Ismail Atacak - Academia.edu (original) (raw)
Papers by Ismail Atacak
Gazi University Journal of Science, 2010
The operation of front-end power converters can cause many undesirable effects in the Alternative... more The operation of front-end power converters can cause many undesirable effects in the Alternative Current (AC) power system. To prevent these undesirable effects, high-quality rectifiers, also called Power Factor Correctors (PFC) should be used. In this paper, power factor correction of switching mode power supply (SMPS) by using Neuro-Fuzzy (NF) controller is proposed. Average current control technique is used in PFC unit of the SMPS and current mode control technique is used in buck converter unit of the SMPS. To make comparison, the proposed SMPS is also controlled using traditional Proportional and Integral (PI) controller. Performances of these two controllers are compared through the computer simulation. Simulations show that NF controlled SMPS offers faster dynamic response and achieves good power factor correction than PI controlled SMPS.
Uluslararası mühendislik araştırma ve geliştirme dergisi, Dec 31, 2022
Öz Haber popülerliği, internet ya da sosyal ağ sitelerinde yayınlanmış haberlere gösterilen ilgi ... more Öz Haber popülerliği, internet ya da sosyal ağ sitelerinde yayınlanmış haberlere gösterilen ilgi düzeyinin bir göstergesidir. Haber sağlayıcıları, bu göstergenin kendi lehlerine değişmesini sağlamak adına, rekabetçi ve kullanıcılar açısından okunurluğu yüksek haberler yapmak zorundadır. Bu durum hem haber servislerinin sürekliliğine hem de haber kalitesinin artırılmasına önemli katkılar sağlar. Bu yüzden, haber popülerliğini otomatik olarak tespit eden sistemlerin varlığı günümüzde kaçınılmaz haline gelmiştir. Bu çalışmada, Kaliforniya Üniversitesi (KU)-Irvine Makine Öğrenmesi Deposu veri tabanından indirilen veriler bileştirilerek oluşturulmuş dengesiz veri seti ve bu veri setinden Sentetik Azınlık Örnekleme Tekniği (Synthetic Minority Oversampling Technique-(SMOTE)) ile üretilen dengeli veri setine Mamdani ve Sugeno-tip bulanık çıkarım sistemi temelli modeller uygulanarak haber popülerliği tahmini yapılmıştır. Haber popülerliği tahmini için, farklı çıkarım ve durulaştırma yöntemleri kullanılarak oluşturulan 8 farklı bulanık mantık temelli model oluşturulmuştur. Oluşturulan modellerden 6 tanesi Mamdani-tip bulanık çıkarım sistemi ile yapılandırılırken, 2 tanesinde Sugeno-tip bulanık çıkarım sistemi kullanılmıştır. Karışıklık matrisi metrikleri ve R 2 eğrileri ile performansları değerlendirilen tahmin modellerinin deneysel sonuçları, dengesiz ve dengeli veri setlerinin her ikisinde de tüm metrikler açısından en iyi performansı mak-min çıkarım yöntemi ve ağırlık merkezi durulaştırma yöntemini kullanan Mamdani-tip bulanık çıkarım sisteminin sağladığını göstermiştir. Ayrıca, burada geliştirilen modellerin deneysel sonuçları literatürde yer alan benzer çalışmalarınki ile kıyaslandığında, ağırlıklı ortalama yöntemini kullanan Sugeno-tip bulanık çıkarım sistemi dışındaki tüm bulanık mantık temelli modellerin benzer çalışmalardaki modellerin en iyileri kadar rekabetçi bir performans sergilemiş olduklarını da ispatlamıştır.
INTERNATIONAL JOURNAL OF INFORMATICS TECHNOLOGIES, Jul 31, 2022
Günümüzde internetin hızlı bir şekilde gelişmesi ve kolay bir şekilde ulaşılır olması; Facebook, ... more Günümüzde internetin hızlı bir şekilde gelişmesi ve kolay bir şekilde ulaşılır olması; Facebook, Instagram, Twitter ve LinkedIN gibi yaygın kullanılan sosyal iletişim platformlarını büyük veri yığınlarının olduğu ortamlara dönüştürmüştür. Bu durum hem aranan bilgiye kolay bir şekilde ulaşılabilmesi için konu tespiti uygulamalarının, hem de konuyla ilgili paylaşım yapan benzer eğilim ve düşünceye sahip topluluklara toplu hizmet verebilmek için topluluk tespit uygulamalarının bu platformlarda kullanımını zorunlu hale getirmiştir. Bu yüzden araştırmacıların sosyal iletiş im ağlarında konu tespiti ve topluluk tespiti alanları üzerine araştırmalar yapması ve problemin çözümü ile ilgili yöntem ve teknikler geliştirmesi bu ortamların etkin kullanımı açısından hayati bir önem arz eder. Bu çalışmada, bu alanlara kapsamlı bir bakış sağlamak için sosyal medya platformlarında konu ve topluluk analizi yapan çalışmalar üzerine sistematik ve derinlemesine bir literatür incelemesi sunulmaktadır. İncelemesi yapılacak çalışmaların çoğu uygulamada başarılı sonuçlar ürettiği bilinen makine öğrenmesi temelli modeller kullanan makalelerden seçilmiştir. Bu çalışmaların incelenmesi neticesinde; topluluk tespiti alanında elde ettiği performans değerleri ile Louvain metodunun öne çıktığ ı görülürken, performans açısından konu analizi alanında tek bir modelin önerilemeyeceği ve uygun modelin ancak verilen sorunun tüm özellikleri göz önünde bulundurularak, probleme özgü şekilde seçilmesi ya da oluş turulması gerektiğ i sonucuna varılmıştır.
