Yazar "Albayrak, Ahmet" seçeneğine göre listele
Listeleniyor 1 - 14 / 14
Sayfa Başına Sonuç
Sıralama seçenekleri
Öğe Analysis of Honey Production with Environmenta Variables(Institute of Electrical and Electronics Engineers Inc., 2021) Atagün, Ercan; Albayrak, AhmetRegression algorithms are included in the supervised learning techniques of machine learning. Regression covers the operations of estimating the variable with the class label (output variable) by using the numerical values in a data with regression algorithms. When the desired performances cannot be achieved with the existing regression algorithms for a problem, Ensemble Learning models are applied. In the Ensemble Learning model, multiple predictive algorithms come together and aim to achieve a higher success than the success of an algorithm alone. In this study, honey production problem was estimated with Support vector machines. Multi-layer Perceptron Regressor, KNeighborsRegressor, Voting Regressor, RandomForestRegressor, AdaBoostRegressor, BaggingRegressor, GradientBoostingRegressor and the results were compared. It was observed that the ensemble learning models increased the prediction success with the regression processes. © 2021 IEEEÖğe Analysis of the Covid-19 Process in Terms of Health Managers(Institute of Electrical and Electronics Engineers Inc., 2022) Palavar, Yunus Emre; Çelik, Zeynep; Albayrak, Ahmet; Özçelik, Emine; Erdil, MustafaIn this study, sentiment analysis was conducted on the data of the Covid-19 epidemic process from the official twitter account of the Republic of Turkey Fahrettin Koca, Minister of Health, @drfahrettinkoca (SO) and the Twitter account of the @WHO (World Health Organization). First of all, twitter data was obtained and necessary arrangements were made for analysis. Then, tweets were shown with a word cloud and it was determined which words were used more frequently. Afterwards, sentiment analysis was performed on the data using the TextBlob library. In addition, it has been found out which subjects are focused on tweets sent from SO and @WHO (World Health Organization) accounts with the LDA algorithm. It has been seen that positive tweets were sent from both accounts, giving positive messages to the society. © 2022 IEEE.Öğe Analysis of User Comments with Sentiment Analysis and Ensemble Learning Approaches(Duzce University, 2023) Zada, Adham Jolosı Jolosı; Albayrak, AhmetIn this study, the comments made by users who purchased products on online shopping platforms were analyzed by using sentiment analysis techniques, which is one of the natural language processing approaches. Sentiment analysis was conducted on user comments received from a platform known as an online shopping platform in Turkey for years. Initially, 2237 comments were collected in a specific category. Basic natural language processing techniques were operated on the comments, the data was cleaned and made available for analysis. Then, the scores given by the users were compared with the sentiment analysis on the data set. While classifying user comments, Random Forest and AdaBoost approaches from community learning techniques were tried. As a result of the study, it was seen that the user comments were not consistent with the given score. The four-star category was the one with the most consistent ratings and comments made by the users. For this reason, it has been concluded that online shopping platforms should collect user comments in a more qualified way and develop systems on the validity of comments, integrate machine learning and natural language processing techniques into their systems.Öğe Design and implementation of modular test equipment for process measurements in mechatronics education(Wiley, 2020) Ceven, Suleyman; Albayrak, AhmetIn this study, an experimental setup is presented which is developed to enrich mechatronics education in terms of content and to provide a variety of applications. The experimental setup was developed to enable students to learn through more practical experiments. The main purpose of this study is to develop an experimental setup that can be used as a basic application tool for many courses that will eliminate the deficiencies in mechatronics education. In addition, the experimental setup contributes to the learning of equipment commonly used in mechatronic systems and to enable students to graduate more readily for the industry. This methodology, which was taken into consideration when designing the experimental setup, provided the students with the basic skills that enable them to acquire interdisciplinary knowledge more