Pub Date : 2022-06-16DOI: 10.1109/CyberneticsCom55287.2022.9865461
Demas Yangindrajat, H. Guntur
This study presents the uses of Fuzzy control for AFPMSG (Axial Flux Permanent Magnet Synchronous Generator), which it is implemented on a Wheel Hub Motor (WHM) 1.5KW. The use of Fuzzy aims to stabilize the voltage used for charging batteries in electric vehicles. Electric vehicles today have a shortage in mileage. This research optimizes the WHM function for driving and also to charging with AFPMSG Fuzzy control. AFPMSG was made on the WHM stator and magnets on the WHM cover. The type of generator is used without a core on the coil. The generator has been simulated using MATLAB and FEM. The simulation results show a maximum voltage of 24 Volts at a speed of 1000 RPM. The system used for Fuzzy input is the speed and distance of the motor. The resulting output is a voltage. Fuzzy control is used for the stability of the charging system in electric vehicles. The research is presented in the form of simulations and field tests.
{"title":"Fuzzy Logic Control Strategy for Axial Flux Permanent Magnet Synchronous Generator in WHM 1.5KW","authors":"Demas Yangindrajat, H. Guntur","doi":"10.1109/CyberneticsCom55287.2022.9865461","DOIUrl":"https://doi.org/10.1109/CyberneticsCom55287.2022.9865461","url":null,"abstract":"This study presents the uses of Fuzzy control for AFPMSG (Axial Flux Permanent Magnet Synchronous Generator), which it is implemented on a Wheel Hub Motor (WHM) 1.5KW. The use of Fuzzy aims to stabilize the voltage used for charging batteries in electric vehicles. Electric vehicles today have a shortage in mileage. This research optimizes the WHM function for driving and also to charging with AFPMSG Fuzzy control. AFPMSG was made on the WHM stator and magnets on the WHM cover. The type of generator is used without a core on the coil. The generator has been simulated using MATLAB and FEM. The simulation results show a maximum voltage of 24 Volts at a speed of 1000 RPM. The system used for Fuzzy input is the speed and distance of the motor. The resulting output is a voltage. Fuzzy control is used for the stability of the charging system in electric vehicles. The research is presented in the form of simulations and field tests.","PeriodicalId":178279,"journal":{"name":"2022 IEEE International Conference on Cybernetics and Computational Intelligence (CyberneticsCom)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114166106","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}
With the increase in the number of drones, it is possible to have the danger of using drones illegally. It is crucial to detect adverse events or conditions so that security operators can obtain that information and situational identification of drones. This paper proposes two methods of classifying acoustic sensor data in a UAV detection system, using Support Vector Machine and Neural Network, that will be compared. This research shows that the accuracy achieved in predicting acoustic sensor data is 82.27% in the SVM method. The accuracy achieved is 90.58% for the NN method under the same input conditions and amount of training data. This comparation needs to do to choose the best accuracy in a public safety environment.
{"title":"Comparison of Support Vector Machine and Neural Network Algorithm in Drone Detection System","authors":"Risa Farrid Christianti, Hanin Latif Fuadi, M. Afandi, Azhari S.N., Andi Dharmawan","doi":"10.1109/CyberneticsCom55287.2022.9865628","DOIUrl":"https://doi.org/10.1109/CyberneticsCom55287.2022.9865628","url":null,"abstract":"With the increase in the number of drones, it is possible to have the danger of using drones illegally. It is crucial to detect adverse events or conditions so that security operators can obtain that information and situational identification of drones. This paper proposes two methods of classifying acoustic sensor data in a UAV detection system, using Support Vector Machine and Neural Network, that will be compared. This research shows that the accuracy achieved in predicting acoustic sensor data is 82.27% in the SVM method. The accuracy achieved is 90.58% for the NN method under the same input conditions and amount of training data. This comparation needs to do to choose the best accuracy in a public safety environment.","PeriodicalId":178279,"journal":{"name":"2022 IEEE International Conference on Cybernetics and Computational Intelligence (CyberneticsCom)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124838488","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 : 2022-06-16DOI: 10.1109/CyberneticsCom55287.2022.9865594
Binh Van Duong, Kim Chi T. Phan, Chien Nhu Ha, Phat Cao Tran, Trong-Hop Do
Vietnam has achieved impressive economic growth in the last two decades. It becomes a worth investing country in the area. Consequently, the need of understanding foreign investors from different countries (S. Korea in specific) is an essential issue. Therefore, building an automatic machine translation system with high precision is a necessary solution, especially during the COVID-19 pandemic, where keeping distance is the best way to avoid spreading the virus. As a result, this research presents some experimental results on the TED Talks 2020 dataset for the task Korean - Vietnamese and Vietnamese - Korean machine translation with the purpose of providing an overview of the dataset and a deep learning machine translation model for the problem.
