Pub Date : 2021-10-21DOI: 10.1109/ISMSIT52890.2021.9604700
Martin Djonov, Miroslav Galabov, T. Georgieva-Trifonova
Internet of Things (IoT) is one relatively new technology, which aims to make our lives easier by automating our daily processes. This article would aim to deliver an idea how to prevent the IoT technology, delivering maliciously and bad things and how to scale. The intention of this research is to explain how a specific implementation of a Blockchain network, enterprise-grade permissioned distributed ledger framework called Hyperledger Fabric, can be used to resolve the security and scalability issues in an IoT network.
{"title":"Solving IoT Security and Scalability Challenges with Blockchain","authors":"Martin Djonov, Miroslav Galabov, T. Georgieva-Trifonova","doi":"10.1109/ISMSIT52890.2021.9604700","DOIUrl":"https://doi.org/10.1109/ISMSIT52890.2021.9604700","url":null,"abstract":"Internet of Things (IoT) is one relatively new technology, which aims to make our lives easier by automating our daily processes. This article would aim to deliver an idea how to prevent the IoT technology, delivering maliciously and bad things and how to scale. The intention of this research is to explain how a specific implementation of a Blockchain network, enterprise-grade permissioned distributed ledger framework called Hyperledger Fabric, can be used to resolve the security and scalability issues in an IoT network.","PeriodicalId":120997,"journal":{"name":"2021 5th International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130613026","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 : 2021-10-21DOI: 10.1109/ISMSIT52890.2021.9604538
Mustafa Nabeel Salim, Ban Shareef Mustafa
In this paper, a model prototype called UTtoKB has been built. It extracts semantic relationships from an unstructured text based on ontology. The model is a pipeline steps based on natural language processing (NLP) tasks and tools like Coreference Resolution (CR), Named Entity Recognition (NER), Semantic Role Labeling (SRL), and Part of Speech (PoS) Tagging. WordNet is the tool used to measure similarities between entities to convert them into ontology concepts and properties. The model works fine in specific domains, while performance degrades in other domains due to the instability of WordNet performance in finding semantic similarities.
{"title":"UTtoKB: a Model for Semantic Relation Extraction from Unstructured Text","authors":"Mustafa Nabeel Salim, Ban Shareef Mustafa","doi":"10.1109/ISMSIT52890.2021.9604538","DOIUrl":"https://doi.org/10.1109/ISMSIT52890.2021.9604538","url":null,"abstract":"In this paper, a model prototype called UTtoKB has been built. It extracts semantic relationships from an unstructured text based on ontology. The model is a pipeline steps based on natural language processing (NLP) tasks and tools like Coreference Resolution (CR), Named Entity Recognition (NER), Semantic Role Labeling (SRL), and Part of Speech (PoS) Tagging. WordNet is the tool used to measure similarities between entities to convert them into ontology concepts and properties. The model works fine in specific domains, while performance degrades in other domains due to the instability of WordNet performance in finding semantic similarities.","PeriodicalId":120997,"journal":{"name":"2021 5th International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT)","volume":"108 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125541405","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 : 2021-10-21DOI: 10.1109/ISMSIT52890.2021.9604585
H. Y. Hasirci, A. Vural
One of the results of the development of technology is the development of power electronics and the elements used in power electronics (such as semiconductor circuit elements). When converting DC-AC to conventional inverters, there are problems with lower voltage capacity, high harmonic content at the input and output, and high switching losses. Multilevel inverters (MLIs) have overcome these problems. In this study, The Packed U Cell (PUC) inverter that is a special type of MLIs is investigated. In addition, the PUC7 MLI inverter is designed, simulated, and integrated into the PMSG based variable speed wind energy conversion systems.
