48 results on '"Dönmez, Emrah"'
Search Results
2. Trish: an efficient activation function for CNN models and analysis of its effectiveness with optimizers in diagnosing glaucoma
- Author
-
Közkurt, Cemil, Diker, Aykut, Elen, Abdullah, Kılıçarslan, Serhat, Dönmez, Emrah, and Demir, Fahrettin Burak
- Published
- 2024
- Full Text
- View/download PDF
3. Human gender estimation from CT images of skull using deep feature selection and feature fusion
- Author
-
Çiftçi, Rukiye, Dönmez, Emrah, Kurtoğlu, Ahmet, Eken, Özgür, Samee, Nagwan Abdel, and Alkanhel, Reem Ibrahim
- Published
- 2024
- Full Text
- View/download PDF
4. Hybrid convolutional neural network and multilayer perceptron vision transformer model for wheat species classification task: E-ResMLP+
- Author
-
Dönmez, Emrah
- Published
- 2024
- Full Text
- View/download PDF
5. Classification of hazelnut varieties based on bigtransfer deep learning model
- Author
-
Dönmez, Emrah, Kılıçarslan, Serhat, and Diker, Aykut
- Published
- 2024
- Full Text
- View/download PDF
6. Advanced Residual Transformer (ART) method for identification of bile duct dilatation on CT data
- Author
-
Güneş, Ali, Kılıçarslan, Serhat, and Dönmez, Emrah
- Published
- 2025
- Full Text
- View/download PDF
7. Identification of apple varieties using hybrid transfer learning and multi-level feature extraction
- Author
-
Kılıçarslan, Serhat, Dönmez, Emrah, and Kılıçarslan, Sabire
- Published
- 2024
- Full Text
- View/download PDF
8. An effective feature extraction method for olive peacock eye leaf disease classification
- Author
-
Diker, Aykut, Elen, Abdullah, Közkurt, Cemil, Kılıçarslan, Serhat, Dönmez, Emrah, Arslan, Kürşad, and Kuran, Emre Can
- Published
- 2024
- Full Text
- View/download PDF
9. Multiple deep learning by majority-vote to classify haploid and diploid maize seeds
- Author
-
Dönmez, Emrah, Diker, Aykut, Elen, Abdullah, and Ulu, Mesut
- Published
- 2024
- Full Text
- View/download PDF
10. Identification of haploid and diploid maize seeds using hybrid transformer model
- Author
-
Dönmez, Emrah, Kılıçarslan, Serhat, Közkurt, Cemil, Diker, Aykut, Demir, Fahrettin Burak, and Elen, Abdullah
- Published
- 2023
- Full Text
- View/download PDF
11. Histogram-based global thresholding method for image binarization
- Author
-
Elen, Abdullah and Dönmez, Emrah
- Published
- 2024
- Full Text
- View/download PDF
12. Identification of multiclass tympanic membranes by using deep feature transfer learning and hyperparameter optimization
- Author
-
Kılıçarslan, Serhat, Diker, Aykut, Közkurt, Cemil, Dönmez, Emrah, Demir, Fahrettin Burak, and Elen, Abdullah
- Published
- 2024
- Full Text
- View/download PDF
13. Enhancing classification capacity of CNN models with deep feature selection and fusion: A case study on maize seed classification
- Author
-
Dönmez, Emrah
- Published
- 2022
- Full Text
- View/download PDF
14. Bacterial Disease Detection of Cherry Plant Using Deep Features
- Author
-
Dönmez, Emrah, primary, Ünal, Yavuz, additional, and Kayhan, Hatice, additional
- Published
- 2024
- Full Text
- View/download PDF
15. The role of morphometric characteristics in predicting 20-meter sprint performance through machine learning.
- Author
-
Kurtoğlu, Ahmet, Eken, Özgür, Çiftçi, Rukiye, Çar, Bekir, Dönmez, Emrah, Kılıçarslan, Serhat, Jamjoom, Mona M., Samee, Nagwan Abdel, Hassan, Dina S. M., and Mahmoud, Noha F.
- Subjects
SPRINTING ,MACHINE learning ,MEAN square algorithms ,MACHINE performance ,FEATURE selection ,FOOT ,PRINCIPAL components analysis - Abstract
The aim of this study was to test the morphometric features affecting 20-m sprint performance in children at the first level of primary education using machine learning (ML) algorithms. In this study, 130 male and 152 female volunteers aged between 6 and 11 years were included. After obtaining demographic information of the participants, skinfold thickness, diameter and circumference measurements, and 20-m sprint performance were determined. The study conducted three distinct experiments to determine the optimal ML technique for predicting outcomes. Initially, the entire feature space was utilized for training the ML models to establish a baseline performance. In the second experiment, only significant features identified through correlation analysis were used for training and testing the models, enhancing the focus on relevant predictors. Lastly, Principal Component Analysis (PCA) was employed to reduce the feature space, aiming to streamline model complexity while retaining data variance. These experiments collectively aimed to evaluate different feature selection and dimensionality reduction techniques, providing insights into the most effective strategies for optimizing predictive performance in the given context. The correlation-based selected features (Age, Height, waist circumference, hip circumference, leg length, thigh length, foot length) has produced a minimum Mean Squared Error (MSE) value of 0.012 for predicting the sprint performance in children. The effective utilization of correlation analysis in the selection of relevant features for our regression model suggests that the features selected exhibit robust linear associations with the target variable and can be relied upon as predictors. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
16. Design of Mobile Robot Control Infrastructure Based on Decision Trees and Adaptive Potential Area Methods
- Author
-
Dönmez, Emrah and Kocamaz, Adnan Fatih
- Published
- 2020
- Full Text
- View/download PDF
17. Identification of apple varieties using hybrid transfer learning and multi-level feature extraction
- Author
-
Kılıçarslan, Serhat, primary, Dönmez, Emrah, additional, and Kılıçarslan, Sabire, additional
- Published
- 2023
- Full Text
- View/download PDF
18. An effective feature extraction method for olive peacock eye leaf disease classification
- Author
-
Diker, Aykut, primary, Elen, Abdullah, additional, Közkurt, Cemil, additional, Kılıçarslan, Serhat, additional, Dönmez, Emrah, additional, Arslan, Kürşad, additional, and Kuran, Emre Can, additional
- Published
- 2023
- Full Text
- View/download PDF
19. Improved multi-layer hybrid adaptive particle swarm optimization based artificial bee colony for optimizing feature selection and classification of microarray data
- Author
-
Kiliçarslan, Serhat, primary and Dönmez, Emrah, additional
- Published
- 2023
- Full Text
- View/download PDF
20. Interactive Classification of Maize Seeds with Batch Mode Active Learning
- Author
-
Güneş, Ali, primary and Dönmez, Emrah, additional
- Published
- 2023
- Full Text
- View/download PDF
21. Hybrid convolutional neural network and multilayer perceptron vision transformer model for wheat species classification task: E-ResMLP+.