In this study, a prototype based on fuzzy logic (FL) controller and internet of things (IoT) was ... more In this study, a prototype based on fuzzy logic (FL) controller and internet of things (IoT) was developed to monitor rumen health parameters in cattle. In the system build as a prototype, the monitoring process related to the parameters is followed through three different applications developed on the Android operating system, the Thingspeak service and the WEB environment. The first application, which is an Android-based program, warns the user in case of any abnormality related to the rumen health. The other two applications allow monitoring and analyzing rumen health parameters in real time. The system implements a process that measures at varying time intervals to display the values of rumen health parameters, pH and temperature. The management of this process is carried out by the FL controller depending on the pH and temperature changes. This measurement, which is made at varying time intervals, is the most important feature that distinguishes our study from studies in the literature. Because in the studies reported in the literature, measurements are made at fixed time intervals. The relevant feature brings with it two important contributions for the system we propose. The first is to accelerate the precautions to be taken regarding animal health by enabling the system to measure at more frequent intervals in cases of deterioration in the pH level of rumen. The second is to reduce the energy consumed by the parameter measuring device from the battery by allowing the system to measure at longer intervals when the pH level of rumen is in balance.
PeerJ Computer Science
Background Social networks are large platforms that allow their users to interact with each other... more Background Social networks are large platforms that allow their users to interact with each other on the Internet. Today, the widespread use of social networks has made them vulnerable to malicious use through different methods such as fake accounts and spam. As a result, many social network users are exposed to the harmful effects of spam accounts created by malicious people. Although Twitter, one of the most popular social networking platforms, uses spam filters to protect its users from the harmful effects of spam, these filters are insufficient to detect spam accounts that exhibit new methods and behaviours. That’s why on social networking platforms like Twitter, it has become a necessity to use robust and more dynamic methods to detect spam accounts. Methods Fuzzy logic (FL) based approaches, as they are the models such that generate results by interpreting the data obtained based on heuristics viewpoint according to past experiences, they can provide robust and dynamic solutio...
PeerJ Computer Science
Background Social networks are large platforms that allow their users to interact with each other... more Background Social networks are large platforms that allow their users to interact with each other on the Internet. Today, the widespread use of social networks has made them vulnerable to malicious use through different methods such as fake accounts and spam. As a result, many social network users are exposed to the harmful effects of spam accounts created by malicious people. Although Twitter, one of the most popular social networking platforms, uses spam filters to protect its users from the harmful effects of spam, these filters are insufficient to detect spam accounts that exhibit new methods and behaviours. That’s why on social networking platforms like Twitter, it has become a necessity to use robust and more dynamic methods to detect spam accounts. Methods Fuzzy logic (FL) based approaches, as they are the models such that generate results by interpreting the data obtained based on heuristics viewpoint according to past experiences, they can provide robust and dynamic solutio...
PeerJ Computer Science
Background Android is the most widely used operating system all over the world. Due to its open n... more Background Android is the most widely used operating system all over the world. Due to its open nature, the Android operating system has become the target of malicious coders. Ensuring privacy and security is of great importance to Android users. Methods In this study, a hybrid architecture is proposed for the detection of Android malware from the permission information of applications. The proposed architecture combines the feature extraction power of the convolutional neural network (CNN) architecture and the decision making capability of fuzzy logic. Our method extracts features from permission information with a small number of filters and convolutional layers, and also makes the feature size suitable for ANFIS input. In addition, it allows the permission information to affect the classification without being neglected. In the study, malware was obtained from two different sources and two different data sets were created. In the first dataset, Drebin was used for malware applica...
Applied Sciences
In this study, a fuzzy logic-based dynamic ensemble (FL-BDE) model was proposed to detect malware... more In this study, a fuzzy logic-based dynamic ensemble (FL-BDE) model was proposed to detect malware exposed to the Android operating system. The FL-BDE model contains a structure that combines both the processing power of machine learning (ML)-based methods and the decision-making power of the Mamdani-type fuzzy inference system (FIS). In this structure, six different methods, namely, logistic regression (LR), Bayes point machine (BPM), boosted decision tree (BDT), neural network (NN), decision forest (DF) and support vector machine (SVM) were used as ML-based methods to benefit from their scores. However, through an approach involving the process of voting and routing, the scores of only three ML-based methods which were more successful in classifying either the negative instances or positive instances were sent to the FIS to be combined. During the combining process, the FIS processed the incoming inputs and determined the malicious application score. Experimental studies were perfo...
PeerJ Comput. Sci., 2023
How to cite this article Atacak İ, Çıtlak O, Doğru İA. 2023. Application of interval type-2 fuzzy... more How to cite this article Atacak İ, Çıtlak O, Doğru İA. 2023. Application of interval type-2 fuzzy logic and type-1 fuzzy logic-based approaches to social networks for spam detection with combined feature capabilities. PeerJ Comput. Sci. 9:e1316 http://doi.org/10.7717/peerjcs.1316 under the curve (AUC) of 0.971. However, it has been observed that FL-based spam models have a higher performance than ML-based spam models in terms of metrics including accuracy, recall, F-score and AUC values.
