Pub Date : 2021-06-11DOI: 10.1109/HORA52670.2021.9461335
Halil İbrahim Şahın, A. Kavsaoğlu
Autonomously controlled intelligent wheelchair is an electric wheelchair system that can reach a desired position by finding paths without any need for user intervention. Pathfinding can be performed in outdoor areas with the support of global positioning system (GPS) while interior mapping is required for indoor areas. In this study, an autonomous control interface design that can work with intelligent wheelchairs has been implemented to be used on indoor areas. This interface is used building floor plans and pathfinding algorithms for planning a path to a selected destination. The autonomous control of an electrically powered wheelchair is performed using fuzzy logic on the planned path. On the hardware side, a depth camera, a single board computer, microcontrollers, speed sensors, lighting systems and a motor driver are added on the electric-powered wheelchair. All components are operated under the coordination that provided with the interface. The instantaneously detection of obstacles that may be encountered causes the path to be changed with an alternative, and this situation can be shown synchronously within a simulation software.
{"title":"Autonomously Controlled Intelligent Wheelchair System for Indoor Areas","authors":"Halil İbrahim Şahın, A. Kavsaoğlu","doi":"10.1109/HORA52670.2021.9461335","DOIUrl":"https://doi.org/10.1109/HORA52670.2021.9461335","url":null,"abstract":"Autonomously controlled intelligent wheelchair is an electric wheelchair system that can reach a desired position by finding paths without any need for user intervention. Pathfinding can be performed in outdoor areas with the support of global positioning system (GPS) while interior mapping is required for indoor areas. In this study, an autonomous control interface design that can work with intelligent wheelchairs has been implemented to be used on indoor areas. This interface is used building floor plans and pathfinding algorithms for planning a path to a selected destination. The autonomous control of an electrically powered wheelchair is performed using fuzzy logic on the planned path. On the hardware side, a depth camera, a single board computer, microcontrollers, speed sensors, lighting systems and a motor driver are added on the electric-powered wheelchair. All components are operated under the coordination that provided with the interface. The instantaneously detection of obstacles that may be encountered causes the path to be changed with an alternative, and this situation can be shown synchronously within a simulation software.","PeriodicalId":270469,"journal":{"name":"2021 3rd International Congress on Human-Computer Interaction, Optimization and Robotic Applications (HORA)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134645479","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 : 2021-06-11DOI: 10.1109/HORA52670.2021.9461268
Tuğba Zeybek, U. Sakarya
Gesture recognition in human-machine interaction is a popular subject of study, but it also includes some problems. The main motivation of the proposed study is developed a novel vector-based feature extraction method for gesture recognition in an unmanned aerial vehicle (UAV) control. In this paper, the use of discrete wavelet transform on the signals acquired by multiple sensors and then, a statistical feature extraction from this transformed signals is proposed for the person-independent gesture recognition. In this way, it is aimed to get the invariant feature space according to speed and magnitude of the movement in different time slices. The success of the proposed method in the problem of person-independent gesture recognition is experimentally demonstrated with the comparative experiments.
{"title":"Wavelet-based Spatial-temporal Feature Extraction for Gesture Recognition","authors":"Tuğba Zeybek, U. Sakarya","doi":"10.1109/HORA52670.2021.9461268","DOIUrl":"https://doi.org/10.1109/HORA52670.2021.9461268","url":null,"abstract":"Gesture recognition in human-machine interaction is a popular subject of study, but it also includes some problems. The main motivation of the proposed study is developed a novel vector-based feature extraction method for gesture recognition in an unmanned aerial vehicle (UAV) control. In this paper, the use of discrete wavelet transform on the signals acquired by multiple sensors and then, a statistical feature extraction from this transformed signals is proposed for the person-independent gesture recognition. In this way, it is aimed to get the invariant feature space according to speed and magnitude of the movement in different time slices. The success of the proposed method in the problem of person-independent gesture recognition is experimentally demonstrated with the comparative experiments.","PeriodicalId":270469,"journal":{"name":"2021 3rd International Congress on Human-Computer Interaction, Optimization and Robotic Applications (HORA)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134361577","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}
Blockchain is a tamper-proof distributed ledger for tracking public or private pair transactions in pair networks that can not be retroactively changed without modifying all corresponding network blocks. The Consensus Protocol upgrades a blockchain, which guarantees a sequential, unambiguous transaction ordering. Blocks ensure that the blockchain is integral and uniform across a network of distributed nodes. Different blockchain implementations use different consensus protocols. This paper offers a brief overview of the most important discrepancies between the Hyperledger Fabric and Ethereum distributed ledger technologies (DLT).
