy Forecasting using LSTM Neural Network and Transfer Learning","authors":"Piyapat Leeraksakiat, W. Pora","doi":"10.1109/ecti-con49241.2020.9158103","DOIUrl":"https://doi.org/10.1109/ecti-con49241.2020.9158103","url":null,"abstract":"Neural networks can be used as a forecasting tool in several fields such as medicine, agriculture, and entertainment. Accurate forecasting of human habit such as the entry/exit behavior of a person may be exploited to control electrical appliances in order to reduce energy consumption while maintaining comfort. However, the neural network has a problem that is it can be trained to forecast behavior of only one person. If the neural network is used to predict another person, It will decrease accuracy. Although new data will be collected to re-train the neural network, data collection might take long time. This paper proposes to use transfer learning on a Long Short-Term Memory (LSTM) network in order to improve the performance of the network after a specific person uses the room, the person changes his/her behavior, or a new person occupies the room. After a network is trained by a norm dataset, then new batches of sampling data can be applied to update the network, in other words, to transfer the new knowledge on top of the existing one. The results show that transfer learning helps the LSTM network to be able to track the behavior change continually. Its forecast becomes more and more accurate, when compared to that of the norm one.","PeriodicalId":371552,"journal":{"name":"2020 17th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology (ECTI-CON)","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130887174","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 : 2020-06-01DOI: 10.1109/ecti-con49241.2020.9158127
C. Khin, May Zin Oo, A. Kyaw
this paper proposes a mechanism that handles the packet-in messages to reduce the bottlenecks of controller in SDN/OpenFlow network. In SDN networks, the Openflow switches send many packet-in messages to forward every new flow of data. Then, the controller responds the flow rule for each packet-in message. Therefore, the bottlenecks can occur between controller and switches for sending three packets (one flooding and two packet-in messages) to add a new flow. The proposed system can reduce this bottleneck effect by adding a couple flow rules only with a single packet-in message. It is implemented using Mininet emulator to create a network topology and Ryu OpenFlow controller to manage the forwarding plane by the controller. The evaluation indicates that the proposed system is able to reduce one-third of packet overhead compared to original OpenFlow.
{"title":"Packet-in Messages Handling Scheme to Reduce Controller Bottlenecks in OpenFlow Networks","authors":"C. Khin, May Zin Oo, A. Kyaw","doi":"10.1109/ecti-con49241.2020.9158127","DOIUrl":"https://doi.org/10.1109/ecti-con49241.2020.9158127","url":null,"abstract":"this paper proposes a mechanism that handles the packet-in messages to reduce the bottlenecks of controller in SDN/OpenFlow network. In SDN networks, the Openflow switches send many packet-in messages to forward every new flow of data. Then, the controller responds the flow rule for each packet-in message. Therefore, the bottlenecks can occur between controller and switches for sending three packets (one flooding and two packet-in messages) to add a new flow. The proposed system can reduce this bottleneck effect by adding a couple flow rules only with a single packet-in message. It is implemented using Mininet emulator to create a network topology and Ryu OpenFlow controller to manage the forwarding plane by the controller. The evaluation indicates that the proposed system is able to reduce one-third of packet overhead compared to original OpenFlow.","PeriodicalId":371552,"journal":{"name":"2020 17th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology (ECTI-CON)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130613675","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 : 2020-06-01DOI: 10.1109/ecti-con49241.2020.9158258
Wipha Thomyamongkol, E. Nantajeewarawat, Pattravadee Ploykitikoon, Paramet Tanwanont
Risk adjusted measurements can be used to measure risk and volatility that are involved in investment returns. They are of great interest to investors. This paper focuses on evaluation of the risk adjusted measurements and aims to find the measurements that are most suitable for evaluating the performance of Thai mutual funds. Three popular risk adjusted measurements, i.e., Sharpe ratio, Treynor ratio, and Jensen’s alpha ratio, are used. Data from all funds in the bond asset class, the real estate asset class, and the equity asset class, from January 2013 to the end of December 2018 are used for the evaluation. The analysis shows that Jensen’s alpha ratio outperforms the other measurements in all the three asset classes.