- Author
-
Dönmez, Emrah
- Subjects
CONVOLUTIONAL neural networks ,TRANSFORMER models ,AGRICULTURE ,WHEAT ,SPECIES - Abstract
Wheat plant is one of the most basic food sources for the whole world. There are many species of wheat that differ according to the conditions of the region where they are grown. In this context, wheat species can exhibit different characteristics. Issues such as resistance to geographical conditions and productivity are at the forefront in this plant as in all other plants. The wheat species should be correctly distinguished for correct agricultural practice. In this study, a hybrid model based on the Vision Transformer (VT) approach and the Convolutional Neural Network (CNN) model was developed to classify wheat species. For this purpose, ResMLP architecture was modified and the EfficientNetV2b0 model was fine-tuned and improved. A hybrid transformer model has been developed by combining these two methods. As a result of the experiments, the overall accuracy performance has been determined as 98.33%. The potential power of the proposed method for computer-aided agricultural analysis systems is demonstrated. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
22. A Vision-Based Real-Time Mobile Robot Controller Design Based on Gaussian Function for Indoor Environment
- Author
-
Dönmez, Emrah, Kocamaz, Adnan Fatih, and Dirik, Mahmut
- Published
- 2018
- Full Text
- View/download PDF
23. Haploid ve Diploid Mısırların Aktif Öğrenme Yaklaşımı ile Sınıflandırılması
- Author
-
GÜNEŞ, Ali, primary and DÖNMEZ, Emrah, additional
- Published
- 2023
- Full Text
- View/download PDF
24. Evde Eğitim: Okul Sistemi İçin Sonun Başlangıcı mı?
- Author
-
Ertürk, Abbas, Dönmez, Emrah, MÜ, Eğitim Fakültesi, Eğitim Bilimleri Bölümü, Ertürk, Abbas, and Dönmez, Emrah
- Subjects
covid-19 ,Ev okulu ,Okulsuz eğitim ,Evde eğitim ,Unschooling ,Homeschooling ,Home school - Abstract
Bu çalışmada okul düzenine alternatif bir eğitim modeli olarak ortaya çıkan evde eğitim modeli incelenmektedir. Her geçen gün, birçok ülkede, yaygınlaşan ve tercih edilen bir eğitim modeli olan evde eğitim modeli yasal zemine oturdukça hem velilerin hem de akademisyenlerin dikkatlerini çekmektedir. Araştırma içerik analizi yöntemiyle yapılmış, veriler model ile ilgili yayınlar üzerinden toplanmıştır. Bu çalışma ile modelin nasıl işletildiği, tarihçesi, yaygınlaşması, veliler tarafından tercih edilme nedenleri ve modele yönelik eleştiriler incelenmiştir. Elde edilen bulgular ışığında Türkiye’de uygulanabilirliği tartışılmış ve öneriler geliştirilmiştir. Araştırma bulgularına göre okul ortamlarında bulunan eksikler ve güvensiz ortam evde eğitim modelinin daha çok tercih edilmesine ve hızla gelişmesine yol açmaktadır. Ancak daha önce çokça eleştirilen model Covid-19 salgını ile birlikte daha güçlü hale geldiği için gelecekte mevcut okul sistemlerinin sadece bu yönde gelişmesine neden olabilecek bir kapasiteye sahip olduğu görülmektedir. In this study, homeschooling which has emerged as an alternative education model to the school system was examined. Day by day, homeschooling, which is a popular and preferred education model in many countries, draws the attention of both parents andacademicians as it becomes legal. This research was conducted with the content analysis method, and data were collected from the studies about the model. With this study, how the model is operated, its history, its spread, the reasons why it is preferred by the parents and the criticisms towards the model were investigated. In the light of the findings, the practicality of it in Turkey has beendiscussed and recommendations were brought forward. According to the research findings, deficiencies at schools and insecure environments lead homeschooling model to be preferred more and improve rapidly. However, since the previously criticized model has become stronger with the Covid-19 epidemic, it appears that it has the capacity to cause existing school systems to evolve onlyin this direction in the future.
- Published
- 2021
25. ADAPTIVE OPERATION MODEL FOR INTERIOR SMART LOGISTICS IN CYBER PHYSICAL SYSTEMS
- Author
-
DÖNMEZ, Emrah, primary, OKUMUŞ, Fatih, additional, and KOCAMAZ, Fatih, additional
- Published
- 2021
- Full Text
- View/download PDF
26. Çok Kameralı Görü Tabanlı Mobil Robot Kontrolü ve Yol Planlaması
- Author
-
DÖNMEZ, Emrah, primary and ÖZCAN, Alper, additional
- Published
- 2021
- Full Text
- View/download PDF
27. UZAKTAN EĞİTİMDE, EĞİTİM KİME UZAK KİME YAKIN: KÜLTÜREL SERMAYE PENCERESİNDEN BİR ANALİZ
- Author
-
DÖNMEZ, Emrah
- Subjects
Social ,Kültürel sermaye,uzaktan eğitim,yoksul çocuklar ,Sosyal - Abstract
Bu çalışmanın amacı kültürel sermaye ile uzaktan eğitim arasındaki ilişkinin incelenmesidir. Literatür taraması yöntemiyle yapılan bu çalışmada, belirlenen amaç çerçevesinde salgın döneminde uygulanan uzaktan eğitim süreci, istatistiki veriler, yayımlanan raporlar, gazetelere ve kurumsal sitelere yansıyan haberler üzerinden değerlendirilmiştir. Eğitim sistemi için önemi büyük olan kültürel sermayenin salgın döneminde bu süreç üzerinde nasıl bir etkiye sahip olduğu incelenmiştir. Araştırmada elde edilen bulgulara göre, 2019 yılı sonu itibariyle ortaya çıkan koronavirüs salgını okullarda devam eden eğitim sürecini ciddi düzeyde kesintiye uğratmıştır. Ülke genelinde vakaların görülmeye başlamasıyla yüz yüze eğitime ara verilmiştir. Öğrenciler bu dönemde TV kanalları üzerinden ve internet üzerinden çevrimiçi olarak eğitimlerine devam etmişlerdir. Ancak tüm öğrenciler bu eğitim ortamlarına eşit şartlarda erişim sağlayamamıştır. Uzaktan eğitim sürecinin evlerden yürütülüyor olması, internet üzerinden çevrimiçi derse girişlerin teknik alt yapı gerektiriyor olması, öğrencilerin ev ortamlarını, ailelerinin sosyoekonomik ve kültürel durumlarını eğitim sürecinin devam ettirilmesinde önemli bir noktaya oturtmuştur. Sosyoekonomik düzeyi yüksek, kültürel düzeyi iyi ailelerin çocukları eğitime erişim sağlayabilirken, bazı kırsal kesimlerde yaşayan, yoksul veya kültürel düzeyi düşük ailelerin çocukları eğitimden uzak kalmıştır. Devlet, eğitime ulaşım konusunda zor durumda olan öğrenciler için çalışmalar yürütmüştür. Öğrencilerin bir kısmına tablet bilgisayar dağıtımı yapmış ve internet desteği sağlamıştır. Ancak yapılan destekler tüm öğrencileri sisteme dâhil edebilecek yeterlilikte olmamıştır. Sonuç olarak bu süreçte öğrencilerin bir kısmı anayasal bir hak olan eğitim haklarından mahrum olmuşlardır.