Gazi mühendislik bilimleri dergisi, May 5, 2022
In this study, a prototype based on fuzzy logic (FL) controller and internet of things (IoT) was ... more In this study, a prototype based on fuzzy logic (FL) controller and internet of things (IoT) was developed to monitor rumen health parameters in cattle. In the system build as a prototype, the monitoring process related to the parameters is followed through three different applications developed on the Android operating system, the Thingspeak service and the WEB environment. The first application, which is an Android-based program, warns the user in case of any abnormality related to the rumen health. The other two applications allow monitoring and analyzing rumen health parameters in real time. The system implements a process that measures at varying time intervals to display the values of rumen health parameters, pH and temperature. The management of this process is carried out by the FL controller depending on the pH and temperature changes. This measurement, which is made at varying time intervals, is the most important feature that distinguishes our study from studies in the literature. Because in the studies reported in the literature, measurements are made at fixed time intervals. The relevant feature brings with it two important contributions for the system we propose. The first is to accelerate the precautions to be taken regarding animal health by enabling the system to measure at more frequent intervals in cases of deterioration in the pH level of rumen. The second is to reduce the energy consumed by the parameter measuring device from the battery by allowing the system to measure at longer intervals when the pH level of rumen is in balance.
Bilişim Teknolojileri Dergisi
In the recent past and in today’s world, the internet is advancing rapidly and is easily accessib... more In the recent past and in today’s world, the internet is advancing rapidly and is easily accessible; this growth has made the social media platforms such as Facebook, Instagram, Twitter, and LinkedIn widely used which produces big data. This requires both topic Detection applications in order to access the required information, as well as community detection practices in order to provide collective services to communities that can be referred to as individuals with similar interests and opinions over the same subject. Therefore, it is vital for researchers to conduct research on topic detection and community detection research areas in social networks and to develop methods and techniques for problem-solving. In this study, a systematic and in-depth literature review is provided on studies that conduct topic and community analysis on social media platforms to provide a comprehensive overview of the given areas. Most of the studies to be analyzed are selected from articles using mach...
Computational and Mathematical Methods in Medicine
Segmentation of skin lesions plays a very important role in the early detection of skin cancer. H... more Segmentation of skin lesions plays a very important role in the early detection of skin cancer. However, indistinguishability due to various artifacts such as hair and contrast between normal skin and lesioned skin is an important challenge for specialist dermatologists. Computer-aided diagnostic systems using deep convolutional neural networks are gaining importance in order to cope with difficulties. This study focuses on deep learning-based fusion networks and fusion loss functions. For the automatic segmentation of skin lesions, U-Net (U-Net + ResNet 2D) with 2D residual blocks and 2D volumetric convolutional neural networks were fused for the first time in this study. Also, a new fusion loss function is proposed by combining Dice Loss (DL) and Focal Tversky Loss (FTL) to make the proposed fused model more robust. Of the 2594 image dataset, 20% is reserved for test data and 80% for training data. In test data training, a Jaccard score of 0.837 and a dice score of 0.918 were obta...
Engineering Sciences, 2011
Uzun sureli oksijen tedavisi (USOT); hastalara yeterli egitimin verilmesi, planlanmis araliklarla... more Uzun sureli oksijen tedavisi (USOT); hastalara yeterli egitimin verilmesi, planlanmis araliklarla hasta takibinin yapilmasi, duzenli bakimi yapilan cihazlar ile uygun bir sure kullanilmasi durumunda, kronik obstruktif akciger hastaligina (KOAH) sahip hastalarin yasam kalitesini ve suresini arttiran bir metottur. Bu calismada, oksijen konsantratorleri ile USOT`ta karsilasilan problemler arastirilmis ve konu ile ilgili tespit edilen sorunlarin istatistiksel analizleri kullanilarak, cozumune yonelik onerilerde bulunulmustur. Bu amacla, Ocak 2007-Aralik 2009 tarihleri arasinda Sosyal Guvenlik Kurumuna (SGK) gelen 531 hastaya ait cihazin hikayesi dinlenmis, cihazlar kontrol edilmis, arizalari, muhtemel sebepleri, sik karsilasilan sorunlar kayit altina alinarak, sorunlarin hasta, doktor ve teknik uzman isbirligi ile tip elektronigi tabaninda cozumune yonelik calismalar yapilmistir.
Artificial Intelligence Studies
Bilgi ve iletişim teknolojilerinin hızlı bir şekilde gelişmesinin bir sonucu olarak, sosyal ağlar... more Bilgi ve iletişim teknolojilerinin hızlı bir şekilde gelişmesinin bir sonucu olarak, sosyal ağlar günlük yaşantımızın önemli bir parçası haline gelmiştir. Twitter, Instagram, Facebook ve Tumblr gibi sosyal ağ platformları üzerinde seyredilen filmler ve satın alınan ürünler üzerine paylaşılan yorumlar, reklamlar ve kampanyalar bu platformları kullanan hedef kullanıcı kitle üzerinde çok önemli bir etkiye sahiptir. Bununla birlikte kullanıcılar ilgili platformlarda çok büyük miktardaki metinsel veri yığınlarını okuyup anlayabilmek için uzun bir zamana ihtiyaç duyarlar. Bu kullanıcılar açısından önemli bir problemdir. Günümüzde problemin çözümüne yönelik olarak duygu analizi ve yapay zekaya dayanan farklı tipte otomatik metin işleme metot ve algoritmaları uygulanmaktadır. Bu çalışmada, Kaggle üzerinden elde edilen IMDB veri setindeki film yorumlarının olumlu mu yoksa olumsuz mu olduğunu belirleyebilmek için Microsoft Azure Makina Öğrenmesi (MÖ) studyosunda iki sınıflı MÖ temelli 6 farklı model geliştirilerek, karışıklık matrisi metrikleri ve ROC eğrileri yoluyla ilgili modellerin performanslarını test eden bir dizi analizler yapılmıştır. Elde edilen sonuçlar tüm karışıklık matrisi metrikleri açısından tek bir modelin en başarılı sonuca ulaşamadığını, ROC analizleri açısından ise bu sonuca iki sınıflı sinir ağı (SA) modelinin ulaştığını göstermiştir.