{"title":"Power Converter Topologies for PMSG Based Wind Energy Systems: Packed U Cell Multilevel Inverter Simulation","authors":"H. Y. Hasirci, A. Vural","doi":"10.1109/ISMSIT52890.2021.9604585","DOIUrl":"https://doi.org/10.1109/ISMSIT52890.2021.9604585","url":null,"abstract":"One of the results of the development of technology is the development of power electronics and the elements used in power electronics (such as semiconductor circuit elements). When converting DC-AC to conventional inverters, there are problems with lower voltage capacity, high harmonic content at the input and output, and high switching losses. Multilevel inverters (MLIs) have overcome these problems. In this study, The Packed U Cell (PUC) inverter that is a special type of MLIs is investigated. In addition, the PUC7 MLI inverter is designed, simulated, and integrated into the PMSG based variable speed wind energy conversion systems.","PeriodicalId":120997,"journal":{"name":"2021 5th International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125560753","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 : 2021-10-21DOI: 10.1109/ISMSIT52890.2021.9604676
I. Ilter, S. Dilibal, H. Zengin
In this study, a piezoelectric force sensor-based experimental recoil force analysis was performed via examining the formation and effects of recoil forces after overviewing the related experimental studies in the literature. The experimental measurement and the analysis of the recoil forces of the selected shotguns were carried out systematically after selecting the accurate piezoelectric force sensor for the dynamic performance of the recoil mechanism. The experimental setup required for the measurement was built via integrating the selected piezoelectric force sensor, signal conditioner, data acquisation card with a software developed in Visual Basic .NET software language. A developed measuring apparatus was designed to measure the dynamic recoil forces of different shotgun system. The selected piezoelectric force sensor can detect the recoil forces with 36 kHz measurement capacity. All of the data were recorded in real-time. The recorded data were examined, and analyzed comparatively. The collected measurement results are evaluated according to the recoil mechanisms, barrel lengths, weights, and other effective parameters that may affect the recoil forces in the experimental analysis. It was observed that the shotgun that spreads the recoil force over time reduces the peak point and has minimum total recoil energy among the gas cycle, inertia and hybrid shotguns with 71cm barrel length and included 12GA caliber.
{"title":"Piezoelectric Force Sensor-based Measurement System for Recoil Force Analysis","authors":"I. Ilter, S. Dilibal, H. Zengin","doi":"10.1109/ISMSIT52890.2021.9604676","DOIUrl":"https://doi.org/10.1109/ISMSIT52890.2021.9604676","url":null,"abstract":"In this study, a piezoelectric force sensor-based experimental recoil force analysis was performed via examining the formation and effects of recoil forces after overviewing the related experimental studies in the literature. The experimental measurement and the analysis of the recoil forces of the selected shotguns were carried out systematically after selecting the accurate piezoelectric force sensor for the dynamic performance of the recoil mechanism. The experimental setup required for the measurement was built via integrating the selected piezoelectric force sensor, signal conditioner, data acquisation card with a software developed in Visual Basic .NET software language. A developed measuring apparatus was designed to measure the dynamic recoil forces of different shotgun system. The selected piezoelectric force sensor can detect the recoil forces with 36 kHz measurement capacity. All of the data were recorded in real-time. The recorded data were examined, and analyzed comparatively. The collected measurement results are evaluated according to the recoil mechanisms, barrel lengths, weights, and other effective parameters that may affect the recoil forces in the experimental analysis. It was observed that the shotgun that spreads the recoil force over time reduces the peak point and has minimum total recoil energy among the gas cycle, inertia and hybrid shotguns with 71cm barrel length and included 12GA caliber.","PeriodicalId":120997,"journal":{"name":"2021 5th International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126773732","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 : 2021-10-21DOI: 10.1109/ISMSIT52890.2021.9604620
Davut Izci, Serdar Ekinci, Erdal Eker, Ahmet Dündar
This paper aims to demonstrate the success of a recently developed metaheuristic algorithm, named slime mould algorithm (SMA), for efficient operation of a magnetic levitation system. A real proportional-integral-derivative (PID) plus second-order derivative (PIDD2) controller was utilized to demonstrate the implementation. This paper is also the first report on SMA based real PIDD2 controller tuning for control of a magnetic levitation system. The transient response analysis was performed to demonstrate the promise of the proposed approach. Besides, a comparative performance analysis in terms of transient stability was also performed by using other available and good performing approaches. The results have shown the SMA based real PIDD2 controller to be a better choice for efficient operation of a magnetic levitation system.