- Published
- 2021
28. Bacterial Disease Detection for Pepper Plant by Utilizing Deep Features Acquired from DarkNet-19 CNN Model
- Author
-
ÖZCAN, Alper, primary and DÖNMEZ, Emrah, additional
- Published
- 2021
- Full Text
- View/download PDF
29. ADAPTIVE OPERATION MODEL FOR INTERIOR SMART LOGISTICS IN CYBER PHYSICAL SYSTEMS
- Author
-
DÖNMEZ, Emrah, OKUMUŞ, Fatih, and KOCAMAZ, Fatih
- Subjects
Cyber Physical System (CPS),Smart Logistics,Autonomous Robots,Industry 4.0,Robotic Control ,Engineering ,Siber Fiziksel Sistem (CPS),Akıllı Lojistik,Otonom Robotlar,Endüstri 4.0,Robotik Kontrol ,Mühendislik - Abstract
Lojistik operasyonlar, endüstriyel üretim alanlarında ana faaliyetler arasındadır. Günümüzde bu işlemleri gerçekleştirmek için genellikle elektrikli olan ve bir sürücü tarafından manuel olarak çalıştırılan araçlar kullanılmaktadır. Lojistik robotlar bu alanda kullanılabilecek önemli bir alternatiftir ve endüstriyel alanlarda siber fiziksel sistemlerle entegrasyonda kullanımları giderek yaygınlaşmaktadır. Lojistik robotların en büyük avantajı, endüstri 4.0 konseptine uygun olarak tüm sistem için otonom sürüş kabiliyetleri ve optimum parametreleri sağlamasıdır. Bu çalışmada, siber fiziksel sistem altyapısı olan bir ortamda Siber Fiziksel Sistem (SFS) içerisine entegre edilebilen uyarlanabilir bir lojistik robot sistemi geliştirilmiştir. Bu kapsamda konumlandırma, yol planlama, çoklu görev dağılımı, enerji yönetimi, görev önceliklendirme, optimizasyon ve engellerden kaçınma konuları analiz edilerek basit çözümler önerilmektedir. Deneyler sekiz farklı konfigürasyonda gerçekleştirilmiş ve ortalama mesafe ve enerji maliyetleri sırasıyla % 5,1 ve % 6,6 oranında iyileştirilmiştir., Logistics operations are among the main activities in industrial production areas. Today, vehicles that are usually electric and manually operated by a driver are used to perform these operations. Logistics robots are an important alternative that can be used in this field, and their use in integration with cyber physical systems in industrial fields is increasingly common. The biggest advantage of the logistics robots is that they provide autonomous driving capabilities and optimum parameters for the entire system in accordance with industry 4.0 concept. In this study, an adaptive logistics robot system that can be integrated into the Cyber Physical System (CPS) system in an environment with cyber physical system infrastructure has been developed. In this context, positioning, path planning, multi-task allocation, energy management, task prioritization, optimization and obstacle avoidance issues are analyzed and simple solutions are proposed. The experiments have been carried out in eight different configurations and the average distance and energy costs have been improved by 5.1% and 6.6%, respectively.
- Published
- 2020
30. A Cloudware Architecture for Collaboration of Multiple AGVs in Indoor Logistics: Case Study in Fabric Manufacturing Enterprises
- Author
-
Okumuş, Fatih, primary, Dönmez, Emrah, additional, and Kocamaz, Adnan Fatih, additional
- Published
- 2020
- Full Text
- View/download PDF
31. Classification of Haploid and Diploid Maize Seeds based on Pre-Trained Convolutional Neural Networks
- Author
-
DÖNMEZ, Emrah, primary
- Published
- 2020
- Full Text
- View/download PDF
32. Assessment of environmental factors affecting software reliability: a survey study
- Author
-
ÖZCAN, Alper, primary, ÇATAL, Çağatay, additional, TOGAY, Cengiz, additional, TEKİNERDOĞAN, Bedir, additional, and DÖNMEZ, Emrah, additional
- Published
- 2020
- Full Text
- View/download PDF
33. Assessment of environmental factors affecting software reliability: A survey study
- Author
-
Özcan, Alper, Çatal, Çaǧatay, Togay, Cengiz, Tekinerdoǧan, Bedir, Dönmez, Emrah, Özcan, Alper, Çatal, Çaǧatay, Togay, Cengiz, Tekinerdoǧan, Bedir, and Dönmez, Emrah
- Abstract
Currently, many systems depend on software, and software reliability as such has become one of the key challenges. Several studies have been carried out that focus on the impact of external environmental factors that impact software reliability. These studies, however, were all carried out in the same geographical context. Given the rapid developments in software engineering, this study aims to identify and reinvestigate the environmental factors that impact software reliability by also considering a different context. The environmental factors that have an impact on software reliability as reported in earlier studies have been analyzed and synthesized. Subsequently, a survey study is conducted to analyze the impact of 32 environmental factors from the perspective of multiple stakeholders. Several statistical analysis methods were applied for the analysis. Data were collected from 24 organizations and 70 software professionals. Most factors shown in top 10 lists of previous studies remain in the top 10 in our study, but their order is different. Testing coverage is now the most significant factor and testing effort is considered as the second most significant factor. The environmental factors defined previously retain their impact. The ordering of the importance of the environmental factors has changed though.