Engineering Sciences, 2011
Long-term oxygen therapy (LTOT) is a method that increases life-quality and life-span in patients... more Long-term oxygen therapy (LTOT) is a method that increases life-quality and life-span in patients with chronic obstructive pulmonary disease (COPD), in the case of giving adequate training to patients, using with regularly maintained devices, and checking up the patient during the scheduled period. In this study, the problems encountered in LTOT with oxygen concentrator(OC)was searched, and the recommendations related to the solution of these problems was presented by using the relevant statistical analysis of detected problems. For this purpose, the story of the 531 device belonging to patients, applied to the Social Security Agency(SSA) between January 2007 and December 2009, was listened. After maintenance of these devices, their malfunctions, probable causes of the malfunctions and the common problems was registered, and then the studies containing the solution based on the medical electronics was made by the cooperation with patients, doctors and technical specialist.
International Review of Electrical Engineering-iree, 2013
In this paper, a digital signal processor based real-time implementation of a type-2 fuzzy logic ... more In this paper, a digital signal processor based real-time implementation of a type-2 fuzzy logic (T2FL) controller on an on-line uninterruptible power supply (UPS) is presented. The UPS consists of three main power circuits. Power circuits are non-linear structure and contain uncertainties. Conventional controllers cannot be enough to overcome uncertainties. In this study, type–2 fuzzy controller which has high performance for modeling uncertainties has been developed as control algorithm to control the UPS system. The system was also controlled with proportional–integral (PI) controller to show the superiority of the proposed type–2 fuzzy controller. When compared with the performance of both controllers in terms of their dynamic responses, it was observed that the T2FL controllers have faster dynamic response under transient loading conditions than PI controllers
International Journal of Intelligent Systems and Applications in Engineering, 2017
Nowadays, with the increasing population in urban settlements, the number of vehicles used in tra... more Nowadays, with the increasing population in urban settlements, the number of vehicles used in traffic has also increased in these settlements. This has brought with it major problems that are caused by insufficient parking lots, in terms of traffic congestion, drivers and environment. In this study, in order to overcome these problems, a multi-stored automatic parking system that automatically performs vehicle recognition, vehicle parking, vehicle delivery and pricing processes is designed and the practical application of this system is realized on a prototype. The vehicle recognition process in the designed system is fulfilled through a software prepared on the personal computer connected to the webcam. A multi-stored semi-circular structure has been used as parking lots to resolve parking lot deficiencies. Therefore, the carrying system that carries out the parking process in the system is designed as a cylindrical coordinated robot that can move horizontally, vertically and in the forward-back direction. The control of the whole system is realized by the PIC16F877A microcontroller. The results obtained from the prepared prototype have showed that the proposed system can provide significant contributions to the solution of problems resulting from parking lot deficiencies.
International Journal of Intelligent Systems and Applications in Engineering, 2017
Air is one of the most important life sources for all living things. Gases that are present and a... more Air is one of the most important life sources for all living things. Gases that are present and absent in the composition of clean air also considered as pollutants in the atmosphere. If the pollutants rise above a certain concentration level, air pollution occurs. Air pollution damages all living things, especially human health. Accurate estimation of pollutant concentrations through air pollution modeling has an important effect in reducing the adverse effects of air pollution and taking necessary precautions. Conventional statistical models are widely used in air pollution forecasting and modeling. As a different approach, in this study, fuzzy logic algorithm (FLA), which has been increasingly successful in many field applications, is used to model air quality and air pollution analyzes are made based on this model. Ankara province data is used in the sample of the research.
Tehnicki vjesnik - Technical Gazette, 2017
Original scientific paper In this study, an optimal control algorithm is proposed to overcome low... more Original scientific paper In this study, an optimal control algorithm is proposed to overcome low performance problems arising from the non-linear characteristics of pneumatic motor in compressed air-based energy conversion systems. The effectiveness of the proposed algorithm is tested on an energy conversion system which includes a compressor, a proportional valve, a pneumatic motor (PM), a permanent magnet direct current (PMDC) generator and a control card. The control function of the system is carried out by driving the proportional valve with the control signals which is obtained depending on the PMDC generator output voltage error. In this structure, an optimal proportional-integral-derivative (PID) controller which tunes on-line its own gain parameters by particle swarm optimization (PSO) algorithm according to the operating conditions of the system used. In order to observe the effects of PSO-based PID controller on the system performance, the energy conversion system is also controlled by a discrete time PID controller. The experimental results show that PSO-based PID controller provides more robust control performance than discrete time PID controller under various operating conditions.
Computer Science & Information Technology (CS & IT), 2017
Liquid level tanks are employed in many industrial and chemical areas. Their level must be keep a... more Liquid level tanks are employed in many industrial and chemical areas. Their level must be keep a defined point or between maximum-minimum points depending on changing of inlet and outlet liquid quantities. In order to overcome the problem, many level control methods have been developed. In the paper, it was aimed that obtain a mathematical model of an installed liquid level tank system. Then, the mathematical model was derived from the installed system depending on the sizes of the liquid level tank. According to some proportional-integralderivative (PID) parameters, the model was simulated by using MATLAB/Simulink program. After that, data of the liquid level tank were taken into a computer by employing data acquisition cards (DAQs). Lastly, the computer-controlled liquid level control was successfully practiced through a written computer program embedded into a PID algorithm used the PID parameters obtained from the simulations into Advantech VisiDAQ software.