{"title":"A study of machine translation for Vietnamese and Korean on the TED Talks 2020 corpus","authors":"Binh Van Duong, Kim Chi T. Phan, Chien Nhu Ha, Phat Cao Tran, Trong-Hop Do","doi":"10.1109/CyberneticsCom55287.2022.9865594","DOIUrl":"https://doi.org/10.1109/CyberneticsCom55287.2022.9865594","url":null,"abstract":"Vietnam has achieved impressive economic growth in the last two decades. It becomes a worth investing country in the area. Consequently, the need of understanding foreign investors from different countries (S. Korea in specific) is an essential issue. Therefore, building an automatic machine translation system with high precision is a necessary solution, especially during the COVID-19 pandemic, where keeping distance is the best way to avoid spreading the virus. As a result, this research presents some experimental results on the TED Talks 2020 dataset for the task Korean - Vietnamese and Vietnamese - Korean machine translation with the purpose of providing an overview of the dataset and a deep learning machine translation model for the problem.","PeriodicalId":178279,"journal":{"name":"2022 IEEE International Conference on Cybernetics and Computational Intelligence (CyberneticsCom)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127777669","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 : 2022-06-16DOI: 10.1109/CyberneticsCom55287.2022.9865466
Ayushi Maurya, Arun C. S. Kumar
Over the years, with the development of e-commerce, people are mostly making online transactions, and the risk of getting scammed has also increased. This in turn forces the financial institutions to improve continuously and upgrade their model. Machine Learning techniques were used to detect fraud in credit card transactions, but working with real-time data can be tough for machine learning to handle. Thus, implementation of blockchain techniques with machine learning to improve the efficiency and accuracy of the model. In the proposed model, Ethereum dataset has been used to check the fraudulent transaction and secure it with the help of machine learning algorithms. Out of all the classifiers XGBoost has attained the highest accuracy of 99.21% for the stated dataset.
{"title":"Credit card fraud detection system using machine learning technique","authors":"Ayushi Maurya, Arun C. S. Kumar","doi":"10.1109/CyberneticsCom55287.2022.9865466","DOIUrl":"https://doi.org/10.1109/CyberneticsCom55287.2022.9865466","url":null,"abstract":"Over the years, with the development of e-commerce, people are mostly making online transactions, and the risk of getting scammed has also increased. This in turn forces the financial institutions to improve continuously and upgrade their model. Machine Learning techniques were used to detect fraud in credit card transactions, but working with real-time data can be tough for machine learning to handle. Thus, implementation of blockchain techniques with machine learning to improve the efficiency and accuracy of the model. In the proposed model, Ethereum dataset has been used to check the fraudulent transaction and secure it with the help of machine learning algorithms. Out of all the classifiers XGBoost has attained the highest accuracy of 99.21% for the stated dataset.","PeriodicalId":178279,"journal":{"name":"2022 IEEE International Conference on Cybernetics and Computational Intelligence (CyberneticsCom)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127848378","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 : 2022-06-16DOI: 10.1109/CyberneticsCom55287.2022.9865467
Bayu Ardianto, Hery Sapto Dwi Nurcahyo, Hasan Muftic, R. Harwahyu, R. F. Sari
Vehicular Ad-hoc Networks (VANET) is used by autonomous vehicles as an efficient and reliable external vehicle communication. The routing protocol that has a stable and efficient performance is one that affects the quality of vehicle communication. This research simulates and analyzes the performance of VANET routing protocols, namely Ad-hoc On-demand Distance Vector (AODV), Ad-hoc On-demand Distance Vector-Expected Transmission (AODV-ETX), and Modified AODV-ETX using Network Simulator 3 (NS3). Our experiment shows that AODV has the best throughput performance, AODV-ETX performs the best Overhead and Packet Delivery Ratio, in terms of Modified AODV-ETX shows the best goodput performance compared to the others. Overall, the Modified AODV-ETX with My Route Timeout (MRT) and Active Route Timeout (ART) values 80 seconds provides better performance compared to AODV-ETX.