- Published
- 2020
34. Design of Mobile Robot Control Infrastructure Based on Decision Trees and Adaptive Potential Area Methods
- Author
-
Dönmez, Emrah, primary and Kocamaz, Adnan Fatih, additional
- Published
- 2019
- Full Text
- View/download PDF
35. Çoklu Hedeflerin Çoklu Robotlara Paylaştırılması İçin Bir Yük Dengeleme Sistemi
- Author
-
DÖNMEZ, Emrah, primary and KOCAMAZ, Adnan Fatih, additional
- Published
- 2019
- Full Text
- View/download PDF
36. Designing controllers for path planning applications to mobile robots with head-cameras
- Author
-
Dönmez, Emrah, Kocamaz, Adnan Fatih, and Bilgisayar Mühendisliği Anabilim Dalı
- Subjects
Bilim ve Teknoloji ,Mobile robots ,Science and Technology ,Computer Engineering and Computer Science and Control ,Bilgisayar Mühendisliği Bilimleri-Bilgisayar ve Kontrol - Abstract
Bu tez çalışmasında, diferansiyel tahrikli bir gezgin robot için iki farklı görü tabanlı kontrolörve potansiyel alan yöntemine dayalı uyarlamalı yol planlama metodu tasarlanmıştır. Tasarlananmetotlar çoklu-kamera ortamında sabit tepe kamera konfigürasyonu ile çalıştırılmıştır. Konfigürasyonuzayı birden fazla statik engel barındırmaktadır. Kontrolör ön-tanımlı bir hedefe ulaşıncaya kadarrobot hareketlerini yürütmektedir. Her bir kontrolör için iki farklı pozisyonlama yöntemindenfaydalanılmıştır. Bu kapsamda; bir ağırlıklı çizge ve bir de trigonometrik üçgen modelleri önerilmiştir.Bu tez çalışması üç aşamadan oluşmaktadır. İlk aşamada; engel içermeyen bir konfigürasyon uzayıiçin temel bir hedefe-gitme kontrolörü tasarlanmıştır. İkinci aşamada; yeni olarak tasarlanan birhedefe-gitme kontrolörü ile yeni olarak tasarlanan bir hedeften kaçınma kontrolörü kaynaştırılmıştır.Son aşamada ise; çoklu-kamera cihazları ile genişletilebilir bir konfigürasyon uzayı oluşturulmuşturve kontrolörler bu yeni konfigürasyon uzayına uyarlanmıştır.Kamera(lar) bir iç mekânda imge çerçevelerini yakalarlar. Robot, hedef ve engellerin globalkonumlarını tespit etmek amacıyla; konfigürasyon uzayı ardışık çerçevelerde gerçek zamanlı olarakizlenmektedir. Ağırlıklı çizge konumlandırma modelinde robot tekerleri ve hedef birer düğümvarsayılarak bir çizge yapısı oluşturulur. Düğümler arasındaki mesafe değerleri çizge kenarlarınaağırlık olarak atanmaktadır. Üçgen konumlandırma modelinde robot tekerleri ve hedef arasında sanalbir üçgen yapısı oluşturulur. Üçgenin kenarları arasındaki iç açılar üçgen köşelerine açı değerleriolarak atanmaktadır. Hem çizge ağırlıkları hem de üçgen iç açıları kullanılan konumlandırmamodeline göre tasarlanmış kontrolörler için giriş parametreleri olarak kullanılmaktadır.İlk aşamada; engel içermeyen bir ortam için hedefe-gitme davranışı modellemiştir. Gaussianfonksiyonu her iki konumlandırma modeli için teker hız değerlerini belirlemek amacıyla varsayılankontrolör içerisinde kullanılmıştır. Bu kontrolörden elde edilen çıktılar ise iki geleneksel kontrolyöntemleri olan PID ve Fuzzy-PID ile karşılaştırılmıştır. Tasarlanan görü tabanlı Gaussian kontrolörükullanarak mobil robot kontrolünün yüksek hassasiyet ve doğruluk ile gerçekleştirildiği görülmüştür.İkinci aşamada; statik bir ortam için karar ağacı tabanlı bir gezgin robot kontrolü veuyarlanabilir potansiyel alan tabanlı engel kaçınma kontrolü geliştirilmiştir. Daha sonra, her ikikontrol birimi uyumlu hale getirilmiş ve gerçek bir dünya deneyi gerçekleştirilmiştir. İlk olarak,uyarlamalı potansiyel alan yöntemi kullanarak bir yol planı çıkartılmıştır. İkinci olarak, karar ağacıtabanlı kontrolör tekerlekli mobil robotu (TMR) bu referans yörünge yolu üzerinde ilerletmeyebaşlamıştır. Deneysel ortam statik engeller ve farklı konfigürasyon uzayları içermektedir. Uyarlamalıpotansiyel alan yöntemi ile bulunan optimum parametrelerden yararlanarak potansiyel alanyönteminin verimi ve dayanıklılığı büyük ölçüde iyileştirilmiştir. Kontrol işleminden simülasyon vegerçek dünya deneysel verileri elde edilmiş ve değerlendirilmiştir.Nihai olan üçüncü aşamada ise tasarlanan tüm kontrolörler ve modeller birleştirilmiş veçoklu-kamera cihaz konfigürasyonu ile çalışabilecek şekilde yeni bir kontrol altyapısı geliştirilmiştir.Çok görüntüyü dikişleme yöntemiyle tek bir görüntüde birleştirerek yeni bir çoklu kamera işletimmodeli önerilmiştir. Bu dikişli görüntü üzerinde geliştirilen yol planlama ve yol bölütleme yöntemleriuygulanmıştır. Deneysel sonuçlar, tasarlanan kontrolörlerin çoklu kamera konfigürasyonu için deTMR hareketlerini farklı konfigürasyon uzayları başarılı bir şekilde karakterize ettiğini göstermiştir. In this thesis study, two different visual based controllers and an adaptive potential fieldbased on path planning methods are designed for a differential drive mobile robot. The designedmethods are operated in a multi-camera environment with fixed head camera configuration.Configuration space hosts a number of static obstacles. The controller performs robot motions until apre-defined target is reached. For each controller two different positioning models are utilized. Aweighted graph and a triangle model have been proposed. This study is comprised of three stages. Infirst stage; a simple go-to-goal controller designed for an obstacle free configuration space. In secondstage, designed controller has been fused with a modified path planning method (for obstacleavoidance) and a newly designed controller. In last stage; an expandable configuration space iscreated with multi-camera device and controllers have been adapted to this new configuration space.The camera(s) captures image frames in an interior space. A real-time system tracks theconfiguration space in consecutive frames to detect global positions of a mobile robot, target andobstacles. A graph structure is formed by assuming robot wheels and target as nodes in weightedgraph positioning model. Distances between nodes are assigned as weights to the graph edges. Avirtual triangle is formed between the robot wheels and target in triangle positioning model. Theangles between edges are assigned as interior angles to the triangle corners. Both graph weights andtriangle angles are input parameters according to the used positioning model for designed controllers.In first stage; go-to-goal behavior is modeled for the obstacle free environment. The generalGaussian function is utilized to determine the velocity of wheels in designed controller for bothpositioning models, separately. We compare outputs of controller with several conventional methodswhich are PID and Fuzzy-PID. Then it has been seen that the mobile robot control has been performedwith high precision and accuracy by employing the developed visual-based Gaussian controller.In second stage; a decision tree based mobile robot control and an adaptive potential fieldbasedobstacle avoidance control have been developed for a static obstacle hosted environment. Then,we harmonized both control unit and performed a real-world experiment. Firstly, a path plan extractedby using adaptive potential field method. To calculate potentials virtual range sensors are used.Secondly, decision tree-based controller has advanced the wheeled mobile robot (WMR) on thisreference trajectory path in real-time. Experimental environment has included static obstacles anddifferent configuration spaces. Efficiency and robustness of potential field method has greatlyimproved by utilizing optimal parameters found with adaptive potential field design. We haveacquired and evaluated both simulation and real-world experiment data from control process.Finally, all the designed controllers and models have been combined and a new controlinfrastructure has been developed to work with multi-camera device configuration in third stage. Weproposed a new multi-camera operating model by stitching multi-images into one image. Developedpath planning and path dividing methods are implemented on this stitched image. Experimental resultsshow designed controllers and methods successfully characterize WMR motions for multi-cameramodel under different configuration spaces. 139
