Karakaya, Kasım Murat

Profile Picture
Name Variants
Karakaya, Murat
Karakaya, Kasım Murat
K., Kasim Murat
K.,Kasım Murat
Karakaya,K.M.
Kasim Murat, Karakaya
K., Karakaya
K.,Kasim Murat
Karakaya, Kasim Murat
Kasım Murat, Karakaya
K.M.Karakaya
K.,Karakaya
Karakaya,M.
Karakaya,M.
Job Title
Profesör Doktor
Email Address
murat.karakaya@atilim.edu.tr
Main Affiliation
Computer Engineering
Status
Former Staff
Website
ORCID ID
Scopus Author ID
Turkish CoHE Profile ID
Google Scholar ID
WoS Researcher ID

Sustainable Development Goals Report Points

SDG data could not be loaded because of an error. Please refresh the page or try again later.
Scholarly Output

44

Articles

20

Citation Count

128

Supervised Theses

4

Filters

2013 - 2019382020 - 20226
Reset filters

Settings

Scholarly Output Search Results

Now showing 1 - 10 of 44
  • Thumbnail Image
    Article
    A Smart Classroom Application: Monitoring and Reporting Attendance Automatically Using Smart Devices
    (International Journal of Scientific Research in Information Systems and Engineering, 2017) Şengül, Gökhan; Karakaya, Murat; Bostan, Atila; Computer Engineering
    For recording attendance in a classroom, generally instructors collect signatures of the attendees. Then, at the end of the semester, those signatures need to be counted and reported. This process causes waste of time and effort for both instructors and attendees. Besides this process is very error prone. Moreover, in crowded classes, there could be some misuses of this process. In this study, a smart classroom application is proposed and developed in order to monitor the attendance of the students in a classroom environment. In the design, a low-energy Bluetooth device is located at each classroom. Identification number (ID) of the low-energy Bluetooth device and the name/number of the classroom that the device is located are matched and stored in a central database. In addition to this information, the name of the courses given in that classroom and their time tables are also stored in the central database. Thus, in the database, the weekly course schedule of the classrooms is available. In addition to this central database infrastructure, a mobile application is developed that can run on both in mobile phones and smart watches. The users first install the application on their own smart devices. Whenever an attendee enters to a classroom, the smart device and its application interacts with the low-energy Bluetooth device. The student’s identification number (Student ID: SID), the identification number (ID) of the low-energy Bluetooth device located at the class, the day and time of the interaction are sent to the central database by the smart device. Using this information, the name of the attendee and the courses that he/she attended are matched using the SID of the attendee, the ID of the low-energy Bluetooth device, the day and time of the interaction. Those matching information are also stored in the central database. The records in the central database are used to create any automatic reports, i.e. the attendance status, the time and duration of the attendance, and the classroom (course) of the record. The advantage of the proposed system is that it is a fully automatic system that records the presence of the students, generates automatic attendance reports, does not require any extra device except installing a mobile application onto smart phones or smart watches of the student, and can be deployed with a low budget. The proposed system is tested in real classroom environment and it is proven to be operational.
  • Thumbnail Image
    Conference Object
    Citation - Scopus: 2
    An Undergraduate Curriculum for Deep Learning
    (Institute of Electrical and Electronics Engineers Inc., 2018) Tirkes,G.; Ekin,C.C.; Engul,G.; Bostan,A.; Karakaya,M.; Computer Engineering
    Deep Learning (DL) is an interesting and rapidly developing field of research which has been currently utilized as a part of industry and in many disciplines to address a wide range of problems, from image classification, computer vision, video games, bioinformatics, and handwriting recognition to machine translation. The starting point of this study is the recognition of a big gap between the sector need of specialists in DL technology and the lack of sufficient education provided by the universities. Higher education institutions are the best environment to provide this expertise to the students. However, currently most universities do not provide specifically designed DL courses to their students. Thus, the main objective of this study is to design a novel curriculum including two courses to facilitate teaching and learning of DL topic. The proposed curriculum will enable students to solve real-world problems by applying DL approaches and gain necessary background to adapt their knowledge to more advanced, industry-specific fields. © 2018 IEEE.