Gazi University Journal of Science, 2010
The operation of front-end power converters can cause many undesirable effects in the Alternative... more The operation of front-end power converters can cause many undesirable effects in the Alternative Current (AC) power system. To prevent these undesirable effects, high-quality rectifiers, also called Power Factor Correctors (PFC) should be used. In this paper, power factor correction of switching mode power supply (SMPS) by using Neuro-Fuzzy (NF) controller is proposed. Average current control technique is used in PFC unit of the SMPS and current mode control technique is used in buck converter unit of the SMPS. To make comparison, the proposed SMPS is also controlled using traditional Proportional and Integral (PI) controller. Performances of these two controllers are compared through the computer simulation. Simulations show that NF controlled SMPS offers faster dynamic response and achieves good power factor correction than PI controlled SMPS.
Uluslararası mühendislik araştırma ve geliştirme dergisi, Dec 31, 2022
Öz Haber popülerliği, internet ya da sosyal ağ sitelerinde yayınlanmış haberlere gösterilen ilgi ... more Öz Haber popülerliği, internet ya da sosyal ağ sitelerinde yayınlanmış haberlere gösterilen ilgi düzeyinin bir göstergesidir. Haber sağlayıcıları, bu göstergenin kendi lehlerine değişmesini sağlamak adına, rekabetçi ve kullanıcılar açısından okunurluğu yüksek haberler yapmak zorundadır. Bu durum hem haber servislerinin sürekliliğine hem de haber kalitesinin artırılmasına önemli katkılar sağlar. Bu yüzden, haber popülerliğini otomatik olarak tespit eden sistemlerin varlığı günümüzde kaçınılmaz haline gelmiştir. Bu çalışmada, Kaliforniya Üniversitesi (KU)-Irvine Makine Öğrenmesi Deposu veri tabanından indirilen veriler bileştirilerek oluşturulmuş dengesiz veri seti ve bu veri setinden Sentetik Azınlık Örnekleme Tekniği (Synthetic Minority Oversampling Technique-(SMOTE)) ile üretilen dengeli veri setine Mamdani ve Sugeno-tip bulanık çıkarım sistemi temelli modeller uygulanarak haber popülerliği tahmini yapılmıştır. Haber popülerliği tahmini için, farklı çıkarım ve durulaştırma yöntemleri kullanılarak oluşturulan 8 farklı bulanık mantık temelli model oluşturulmuştur. Oluşturulan modellerden 6 tanesi Mamdani-tip bulanık çıkarım sistemi ile yapılandırılırken, 2 tanesinde Sugeno-tip bulanık çıkarım sistemi kullanılmıştır. Karışıklık matrisi metrikleri ve R 2 eğrileri ile performansları değerlendirilen tahmin modellerinin deneysel sonuçları, dengesiz ve dengeli veri setlerinin her ikisinde de tüm metrikler açısından en iyi performansı mak-min çıkarım yöntemi ve ağırlık merkezi durulaştırma yöntemini kullanan Mamdani-tip bulanık çıkarım sisteminin sağladığını göstermiştir. Ayrıca, burada geliştirilen modellerin deneysel sonuçları literatürde yer alan benzer çalışmalarınki ile kıyaslandığında, ağırlıklı ortalama yöntemini kullanan Sugeno-tip bulanık çıkarım sistemi dışındaki tüm bulanık mantık temelli modellerin benzer çalışmalardaki modellerin en iyileri kadar rekabetçi bir performans sergilemiş olduklarını da ispatlamıştır.
INTERNATIONAL JOURNAL OF INFORMATICS TECHNOLOGIES, Jul 31, 2022
Günümüzde internetin hızlı bir şekilde gelişmesi ve kolay bir şekilde ulaşılır olması; Facebook, ... more Günümüzde internetin hızlı bir şekilde gelişmesi ve kolay bir şekilde ulaşılır olması; Facebook, Instagram, Twitter ve LinkedIN gibi yaygın kullanılan sosyal iletişim platformlarını büyük veri yığınlarının olduğu ortamlara dönüştürmüştür. Bu durum hem aranan bilgiye kolay bir şekilde ulaşılabilmesi için konu tespiti uygulamalarının, hem de konuyla ilgili paylaşım yapan benzer eğilim ve düşünceye sahip topluluklara toplu hizmet verebilmek için topluluk tespit uygulamalarının bu platformlarda kullanımını zorunlu hale getirmiştir. Bu yüzden araştırmacıların sosyal iletiş im ağlarında konu tespiti ve topluluk tespiti alanları üzerine araştırmalar yapması ve problemin çözümü ile ilgili yöntem ve teknikler geliştirmesi bu ortamların etkin kullanımı açısından hayati bir önem arz eder. Bu çalışmada, bu alanlara kapsamlı bir bakış sağlamak için sosyal medya platformlarında konu ve topluluk analizi yapan çalışmalar üzerine sistematik ve derinlemesine bir literatür incelemesi sunulmaktadır. İncelemesi yapılacak çalışmaların çoğu uygulamada başarılı sonuçlar ürettiği bilinen makine öğrenmesi temelli modeller kullanan makalelerden seçilmiştir. Bu çalışmaların incelenmesi neticesinde; topluluk tespiti alanında elde ettiği performans değerleri ile Louvain metodunun öne çıktığ ı görülürken, performans açısından konu analizi alanında tek bir modelin önerilemeyeceği ve uygun modelin ancak verilen sorunun tüm özellikleri göz önünde bulundurularak, probleme özgü şekilde seçilmesi ya da oluş turulması gerektiğ i sonucuna varılmıştır.