- Published
- 2018
37. Okul müdürlerinin örgütsel yenilik yönetimi davranış düzeyi ile öğretmenlerin örgütsel bağlılık düzeyleri arasındaki ilişki
- Author
-
Dönmez, Emrah, Ertürk, Abbas, and Eğitim Bilimleri Anabilim Dalı
- Subjects
Organizational innovations ,Organizational management ,Eğitim ve Öğretim ,Innovative behaviour ,Education and Training ,Organizational commitment ,Teachers ,School administrators - Abstract
Bu araştırmada, okul müdürlerinin örgütsel yenilik yönetimi davranışı düzeyleri ile öğretmenlerin örgütsel bağlılık düzeyi arasındaki ilişkinin belirlenmesi amaçlanmıştır. Araştırmanın evrenini 2017-2018 eğitim öğretim yılında Muğla il merkezi ve ilçelerindeki ilkokul, ortaokul ve liselerde görev yapan öğretmenler oluşturmaktadır. Tarama modelinde yapılan araştırmanın örneklemi 418 öğretmenden oluşmaktadır. Araştırmada, okul müdürlerinin örgütsel yenilik yönetimi davranışı düzeylerini belirlemek amacıyla Bülbül (2012b) tarafından geliştirilen `Eğitim Örgütleri İçin Yenilik Yönetimi Ölçeği` kullanılmıştır. Öğretmenlerin örgütsel bağlılık düzeylerini belirlemek için ise Balay (2000) tarafından geliştirilen `Örgütsel Bağlılık Ölçeği` kullanılmıştır. Okul müdürlerinin örgütsel yenilik yönetimi davranışı düzeylerinin ve öğretmenlerin örgütsel bağlılık düzeylerinin belirlenmesinde aritmetik ortalama ve standart sapma değerleri kullanılmıştır. Okul müdürlerinin yenilik yönetimi davranışı düzeylerinin ve öğretmenlerin örgütsel bağlılık düzeylerinin öğretmenlerin cinsiyetleri ve eğitim durumlarına göre farklılaşıp farklılaşmadığını belirlemek amacıyla t-testi; öğretmenlerin alanlarına, okul türlerine, kıdem yıllarına ve okulda çalışma sürelerine göre farklılaşıp farklılaşmadığını belirlemek için ise tek yönlü varyans analizi (ANOVA) kullanılmıştır. Tek yönlü varyans analizi sonuçlarına göre anlamlı farklılığın kaynağının belirlenmesinde çoklu karşılaştıma testlerinden Tukey ve Games-Howell testleri kullanılmıştır. Okul müdürlerinin örgütsel yenilik yönetimi düzeylerinin öğretmenlerin örgütsel bağlılık düzeylerini anlamlı bir şekilde yordayıp yordamadığını belirlemek için ise çoklu regresyon analizi kullanılmıştır.Araştırmaya katılan öğretmenlere göre yenilik yönetimi konusunda okul müdürleri en fazla örgütsel kültür ve yapıya, en az ise girdi yönetimine önem vermektedir. Öğretmenlerin örgütsel bağlılıkları en fazla içselleştirme, en az ise uyum davranışı şeklinde olmaktadır. Öğretmenlerin okul müdürlerinin yenilik yönetimi davranışları hakkındaki görüşleri kıdem yılı değişkenine göre anlamlı düzeyde farklılaşmakta; cinsiyet, alan, okul türü, okulda çalışma süresi, eğitim durumu değişkenlerine göre anlamlı düzeyde farklılaşmamaktadır. Öğretmenlerin örgütsel bağlılık düzeyleri cinsiyet, alan, okul türü, kıdem yılı değişkenine göre anlamlı düzeyde farklılaşmakta; okulda çalışma süresi ve eğitim durumu değişkenine göre anlamlı düzeyde farklılaşmamaktadır. Öğretmenlerin görüşlerine göre okul müdürlerinin yenilik yönetimi davranışının boyutları olan girdi yönetimi, yenilik stratejileri, örgütsel kültür ve yapı ve proje yönetimi boyutları ile öğretmenlerin örgütsel bağlılık davranışının uyum, özdeşleşme, içselleştirme boyutları arasında orta düzeyde ve anlamlı ilişki bulunmaktadır. Okul müdürlerinin yenilik yönetimi davranışı boyutlarının, öğretmenlerin örgütsel bağlılık düzeylerini tüm boyutlarda anlamlı şekilde yordadığı söylenebilir.Anahtar kelimeler: Örgütsel yenilik, örgütsel bağlılık, yenilik yönetimi, öğretmen, okul müdürü In this study, it was aimed to determine the relationship between school administrators' organizational innovation behaviour levels and teachers' organizational commitment levels. The population of this study consisted of teachers working at primary, secondary and high schools in the centre and counties of Mugla in 2017-2018 education year. The sample of this study in survey model consisted of 418 teachers. In the study, to determine the levels of school administrators' organizational innovation manegement behaviour, `Innovation Management At Schools Scale` developed by Bülbül (2012b) was used. To determine the levels of teachers' organizational commitment, `Orgnizational Commitment Scale` developed by Balay (2000) was used. The arithmetic mean and standard deviation were calculated in order to determine school administrators' organizational innovation management behaviours levels and teachers' organizational commitment levels. The t-test was used to find out whether or not the school administrators' organizational innovation management behaviour levels and teachers' organizational commitment levels differed according to the teachers' gender and educational status; the variance analysis (ANOVA) was used to find out whether or not they differed according to the teachers' branch, school type, years of seniority, working years at the school. According to the results of variance analysis, Tukey and Games-Howell post-hoc comparison tests were used to determine the source of significant differences. The multivariate regression analysis was used to determine whether or not school administrators' organizational innovation levels predicted teachers' organizational commitment levels.According to the teachers, school administrators care organizational culture and structure at the most, input management at the least about the innovation management. Teachers' organizational commitment is in the way of internalization at the most, in the way of compliance at the least. Teachers' views about the school administrators' organizational management behaviours differ significantly according to their year of seniority variables; but not according to their gender, branch, school type, working years at the school and educational status variables. Teachers' organizational commitment levels differ significantly according to their gender, branch, school type and seniority variables; but not according to the working years at the school and educational status variables. According to the views of teachers, there are moderate significant relationship between the input management, innovation strategies, organizational culture and structure and project management dimensions of school administrators' innovation management and comliance, identification and internalization dimensions of teachers' organizational commitment. It can be stated that the all dimensions of school administratos' innovation management behaviours predict the dimensions of teachers' organizational commitment behaviours significantly.Keywords: Organizational innovation, organizational commitment, innovation management, teacher, administrator 118