{"title":"Assessment of Slime Mould Algorithm Based Real PID Plus Second-order Derivative Controller for Magnetic Levitation System","authors":"Davut Izci, Serdar Ekinci, Erdal Eker, Ahmet Dündar","doi":"10.1109/ISMSIT52890.2021.9604620","DOIUrl":"https://doi.org/10.1109/ISMSIT52890.2021.9604620","url":null,"abstract":"This paper aims to demonstrate the success of a recently developed metaheuristic algorithm, named slime mould algorithm (SMA), for efficient operation of a magnetic levitation system. A real proportional-integral-derivative (PID) plus second-order derivative (PIDD2) controller was utilized to demonstrate the implementation. This paper is also the first report on SMA based real PIDD2 controller tuning for control of a magnetic levitation system. The transient response analysis was performed to demonstrate the promise of the proposed approach. Besides, a comparative performance analysis in terms of transient stability was also performed by using other available and good performing approaches. The results have shown the SMA based real PIDD2 controller to be a better choice for efficient operation of a magnetic levitation system.","PeriodicalId":120997,"journal":{"name":"2021 5th International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114100618","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 : 2021-10-21DOI: 10.1109/ISMSIT52890.2021.9604660
Bilal Canol, A. Yildiz
A new model has been proposed for the analysis of Flyback converter with coupled inductance. The model transforms any dynamic circuit into a resistive circuit. The method is based on the discrete equivalent circuit approach. In this way, a fully resistive flyback circuit has been obtained with discrete equivalents of coupled inductor and capacitor. The proposed model makes the analysis easier.
{"title":"Discrete-Model Based Analysis of Flyback Converter Circuit","authors":"Bilal Canol, A. Yildiz","doi":"10.1109/ISMSIT52890.2021.9604660","DOIUrl":"https://doi.org/10.1109/ISMSIT52890.2021.9604660","url":null,"abstract":"A new model has been proposed for the analysis of Flyback converter with coupled inductance. The model transforms any dynamic circuit into a resistive circuit. The method is based on the discrete equivalent circuit approach. In this way, a fully resistive flyback circuit has been obtained with discrete equivalents of coupled inductor and capacitor. The proposed model makes the analysis easier.","PeriodicalId":120997,"journal":{"name":"2021 5th International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT)","volume":"231 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121035433","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 : 2021-10-21DOI: 10.1109/ISMSIT52890.2021.9604654
Salih Palamut, Abdullah Elewi, Erdinç Avaroglu
Bu çalışmada merkezler arası uzaklığı 65 mm olan iki kamera, metal plaka yardımıyla sabitlenmiştir. Gömülü sistem olarak iki kamera destekli Jeston Nano tek kart bilgisayarı üzerinde C++ dili ile OpenCv kitaplığı kullanarak çalışma düzlemi kurulmuştur. Bu düzlemde basit kenar bulma algoritması yöntemiyle iki kameradan elde edilen görüntülerin matematiksel hesaplama yöntemleriyle kullanılan kameralar üzerinde piksel hesabıyla görüş alanında bulunan nesnenin uzaklığı hesaplanmış ve analog ölçüm aletiyle hesaplanan değerin sağlaması yapılmıştır. Yapılan çalışmalarda nesnenin 20 cm’den daha yakın konumlanması hesaplanan değerin kenar algoritmasının yetersizliğinden dolayı hata payını arttırdığı 20 cm ve üstü değerler için çevresel etmenlerden dolayı değişken sapmalar olduğu gözlemlenmiştir.In this study, two cameras with 65 mm distance between centers were fixed with the help of metal plate. As an embedded system, a work plane was set up using the C++ language and OpenCv library on a Jeston Nano single board computer with two cameras. In this plane, the distance of the object in the field of view was calculated with the pixel calculation on the cameras used with the mathematical calculation methods of the images obtained from the two cameras by the simple edge detection algorithm method, and the value calculated with the analog measuring instrument was verified. In the studies, it has been observed that there are variable deviations due to environmental factors for values of 20 cm and above, where the calculated value increases the margin of error due to the inadequacy of the edge algorithm.
