Pub Date : 2021-10-20DOI: 10.23919/eecsi53397.2021.9624299
Susanto, D. Stiawan, M. Arifin, J. Rejito, Mohd Yazid Bin Idris, R. Budiarto
The use of Internet of Thing (IoT) technology in industry or daily lives are improving massively. This improvement attracts hackers to perform cyber attack which one of them is botnet. One of the botnet threat is disrupting network and denial service to IoT devices. Therefore, a reliable detection system to keep the security is required urgently. One of the detection method which has been widely used by previous research works is machine learning. However, performance problem on machine learning needs more attention, especially for data with high scalability. In this paper, we conduct experiments on random projection dimensionality reduction approach to boost the machine learning performance to detect botnet IoT. Experiment results show random projection method combined with decision tree is able to detect IoT botnet within 8.44 seconds with accuracy of 100% and very low false positive rate (close to 0).
{"title":"A Dimensionality Reduction Approach for Machine Learning Based IoT Botnet Detection","authors":"Susanto, D. Stiawan, M. Arifin, J. Rejito, Mohd Yazid Bin Idris, R. Budiarto","doi":"10.23919/eecsi53397.2021.9624299","DOIUrl":"https://doi.org/10.23919/eecsi53397.2021.9624299","url":null,"abstract":"The use of Internet of Thing (IoT) technology in industry or daily lives are improving massively. This improvement attracts hackers to perform cyber attack which one of them is botnet. One of the botnet threat is disrupting network and denial service to IoT devices. Therefore, a reliable detection system to keep the security is required urgently. One of the detection method which has been widely used by previous research works is machine learning. However, performance problem on machine learning needs more attention, especially for data with high scalability. In this paper, we conduct experiments on random projection dimensionality reduction approach to boost the machine learning performance to detect botnet IoT. Experiment results show random projection method combined with decision tree is able to detect IoT botnet within 8.44 seconds with accuracy of 100% and very low false positive rate (close to 0).","PeriodicalId":259450,"journal":{"name":"2021 8th International Conference on Electrical Engineering, Computer Science and Informatics (EECSI)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129610282","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 : 2021-10-20DOI: 10.23919/eecsi53397.2021.9624240
Mohammad Minhazur Rahman, A. Z. M. Tahmidul Kabir, Shoumic Zaman Khan, Nahin Akhtar, Abdullah Al Mamun, S. Hossain
Reckless driving is one of the prominent causes of human-based vehicle collisions, which are gradually increasing. Furthermore, due to a lack of real-time evidence, very few further investigations are done to determine the actual causes of these accidents. The central theme of this titled paper is to construct a few sensor-based black box systems that will assist us in reducing traffic collisions by giving accurate instructions to the driver constantly. At the same time, it will upload the evidence to its server for further analysis. Firstly, there is a variety of sensors in this black box system, including LIDAR, alcohol sensors, a camera, and RFID. This technology also has a method for detecting the driver's drowsiness. All of the information will be shown on a monitor directly in front of the driver's seat. Lastly, the relevant authority will receive information on the vehicle's condition and location via GPS and GSM.
{"title":"Smart Vehicle Management System for Accident Reduction by Using Sensors and An IoT Based Black Box","authors":"Mohammad Minhazur Rahman, A. Z. M. Tahmidul Kabir, Shoumic Zaman Khan, Nahin Akhtar, Abdullah Al Mamun, S. Hossain","doi":"10.23919/eecsi53397.2021.9624240","DOIUrl":"https://doi.org/10.23919/eecsi53397.2021.9624240","url":null,"abstract":"Reckless driving is one of the prominent causes of human-based vehicle collisions, which are gradually increasing. Furthermore, due to a lack of real-time evidence, very few further investigations are done to determine the actual causes of these accidents. The central theme of this titled paper is to construct a few sensor-based black box systems that will assist us in reducing traffic collisions by giving accurate instructions to the driver constantly. At the same time, it will upload the evidence to its server for further analysis. Firstly, there is a variety of sensors in this black box system, including LIDAR, alcohol sensors, a camera, and RFID. This technology also has a method for detecting the driver's drowsiness. All of the information will be shown on a monitor directly in front of the driver's seat. Lastly, the relevant authority will receive information on the vehicle's condition and location via GPS and GSM.","PeriodicalId":259450,"journal":{"name":"2021 8th International Conference on Electrical Engineering, Computer Science and Informatics (EECSI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131294674","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 : 2021-10-20DOI: 10.23919/eecsi53397.2021.9624248
H. A. Nugroho, Eka Legya Frannita, Rizki Nurfauzi
Recently, some countries have been distressing with the increasing number of thyroid cancer cases. The number of cases is increased every year. Practically, one of the causes of the increase in the number of patients was due to manual examination. Recently, some researchers have involved in the development of CAD to solve this problem. However, CAD itself still has some limitations. One of the major limitations is that the nodules segmentation process was not well-conducted. Thus, to overcome that problem, we proposed a scheme for detecting and segmenting the thyroid nodules. Our scheme consisted of four major steps which were data augmentation process, normalization process, segmentation and evaluation process. The proposed scheme was tested in 480 thyroid ultrasound images. The proposed scheme successfully achieved more than 90% in all evaluation metrics in both detection and segmentation process. According to this achievement, we concluded that our proposed method had potential to be integrated as part of the intelligent system for detecting and segmenting thyroid cancer.