- Published
- 2018
38. Design of a Resource Management for GPGPU Supported Grid Computing
- Author
-
Dönmez, Emrah
- Subjects
Grid computing,GPGPU,QoS,resource management - Abstract
—In this study; we aimed to propose design of a QoS aware resource managementinfrastructure for a GPGPU supported Grid computing system. This Grid systemconsists of hybrid (CPU + CPU) and heterogeneous (Nvidia + AMD Radeon) GPGPUcomputational nodes. It can manage both small scale unit (connections, threads,buffer pools etc.) and large scale unit (whole computing machines). Asincreasing of the network communication bandwidth and developing powerfulcomputer hardware (CPU, GPU etc.), distributed computing systems acquire moreand more attention day by day. Grid computing is as a major player in such kindof distributed system environments like cloud, volunteer, hybrid and etc. Sinceit supports large scale resource sharing between geographically distributedcomputer clusters and even single computers. Nowadays, there is anotherimportant technology pillar to implement high performance computing rather thanCPU, it is known as GPU computing. The GPU systems are ideal especially to dataintensive applications; such as image processing, data mining, financialcomputations etc. Therefore, GPU based grids give an undertaking highercomputational performance. GPU processor consists of lots of controllable coreswhich can be used for high performance demanded applications. Ultimately, themajor concerns in grid computing are particularly related to managing QoSrequirements, granularity of resources, and heterogeneous resources (both CPUand GPU). 
- Published
- 2017
39. Visual servoing based control methods for nonholonomic mobile robot.
- Author
-
Dirik, Mahmut, Kocamaz, Adnan Fatih, and Dönmez, Emrah
- Subjects
ROBOT kinematics ,ROBOT motion ,ROBOT control systems ,MOBILE robots ,DECISION trees ,CAMERA calibration - Abstract
In this paper, we utilized two different vision-based go-to-goal robot control approaches on indoor nonholonomic mobile robot systems. In the proposed methods, eye-out-device configured camera (overhead camera) image data are used as the input parameters to determine the speeds of robot wheels. The main purpose of this system is to minimize the complexity of conventional robot control kinematics and to provide an efficient control approach to manage the wheel speeds and the direction angle of the mobile robot. In addition to reducing the complexity of robot control kinematics, it is also intended to reduce systematic and nonsystematic errors. The proposed method is divided into three stages: the first stage consists of the overhead camera calibration and the configuration of the robot motion environment. At this stage, the labels placed on the robot and target position were identified and the position information of the robot was obtained. In the second stage, control inputs such as position and orientation based on robot motion tracking and visual feature information were obtained. In the third stage, Graph-based Gaussian and Angle-based Decision tree control approaches were performed. We have briefly described these control approaches as follows: Graph-based Decision Tree Control (GDTC), Graph-based Gaussian Control (GGC), Angle-based Decision Tree Control (ADTC), and Angle-based Gaussian Control (AGC). Using these control approaches, many real-time experimental studies with eye-catching device configuration have been performed. The efficacy and usability of the methods have been demonstrated by experimental results. [ABSTRACT FROM AUTHOR]
- Published
- 2020
40. A Vision-Based Real-Time Mobile Robot Controller Design Based on Gaussian Function for Indoor Environment
- Author
-
Dönmez, Emrah, primary, Kocamaz, Adnan Fatih, additional, and Dirik, Mahmut, additional
- Published
- 2017
- Full Text
- View/download PDF
41. Ruhsal Liderlik ve Eğitimdeki Yansımaları
- Author
-
Ertürk, Abbas, primary and Dönmez, Emrah, additional
- Published
- 2017
- Full Text
- View/download PDF
42. Chemical properties of hawthorn (Crataegus L. spp.) taxa naturally distributed in Western Anatolia part of Turkey
- Author
-
Özderin, Sevgin, primary, Fakir, Hüseyin, additional, and Dönmez, Emrah, additional
- Published
- 2016
- Full Text
- View/download PDF
43. Bulut hesaplama için veri güvenlik sistemi tasarımı
- Author
-
Dönmez, Emrah, Kutlu, Akif, and Elektronik-Bilgisayar Eğitimi Anabilim Dalı
- Subjects
Teknik Eğitim ,Technical Education ,Computer network protocols ,Computer networks security ,Computer arithmetic ,Computer Engineering and Computer Science and Control ,Computer networks ,Bilgisayar Mühendisliği Bilimleri-Bilgisayar ve Kontrol - Abstract
Bu çalışmada cloud computing (bulut hesaplama) sistemi için internet ortamında, dağıtık şekilde bulunan bilgisayarların işlemci gücü, hafıza, disk boyutu, ağ çıktıları, istemci erişilebilirliği gibi parametrelerden oluşan işlem hesaplama güçlerinden faydalanarak, bir veri güvenlik sisteminin geliştirilmesi amaçlanmıştır. Sistem üzerinde hesaplama yapan her bir bilgisayara ?gönüllü üstlenici? adı verilmiştir. Veri Güvenlik Sistemi (VGS) sistemine bağlanan gönüllü üstlenicilere harici bir güvenlik duvarı programı kurulmamıştır. Çünkü sistemde, veri güvenliğini sağlama görevini MD5, RAS ve XOR şifreleme algoritmaları ile oluşturulan güvenlik modülleri üstlenmiştir. Bu durum üstlenici bilgisayarlara performans kazanımı olarak geri dönmüştür. Bulut hesaplama ortamında çalıştırılan veri güvenlik sistemi iki aşamada oluşturulmuştur.İlk aşamada, sistemin bulut hesaplama tekniği düzeyinde geliştirilmesinden dolayı ağ programlama modülleri kullanılmıştır. Sistemin yer aldığı ağdaki seri iletişim hatları birleştirilmiştir. Bu şekilde tek ya da çoklu işlem hesaplamasında kullanılacak paralel bir hesaplama hattı oluşturulmuştur. Hesaplama işlemi bu hat üzerinde iş yüklerini üstleniciler arasında paylaştıran yük dengeleme sistemine göre gerçekleştirilmiştir.