{"title":"Performance Comparison of AODV, AODV-ETX and Modified AODV-ETX in VANET using NS3","authors":"Bayu Ardianto, Hery Sapto Dwi Nurcahyo, Hasan Muftic, R. Harwahyu, R. F. Sari","doi":"10.1109/CyberneticsCom55287.2022.9865467","DOIUrl":"https://doi.org/10.1109/CyberneticsCom55287.2022.9865467","url":null,"abstract":"Vehicular Ad-hoc Networks (VANET) is used by autonomous vehicles as an efficient and reliable external vehicle communication. The routing protocol that has a stable and efficient performance is one that affects the quality of vehicle communication. This research simulates and analyzes the performance of VANET routing protocols, namely Ad-hoc On-demand Distance Vector (AODV), Ad-hoc On-demand Distance Vector-Expected Transmission (AODV-ETX), and Modified AODV-ETX using Network Simulator 3 (NS3). Our experiment shows that AODV has the best throughput performance, AODV-ETX performs the best Overhead and Packet Delivery Ratio, in terms of Modified AODV-ETX shows the best goodput performance compared to the others. Overall, the Modified AODV-ETX with My Route Timeout (MRT) and Active Route Timeout (ART) values 80 seconds provides better performance compared to AODV-ETX.","PeriodicalId":178279,"journal":{"name":"2022 IEEE International Conference on Cybernetics and Computational Intelligence (CyberneticsCom)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114579852","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 : 2022-06-16DOI: 10.1109/CyberneticsCom55287.2022.9865487
F. Zhultriza, Aries Subiantoro
The fault and anomaly of real-time performance gas turbine data are difficult to predict because of the complexity of feature data and dynamically time series. In the case of real performance gas turbine, the complexity of the physical model is hard to interpret. In deep learning, the Convolutional Neural Network (CNN) is used to perform the identification of data with great feature extraction. But, since CNN is poorly accurate for time-series data, the prediction for gas turbine anomaly could be hardly optimized. Another neural network method that can interact with time-series data is Recurrent Neural Network (RNN), especially, the Long Short-Term Memory (LSTM) that can deal with the vanishing gradient problem in traditional RNN. This paper aims to develop hybrid CNN-LSTM as a proposed method to predict gas turbine anomaly more accurately than single CNN. The accuracy of the single CNN method is 81.33%. With the addition of LSTM in the same CNN architecture, the accuracy of hybrid CNN-LSTM is 91.79%. The accuracy of model data is significantly increased by adding LSTM layer after the convolutional and pooling layer.