In this study, a prototype based on fuzzy logic (FL) controller and internet of things (IoT) was ... more In this study, a prototype based on fuzzy logic (FL) controller and internet of things (IoT) was developed to monitor rumen health parameters in cattle. In the system build as a prototype, the monitoring process related to the parameters is followed through three different applications developed on the Android operating system, the Thingspeak service and the WEB environment. The first application, which is an Android-based program, warns the user in case of any abnormality related to the rumen health. The other two applications allow monitoring and analyzing rumen health parameters in real time. The system implements a process that measures at varying time intervals to display the values of rumen health parameters, pH and temperature. The management of this process is carried out by the FL controller depending on the pH and temperature changes. This measurement, which is made at varying time intervals, is the most important feature that distinguishes our study from studies in the literature. Because in the studies reported in the literature, measurements are made at fixed time intervals. The relevant feature brings with it two important contributions for the system we propose. The first is to accelerate the precautions to be taken regarding animal health by enabling the system to measure at more frequent intervals in cases of deterioration in the pH level of rumen. The second is to reduce the energy consumed by the parameter measuring device from the battery by allowing the system to measure at longer intervals when the pH level of rumen is in balance.
PeerJ Computer Science
Background Social networks are large platforms that allow their users to interact with each other... more Background Social networks are large platforms that allow their users to interact with each other on the Internet. Today, the widespread use of social networks has made them vulnerable to malicious use through different methods such as fake accounts and spam. As a result, many social network users are exposed to the harmful effects of spam accounts created by malicious people. Although Twitter, one of the most popular social networking platforms, uses spam filters to protect its users from the harmful effects of spam, these filters are insufficient to detect spam accounts that exhibit new methods and behaviours. That’s why on social networking platforms like Twitter, it has become a necessity to use robust and more dynamic methods to detect spam accounts. Methods Fuzzy logic (FL) based approaches, as they are the models such that generate results by interpreting the data obtained based on heuristics viewpoint according to past experiences, they can provide robust and dynamic solutio...
PeerJ Computer Science
Background Social networks are large platforms that allow their users to interact with each other... more Background Social networks are large platforms that allow their users to interact with each other on the Internet. Today, the widespread use of social networks has made them vulnerable to malicious use through different methods such as fake accounts and spam. As a result, many social network users are exposed to the harmful effects of spam accounts created by malicious people. Although Twitter, one of the most popular social networking platforms, uses spam filters to protect its users from the harmful effects of spam, these filters are insufficient to detect spam accounts that exhibit new methods and behaviours. That’s why on social networking platforms like Twitter, it has become a necessity to use robust and more dynamic methods to detect spam accounts. Methods Fuzzy logic (FL) based approaches, as they are the models such that generate results by interpreting the data obtained based on heuristics viewpoint according to past experiences, they can provide robust and dynamic solutio...
PeerJ Computer Science
Background Android is the most widely used operating system all over the world. Due to its open n... more Background Android is the most widely used operating system all over the world. Due to its open nature, the Android operating system has become the target of malicious coders. Ensuring privacy and security is of great importance to Android users. Methods In this study, a hybrid architecture is proposed for the detection of Android malware from the permission information of applications. The proposed architecture combines the feature extraction power of the convolutional neural network (CNN) architecture and the decision making capability of fuzzy logic. Our method extracts features from permission information with a small number of filters and convolutional layers, and also makes the feature size suitable for ANFIS input. In addition, it allows the permission information to affect the classification without being neglected. In the study, malware was obtained from two different sources and two different data sets were created. In the first dataset, Drebin was used for malware applica...
Applied Sciences
In this study, a fuzzy logic-based dynamic ensemble (FL-BDE) model was proposed to detect malware... more In this study, a fuzzy logic-based dynamic ensemble (FL-BDE) model was proposed to detect malware exposed to the Android operating system. The FL-BDE model contains a structure that combines both the processing power of machine learning (ML)-based methods and the decision-making power of the Mamdani-type fuzzy inference system (FIS). In this structure, six different methods, namely, logistic regression (LR), Bayes point machine (BPM), boosted decision tree (BDT), neural network (NN), decision forest (DF) and support vector machine (SVM) were used as ML-based methods to benefit from their scores. However, through an approach involving the process of voting and routing, the scores of only three ML-based methods which were more successful in classifying either the negative instances or positive instances were sent to the FIS to be combined. During the combining process, the FIS processed the incoming inputs and determined the malicious application score. Experimental studies were perfo...
PeerJ Comput. Sci., 2023
How to cite this article Atacak İ, Çıtlak O, Doğru İA. 2023. Application of interval type-2 fuzzy... more How to cite this article Atacak İ, Çıtlak O, Doğru İA. 2023. Application of interval type-2 fuzzy logic and type-1 fuzzy logic-based approaches to social networks for spam detection with combined feature capabilities. PeerJ Comput. Sci. 9:e1316 http://doi.org/10.7717/peerjcs.1316 under the curve (AUC) of 0.971. However, it has been observed that FL-based spam models have a higher performance than ML-based spam models in terms of metrics including accuracy, recall, F-score and AUC values.