{"title":"Hyperledger, Ethereum and Blockchain Technology: A Short Overview","authors":"Alaa Hamid Mohammed, Alaa Amjed Abdulateef, Ihsan Amjad Abdulateef","doi":"10.1109/HORA52670.2021.9461294","DOIUrl":"https://doi.org/10.1109/HORA52670.2021.9461294","url":null,"abstract":"Blockchain is a tamper-proof distributed ledger for tracking public or private pair transactions in pair networks that can not be retroactively changed without modifying all corresponding network blocks. The Consensus Protocol upgrades a blockchain, which guarantees a sequential, unambiguous transaction ordering. Blocks ensure that the blockchain is integral and uniform across a network of distributed nodes. Different blockchain implementations use different consensus protocols. This paper offers a brief overview of the most important discrepancies between the Hyperledger Fabric and Ethereum distributed ledger technologies (DLT).","PeriodicalId":270469,"journal":{"name":"2021 3rd International Congress on Human-Computer Interaction, Optimization and Robotic Applications (HORA)","volume":"125 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134375486","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 : 2021-06-11DOI: 10.1109/HORA52670.2021.9461342
A. Sezer, Aytaç Altan
Mass production processes of printed circuit boards (PCBs) are interrupted due to problems caused by soldering defects during the assembly of surface-mounted semiconductor electronics components to PCBs. This situation causes both an increase in production processes and costs and a decrease in production quality. Increasing production processes due to solder paste defects on PCBs, which can generally be detected at the final stage of the mass production process, cause the test processes of especially strategic projects to be disrupted. In this study, a deep learning model whose model parameters are estimated with population-based optimization algorithm that mimics atomic motion is proposed in order to detect the solder paste defects on PCBs at the early phase of the mass production process. AlexNet, one of the architectures with the least model complexity, is chosen for the convolutional neural network (CNN) model. The proposed optimization algorithm plays an important role in improving the performance of the model. In the study, six types classes are used, consisting of correct soldering, incorrect soldering, missing soldering, excess soldering, short circuit and undefined object. The performance of the proposed model has been experimentally tested and compared with the particle swarm optimization (PSO) based model approach. The results obtained confirm that the proposed model is satisfactorily successful in detecting solder paste defects on the PCB.
{"title":"Optimization of Deep Learning Model Parameters in Classification of Solder Paste Defects","authors":"A. Sezer, Aytaç Altan","doi":"10.1109/HORA52670.2021.9461342","DOIUrl":"https://doi.org/10.1109/HORA52670.2021.9461342","url":null,"abstract":"Mass production processes of printed circuit boards (PCBs) are interrupted due to problems caused by soldering defects during the assembly of surface-mounted semiconductor electronics components to PCBs. This situation causes both an increase in production processes and costs and a decrease in production quality. Increasing production processes due to solder paste defects on PCBs, which can generally be detected at the final stage of the mass production process, cause the test processes of especially strategic projects to be disrupted. In this study, a deep learning model whose model parameters are estimated with population-based optimization algorithm that mimics atomic motion is proposed in order to detect the solder paste defects on PCBs at the early phase of the mass production process. AlexNet, one of the architectures with the least model complexity, is chosen for the convolutional neural network (CNN) model. The proposed optimization algorithm plays an important role in improving the performance of the model. In the study, six types classes are used, consisting of correct soldering, incorrect soldering, missing soldering, excess soldering, short circuit and undefined object. The performance of the proposed model has been experimentally tested and compared with the particle swarm optimization (PSO) based model approach. The results obtained confirm that the proposed model is satisfactorily successful in detecting solder paste defects on the PCB.","PeriodicalId":270469,"journal":{"name":"2021 3rd International Congress on Human-Computer Interaction, Optimization and Robotic Applications (HORA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133439828","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 : 2021-06-11DOI: 10.1109/HORA52670.2021.9461331
Burkay Karadayi, Yusuf Kuvvetli, S. Ural
Renewable energy sources and production facilities have increasing prevalence around the world. Thanks to technology, this type of energy production facilities use and produce more data day by day. Wind power turbines use SCADA (supervisory control and data acquisition) systems to monitor and control production, alarms, faults, etc. Data that is produced by SCADA systems are used for fault and alarm prediction. In this study, the SCADA system data of a wind farm located in the southeast of Turkey is used to predict the system’s alarms. While some alarms are about faults, it could be that the others are about non-fault situations. This study aims to predict fault-related and non-fault-related alarms. SMOTE is used to balance unbalanced classes to increase the performance of the model. The proposed model consists of 4 main steps: The first step is data acquisition from SCADA data. The second step is data analysis and pre-processing. The third step of the model is feature selection, and the last step is classification study. SVC (support vector classifiers) and decision trees are compared for the classification step, and according to the performance results, the decision tree is selected to model prediction.