{"title":"An Automated Detection and Segmentation of Thyroid Nodules using Res-UNet","authors":"H. A. Nugroho, Eka Legya Frannita, Rizki Nurfauzi","doi":"10.23919/eecsi53397.2021.9624248","DOIUrl":"https://doi.org/10.23919/eecsi53397.2021.9624248","url":null,"abstract":"Recently, some countries have been distressing with the increasing number of thyroid cancer cases. The number of cases is increased every year. Practically, one of the causes of the increase in the number of patients was due to manual examination. Recently, some researchers have involved in the development of CAD to solve this problem. However, CAD itself still has some limitations. One of the major limitations is that the nodules segmentation process was not well-conducted. Thus, to overcome that problem, we proposed a scheme for detecting and segmenting the thyroid nodules. Our scheme consisted of four major steps which were data augmentation process, normalization process, segmentation and evaluation process. The proposed scheme was tested in 480 thyroid ultrasound images. The proposed scheme successfully achieved more than 90% in all evaluation metrics in both detection and segmentation process. According to this achievement, we concluded that our proposed method had potential to be integrated as part of the intelligent system for detecting and segmenting thyroid cancer.","PeriodicalId":259450,"journal":{"name":"2021 8th International Conference on Electrical Engineering, Computer Science and Informatics (EECSI)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125353061","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 : 2021-10-20DOI: 10.23919/eecsi53397.2021.9624243
Marisa Marisa, Suhadi Suhadi, M. Nur, Prima Dina Atika, Sugiyatno Sugiyatno, Davi Afandi
Computers are essential in industrial processes because they play a part in the life cycle of company-produced product systems. Damage to production equipment happens frequently as a result of a lack of detailed periodic maintenance, making it difficult for operator and technician staff to maintain production machines. Because they are still utilizing the manual approach, repair times are long and costly accurate. Case-Based Reasoning (CBR), a problem-solving technique based on prior experience and applied in the present, is one discipline of computer science that is commonly employed by humans to help and facilitate work. CBR is used to find solutions by exploiting or analyzing previously collected case data. Case representation, case indexing, case retrieval, case adaptation, and case maintenance are the five goals of CBR in knowledge formation. The process of discovering and measuring the case with the greatest closeness is known as case retrieval. The goal of this research is to create a way to automatically detect system failures in machines, so that if a malfunction happens with a CBR-based system, it will be easier to detect early, repair faster, and be more accurate. The accuracy of the system utilized is 90%, according to the results of testing the tools manufactured, and it is effective for managing production machine repairs. While the test error is twenty times with the highest result of 33.33 % and the lowest is 0% according to the level of accuracy of the sensor on the object.