easily and achieve a successful career. The experimental setup was tested in process measurements course. For the mechanism which was tested with 65 students, the opinions of the students were taken with the help of a questionnaire. These opinions were analyzed with SPSS software. As a result of the analysis, Cronbach's alpha was calculated and found to be .815. In addition, descriptive statistics and chi(2) tests were conducted on the questionnaire results. As a result of all these analyzes, it was seen that the experimental setup should be made more interactive. With the integration of new technologies, the experimental setup will be available for many years in associate degree and undergraduate education.Öğe Detection of Intrusions with Machine Learning Methods(Ieee, 2021) Bostancı, Beyzanur; Albayrak, AhmetToday, especially with the emergence of social networks and IoT technologies, big data has entered the literature. With the development of technology, the size of the data has increased and accordingly data security gaps have emerged. In this study, Support Vector Machines and Random Forest algorithms, which are Supervised Machine Learning Algorithms, were used to analyze a data set consisting of unauthorized network logins. As a result of the experimental studies, it was observed that both algorithms produced good results, but the Random Forest approach produced better results.Öğe Development of a Mecanum-Wheeled Mobile Robot for Dynamic- and Static-Obstacle Avoidance Based on Laser Range Sensor(Korean Inst Intelligent Systems, 2020) Matli, Musa; Albayrak, Ahmet; Bayir, RaifThis study aims to present an idea about the practical consequences of using mobile robots with Mecanum wheels. For mobile robots, an approach is proposed to avoid obstacles without location and map information. This approach is presented using a series of developed solutions. This article shares the process on how a set of discussed conceptual methodologies can be applied as well as their practical results. This method is provided using fuzzy logic and gap tracking. LIDAR is used to recognize obstacles around the mobile robot. By using the LIDAR, the robot detects gaps around it and moves according to fuzzy logic. The fuzzy logic consists of three inputs, an output, and 45 rules. The first of the membership functions represents the membership function that replaces the obstacle. The second membership function calculates the distance to the obstacle. The final login membership function is used to determine the angle between the obstacle and robot view. The output membership function represents the membership function that moves the robot. The results are analyzed under three different scenarios with five different experiments for each scenario. The results show that the mobile robot can avoid obstacles without location and map information. We believe that the proposed method can be used in mobile robots such as guard and service robots.Öğe Development of IoT Based Battery Management System(Ieee, 2021) Çeven, Süleyman; Küçükkülahli, Enver; Albayrak, Ahmet; Biçen, YunusIn this study, the modular battery management system used in electric vehicles was developed and monitored with the IoT-based MQTT protocol. In recent years, electric vehicles have been widely studied by researchers and long-lasting battery systems have been developed. In this study, a modular battery management system that performs the charging process with the passive balancing method has been developed. The battery has been developed for electric vehicles with more than 1 kWh of energy. There is temperature, current and voltage sensors at each node for battery management. A temperature sensor has been added to the system in case of overheating of the battery. The data collected over the battery is transferred to the web environment with MQTT, one of the IoT protocols. Passive balancing is preferred for balancing the batteries during charging. During charging, the MQTT server notifies the network to set the required voltage for each node.Öğe Doğal Dil İşleme Teknikleri Kullanılarak Disiplinler Arası Lisansüstü Ders İçeriği Hazırlanması(2020) Albayrak, AhmetBu çalışmada lisansüstü seviyede açılan düşünülen disiplinler arası bir dersin içeriğinin hazırlanması için veri madenciliği tekniklerinden doğal dil işleme yöntemleri kullanılmıştır. Lisansüstü ders, Veri Bilimi ve Uygulamaları adını taşımaktadır. Veri bilimi temelde istatistik ve bilgisayar bilimlerini içine alan disiplinler arası bir kavramdır. Dersin benzer bir ad ile literatürde yeri yoktur. Veri bilimi yaklaşımı veriyi öncelikleyen ve oldukça fazla alanda uygulanan bir yaklaşımdır. Uygulama alanı çok geniş olduğundan derse Veri Bilimi ve Uygulamaları adı verilmiştir. IEEE’nin yıllardır düzenlediği bir konferansta basılan bildiriler ders içeriğinin belirlenmesinde veri seti olarak kullanılmıştır. Data Science and Advanced Analytics adındaki konferansın bu yıl 7. si düzenlenecektir. 