{"title":"Gas Turbine Anomaly Prediction using Hybrid Convolutional Neural Network with LSTM in Power Plant","authors":"F. Zhultriza, Aries Subiantoro","doi":"10.1109/CyberneticsCom55287.2022.9865487","DOIUrl":"https://doi.org/10.1109/CyberneticsCom55287.2022.9865487","url":null,"abstract":"The fault and anomaly of real-time performance gas turbine data are difficult to predict because of the complexity of feature data and dynamically time series. In the case of real performance gas turbine, the complexity of the physical model is hard to interpret. In deep learning, the Convolutional Neural Network (CNN) is used to perform the identification of data with great feature extraction. But, since CNN is poorly accurate for time-series data, the prediction for gas turbine anomaly could be hardly optimized. Another neural network method that can interact with time-series data is Recurrent Neural Network (RNN), especially, the Long Short-Term Memory (LSTM) that can deal with the vanishing gradient problem in traditional RNN. This paper aims to develop hybrid CNN-LSTM as a proposed method to predict gas turbine anomaly more accurately than single CNN. The accuracy of the single CNN method is 81.33%. With the addition of LSTM in the same CNN architecture, the accuracy of hybrid CNN-LSTM is 91.79%. The accuracy of model data is significantly increased by adding LSTM layer after the convolutional and pooling layer.","PeriodicalId":178279,"journal":{"name":"2022 IEEE International Conference on Cybernetics and Computational Intelligence (CyberneticsCom)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114867931","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}
Indonesia is a country where most of the population work in the agricultural and plantation sectors. Both sectors are significant for the economy of Indonesia because it contributes to the increase in Gross Domestic Product (GDP). Such as the tea plantation sub-sector, which is one of the export commodities in Indonesia. However, several problems occur to the tea farmers in Indonesia. These problems influence decreasing in tea quality and farmers' welfare in Indonesia. For that reason, TehNusa is created to help solve the issues. TehNusa can be utilized to buy and sell harvested or processed tea. Another hand, TehNusa also has other functions to develop the quality and ability of the community in caring for and managing processed tea. Another side, BUMDes will play a role by managing and developing village prospects and tea farmers to minimize gaps. The design of the TehNusa application is created using the design sprint methodology and for the design validation, we're using the system usability scale methodology. The design of the TehNusa application can be made within 40 working hours, and the test result of design validation gets a conclusion of 81 points or equivalent to grade B. The TehNusa application is rated by users as being able to help make it easier to solve problems. In addition, further research needs to be carried out to determine the implementation of making applications and building business cooperation with BUMDes in Indonesian villages that have skilled farmers and have the potential to become processed tea producers.
{"title":"Designing TehNusa Mobile Based Application Using Design Sprint Method","authors":"Dinda Maylan Setianti, Daffa Raihan Zaki, Gita Fadila Fitriana, Aditya Ammar Pradana","doi":"10.1109/CyberneticsCom55287.2022.9865534","DOIUrl":"https://doi.org/10.1109/CyberneticsCom55287.2022.9865534","url":null,"abstract":"Indonesia is a country where most of the population work in the agricultural and plantation sectors. Both sectors are significant for the economy of Indonesia because it contributes to the increase in Gross Domestic Product (GDP). Such as the tea plantation sub-sector, which is one of the export commodities in Indonesia. However, several problems occur to the tea farmers in Indonesia. These problems influence decreasing in tea quality and farmers' welfare in Indonesia. For that reason, TehNusa is created to help solve the issues. TehNusa can be utilized to buy and sell harvested or processed tea. Another hand, TehNusa also has other functions to develop the quality and ability of the community in caring for and managing processed tea. Another side, BUMDes will play a role by managing and developing village prospects and tea farmers to minimize gaps. The design of the TehNusa application is created using the design sprint methodology and for the design validation, we're using the system usability scale methodology. The design of the TehNusa application can be made within 40 working hours, and the test result of design validation gets a conclusion of 81 points or equivalent to grade B. The TehNusa application is rated by users as being able to help make it easier to solve problems. In addition, further research needs to be carried out to determine the implementation of making applications and building business cooperation with BUMDes in Indonesian villages that have skilled farmers and have the potential to become processed tea producers.","PeriodicalId":178279,"journal":{"name":"2022 IEEE International Conference on Cybernetics and Computational Intelligence (CyberneticsCom)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128670523","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 : 2022-06-16DOI: 10.1109/CyberneticsCom55287.2022.9865663
Swardiantara Silalahi, T. Ahmad, H. Studiawan
Data mining techniques in analyzing log data can discover a useful pattern which then is used to infer knowledge. Interesting patterns in log data can help the stakeholder to take action to diagnose a problem or improve the running system. Drone as one loT device, which consists of subsystems working together, also implements a logging mechanism. While a drone is flying, event-related logs are written into specific log files. These files contain precious information in case of incident happens to the drone. Assuming that the integrity of the log files is guaranteed, the investigator can find useful patterns and help conclude the incidents. To this end, this paper studies the sequence mining approach to discover some pre-defined incident-related events. As this is an initial study, the main contribution of this paper is the domain adaptation and modeling of the flight logs into a sequence database. After experimenting, we conclude that the modeling procedure is an essential step in conducting sequence mining. Frequency-oriented techniques are not suitable for small sequence databases, as the found patterns tend to have less critical events. Finally, two potential future directions are elaborated.