{"title":"Factory Production Machine Damage Detection System Using Case-Based Reasoning Method","authors":"Marisa Marisa, Suhadi Suhadi, M. Nur, Prima Dina Atika, Sugiyatno Sugiyatno, Davi Afandi","doi":"10.23919/eecsi53397.2021.9624243","DOIUrl":"https://doi.org/10.23919/eecsi53397.2021.9624243","url":null,"abstract":"Computers are essential in industrial processes because they play a part in the life cycle of company-produced product systems. Damage to production equipment happens frequently as a result of a lack of detailed periodic maintenance, making it difficult for operator and technician staff to maintain production machines. Because they are still utilizing the manual approach, repair times are long and costly accurate. Case-Based Reasoning (CBR), a problem-solving technique based on prior experience and applied in the present, is one discipline of computer science that is commonly employed by humans to help and facilitate work. CBR is used to find solutions by exploiting or analyzing previously collected case data. Case representation, case indexing, case retrieval, case adaptation, and case maintenance are the five goals of CBR in knowledge formation. The process of discovering and measuring the case with the greatest closeness is known as case retrieval. The goal of this research is to create a way to automatically detect system failures in machines, so that if a malfunction happens with a CBR-based system, it will be easier to detect early, repair faster, and be more accurate. The accuracy of the system utilized is 90%, according to the results of testing the tools manufactured, and it is effective for managing production machine repairs. While the test error is twenty times with the highest result of 33.33 % and the lowest is 0% according to the level of accuracy of the sensor on the object.","PeriodicalId":259450,"journal":{"name":"2021 8th International Conference on Electrical Engineering, Computer Science and Informatics (EECSI)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126561900","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 : 2021-10-20DOI: 10.23919/eecsi53397.2021.9624254
M. Attamimi, D. Purwanto, Rudy Dikairono
Intelligent robots such as domestic service robots (DSR), office robots are required to be able to interact with dynamic and complex environments. In order to carry out the tasks given in such environments, the ability to interact with the objects becomes prevalent. In particular, the DSR need to interact with a household object that is normally being lied in arbitrary positions at the home. To accomplish such a challenging task, the robot has to be able to recognize the object. As human does, a visual-based recognition is most common and natural for intelligent robots. To realize such ability the use of visual information captured from a visual sensor is necessary. Thanks to the second version of Microsoft Kinect (Kinect V2), visual information such as color, depth, and near-infrared information can be acquired. In this study, the captured visual information is then processed for object extraction and object recognition. To solve the problems, we propose a method that exploits multiple features such as color and shape features. The proposed method has incorporated the results of each classifier such as k-nearest neighbor (kNN) using a simple probabilistic method to obtain robust recognition results of household objects. To validate the proposed method, we have conducted several experiments. The results reveal that our method can achieve an accuracy of (84.02 ± 18.85) % for the recognition of household objects with extreme conditions.
{"title":"Integration of Color and Shape Features for Household Object Recognition","authors":"M. Attamimi, D. Purwanto, Rudy Dikairono","doi":"10.23919/eecsi53397.2021.9624254","DOIUrl":"https://doi.org/10.23919/eecsi53397.2021.9624254","url":null,"abstract":"Intelligent robots such as domestic service robots (DSR), office robots are required to be able to interact with dynamic and complex environments. In order to carry out the tasks given in such environments, the ability to interact with the objects becomes prevalent. In particular, the DSR need to interact with a household object that is normally being lied in arbitrary positions at the home. To accomplish such a challenging task, the robot has to be able to recognize the object. As human does, a visual-based recognition is most common and natural for intelligent robots. To realize such ability the use of visual information captured from a visual sensor is necessary. Thanks to the second version of Microsoft Kinect (Kinect V2), visual information such as color, depth, and near-infrared information can be acquired. In this study, the captured visual information is then processed for object extraction and object recognition. To solve the problems, we propose a method that exploits multiple features such as color and shape features. The proposed method has incorporated the results of each classifier such as k-nearest neighbor (kNN) using a simple probabilistic method to obtain robust recognition results of household objects. To validate the proposed method, we have conducted several experiments. The results reveal that our method can achieve an accuracy of (84.02 ± 18.85) % for the recognition of household objects with extreme conditions.","PeriodicalId":259450,"journal":{"name":"2021 8th International Conference on Electrical Engineering, Computer Science and Informatics (EECSI)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122915466","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 : 2021-10-20DOI: 10.23919/EECSI53397.2021.9624218
Ahmad Alfi Adz-Dzikri, Agus Virgono, F. M. Dirgantara
Most of the traffic accident was caused by human error. Vehicle collision accident may happen due to the driver miscalculating the distance between other vehicles. To prevent this type of accident, we implemented an Advanced Driving Assistance System to estimate distance objects and Object detection. The architecture implemented for object detection is MobileNetV2, EfficientNet, and VGGNet16. The localization method uses Single Shot Detector (SSD). Distance Estimation method applies Depth prediction approaches using Deep Learning, with DenseDepth and MonoDepth2 as deep learning architectures. In the object detection experiment test using KITTI and PASCAL Datasets, the highest score was achieved by MobileNetV2 architecture with mean Average Precision of 75%. In terms of Deep Learning Architecture for distance estimation, comparison of prediction depth and actual distance shows that Densedepth have the lowest error with average error 3.6043 meters during the cloudy weather, and 4.0565 meters during the sunny weather.