2015, 2016, 2017 ve 2018 yıllarında konferansa kabul edilen bildiriler veri setinde kullanılmıştır. Bildirilerin başlık kısımları ve anahtar kelimeler doğal dil işleme teknikleri ile analiz edilerek ders içeriği belirlenmiştir. Bu çalışmada ilk olarak veri seti hazırlandıktan sonra, veri üzerinde veri temizleme işlemi yapılmış ardından bildiri başlıkları sözcüklere ayrılmıştır. Sözcüklere ayrılan veri seti içinde sözcüklerin frekansları bulunarak frekansa göre ilk yirmi sözcük seçilmiştir. Doğal dil işleme sürecinde Apache Spark NTK paketi kullanılmıştır. Seçilen 20 sözcük atomik olduğundan tümevarım yöntemi ile ana konu başlıkları belirlenmiştir.Öğe Duygu Analizi İle Kişiye Özel İçerik Önermek(Murat GÖK, 2021) Bostancı, Beyzanur; Albayrak, AhmetBu çalışmada, günümüzde yoğun biçimde kullanılan Facebook ve Twitter sosyal medya platformlarında paylaşılan kullanıcı yorumları duygu analizi teknikleri ile değerlendirilmiştir. Kullanıcı yorumları olarak üniversite tercih döneminde olan kişilerin paylaşımlarını içeren kısıtlı bir veri seti üzerinde çalışılmıştır. Bu veri setinin seçilmesinin nedeni günümüzde üniversite tercih dönemlerinde özellikle TV ve gazeteler aracılığıyla özel ve vakıf üniversitelerinin verdikleri yoğun reklamların sosyal medya kullanıcı profilleri analiz edilerek kişiye özel içerik oluşturma amacıyla kullanılmak istenmesidir. Sosyal medya üzerinden verilecek reklam içeriklerinin TV’lerde verilen reklamlardan maliyet olarak daha uygun olacağı açıktır. Özellikle kamu üniversitelerinin sosyal medya üzerinden reklam verebilmesi daha nitelikli ve bilinçli öğrencileri çekebileceği düşünülmektedir. Burada iki aşamalı bir yaklaşım önerilmektedir. İlk aşamada sosyal medya ortamından toplanan veriler analiz edilmiştir. İkinci aşamada önceden belirlenen sınıfların TF-IDF tekniği puanına göre iyimser, karamsar, mizahi, üretken ve dışa dönük olmak üzere kategorilere ayrılmaktadır. Ayrılan bu kategorilere göre de kullanıcıların profiline uygun reklamlar içerikleri sunulmaktadır.Öğe Modeling of migratory beekeeper behaviors with machine learning approach using meteorological and environmental variables: The case of Turkey(Elsevier, 2021) Albayrak, Ahmet; Ceven, Suleyman; Bayir, RaifIn this study, migratory beekeeping behavior, which is an important form of beekeeping, has been modeled. Modeling was performed in conditions of Turkey. Modeling was made by considering food sources (nectar / pollen) and meteorological variables (temperature, humidity, number of rainy days, number of cloudy days and sunshine duration) for Turkey in which migratory beekeeping carried out in a different form than in developed countries. The main output in migratory beekeeping is honey production. Considering honey production, modeling has been made with the food sources and meteorological variables that have the greatest effect on honey production. Since the data set developed for modeling consists of relatively few samples, the ensemble learning approach was preferred from the machine learning approaches. Random Forest and Decision Tree algorithms, which are among the ensemble learning techniques, were used. As a result, the migratory beekeeping behavior was correctly classified at a rate of 92%. As a result of classification of Turkey's 81 provinces in five different categories, it was concluded that 33 provinces are suitable for migratory beekeeping at different times of the year. These 33 provinces are regions in the good and very good categories. In the next stage, thematic maps were produced for migratory beekeepers. Maps were produced for each month of the year. Thus, a guidance and information system has been obtained for migratory beekeepers.Öğe Modelling of PID and LQR Controller for Stability and Position Control in Double Inverted Pendulum System(Osman SAĞDIÇ, 2020) Çeven, Süleyman; Albayrak, AhmetNowadays, stability of the inverted pendulum system is an up-to-date topic in which researchers working on control systems compare control theories and methods. The inverse pendulum systems are unstable and nonlinear systems in terms of controllability. Due to the complexity of the structure and the difficulty of the control process, many advanced control theories can be applied on these systems to improving the performance of the controllers. In this study, PID and LQR controller methods were applied on a double inverted pendulum modeled in MATLAB environment and their controller performances were compared. The results via experimental studies were evaluated on the applicability of PID and LQR control methods.