İkinci olarak, sisteme dâhil olan bilgisayarların programsal açık ya da saldırılardan izole olmasını sağlayacak şifreleme algoritmaları oluşturulmuştur. Bu algoritmalar ile kriptografik (şifreli) güvenlik kanalları oluşturulmuştur. Bu kanallar aracılığıyla sistemin tüm gönüllü üstlenicilerle güvenli protokoller üzerinden iletişim kurması sağlanmıştır.Bu sistem bulut hesaplama tekniği ile oluşturulan bir gönüllü hesaplama projesinin veri güvenliği açısından potansiyel kapasitesini ortaya koymuştur. Sistem aracığıyla gönüllü üstlenicilerde veri güvenliği analizleri elde edilmiştir. Bu analizler cevaplama zamanı, performans kaybı ve gecikme süresi olmak üzere incelenmiştir. Bulut hesaplama sistemi güvenlik sistemi olmadan 2.802 GFLOPS hesaplama gücünde çalışırken güvenlik sisteminin çalıştırılmasıyla bu gücün ortalama % 0,011 oranında bir kayıpla 2.771 GFLOPS' a düştüğü tespit edilmiştir. This scientific/thesis study has offered a newly designed data security system, which is based on cloud computing technique. System obtains power from the volunteer clients located on the internet as a distributed manner. Each computer, which takes part on the system, has been named as ?volunteer contractor?. Volunteer contractors, which connected to Data Security System (DSS), have not needed to install an external firewall program. For, security modules created with encryption algorithms has taken the duty to ensure system security on. This situation has returned to volunteer contractors as performance gains.The first stage, Network programming modules have been used due to the system is developed in level of cloud computing technique. Serial communication lines locating on network of system has been combined with each other. In this way; a parallel computation line using for single or multi process computation has been created. Computation process has been implemented on this line according to load balancing system. Computation results produced by the system have been observed that the data are quickly transmitted to the client computers.Secondly, the encryption algorithms that ensure to isolate computers from programmatically deficiency or attacks in system have been generated. Cryptographic (cryptic) security channels have been created with these algorithms. The system has established communication with all volunteer constructors through these channels. Therefore, data transfers have been executed on secure protocols with these security lines which are canalized to the system.This system puts forward to the potential capacity of a volunteer computing project, generated with cloud computing technique. Performance capacities of volunteer contractors have been analyzed by making measurements through the system. These measurements compose of significant topics; CPU power, memory, disk size, network outputs and client availability. This system has been coded in Visual Studio 2010 environment by using C++ and C# programming languages. 107
- Published
- 2011
44. Design of Security & Privacy Issues for Cloud Computing.
- Author
-
Dönmez, Emrah
- Subjects
- *
CLOUD computing security measures , *INTERNET privacy , *WEB-based user interfaces , *RIGHT of privacy , *INTERNET security , *CRYPTOGRAPHY - Abstract
Data privacy is one of the most significant issues in web environment. Users surfing on the Internet always want to be invisible from any aspect of web environment. Because of the importance of the privacy, designs should be considered and implemented as block boxes for web applications. Users want to take full control of their privacy but web applications become more and more public and transparent and as a result, privacy control becomes a challenging issue. Privacy in cloud is under pressure by both legal and commercial domains. Therefore privacy primitives should be defined as clearly as possible and management rights of privacy related to the end users should be handed over to them completely. On the other hand, there is another issue which is mostly related to the privacy, and known as security. It is a common sense issue between users and developers in terms of all kind of applications especially for web applications. Security in cloud is the most critical issue which should be increased as maximum as possible. User data are hold or processed in cloud servers, therefore data corruption or loss give rise to high costs if it is not prevented through security precautions, such as; backup modules, secure proxy channels, alternative communication lines (satellite etc.), and cryptographic security modules. In this study major privacy and security problems are defined and possible solutions are proposed, and as future concepts which are related to the privacy and security in cloud are introduced. [ABSTRACT FROM AUTHOR]
- Published
- 2015
45. ULTRASONİK SENSÖR İLE İKİ BOYUTLU HARİTALANDIRMA SİSTEMİ.
- Author
-
Aydoğan, Tuncay, Gül, Kağan, and Dönmez, Emrah
- Subjects
- *
CARTOGRAPHY software , *ULTRASONIC equipment , *DETECTORS , *LASERS , *SCANNING systems , *INFRARED detectors , *DEFENSE industries , *NATURAL disasters , *ARCHAEOLOGY - Abstract
The aim of this paper, today, as the sensors to receive realtime data and of this data in the computer environment, increasing efforts are being processed. Especially, recently mapping systems has contained the research which quite on the occupation. This mapping system is designed for the various structures and properties of many types of sensor are available. Especially, laser scanners are used in professional mapping systems. Considering the laser scanners to high price, need to develop a less costly system has emerged. Outside the laser scanner, alternative measures of distance; infrared, sensors, ultrasonic sensors, etc. to conducting studies on their and of these systems are designed defence industry, archelogy, natural disasters areas, etc. are used. In this study, an ultrasonic distance sensor using two-dimensional mapping system developed as a hardware and software applications. [ABSTRACT FROM AUTHOR]
- Published
- 2009
46. Classification of Haploid and Diploid Maize Seeds based on Pre-Trained Convolutional Neural Networks
- Author
-
Emrah Donmez and Dönmez, Emrah
- Subjects
business.industry ,Image Processing ,Convolutional Neural Networks ,Mühendislik ,Artificial Learning ,Pattern recognition ,Biology ,Convolutional neural network ,Engineering ,Maize Seed Identification ,Materials Chemistry ,Artificial intelligence ,Deep Features ,Ploidy ,business ,Maize Seed Identification,Deep Features,Artificial Learning,Convolutional Neural Networks,Image Processing - Abstract
Analysis of agricultural products is an important area that is widely emphasized today. In this context, with the development of technology, computer-aided analysis systems are also being developed. In this study, a system has been proposed for classifying maize seeds as haploid and diploid using pre-trained convolutional neural networks. For this purpose, AlexNet, GoogLeNet, ResNet-18, ResNet-50, and VGG-16 pre-trained models have been used as feature extractors for the haploid and diploid seed classification process. In the first stage, the deep features of haploid and diploid maize seeds have been obtained in these models. The features have been taken from different layers of network architecture. Instead of softmax classifier in the last layer of the network, classifiers based on decision tree, k-nearest neighbor, and support vector machine have been used. According to the classification results with these features, the achievements in network architectures and classifier methods have been observed. The experiments have been carried out on a publicly available dataset consisting of 3000 haploid and diploid maize seed images. The experimental results revealed that the developed classification systems demonstrate a remarkable performance.