{"title":"Jetson Nano Üzerinde Çift Kameralı Uzaklık Hesaplama Uygulanması","authors":"Salih Palamut, Abdullah Elewi, Erdinç Avaroglu","doi":"10.1109/ISMSIT52890.2021.9604654","DOIUrl":"https://doi.org/10.1109/ISMSIT52890.2021.9604654","url":null,"abstract":"Bu çalışmada merkezler arası uzaklığı 65 mm olan iki kamera, metal plaka yardımıyla sabitlenmiştir. Gömülü sistem olarak iki kamera destekli Jeston Nano tek kart bilgisayarı üzerinde C++ dili ile OpenCv kitaplığı kullanarak çalışma düzlemi kurulmuştur. Bu düzlemde basit kenar bulma algoritması yöntemiyle iki kameradan elde edilen görüntülerin matematiksel hesaplama yöntemleriyle kullanılan kameralar üzerinde piksel hesabıyla görüş alanında bulunan nesnenin uzaklığı hesaplanmış ve analog ölçüm aletiyle hesaplanan değerin sağlaması yapılmıştır. Yapılan çalışmalarda nesnenin 20 cm’den daha yakın konumlanması hesaplanan değerin kenar algoritmasının yetersizliğinden dolayı hata payını arttırdığı 20 cm ve üstü değerler için çevresel etmenlerden dolayı değişken sapmalar olduğu gözlemlenmiştir.In this study, two cameras with 65 mm distance between centers were fixed with the help of metal plate. As an embedded system, a work plane was set up using the C++ language and OpenCv library on a Jeston Nano single board computer with two cameras. In this plane, the distance of the object in the field of view was calculated with the pixel calculation on the cameras used with the mathematical calculation methods of the images obtained from the two cameras by the simple edge detection algorithm method, and the value calculated with the analog measuring instrument was verified. In the studies, it has been observed that there are variable deviations due to environmental factors for values of 20 cm and above, where the calculated value increases the margin of error due to the inadequacy of the edge algorithm.","PeriodicalId":120997,"journal":{"name":"2021 5th International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131199269","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 : 2021-10-21DOI: 10.1109/ISMSIT52890.2021.9604606
Umit Ilhan, Ahmet Ilhan, K. Uyar, E. Iseri
Rice is one of the most widely consumed grains in the world. It is globally known that countries in southern Asia are the ones that mostly produce and also consume this particular type of grain. About 800 million tons of rice in many varieties is produced in the world every year. Each variety has its unique characteristics. This study covers research on the classification of Osmancik and Cammeo rice varieties using Deep Neural Networks (DNNs). There are 3810 numerical data of which 2180 belong to Osmancik and 1630 to Cammeo in the University of California Irvine (UCI) Rice (Osmancik and Cammeo) Data Set that is used in this work. The data is subjected to a normalization process which improves the performance of the multilayer neural networks. The performance of this study is measured thru calculating accuracy, sensitivity, specificity, precision, F1-score, NPV, FPR, FDR and, FNR. The overall success rate of this study is found to be 93.04%.
大米是世界上消费最广泛的谷物之一。众所周知，南亚国家是主要生产和消费这种特殊谷物的国家。世界上每年大约生产8亿吨品种繁多的大米。每个品种都有其独特的特点。本研究利用深度神经网络(DNNs)对Osmancik和Cammeo水稻品种进行分类研究。在加州大学欧文分校(UCI) Rice (Osmancik and Cammeo) data Set中有3810个数值数据，其中2180个属于Osmancik, 1630个属于Cammeo。数据经过归一化处理，提高了多层神经网络的性能。通过计算准确性、敏感性、特异性、精密度、f1评分、NPV、FPR、FDR和FNR来衡量本研究的效果。本研究的总体成功率为93.04%。
{"title":"Classification of Osmancik and Cammeo Rice Varieties using Deep Neural Networks","authors":"Umit Ilhan, Ahmet Ilhan, K. Uyar, E. Iseri","doi":"10.1109/ISMSIT52890.2021.9604606","DOIUrl":"https://doi.org/10.1109/ISMSIT52890.2021.9604606","url":null,"abstract":"Rice is one of the most widely consumed grains in the world. It is globally known that countries in southern Asia are the ones that mostly produce and also consume this particular type of grain. About 800 million tons of rice in many varieties is produced in the world every year. Each variety has its unique characteristics. This study covers research on the classification of Osmancik and Cammeo rice varieties using Deep Neural Networks (DNNs). There are 3810 numerical data of which 2180 belong to Osmancik and 1630 to Cammeo in the University of California Irvine (UCI) Rice (Osmancik and Cammeo) Data Set that is used in this work. The data is subjected to a normalization process which improves the performance of the multilayer neural networks. The performance of this study is measured thru calculating accuracy, sensitivity, specificity, precision, F1-score, NPV, FPR, FDR and, FNR. The overall success rate of this study is found to be 93.04%.","PeriodicalId":120997,"journal":{"name":"2021 5th International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128123563","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 : 2021-10-21DOI: 10.1109/ISMSIT52890.2021.9604588
B. Atasoy, S. S. Tezcan
In Turkey, solar power technology is quickly advancing, and investors are interested in establishing solar power plant. With the support of YEKDEM(Turkish Renewable Energy Resources Support Mechanism) and YEKA(Regulation on Renewable Energy Zones) mechanisms implemented by the state, solar investments have increased with a very serious momentum in recent years. With the recently announced YEKA GES-4 and YEKA GES-5 projects we foresee that the investments in solar power plants in Turkey will increase rapidly in the future. There is a difference in investment operation and maintenance costs, and operation efficiency of grid-tie inverter technology between string and central inverter. In this stud, we will find the optimum inverter selection by performing cost analysis and annual production with string and central inverter in 10 MW solar power plant.