{"title":"An Evaluation of Risk Adjusted Measurements for Thai Mutual Funds","authors":"Wipha Thomyamongkol, E. Nantajeewarawat, Pattravadee Ploykitikoon, Paramet Tanwanont","doi":"10.1109/ecti-con49241.2020.9158258","DOIUrl":"https://doi.org/10.1109/ecti-con49241.2020.9158258","url":null,"abstract":"Risk adjusted measurements can be used to measure risk and volatility that are involved in investment returns. They are of great interest to investors. This paper focuses on evaluation of the risk adjusted measurements and aims to find the measurements that are most suitable for evaluating the performance of Thai mutual funds. Three popular risk adjusted measurements, i.e., Sharpe ratio, Treynor ratio, and Jensen’s alpha ratio, are used. Data from all funds in the bond asset class, the real estate asset class, and the equity asset class, from January 2013 to the end of December 2018 are used for the evaluation. The analysis shows that Jensen’s alpha ratio outperforms the other measurements in all the three asset classes.","PeriodicalId":371552,"journal":{"name":"2020 17th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology (ECTI-CON)","volume":"136 10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131212573","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 : 2020-06-01DOI: 10.1109/ecti-con49241.2020.9158326
T. Sopon, W. Wongtrairat, Maitree Thamma, W. Wiboonjaroen, S. Kampeephat, Thanat Sooknuan
In this work, we investigate the voltage reference of comparator circuit for the receiver circuit on visible light communication (VLC) system. The method is the voltage reference comparator of the VLC receiver circuit in the data pulse signal compensation which is the data pulse signal detection circuit. In the experiment, we consider the signal with Manchester modulation on the FPGA board of the data signal via channel with the range of light intensity between 300 to 1,300 lux. The result of experiment sent the data inputs via the white LED at a distance of 70 - 90 centimeters which measured the signal outputs with the average percentage of bit error 0.145.
{"title":"Investigation of Comparator Circuit Base-on Voltage Reference on Visible Light Communication System","authors":"T. Sopon, W. Wongtrairat, Maitree Thamma, W. Wiboonjaroen, S. Kampeephat, Thanat Sooknuan","doi":"10.1109/ecti-con49241.2020.9158326","DOIUrl":"https://doi.org/10.1109/ecti-con49241.2020.9158326","url":null,"abstract":"In this work, we investigate the voltage reference of comparator circuit for the receiver circuit on visible light communication (VLC) system. The method is the voltage reference comparator of the VLC receiver circuit in the data pulse signal compensation which is the data pulse signal detection circuit. In the experiment, we consider the signal with Manchester modulation on the FPGA board of the data signal via channel with the range of light intensity between 300 to 1,300 lux. The result of experiment sent the data inputs via the white LED at a distance of 70 - 90 centimeters which measured the signal outputs with the average percentage of bit error 0.145.","PeriodicalId":371552,"journal":{"name":"2020 17th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology (ECTI-CON)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130229994","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 : 2020-06-01DOI: 10.1109/ecti-con49241.2020.9158120
J. Mongkolnavin, Widakorn Saewong
Call center is a department that is most relevant to audio data usage. One of its major tasks is to monitor customers’ anguish because it has a negative impact on the organization. One challenging task is to develop a model that can predict whether a customer is getting angry in the next turn of conversation. Such model can assist agents in taking appropriate action(s) to prevent the incidents. In this study, we investigate an approach to build an anger prediction model from customers’ voice in call center dialogs. To create the model requires 5 processes: (1) Customer’s turn extraction (2) Emotion annotation (3) Voice feature selection (4) Data pre-processing for long short-term memory networks, and (5) Anger prediction modeling. Five long short-term memory networks were built with the time series data sets of 1, 2, 3, 4, and 5 consecutive turns. The experimental results showed that the long short-term memory network built with the 3-consecutive turn data has promising performance in aspect of Average Precision and False Negative Rate when compared to the random and good guess benchmarks.
{"title":"Prediction of Forthcoming Anger of Customer in Call Center Dialogs","authors":"J. Mongkolnavin, Widakorn Saewong","doi":"10.1109/ecti-con49241.2020.9158120","DOIUrl":"https://doi.org/10.1109/ecti-con49241.2020.9158120","url":null,"abstract":"Call center is a department that is most relevant to audio data usage. One of its major tasks is to monitor customers’ anguish because it has a negative impact on the organization. One challenging task is to develop a model that can predict whether a customer is getting angry in the next turn of conversation. Such model can assist agents in taking appropriate action(s) to prevent the incidents. In this study, we investigate an approach to build an anger prediction model from customers’ voice in call center dialogs. To create the model requires 5 processes: (1) Customer’s turn extraction (2) Emotion annotation (3) Voice feature selection (4) Data pre-processing for long short-term memory networks, and (5) Anger prediction modeling. Five long short-term memory networks were built with the time series data sets of 1, 2, 3, 4, and 5 consecutive turns. The experimental results showed that the long short-term memory network built with the 3-consecutive turn data has promising performance in aspect of Average Precision and False Negative Rate when compared to the random and good guess benchmarks.","PeriodicalId":371552,"journal":{"name":"2020 17th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology (ECTI-CON)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128183278","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：