  • Thumbnail Image
    Master Thesis
    Havada Kalış Süresi Kısıtlı Seyir Halindeki Gemiye Konuşlu İnsansız Hava Aracının Hedef En Çoklaması
    (2015) Savuran, Halil; Karakaya, Kasım Murat; Computer Engineering
    Bu tez seyir halindeki bir gemi üzerine konuşlu, menzil kısıtlı bir insansız hava aracının (İHA) hedef en çoklaması problemi için bir çözüm yaklaşımı önermektedir. Bu problem, Araç Rotalama Probleminin (ARP) menzil kapasitesi ve depo mobilitesi kısıtlarıyla genişletilmesiyle modellenmekte ve bu özgün genişletme çalışma boyunca Kapasite kısıtlı Mobil Depo ARP (K-MoDARP) olarak tanımlanmaktadır. Bu problemin doğasının dikte ettiği özgün çözüm gereksinimi probleme özel kısıtlar için uyarlanmış bir genetik algoritma (GA-KMoD) ile karşılanmaktadır. Tezde, çalışmanın amacı, problem tanımı ve önerilen çözümün geliştirme ve uygulaması anlatılmıştır. Ayrıca, önerilen GA-KMoD'un performansı farklı problem kıstasları için yoğun benzetim testleri vasıtasıyla değerlendirilmiştir. GA-KMoD'un ürettiği rotaların kalitesi alternatif yöntemlerle üretilen sonuçlarla karşılaştırılmıştır. Deneysel sonuçlar, önerilen çözüm yönteminin alternatif yöntemlere göre olan üstünlüğünü net bir şekilde ortaya koymaktadır.
  • Thumbnail Image
    Article
    Harmanlanmış Öğrenme Ortamlarında Sosyal Medya Kullanımının Öğrenci Doyumu Üzerine Etkisi
    (2018) Eryılmaz, Meltem; Karakaya, Kasım Murat; Computer Engineering
    Bu deneysel araştırmanın amacı sosyal medya kullanımının harmanlanmış öğrenmeortamlarında öğrenci doyumu üzerindeki etkisini belirlemektir. Araştırma Ankara’daki birüniversitede okuyan ve bilgisayara giriş dersi alan 109 öğrenci üzerinde uygulanmıştır.Uygulama sürecinde öğrenciler dersi haftada bir kez yüz yüze geri kalanı çevirimiçi olmaküzere harmanlanmış öğrenme yaklaşımı ile almışlardır. Çevirimiçi öğrenme ortamı dersmateryallerinin, forum, sınav, ders notu, resim ve video destekli ders özetlerinin paylaşıldığıbir ortam olarak tasarlanmıştır. Araştırmada, çevirimiçi öğrenme ortamlarını desteklemeküzere tasarlanmış bir sosyal medya ortamı sunan Course Networking (CN) adlı sistemkullanılmıştır. Seçilen dersin ilk 7 haftasında ders sadece Moodle sistemi ile desteklenirken,8nci haftadan sonra CN sistemi kullanıma açılmıştır. 7nci ve 15nci haftalarda yapılan ölçek veanket uygulamaları ile öğrencilerin bu dersten aldıkları tatmin duygusu ve harmanlanmışöğrenme ortamlarında sosyal medya kullanımının öğrencilerin algıları üzerine etkileriincelenmiştir.
  • Thumbnail Image
    Master Thesis
    Kontrollü Çok Konulu Metin Üretimi için Yeni Bir Derin Öğrenme Yaklaşımı
    (2022) Çağlayan, Cansen; Karakaya, Kasım Murat; Computer Engineering
    One of the most important tasks in the Controllable Text Generation (CTG) domain is to create topic-controlled texts. In this study, we propose and design three different approaches, and conduct extensive experiments on them to observe the performance of the controlled multi-topic reviews generated in Turkish. In the first approach, we generate controlled multi-topic text using a single-layer GPT language model by incorporating several control techniques. To control the language model, we first add topic information to the sequential input, as a second technique we add the automatically extracted keywords for each topic to the sequential input in addition to the first technique. The last technique that we propose is a novel sampling strategy. We propose to use a topic selection classifier that enables the next token selection according to the probability of the selected tokens being on the desired topic. Then, we apply these approaches to a more advanced language model, the multi-layer GPT, and interpret the results. In addition to these experiments, we compare three different deep learning text classification models in order to create a reliable multi-topic review classifier.
  • Thumbnail Image
    Master Thesis
    Ss-mla: Uzaktan Algılamalı Görüntülerin Çok Etiketli Sınıflandırması için Yeni Bir Çözüm
    (2021) Üstünkök, Tolga; Karakaya, Kasım Murat; Software Engineering; Computer Engineering
    Uzaktan algılanan görüntülerin çok etiketli sınıflandırması çok önemli bir araştırma alanıdır. Kentsel büyümeyi izlemekten askeri gözetlemeye kadar birçok uygulamaya sahiptir. Uzaktan algılanan görüntülerin çok etiketli sınıflandırması için birçok algoritma ve yöntem önerilmiştir. Bu tezde iki yaklaşım sunulmaktadır. İlki, küçük veri kümelerinde karmaşık yöntemlerin daha basit olanlara göre avantajı olmadığını gösteren CNN tabanlı basit bir modeldir. İkincisi, uzaktan algılanan görüntülerin çoklu etiketli sınıflandırması için Semi-Supervised Multi-Label Annotizer (SS-MLA) adı verilen rekabetçi bir Vector-Quantized Temporal Associative Memory (VQTAM) tabanlı yöntemdir. İlk yöntem, uzaktan algılanmış dört farklı veri kümesi üzerinde F1-Skorlarına göre literatürdeki diğer son teknoloji yöntemlerle ve SS-MLA ile karşılaştırılmıştır. Deney sonuçları, yeni bir yaklaşım olarak SS-MLA'nın, karşılaştırmaların yarısından ve önerilen basit yöntemden daha iyi sonuçlar verdiğini göstermektedir. Algoritma ve yöntemlerin tüm uygulamaları için Python 3.8 ortamında Tensorflow-GPU 2.4.0 ve Numpy 1.19.5 çerçeveleri kullanılmıştır.