{"title":"Fault-related Alarm Detection of a Wind Turbine SCADA System","authors":"Burkay Karadayi, Yusuf Kuvvetli, S. Ural","doi":"10.1109/HORA52670.2021.9461331","DOIUrl":"https://doi.org/10.1109/HORA52670.2021.9461331","url":null,"abstract":"Renewable energy sources and production facilities have increasing prevalence around the world. Thanks to technology, this type of energy production facilities use and produce more data day by day. Wind power turbines use SCADA (supervisory control and data acquisition) systems to monitor and control production, alarms, faults, etc. Data that is produced by SCADA systems are used for fault and alarm prediction. In this study, the SCADA system data of a wind farm located in the southeast of Turkey is used to predict the system’s alarms. While some alarms are about faults, it could be that the others are about non-fault situations. This study aims to predict fault-related and non-fault-related alarms. SMOTE is used to balance unbalanced classes to increase the performance of the model. The proposed model consists of 4 main steps: The first step is data acquisition from SCADA data. The second step is data analysis and pre-processing. The third step of the model is feature selection, and the last step is classification study. SVC (support vector classifiers) and decision trees are compared for the classification step, and according to the performance results, the decision tree is selected to model prediction.","PeriodicalId":270469,"journal":{"name":"2021 3rd International Congress on Human-Computer Interaction, Optimization and Robotic Applications (HORA)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125633407","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 : 2021-06-11DOI: 10.1109/HORA52670.2021.9461313
M. Khatun, Milin Patel, Rolf Jung, Michael Glass
In recent decades, research in both academic and industry has focused on the area of highly automated driving systems and is expected to do so in the near future. The scenario-based analysis is widely used in automated vehicles that requires simulation-based vehicle control estimation. One of the assist system is transverse guidance that is inescapable for highly automated driving system. The transverse guidance assist system deals with the longitudinal and lateral behavior of the vehicle. For a specific use case, merging functions like adaptive cruise control and lane keeping assist system are considered. The paper is focused on the development of transverse guidance that forms the combined lateral and longitudinal control of highly automated driving system like Lane Change maneuver planning in highway scenario. Moreover, the parameters are demonstrated for the model and performance of the model has been shown for the use case scenario. The proposed approach is then evaluated for a scenario in a simulation environment modeled using MATLAB/Simulink.