{"title":"Advance Driving Assistance Systems: Object Detection and Distance Estimation Using Deep Learning","authors":"Ahmad Alfi Adz-Dzikri, Agus Virgono, F. M. Dirgantara","doi":"10.23919/EECSI53397.2021.9624218","DOIUrl":"https://doi.org/10.23919/EECSI53397.2021.9624218","url":null,"abstract":"Most of the traffic accident was caused by human error. Vehicle collision accident may happen due to the driver miscalculating the distance between other vehicles. To prevent this type of accident, we implemented an Advanced Driving Assistance System to estimate distance objects and Object detection. The architecture implemented for object detection is MobileNetV2, EfficientNet, and VGGNet16. The localization method uses Single Shot Detector (SSD). Distance Estimation method applies Depth prediction approaches using Deep Learning, with DenseDepth and MonoDepth2 as deep learning architectures. In the object detection experiment test using KITTI and PASCAL Datasets, the highest score was achieved by MobileNetV2 architecture with mean Average Precision of 75%. In terms of Deep Learning Architecture for distance estimation, comparison of prediction depth and actual distance shows that Densedepth have the lowest error with average error 3.6043 meters during the cloudy weather, and 4.0565 meters during the sunny weather.","PeriodicalId":259450,"journal":{"name":"2021 8th International Conference on Electrical Engineering, Computer Science and Informatics (EECSI)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116935449","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 : 2021-10-20DOI: 10.23919/eecsi53397.2021.9624274
Zahraa A. Jaaz, M. Rusli, N. A. Rahmat, Inteasar Yaseen Khudhair, Israa Al Barazanchi, H. Mehdy
The aim of this study survey is to analyze energy-efficient smart home load forecasting techniques and determine the usage of energy or power with high spectrum allocation in future smart home with the help of clustering in data mining. The study work starts presenting an overview of the smart home energy sector and the challenges it is facing; it is observed a change on the energy policies promoting the energy efficiency, encouraging an active role of the consumer, instructing them about the importance of the consumer behavior and protecting consumer rights. Electricity is gaining room as energy source; its share will keep increasing constantly in the following decades. In this close future, smart homes and smart meters' deployment will benefit both the utility and the consumer. In this environment, new services and new business appear, focusing on the energy management field and tools, they require specialization in fields such as, computer science, software development and data science. This study work has segmented the smart home according to the similarities of their electrical load profiles, using the proportion of energy usage per hour (%) as a common framework with analysis done in this proposed research. The objective behind this energy consumption segmentation is to be able to provide personalized recommendations to each group to reduce their energy consumption and the associated costs, fostering energy efficiency measures and improving the consumer engagement for future smart homes.
{"title":"A Review on Energy-Efficient Smart Home Load Forecasting Techniques","authors":"Zahraa A. Jaaz, M. Rusli, N. A. Rahmat, Inteasar Yaseen Khudhair, Israa Al Barazanchi, H. Mehdy","doi":"10.23919/eecsi53397.2021.9624274","DOIUrl":"https://doi.org/10.23919/eecsi53397.2021.9624274","url":null,"abstract":"The aim of this study survey is to analyze energy-efficient smart home load forecasting techniques and determine the usage of energy or power with high spectrum allocation in future smart home with the help of clustering in data mining. The study work starts presenting an overview of the smart home energy sector and the challenges it is facing; it is observed a change on the energy policies promoting the energy efficiency, encouraging an active role of the consumer, instructing them about the importance of the consumer behavior and protecting consumer rights. Electricity is gaining room as energy source; its share will keep increasing constantly in the following decades. In this close future, smart homes and smart meters' deployment will benefit both the utility and the consumer. In this environment, new services and new business appear, focusing on the energy management field and tools, they require specialization in fields such as, computer science, software development and data science. This study work has segmented the smart home according to the similarities of their electrical load profiles, using the proportion of energy usage per hour (%) as a common framework with analysis done in this proposed research. The objective behind this energy consumption segmentation is to be able to provide personalized recommendations to each group to reduce their energy consumption and the associated costs, fostering energy efficiency measures and improving the consumer engagement for future smart homes.","PeriodicalId":259450,"journal":{"name":"2021 8th International Conference on Electrical Engineering, Computer Science and Informatics (EECSI)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128856648","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 : 2021-10-20DOI: 10.23919/eecsi53397.2021.9624283
Zahraa A. Jaaz, Inteasar Yaseen Khudhair, H. Mehdy, Israa Al Barazanchi
