Mehtap Köse Ulukök

Mehtap Köse Ulukök

Auto-generated profile, based on publicly available information

Mehtap Köse Ulukök

Department of Software Engineering, Cyprus Aydn University, Northern Cyprus, Mersin, Trkiye

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
19 July 2022 in IEEE Access
Verified
Journal Article
Open access
EÖEmre Özbilge
Emre Özbilge
MUMehtap Köse Ulukök
Mehtap Köse Ulukök
ÖTÖnsen Toygar
Önsen Toygar
EOEbru Ozbilge
Ebru Ozbilge
Detection of the diseases on tomatoes in advance and making early intervention and treating increases the production amount, efficiency and quality which will satisfy the consumer with a more affordable shelf price. In this way, the efforts of the farmers who are waiting for the harvest throughout the season will not be wasted. In this paper a compact convolutional neural network (CNN) is proposed for diseases identification task where the network is comprised of only 6 layers that is why it is computationally cheap in terms of parameters employed in the network. This network is trained by using PlantVillage’s tomato crops dataset which consists of 10 classes (9 diseases and 1 healthy). The proposed network is first compared with well-known pre-trained ImageNet deep networks using transfer learning approach. The results show that the proposed network performed better than pre-trained knowledge transferred deep network models and it is shown that there is no need to constitute very large, complicated network architectures to achieve a superior tomato diseases identification performance. Furthermore, to increase the performance of proposed network, data augmentation techniques are also employed during the network training. The proposed network achieves an accuracy, F1 score, Matthews correlation coefficient, true positive rate and true negative rate of 99.70%, 98.49%, 98.31%, 98.49% and 99.81%, respectively using 9,077 unseen test images. Our results are better than or similar to the results of the state-of-the-art deep neural network approaches that used PlantVillage database and the proposed method employs the cheapest architecture.

21 April 2025 in IEEE Access
Verified
Journal Article
Open access
MUMehtap Köse Ulukök
Mehtap Köse Ulukök
ISIrfan Sariyildiz
Irfan Sariyildiz
VEVesile Evrim
Vesile Evrim
The Raft consensus algorithm is widely used in private networks as an alternative to the energy-intensive PoW consensus algorithm in blockchains. The Raft consensus algorithm’s voting mechanism performs well in reliable and well-planned networks with optimized timeouts. However, in unreliable or poorly configured networks, it encounters several challenges. These include multiple candidacies, repeated election cycles, insufficient or failed leader elections during network splits, prolonged leader election times and vulnerability to Sybil attacks. In this study, a novel Hybrid Raft-PoW consensus algorithm is introduced. It integrates the hash puzzle-based competition of the PoW consensus algorithm with the fast leader election mechanism of the Raft consensus algorithm. This combination ensures both speed and certainty in leader election, ensuring that leadership is delegated to the most capable nodes. At the same time, it promotes decentralization by ensuring a fair distribution across nodes, achieving at least 80% leadership distribution. Therefore, the proposed Hybrid Raft-PoW consensus algorithm improves or eliminates problems caused by Raft consensus algorithm’s leader election mechanism.

26 April 2023 in Water Resources Management
Verified
Journal Article
Closed access
PDF file
BYBurhan Yildiz
Burhan Yildiz
MUMehtap Kose Ulukok
Mehtap Kose Ulukok
VBVali Bashiry
Vali Bashiry

26 August 2023 in Computer Science
Verified
Journal Article
Closed access
ISİrfan Sariyildiz
İrfan Sariyildiz
MUMehtap Köse Ulukök
Mehtap Köse Ulukök

28 July 2023 in Çukurova Üniversitesi Mühendislik Fakültesi Dergisi
Verified
Journal Article
Closed access
PDF file
MUMehtap Köse Ulukök
Mehtap Köse Ulukök
Sayısal iyileştirme, mühendislik alanında en çok uğraşılan problemlerden biridir. Bu çalışmada, son zamanlarda geliştirilen Çift-Girişim Tabanlı İyileştirme Algoritması’nın (Bi-Attempted Based Optimization Algorithm) (ABaOA) arama yakınsama kabiliyeti yirmi iyi bilinen referans fonksiyonu üzerinde test edilmiştir. Elde edilen sonuçlar Genetik Algoritma (GA) ve Temel İyileştirme Algoritması (Based Optimization Algoritması) (BaOA) ile karşılaştırılmıştır. ABaOA, tüm yinelemeler boyunca iki sabit adım boyutlu çoğaltma parametresi ve iki işlem operatörü kullanan nüfus tabanlı bir Evrimsel Algoritma’dır. Evrimsel algoritmalar arama alanı boyunca global optimuma hızlı bir şekilde yaklaşır ve uygulanabilir bir çözümü garanti ederler. Deneysel sonuçlar ABaOA'nın hem BAOA'ya hem de GA'ya göre global optimuma daha hızlı yaklaştığını açıkça göstermiştir.