Gazi mühendislik bilimleri dergisi, May 5, 2022
In this study, a prototype based on fuzzy logic (FL) controller and internet of things (IoT) was ... more In this study, a prototype based on fuzzy logic (FL) controller and internet of things (IoT) was developed to monitor rumen health parameters in cattle. In the system build as a prototype, the monitoring process related to the parameters is followed through three different applications developed on the Android operating system, the Thingspeak service and the WEB environment. The first application, which is an Android-based program, warns the user in case of any abnormality related to the rumen health. The other two applications allow monitoring and analyzing rumen health parameters in real time. The system implements a process that measures at varying time intervals to display the values of rumen health parameters, pH and temperature. The management of this process is carried out by the FL controller depending on the pH and temperature changes. This measurement, which is made at varying time intervals, is the most important feature that distinguishes our study from studies in the literature. Because in the studies reported in the literature, measurements are made at fixed time intervals. The relevant feature brings with it two important contributions for the system we propose. The first is to accelerate the precautions to be taken regarding animal health by enabling the system to measure at more frequent intervals in cases of deterioration in the pH level of rumen. The second is to reduce the energy consumed by the parameter measuring device from the battery by allowing the system to measure at longer intervals when the pH level of rumen is in balance.
Bilişim Teknolojileri Dergisi
In the recent past and in today’s world, the internet is advancing rapidly and is easily accessib... more In the recent past and in today’s world, the internet is advancing rapidly and is easily accessible; this growth has made the social media platforms such as Facebook, Instagram, Twitter, and LinkedIn widely used which produces big data. This requires both topic Detection applications in order to access the required information, as well as community detection practices in order to provide collective services to communities that can be referred to as individuals with similar interests and opinions over the same subject. Therefore, it is vital for researchers to conduct research on topic detection and community detection research areas in social networks and to develop methods and techniques for problem-solving. In this study, a systematic and in-depth literature review is provided on studies that conduct topic and community analysis on social media platforms to provide a comprehensive overview of the given areas. Most of the studies to be analyzed are selected from articles using mach...
Computational and Mathematical Methods in Medicine
Segmentation of skin lesions plays a very important role in the early detection of skin cancer. H... more Segmentation of skin lesions plays a very important role in the early detection of skin cancer. However, indistinguishability due to various artifacts such as hair and contrast between normal skin and lesioned skin is an important challenge for specialist dermatologists. Computer-aided diagnostic systems using deep convolutional neural networks are gaining importance in order to cope with difficulties. This study focuses on deep learning-based fusion networks and fusion loss functions. For the automatic segmentation of skin lesions, U-Net (U-Net + ResNet 2D) with 2D residual blocks and 2D volumetric convolutional neural networks were fused for the first time in this study. Also, a new fusion loss function is proposed by combining Dice Loss (DL) and Focal Tversky Loss (FTL) to make the proposed fused model more robust. Of the 2594 image dataset, 20% is reserved for test data and 80% for training data. In test data training, a Jaccard score of 0.837 and a dice score of 0.918 were obta...
Engineering Sciences, 2011
Uzun sureli oksijen tedavisi (USOT); hastalara yeterli egitimin verilmesi, planlanmis araliklarla... more Uzun sureli oksijen tedavisi (USOT); hastalara yeterli egitimin verilmesi, planlanmis araliklarla hasta takibinin yapilmasi, duzenli bakimi yapilan cihazlar ile uygun bir sure kullanilmasi durumunda, kronik obstruktif akciger hastaligina (KOAH) sahip hastalarin yasam kalitesini ve suresini arttiran bir metottur. Bu calismada, oksijen konsantratorleri ile USOT`ta karsilasilan problemler arastirilmis ve konu ile ilgili tespit edilen sorunlarin istatistiksel analizleri kullanilarak, cozumune yonelik onerilerde bulunulmustur. Bu amacla, Ocak 2007-Aralik 2009 tarihleri arasinda Sosyal Guvenlik Kurumuna (SGK) gelen 531 hastaya ait cihazin hikayesi dinlenmis, cihazlar kontrol edilmis, arizalari, muhtemel sebepleri, sik karsilasilan sorunlar kayit altina alinarak, sorunlarin hasta, doktor ve teknik uzman isbirligi ile tip elektronigi tabaninda cozumune yonelik calismalar yapilmistir.
Artificial Intelligence Studies
Bilgi ve iletişim teknolojilerinin hızlı bir şekilde gelişmesinin bir sonucu olarak, sosyal ağlar... more Bilgi ve iletişim teknolojilerinin hızlı bir şekilde gelişmesinin bir sonucu olarak, sosyal ağlar günlük yaşantımızın önemli bir parçası haline gelmiştir. Twitter, Instagram, Facebook ve Tumblr gibi sosyal ağ platformları üzerinde seyredilen filmler ve satın alınan ürünler üzerine paylaşılan yorumlar, reklamlar ve kampanyalar bu platformları kullanan hedef kullanıcı kitle üzerinde çok önemli bir etkiye sahiptir. Bununla birlikte kullanıcılar ilgili platformlarda çok büyük miktardaki metinsel veri yığınlarını okuyup anlayabilmek için uzun bir zamana ihtiyaç duyarlar. Bu kullanıcılar açısından önemli bir problemdir. Günümüzde problemin çözümüne yönelik olarak duygu analizi ve yapay zekaya dayanan farklı tipte otomatik metin işleme metot ve algoritmaları uygulanmaktadır. Bu çalışmada, Kaggle üzerinden elde edilen IMDB veri setindeki film yorumlarının olumlu mu yoksa olumsuz mu olduğunu belirleyebilmek için Microsoft Azure Makina Öğrenmesi (MÖ) studyosunda iki sınıflı MÖ temelli 6 farklı model geliştirilerek, karışıklık matrisi metrikleri ve ROC eğrileri yoluyla ilgili modellerin performanslarını test eden bir dizi analizler yapılmıştır. Elde edilen sonuçlar tüm karışıklık matrisi metrikleri açısından tek bir modelin en başarılı sonuca ulaşamadığını, ROC analizleri açısından ise bu sonuca iki sınıflı sinir ağı (SA) modelinin ulaştığını göstermiştir.