With regard to the forthcoming requirements for mobile services in 5G networks, several new technologies have recently become the focus of leading-edge research. One of those is in-band full-duplex communications in processing data with bigdata based Apache spark. The idea is to simply employ the same frequency band to simultaneously transmit and receive information, allowing more spectrally efficient communications when compared to the traditional half-duplex or out-of-band full-duplex counterparts. By breaking a long-held assumption in wireless communications, in-band full-duplex. this paper aims to study wireless communication in 5G network with use of bigdata based Apache spark. Particularly, apache spark suppression filters are studied, as well as feedback adaptive filtering is proposed for relay systems with multiple-input multiple-out (MIMO) antennas. In this case, the relay system energy efficiency is maximized by finding the optimal transmit powers, while maintaining a certain individual link quality. For this scenario, the effect of massive MIMO is likewise addressed, and an algorithm that maximizes the system total achievable rate is derived. 5G technologies have pressing security challenges to secure data integrity and privacy in critical wireless communications requiring extensive research before implementing these technologies into use. This paper examines the new possibilities 5G networks offer for wireless network communication with high bandwidth of 90 GHz. The prediction of 5G network bandwidth maximum recoded at 90 GHz on 5 nodes of apache spark at 80% of data trained with total 12 nodes. The main question is will the 5G technology offers sufficient performance for wireless communication.
{"title":"Imparting Full-Duplex Wireless Cellular Communication in 5G Network Using Apache Spark Engine","authors":"Zahraa A. Jaaz, Inteasar Yaseen Khudhair, H. Mehdy, Israa Al Barazanchi","doi":"10.23919/eecsi53397.2021.9624283","DOIUrl":"https://doi.org/10.23919/eecsi53397.2021.9624283","url":null,"abstract":"With regard to the forthcoming requirements for mobile services in 5G networks, several new technologies have recently become the focus of leading-edge research. One of those is in-band full-duplex communications in processing data with bigdata based Apache spark. The idea is to simply employ the same frequency band to simultaneously transmit and receive information, allowing more spectrally efficient communications when compared to the traditional half-duplex or out-of-band full-duplex counterparts. By breaking a long-held assumption in wireless communications, in-band full-duplex. this paper aims to study wireless communication in 5G network with use of bigdata based Apache spark. Particularly, apache spark suppression filters are studied, as well as feedback adaptive filtering is proposed for relay systems with multiple-input multiple-out (MIMO) antennas. In this case, the relay system energy efficiency is maximized by finding the optimal transmit powers, while maintaining a certain individual link quality. For this scenario, the effect of massive MIMO is likewise addressed, and an algorithm that maximizes the system total achievable rate is derived. 5G technologies have pressing security challenges to secure data integrity and privacy in critical wireless communications requiring extensive research before implementing these technologies into use. This paper examines the new possibilities 5G networks offer for wireless network communication with high bandwidth of 90 GHz. The prediction of 5G network bandwidth maximum recoded at 90 GHz on 5 nodes of apache spark at 80% of data trained with total 12 nodes. The main question is will the 5G technology offers sufficient performance for wireless communication.","PeriodicalId":259450,"journal":{"name":"2021 8th International Conference on Electrical Engineering, Computer Science and Informatics (EECSI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129977700","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 : 2021-10-20DOI: 10.23919/eecsi53397.2021.9624256
Muhammad Fachrie, Farida Ardiani
User-generated contents from Twitter have been utilized to do sentiment analysis for predicting the presidential election result. Researchers successfully proposed methods based on Text Mining and Machine Learning approach to create sentiment analysis model as basis for prediction. However, Twitter-based prediction is difficult to be utilized in regional election, as massive tweets usually posted regarding elections held in provinces, cities, or large districts only. Moreover, Twitter-based prediction must deal with unstructured data, fake/ bot account, wrong information, mixed of languages, nonstandard writing style, and even subjectivity when labeling the dataset. Therefore, this work proposed an alternative prediction model for regional election result based on candidate's profile which is officially published by General Election Commission of the Republic of Indonesia. There are four main tasks in this work, i.e., data collection, data preprocessing, feature engineering, and data classification using C4.5 decision tree algorithm. As the result, the predictive model achieved accuracy of 72.96% after doing post and pre-prunning procedures. This work also contributes to generating a new dataset for predicting the result of regional election in Indonesia which contains related features that affect the winning of candidates.