{"title":"Drone Flight Logs Sequence Mining","authors":"Swardiantara Silalahi, T. Ahmad, H. Studiawan","doi":"10.1109/CyberneticsCom55287.2022.9865663","DOIUrl":"https://doi.org/10.1109/CyberneticsCom55287.2022.9865663","url":null,"abstract":"Data mining techniques in analyzing log data can discover a useful pattern which then is used to infer knowledge. Interesting patterns in log data can help the stakeholder to take action to diagnose a problem or improve the running system. Drone as one loT device, which consists of subsystems working together, also implements a logging mechanism. While a drone is flying, event-related logs are written into specific log files. These files contain precious information in case of incident happens to the drone. Assuming that the integrity of the log files is guaranteed, the investigator can find useful patterns and help conclude the incidents. To this end, this paper studies the sequence mining approach to discover some pre-defined incident-related events. As this is an initial study, the main contribution of this paper is the domain adaptation and modeling of the flight logs into a sequence database. After experimenting, we conclude that the modeling procedure is an essential step in conducting sequence mining. Frequency-oriented techniques are not suitable for small sequence databases, as the found patterns tend to have less critical events. Finally, two potential future directions are elaborated.","PeriodicalId":178279,"journal":{"name":"2022 IEEE International Conference on Cybernetics and Computational Intelligence (CyberneticsCom)","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131081683","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 : 2022-06-16DOI: 10.1109/CyberneticsCom55287.2022.9865255
Inam Abdullah Abdulmajeed, I. Husien
Intrusion Detection System (IDS) is a critical component in cyber security to capture and analyze the traffic and then differentiate between benignant and malicious traffic indicating the attack type. This review is aimed to investigate various Machine Learning (ML) algorithms utilized in IDS design; with particular focus on dataset used. The parameters used to compare the performance of each algorithm have been studied also. Dataset choice is exceptionally critical to guarantee that it is matching the IDS requirements. The dataset structure can influence in a great manner the selection of the of ML algorithm. Hence, metric will provide a numerical relation between ML algorithm against specific dataset. This review concluded that researches are liberating themselves from Supervised Learning and moving toward Clustering and other algorithms, which gives the hope that IDS in the future will be able to detect more unknown and zero-day attacks, also the percentage of utilizing hybrid algorithms has increased dramatically. On the other hand, recent ML researchers are depending more and more on modern datasets which contributes as a significant consideration in IDS design although some research articles are still seeing the KDDCup99 and its reduced variant as principal training dataset of IDSs, despite the fact that it is more than 20 years old, while cyber-threats keep rising together with adapting new technologies in the cyber world like cloud computing, IoT, and IPv6.