{"title":"A simulation-based analysis for a transverse guidance for highly automated driving functions","authors":"M. Khatun, Milin Patel, Rolf Jung, Michael Glass","doi":"10.1109/HORA52670.2021.9461313","DOIUrl":"https://doi.org/10.1109/HORA52670.2021.9461313","url":null,"abstract":"In recent decades, research in both academic and industry has focused on the area of highly automated driving systems and is expected to do so in the near future. The scenario-based analysis is widely used in automated vehicles that requires simulation-based vehicle control estimation. One of the assist system is transverse guidance that is inescapable for highly automated driving system. The transverse guidance assist system deals with the longitudinal and lateral behavior of the vehicle. For a specific use case, merging functions like adaptive cruise control and lane keeping assist system are considered. The paper is focused on the development of transverse guidance that forms the combined lateral and longitudinal control of highly automated driving system like Lane Change maneuver planning in highway scenario. Moreover, the parameters are demonstrated for the model and performance of the model has been shown for the use case scenario. The proposed approach is then evaluated for a scenario in a simulation environment modeled using MATLAB/Simulink.","PeriodicalId":270469,"journal":{"name":"2021 3rd International Congress on Human-Computer Interaction, Optimization and Robotic Applications (HORA)","volume":"121 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133951999","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 : 2021-06-11DOI: 10.1109/HORA52670.2021.9461288
Koray Kavlak, Yiğit Osman Taner
Multi legged robots in mobile robots have a wide range of use in the defense and space industry, in places harmful to human health, such as earthquake zones. The advantage of legged robots is that they can reach places that are inaccessible to wheeled and tracked robots. By modelling the physical structure of legged animals, mobile robots are designed and manufactured. In this paper, a mobile robot with Klann walking mechanism was modelled in SolidWorks program. Eight legs were preferred to ensure balance and prevent vibration in walking mechanism. Parts such as gear, shaft, disc, battery and motor are used in robot design. The coupler curve at the position where the Klann walking mechanism contact the ground has been drawn in the Cinderella program. Stress and strain values were found as a result of the strength analysis of the mobile robot, and natural frequency values were found as a result of the modal analysis.
{"title":"Strength and Modal Analysis of Mobile Robot with Klann Walking Mechanism","authors":"Koray Kavlak, Yiğit Osman Taner","doi":"10.1109/HORA52670.2021.9461288","DOIUrl":"https://doi.org/10.1109/HORA52670.2021.9461288","url":null,"abstract":"Multi legged robots in mobile robots have a wide range of use in the defense and space industry, in places harmful to human health, such as earthquake zones. The advantage of legged robots is that they can reach places that are inaccessible to wheeled and tracked robots. By modelling the physical structure of legged animals, mobile robots are designed and manufactured. In this paper, a mobile robot with Klann walking mechanism was modelled in SolidWorks program. Eight legs were preferred to ensure balance and prevent vibration in walking mechanism. Parts such as gear, shaft, disc, battery and motor are used in robot design. The coupler curve at the position where the Klann walking mechanism contact the ground has been drawn in the Cinderella program. Stress and strain values were found as a result of the strength analysis of the mobile robot, and natural frequency values were found as a result of the modal analysis.","PeriodicalId":270469,"journal":{"name":"2021 3rd International Congress on Human-Computer Interaction, Optimization and Robotic Applications (HORA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128771113","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 : 2021-06-11DOI: 10.1109/HORA52670.2021.9461369
V. Chobanov
The quality of the power supply is a basic prerequisite both for the proper functioning of electrical devices and for reducing the risk of accidents and technological interruptions. The pressure for an increasing share of RES imposes the need for electricity distribution companies to connect more power plants, but this pressure leads to an increase in the risk of quality electricity supply and at the same time is a prerequisite for financial losses when investing in renewable energy sources due to lack of congestion management. The problems that lead to these risks are the subject of this article, considering the impact they have not only on investments in new power plants, but also on already connected ones, as well as on electricity consumers.