{"title":"Predictive Model for Regional Elections Results based on Candidate Profiles","authors":"Muhammad Fachrie, Farida Ardiani","doi":"10.23919/eecsi53397.2021.9624256","DOIUrl":"https://doi.org/10.23919/eecsi53397.2021.9624256","url":null,"abstract":"User-generated contents from Twitter have been utilized to do sentiment analysis for predicting the presidential election result. Researchers successfully proposed methods based on Text Mining and Machine Learning approach to create sentiment analysis model as basis for prediction. However, Twitter-based prediction is difficult to be utilized in regional election, as massive tweets usually posted regarding elections held in provinces, cities, or large districts only. Moreover, Twitter-based prediction must deal with unstructured data, fake/ bot account, wrong information, mixed of languages, nonstandard writing style, and even subjectivity when labeling the dataset. Therefore, this work proposed an alternative prediction model for regional election result based on candidate's profile which is officially published by General Election Commission of the Republic of Indonesia. There are four main tasks in this work, i.e., data collection, data preprocessing, feature engineering, and data classification using C4.5 decision tree algorithm. As the result, the predictive model achieved accuracy of 72.96% after doing post and pre-prunning procedures. This work also contributes to generating a new dataset for predicting the result of regional election in Indonesia which contains related features that affect the winning of candidates.","PeriodicalId":259450,"journal":{"name":"2021 8th International Conference on Electrical Engineering, Computer Science and Informatics (EECSI)","volume":"244 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134646108","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 : 2021-10-20DOI: 10.23919/eecsi53397.2021.9624293
I. Ajayi, Y. Medjahdi, L. Mroueh, F. Kaddour
In recent years, physical layer security (PLS) has emerged as a promising concept to complement cryptography solutions. Many PLS schemes require perfect knowledge of the channel state information (CSI) at the transmitter. However, in practical cases, CSI is often imperfect due to channel estimation errors, noisy feedback channels and outdated CSI. In this paper, we study the impact of imperfect CSI on an adaptive PLS scheme that combines diversity with interleaving to provide security. Particularly, we derive the secrecy capacity expressions for the legitimate receiver and the eavesdropper's channels under imperfect CSI conditions. Numerical and theoretical simulations for secrecy capacity and bit error rate (BER) are carried out for the frequency-selective Rayleigh fading wiretap channel model. The results reveal the negative impact of imperfect CSI on the secrecy and BER performance of the single input single output (SISO) orthogonal frequency division multiplexing (OFDM) system. The analysis is done under both frequency division duplex (FDD) and time division duplex (TDD) modes.
{"title":"Physical Layer Security by Interleaving and Diversity: Impact of Imperfect Channel State Information","authors":"I. Ajayi, Y. Medjahdi, L. Mroueh, F. Kaddour","doi":"10.23919/eecsi53397.2021.9624293","DOIUrl":"https://doi.org/10.23919/eecsi53397.2021.9624293","url":null,"abstract":"In recent years, physical layer security (PLS) has emerged as a promising concept to complement cryptography solutions. Many PLS schemes require perfect knowledge of the channel state information (CSI) at the transmitter. However, in practical cases, CSI is often imperfect due to channel estimation errors, noisy feedback channels and outdated CSI. In this paper, we study the impact of imperfect CSI on an adaptive PLS scheme that combines diversity with interleaving to provide security. Particularly, we derive the secrecy capacity expressions for the legitimate receiver and the eavesdropper's channels under imperfect CSI conditions. Numerical and theoretical simulations for secrecy capacity and bit error rate (BER) are carried out for the frequency-selective Rayleigh fading wiretap channel model. The results reveal the negative impact of imperfect CSI on the secrecy and BER performance of the single input single output (SISO) orthogonal frequency division multiplexing (OFDM) system. The analysis is done under both frequency division duplex (FDD) and time division duplex (TDD) modes.","PeriodicalId":259450,"journal":{"name":"2021 8th International Conference on Electrical Engineering, Computer Science and Informatics (EECSI)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130810179","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：