- Published
- 2020
- Full Text
- View/download PDF
47. A hybrid DNN-LSTM model for detecting phishing URLs
- Author
-
Emrah Donmez, Alper Ozcan, Cagatay Catal, Behcet Senturk, and Dönmez, Emrah
- Subjects
Password ,Artificial neural network ,business.industry ,Computer science ,Deep learning ,Feature extraction ,S.I. : Machine Learning Applications for Security ,Machine learning ,computer.software_genre ,Phishing ,Credit card ,Identification (information) ,Phishing detection ,Artificial Intelligence ,Isolation (database systems) ,Artificial intelligence ,business ,computer ,Software - Abstract
Phishing is an attack targeting to imitate the official websites of corporations such as banks, e-commerce, financial institutions, and governmental institutions. Phishing websites aim to access and retrieve users' important information such as personal identification, social security number, password, e-mail, credit card, and other account information. Several anti-phishing techniques have been developed to cope with the increasing number of phishing attacks so far. Machine learning and particularly, deep learning algorithms are nowadays the most crucial techniques used to detect and prevent phishing attacks because of their strong learning abilities on massive datasets and their state-of-the-art results in many classification problems. Previously, two types of feature extraction techniques [i.e., character embedding-based and manual natural language processing (NLP) feature extraction] were used in isolation. However, researchers did not consolidate these features and therefore, the performance was not remarkable. Unlike previous works, our study presented an approach that utilizes both feature extraction techniques. We discussed how to combine these feature extraction techniques to fully utilize from the available data. This paper proposes hybrid deep learning models based on long short-term memory and deep neural network algorithms for detecting phishing uniform resource locator and evaluates the performance of the models on phishing datasets. The proposed hybrid deep learning models utilize both character embedding and NLP features, thereby simultaneously exploiting deep connections between characters and revealing NLP-based high-level connections. Experimental results showed that the proposed models achieve superior performance than the other phishing detection models in terms of accuracy metric. 2021, The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature. Scopus 2-s2.0-85112070505
- Published
- 2021
48. A Cloudware Architecture for Collaboration of Multiple AGVs in Indoor Logistics: Case Study in Fabric Manufacturing Enterprises
- Author
-
Fatih Okumuş, Adnan Fatih Kocamaz, Emrah Donmez, Okumuş, Fatih, and Dönmez, Emrah
- Subjects
0209 industrial biotechnology ,Intelligent manufacturing ,Computer Networks and Communications ,Computer science ,media_common.quotation_subject ,lcsh:TK7800-8360 ,Cloud computing ,multi-AGVs collaboration ,02 engineering and technology ,computer.software_genre ,cloud robotics ,020901 industrial engineering & automation ,Logistics planning ,0202 electrical engineering, electronic engineering, information engineering ,Motion planning ,Electrical and Electronic Engineering ,Function (engineering) ,media_common ,business.industry ,lcsh:Electronics ,Multi-task allocation ,Industrial engineering ,multi-task allocation ,Simulation software ,Task (computing) ,logistics planning ,Cloud robotics ,Hardware and Architecture ,Control and Systems Engineering ,intelligent manufacturing ,Signal Processing ,Factory (object-oriented programming) ,020201 artificial intelligence & image processing ,business ,computer ,Multi-AGVs collaboration - Abstract
In Industry 4.0 compatible workshops, the demand for Automated Guided Vehicles (AGVs) used in indoor logistics systems has increased remarkably. In these indoor logistics systems, it may be necessary to execute multiple transport tasks simultaneously using multiple AGVs. However, some challenges require special solutions for AGVs to be used in industrial autonomous transportation. These challenges can be addressed under four main headings: positioning, optimum path planning, collision avoidance and optimum task allocation. The solutions produced for these challenges may require special studies that vary depending on the type of tasks and the working environment in which AGVs are used. This study focuses on the problem of automated indoor logistics carried out in the simultaneous production of textile finishing enterprises. In the study, a centralized cloud system that enables multiple AGVs to work in collaboration has been developed. The finishing enterprise of a denim manufacturing factory was handled as a case study and modelling of mapping-planning processes was carried out using the developed cloud system. In the cloud system, RestFul APIs, for mapping the environment, and WebSocket methods, to track the locations of AGVs, have been developed. A collaboration module in harmony with the working model has been developed for AGVs to be used for fabric transportation. The collaboration module consists of task definition, battery management-optimization, selection of the most suitable batch trolleys (provides mobility of fabrics for the finishing mills), optimum task distribution and collision avoidance stages. In the collaboration module, all the finishing processes until the product arrives the delivery point are defined as tasks. A task allocation algorithm has been developed for the optimum performance of these tasks. The multi-fitness function that optimizes the total path of the AGVs, the elapsed time and the energy spent while performing the tasks have been determined. An assignment matrix based on K nearest neighbor (k-NN) and permutation possibilities was created for the optimal task allocation, and the most appropriate row was selected according to the optimal path totals of each row in the matrix. The D* Lite algorithm has been used to calculate the optimum path between AGVs and goals by avoiding static obstacles. By developing simulation software, the problem model was adapted and the operation of the cloud system was tested. Simulation results showed that the developed cloud system was successfully implemented. Although the developed cloud system has been applied as a case study in fabric finishing workshops with a complex structure, it can be used in different sectors as its logistic processes are similar.
- Published
- 2020
- Full Text
- View/download PDF
Catalog
Discovery Service for Jio Institute Digital Library
For full access to our library's resources, please sign in.