{"title":"Power Quality and financial risk for RES investments","authors":"V. Chobanov","doi":"10.1109/HORA52670.2021.9461369","DOIUrl":"https://doi.org/10.1109/HORA52670.2021.9461369","url":null,"abstract":"The quality of the power supply is a basic prerequisite both for the proper functioning of electrical devices and for reducing the risk of accidents and technological interruptions. The pressure for an increasing share of RES imposes the need for electricity distribution companies to connect more power plants, but this pressure leads to an increase in the risk of quality electricity supply and at the same time is a prerequisite for financial losses when investing in renewable energy sources due to lack of congestion management. The problems that lead to these risks are the subject of this article, considering the impact they have not only on investments in new power plants, but also on already connected ones, as well as on electricity consumers.","PeriodicalId":270469,"journal":{"name":"2021 3rd International Congress on Human-Computer Interaction, Optimization and Robotic Applications (HORA)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115573367","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 : 2021-06-11DOI: 10.1109/HORA52670.2021.9461290
Amal Alzahrani, N. Beloff, Martin White
The mobile industry is one of the rapidly growing markets in the world. This has created a unique platform for delivering mobile network-based social and financial services. Mobile banking is the best and last banking platform that provides value-added services anytime and anywhere with a reduction in effort, time, and money. However, there is a decrease in the adoption rate of these services in Arabian countries, including Saudi Arabia. Although there have been several studies to determine factors influencing the adoption of these services worldwide, few studies have been done in this part of the world. This paper considers the current literature on mobile banking to investigate the factors that increase mobile banking adoption in Saudi Arabia. We propose a new integrative model for mobile banking adoption (IMMBA) that combines and expands the IS Success and UTAUT2 models to include factors that account for Perceived Trust, Perceived Privacy, and Perceived Compatibility. IMMBA provides a comprehensive analysis of the current challenges of mobile banking adoption in Saudi Arabia. Identifying the factors that affect mobile banking adoption and understanding the relationships between them will help banks, particularly in Saudi Arabia, to lay a roadmap for the proper implementation of it following the perceptions of their customers.
{"title":"IMMBA – An Integrative Model for Mobile Banking Adoption: The Case of Saudi Arabia","authors":"Amal Alzahrani, N. Beloff, Martin White","doi":"10.1109/HORA52670.2021.9461290","DOIUrl":"https://doi.org/10.1109/HORA52670.2021.9461290","url":null,"abstract":"The mobile industry is one of the rapidly growing markets in the world. This has created a unique platform for delivering mobile network-based social and financial services. Mobile banking is the best and last banking platform that provides value-added services anytime and anywhere with a reduction in effort, time, and money. However, there is a decrease in the adoption rate of these services in Arabian countries, including Saudi Arabia. Although there have been several studies to determine factors influencing the adoption of these services worldwide, few studies have been done in this part of the world. This paper considers the current literature on mobile banking to investigate the factors that increase mobile banking adoption in Saudi Arabia. We propose a new integrative model for mobile banking adoption (IMMBA) that combines and expands the IS Success and UTAUT2 models to include factors that account for Perceived Trust, Perceived Privacy, and Perceived Compatibility. IMMBA provides a comprehensive analysis of the current challenges of mobile banking adoption in Saudi Arabia. Identifying the factors that affect mobile banking adoption and understanding the relationships between them will help banks, particularly in Saudi Arabia, to lay a roadmap for the proper implementation of it following the perceptions of their customers.","PeriodicalId":270469,"journal":{"name":"2021 3rd International Congress on Human-Computer Interaction, Optimization and Robotic Applications (HORA)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114307450","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 : 2021-06-11DOI: 10.1109/HORA52670.2021.9461333
Tsvetelina Mladenova, Irena Valova
The problem with fake news and click-bait headlines is not new. Despite that this kind of news has existed for many years now, it was just a few years ago that the focus of the scientific community turned to them. Even though there is quite a lot of research on the topic of detecting fake news in general, there is a limited number of studies on fake news in Cyrillic. This paper focuses on the classification of fake news and click-bait headlines from Bulgarian Facebook Pages. The KNN machine-learning algorithm is chosen and four different distance metrics are tested and analyzed.
{"title":"Analysis of the KNN Classifier Distance Metrics for Bulgarian Fake News Detection","authors":"Tsvetelina Mladenova, Irena Valova","doi":"10.1109/HORA52670.2021.9461333","DOIUrl":"https://doi.org/10.1109/HORA52670.2021.9461333","url":null,"abstract":"The problem with fake news and click-bait headlines is not new. Despite that this kind of news has existed for many years now, it was just a few years ago that the focus of the scientific community turned to them. Even though there is quite a lot of research on the topic of detecting fake news in general, there is a limited number of studies on fake news in Cyrillic. This paper focuses on the classification of fake news and click-bait headlines from Bulgarian Facebook Pages. The KNN machine-learning algorithm is chosen and four different distance metrics are tested and analyzed.","PeriodicalId":270469,"journal":{"name":"2021 3rd International Congress on Human-Computer Interaction, Optimization and Robotic Applications (HORA)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114359179","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：