{"title":"Machine Learning Algorithms and Datasets for Modern IDS Design","authors":"Inam Abdullah Abdulmajeed, I. Husien","doi":"10.1109/CyberneticsCom55287.2022.9865255","DOIUrl":"https://doi.org/10.1109/CyberneticsCom55287.2022.9865255","url":null,"abstract":"Intrusion Detection System (IDS) is a critical component in cyber security to capture and analyze the traffic and then differentiate between benignant and malicious traffic indicating the attack type. This review is aimed to investigate various Machine Learning (ML) algorithms utilized in IDS design; with particular focus on dataset used. The parameters used to compare the performance of each algorithm have been studied also. Dataset choice is exceptionally critical to guarantee that it is matching the IDS requirements. The dataset structure can influence in a great manner the selection of the of ML algorithm. Hence, metric will provide a numerical relation between ML algorithm against specific dataset. This review concluded that researches are liberating themselves from Supervised Learning and moving toward Clustering and other algorithms, which gives the hope that IDS in the future will be able to detect more unknown and zero-day attacks, also the percentage of utilizing hybrid algorithms has increased dramatically. On the other hand, recent ML researchers are depending more and more on modern datasets which contributes as a significant consideration in IDS design although some research articles are still seeing the KDDCup99 and its reduced variant as principal training dataset of IDSs, despite the fact that it is more than 20 years old, while cyber-threats keep rising together with adapting new technologies in the cyber world like cloud computing, IoT, and IPv6.","PeriodicalId":178279,"journal":{"name":"2022 IEEE International Conference on Cybernetics and Computational Intelligence (CyberneticsCom)","volume":"87 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122566110","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 : 2022-06-16DOI: 10.1109/CyberneticsCom55287.2022.9865610
Kien Trang, Hoang An Nguyen, Long TonThat, Hung Ngoc Do, B. Vuong
The rapid spreading rate of the Coronavirus disease 2019 (COVID-19) has resulted in more than 6.2 million deceased cases. Furthermore, the patients of the latest Omicron variation carry light to almost no symptoms of the disease themselves. Thus, the requirement for a new diagnosis method besides Reverse Transcription-Polymerase Chain Reaction (RT-PCR) becomes the most important step to successfully detect infected cases. In this research, the application of the KNN, Ensemble and SincNet models are implemented as the main models for classification diagnosis based on cough sound records of infected patients. After pre-processing steps for removing silence ranges in the audio scripts, the cough sounds are augmented, subsequently separated into single cough samples, then generated 3 testing scenarios for dealing with the imbalanced problem between the sample classes. Afterward, MelFrequency information and MelSprectrogram are extracted as main features for analysis in order to distinguish patients with COVID-19 disease and healthy cases. The AICV115M dataset consisting of two classes COVID-19 and NonCOVID-19 is implemented for performance evaluation. The recorded highest accuracy on the models KNN, Ensemble and SincNet are 92.49%, 90.1% and 85.15%, respectively.
{"title":"COVID-19 Disease Classification by Cough Records Analysis using Machine Learning","authors":"Kien Trang, Hoang An Nguyen, Long TonThat, Hung Ngoc Do, B. Vuong","doi":"10.1109/CyberneticsCom55287.2022.9865610","DOIUrl":"https://doi.org/10.1109/CyberneticsCom55287.2022.9865610","url":null,"abstract":"The rapid spreading rate of the Coronavirus disease 2019 (COVID-19) has resulted in more than 6.2 million deceased cases. Furthermore, the patients of the latest Omicron variation carry light to almost no symptoms of the disease themselves. Thus, the requirement for a new diagnosis method besides Reverse Transcription-Polymerase Chain Reaction (RT-PCR) becomes the most important step to successfully detect infected cases. In this research, the application of the KNN, Ensemble and SincNet models are implemented as the main models for classification diagnosis based on cough sound records of infected patients. After pre-processing steps for removing silence ranges in the audio scripts, the cough sounds are augmented, subsequently separated into single cough samples, then generated 3 testing scenarios for dealing with the imbalanced problem between the sample classes. Afterward, MelFrequency information and MelSprectrogram are extracted as main features for analysis in order to distinguish patients with COVID-19 disease and healthy cases. The AICV115M dataset consisting of two classes COVID-19 and NonCOVID-19 is implemented for performance evaluation. The recorded highest accuracy on the models KNN, Ensemble and SincNet are 92.49%, 90.1% and 85.15%, respectively.","PeriodicalId":178279,"journal":{"name":"2022 IEEE International Conference on Cybernetics and Computational Intelligence (CyberneticsCom)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116989694","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：