  • Thumbnail Image
    Conference Object
    Citation - Scopus: 7
    Parking space occupancy detection using deep learning methods;
    (Institute of Electrical and Electronics Engineers Inc., 2018) Akinci,F.C.; Karakaya,M.; Computer Engineering
    This paper presents an approach for gathering information about the availabilty of the parking lots using Convoltional Neural Network (CNN) for image processing running on an embedded system. By using an eflicent neural network model, we made it possible to use a very low cost embedded system compared to the ones used in previous works on this topic. This efficient model's performance is compared to one of the models that proved its accuracy in image classification competitions. In these tests, we used datasets that has thousands of different images taken from parking lots in different light and weather conditions. © 2018 IEEE.
  • Thumbnail Image
    Conference Object
    Citation - Scopus: 2
    Detecting Errors in Automatic Image Captioning by Deep Learning;
    (Institute of Electrical and Electronics Engineers Inc., 2021) Karakaya,M.; Computer Engineering
    Automatic tagging of images is an important researcli topic in tlie field of image processing. Anotlier area similar to this is the automatic generation of picture captions. In this study, a deep learning model that automatically tags the pictures is used to detect errors in image captions. As a result of the initial experiments, it is observed that the proposed system can find up to 80% of the errors in the image captions. © 2021 IEEE
  • Thumbnail Image
    Conference Object
    Citation - WoS: 1
    An Undergraduate Curriculum for Deep Learning
    (Ieee, 2018) Tirkes, Guzin; Ekin, Cansu Cigdem; Sengul, Gokhan; Bostan, Atila; Karakaya, Murat; Computer Engineering
    Deep Learning (DL) is an interesting and rapidly developing field of research which has been currently utilized as a part of industry and in many disciplines to address a wide range of problems, from image classification, computer vision, video games, bioinformatics, and handwriting recognition to machine translation. The starting point of this study is the recognition of a big gap between the sector need of specialists in DL technology and the lack of sufficient education provided by the universities. Higher education institutions are the best environment to provide this expertise to the students. However, currently most universities do not provide specifically designed DL courses to their students. Thus, the main objective of this study is to design a novel curriculum including two courses to facilitate teaching and learning of DL topic. The proposed curriculum will enable students to solve real-world problems by applying DL approaches and gain necessary background to adapt their knowledge to more advanced, industry-specific fields.
  • Thumbnail Image
    Article
    Unidirectional Data Transfer: a Secure System To Push the Data From a High Security Network To a Lower One Over an Actual Air-Gap
    (International Journal of Scientific Research in Information Systems and Engineering, 2017) Şengül, Gökhan; Bostan, Atila; Karakaya, Murat; Computer Engineering
    The term “air-gap” is typically used to refer physical and logical separation of two computer networks. This type of a separation is generally preferred when the security levels of the networks are not identical. Although the security requirements entail parting the data networks, there is a growing need for fast and automatic transfer of data especially from high-security networks to low-security ones. To protect security sensitive system from the risks originating from low-security network, unidirectional connections that permit the data transfer only from high to low-security network, namely information-diodes, are in use. Nonetheless, each diode solution has its drawbacks either in performance or security viewpoints. In this study, we present a unidirectional data transfer system in which the primary focus is data and signal security in technical design and with a plausible and adaptable data transfer performance. Such that the networks do not touch each other either in physically or logically and the transfer is guaranteed to be unidirectional. Apart from avoiding the malicious transmissions from low to high-security network, we claim that the proposed data diode design is safe from emanation leakage with respect to the contemporary sniffing and spoofing techniques.