Engineering Sciences, 2011
Long-term oxygen therapy (LTOT) is a method that increases life-quality and life-span in patients... more Long-term oxygen therapy (LTOT) is a method that increases life-quality and life-span in patients with chronic obstructive pulmonary disease (COPD), in the case of giving adequate training to patients, using with regularly maintained devices, and checking up the patient during the scheduled period. In this study, the problems encountered in LTOT with oxygen concentrator(OC)was searched, and the recommendations related to the solution of these problems was presented by using the relevant statistical analysis of detected problems. For this purpose, the story of the 531 device belonging to patients, applied to the Social Security Agency(SSA) between January 2007 and December 2009, was listened. After maintenance of these devices, their malfunctions, probable causes of the malfunctions and the common problems was registered, and then the studies containing the solution based on the medical electronics was made by the cooperation with patients, doctors and technical specialist.
International Review of Electrical Engineering-iree, 2013
In this paper, a digital signal processor based real-time implementation of a type-2 fuzzy logic ... more In this paper, a digital signal processor based real-time implementation of a type-2 fuzzy logic (T2FL) controller on an on-line uninterruptible power supply (UPS) is presented. The UPS consists of three main power circuits. Power circuits are non-linear structure and contain uncertainties. Conventional controllers cannot be enough to overcome uncertainties. In this study, type–2 fuzzy controller which has high performance for modeling uncertainties has been developed as control algorithm to control the UPS system. The system was also controlled with proportional–integral (PI) controller to show the superiority of the proposed type–2 fuzzy controller. When compared with the performance of both controllers in terms of their dynamic responses, it was observed that the T2FL controllers have faster dynamic response under transient loading conditions than PI controllers
International Journal of Intelligent Systems and Applications in Engineering, 2017
Nowadays, with the increasing population in urban settlements, the number of vehicles used in tra... more Nowadays, with the increasing population in urban settlements, the number of vehicles used in traffic has also increased in these settlements. This has brought with it major problems that are caused by insufficient parking lots, in terms of traffic congestion, drivers and environment. In this study, in order to overcome these problems, a multi-stored automatic parking system that automatically performs vehicle recognition, vehicle parking, vehicle delivery and pricing processes is designed and the practical application of this system is realized on a prototype. The vehicle recognition process in the designed system is fulfilled through a software prepared on the personal computer connected to the webcam. A multi-stored semi-circular structure has been used as parking lots to resolve parking lot deficiencies. Therefore, the carrying system that carries out the parking process in the system is designed as a cylindrical coordinated robot that can move horizontally, vertically and in the forward-back direction. The control of the whole system is realized by the PIC16F877A microcontroller. The results obtained from the prepared prototype have showed that the proposed system can provide significant contributions to the solution of problems resulting from parking lot deficiencies.
International Journal of Intelligent Systems and Applications in Engineering, 2017
Air is one of the most important life sources for all living things. Gases that are present and a... more Air is one of the most important life sources for all living things. Gases that are present and absent in the composition of clean air also considered as pollutants in the atmosphere. If the pollutants rise above a certain concentration level, air pollution occurs. Air pollution damages all living things, especially human health. Accurate estimation of pollutant concentrations through air pollution modeling has an important effect in reducing the adverse effects of air pollution and taking necessary precautions. Conventional statistical models are widely used in air pollution forecasting and modeling. As a different approach, in this study, fuzzy logic algorithm (FLA), which has been increasingly successful in many field applications, is used to model air quality and air pollution analyzes are made based on this model. Ankara province data is used in the sample of the research.
Tehnicki vjesnik - Technical Gazette, 2017
Original scientific paper In this study, an optimal control algorithm is proposed to overcome low... more Original scientific paper In this study, an optimal control algorithm is proposed to overcome low performance problems arising from the non-linear characteristics of pneumatic motor in compressed air-based energy conversion systems. The effectiveness of the proposed algorithm is tested on an energy conversion system which includes a compressor, a proportional valve, a pneumatic motor (PM), a permanent magnet direct current (PMDC) generator and a control card. The control function of the system is carried out by driving the proportional valve with the control signals which is obtained depending on the PMDC generator output voltage error. In this structure, an optimal proportional-integral-derivative (PID) controller which tunes on-line its own gain parameters by particle swarm optimization (PSO) algorithm according to the operating conditions of the system used. In order to observe the effects of PSO-based PID controller on the system performance, the energy conversion system is also controlled by a discrete time PID controller. The experimental results show that PSO-based PID controller provides more robust control performance than discrete time PID controller under various operating conditions.
Computer Science & Information Technology (CS & IT), 2017
Liquid level tanks are employed in many industrial and chemical areas. Their level must be keep a... more Liquid level tanks are employed in many industrial and chemical areas. Their level must be keep a defined point or between maximum-minimum points depending on changing of inlet and outlet liquid quantities. In order to overcome the problem, many level control methods have been developed. In the paper, it was aimed that obtain a mathematical model of an installed liquid level tank system. Then, the mathematical model was derived from the installed system depending on the sizes of the liquid level tank. According to some proportional-integralderivative (PID) parameters, the model was simulated by using MATLAB/Simulink program. After that, data of the liquid level tank were taken into a computer by employing data acquisition cards (DAQs). Lastly, the computer-controlled liquid level control was successfully practiced through a written computer program embedded into a PID algorithm used the PID parameters obtained from the simulations into Advantech VisiDAQ software.