Öğe Real-time range estimation in electric vehicles using fuzzy logic classifier(Elsevier Ltd, 2020) Çeven, Süleyman; Albayrak, Ahmet; Bayır, RaifNowadays, many scientists and companies in the automotive sector in the world are undertaking many important studies on electric vehicle technologies. For the electric vehicle to function as desired, the subsystems of the vehicle must be monitored and the parameters related to the vehicle must be kept in the most efficient range. Efficient use of these systems in electric vehicle will increase the vehicle range, as well as ensure the long life of the components used in the vehicle subsystems. Today, problem areas such as calculating the range of electric vehicles and battery state of charge have not yet been sufficiently standardized. The aim of this study is to make a range estimation in electric vehicle with fuzzy logic classifier which has been successfully applied in various problem areas. The fuzzy logic classifier is designed for range estimation, which is one of the most important research areas of electric vehicles today. In the Mamdani type fuzzy logic approach, dynamic vehicle parameters are taken into consideration. The fuzzy logic classifier considers the battery parameters of the vehicle and the power consumed instantly. In the prediction system, the power spent on the vehicle and the battery charge status are selected as inputs. The developed system was evaluated with three different test scenarios on the same track. These tests were conducted with no load (driver only), half load (driver + one person) and fully load (driver + three persons). The fuzzy logic classifier system determines in real-time how far electric vehicle can travel. © 2020 Elsevier LtdÖğe Topic Modeling Using LDA and BERT Techniques: Teknofest Example(Institute of Electrical and Electronics Engineers Inc., 2021) Atagün, Ercan; Hartoka, B.; Albayrak, AhmetThis paper is a natural language processing study and includes models used in natural language processing. In this paper, topic modeling, which is one of the sub-fields of natural language processing, has been studied. In order to make topic modeling, the data set was obtained by using the data scraping method, which has been very popular in recent years, over social media. The dataset is related to Teknofest competitions. The dataset was created by utilizing the Selenium library, one of the popular libraries used for the data scraping method. In order to be able to analyze on the prepared data set and to ensure the consistency of the clustering process, the text to be used before the analysis was preprocessed. After text preprocessing, clustering was performed on the data set with natural language processing techniques such as BERT and LDA . © 2021 IEEEÖğe Traffic accident severity prediction with ensemble learning methods(Pergamon-Elsevier Science Ltd, 2024) Ceven, Sueleyman; Albayrak, AhmetIn this study, decision tree-based models are proposed for classification of traffic accident severity. Traffic accident severity is classified into three categories. The data set used in the study belongs to the province of Kayseri, Turkey. The data consists of urban traffic accident reports (23074 accidents) between 2013 and 2021. There are 39 variables in the data set. As a result of data preprocessing, 15 variables that are meaningful and can be used for the model in the data set were determined. Since the input variables of the model mainly contain categorical data, they were coded with pseudo-coding and a total of 93 input variables were obtained. In the studies, ensemble learning methods such as Random Forest, AdaBoost and MLP methods were used. F1 scores of these methods were found to be 91.72%, 91.27% and 88.95%, respectively. Feature importance levels were calculated for 15 variables used in the model. Gini index and decision trees were used while calculating the importance of the features. Driver fault (0.64) was found to have the most effect on traffic accident severity. This study focuses especially on urban traffic accidents. Urban traffic is crowded in terms of both vehicles and pedestrians. As a result of this, according to the findings obtained in this study, traffic accidents occurred mostly at the intersections with crowded urban areas.