{"title":"Comparison of String and Central Inverter for 10MW PV Plant","authors":"B. Atasoy, S. S. Tezcan","doi":"10.1109/ISMSIT52890.2021.9604588","DOIUrl":"https://doi.org/10.1109/ISMSIT52890.2021.9604588","url":null,"abstract":"In Turkey, solar power technology is quickly advancing, and investors are interested in establishing solar power plant. With the support of YEKDEM(Turkish Renewable Energy Resources Support Mechanism) and YEKA(Regulation on Renewable Energy Zones) mechanisms implemented by the state, solar investments have increased with a very serious momentum in recent years. With the recently announced YEKA GES-4 and YEKA GES-5 projects we foresee that the investments in solar power plants in Turkey will increase rapidly in the future. There is a difference in investment operation and maintenance costs, and operation efficiency of grid-tie inverter technology between string and central inverter. In this stud, we will find the optimum inverter selection by performing cost analysis and annual production with string and central inverter in 10 MW solar power plant.","PeriodicalId":120997,"journal":{"name":"2021 5th International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134379649","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 : 2021-10-21DOI: 10.1109/ISMSIT52890.2021.9604550
Mustafa Çetın, Yunus Koç
Machine Learning (ML) algorithms are used in many fields such as finance, education, industry, medicine and e-commerce. ML algorithms show performance differences depending on the dataset and processing steps. Choosing the right algorithm, preprocessing and postprocessing methods has great importance to achieve good results. In this paper, Random Forest Classifier, Logistic Regression Classifier, Decision Tree Classifier, Linear Discriminant Analysis, K-Nearest Neighbor Classifier and SVC methods are compared to predict mobile phone price class. The "Mobile Price Classification" dataset which is taken from Kaggle.com is used to evaluate methods. Firstly, all values at the dataset are checked to verify that there are no missing values. After that, scaling is applied to dataset in order to obtain more relevant data for ML algorithms. Then, feature selection methods which reduce the computational cost by reducing the number of inputs are performed to get meaningful features. Finally, the parameters of classification algorithms are tuned to improve the system accuracy. According to obtained results, it is seen that ANOVA f-test feature selection method is more convenient for this dataset. It gives satisfying accuracy with a minimum number of features. It is also seen that the SVC classifier has the highest test accuracy compared to other models.
{"title":"Mobile Phone Price Class Prediction Using Different Classification Algorithms with Feature Selection and Parameter Optimization","authors":"Mustafa Çetın, Yunus Koç","doi":"10.1109/ISMSIT52890.2021.9604550","DOIUrl":"https://doi.org/10.1109/ISMSIT52890.2021.9604550","url":null,"abstract":"Machine Learning (ML) algorithms are used in many fields such as finance, education, industry, medicine and e-commerce. ML algorithms show performance differences depending on the dataset and processing steps. Choosing the right algorithm, preprocessing and postprocessing methods has great importance to achieve good results. In this paper, Random Forest Classifier, Logistic Regression Classifier, Decision Tree Classifier, Linear Discriminant Analysis, K-Nearest Neighbor Classifier and SVC methods are compared to predict mobile phone price class. The \"Mobile Price Classification\" dataset which is taken from Kaggle.com is used to evaluate methods. Firstly, all values at the dataset are checked to verify that there are no missing values. After that, scaling is applied to dataset in order to obtain more relevant data for ML algorithms. Then, feature selection methods which reduce the computational cost by reducing the number of inputs are performed to get meaningful features. Finally, the parameters of classification algorithms are tuned to improve the system accuracy. According to obtained results, it is seen that ANOVA f-test feature selection method is more convenient for this dataset. It gives satisfying accuracy with a minimum number of features. It is also seen that the SVC classifier has the highest test accuracy compared to other models.","PeriodicalId":120997,"journal":{"name":"2021 5th International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134561552","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：