Güleş, Şeyma

Profile URL:
Email Address:sgules@ktun.edu.tr
Main Affiliation:08. Distance Education Application and Research Centre
Status: Current Staff
ORCID:ORCID Profile0000-0002-1465-3462
YÖK Akademik: 067910732E75C7BC
Name Variants:
Gules, S. Güleş, Ş.
Full item page

Filters

2020 - 20263

Settings

Author of Publication: search.filters.isAuthorOfPublication.c210fbb6-029f-4141-80a7-a0443f055be0

Scholarly Output Search Results

Now showing 1 - 3 of 3
  • Article
    Citation - WoS: 1
    Citation - Scopus: 1
    A Logarithmic Transfer Function for Binary Swarm Intelligence Algorithms: Enhanced Feature Selection with White Shark Optimizer
    (MDPI, 2025) Gules, Seyma; Kilic, Alper; Kiran, Mustafa Servet; Gunduz, Mesut
    With the increasing size of datasets in data mining applications, feature selection has become critical for enhancing classification accuracy and reducing computational complexity. In this study, a novel binary feature selection algorithm, called bWSO-log, is proposed based on the White Shark Optimizer (WSO). Unlike the commonly used S-shaped and V-shaped transfer functions in the literature, the WSO algorithm is converted into a binary form for the first time using a logarithmic transfer function. The performance of the proposed method was tested on nineteen benchmark datasets and compared with eight widely used metaheuristic algorithms. The results show that the bWSO-log algorithm demonstrates superior or competitive performance in terms of classification accuracy and the number of selected features. These findings reveal the effectiveness of the proposed logarithmic function and highlight the potential of WSO-based binary optimization in feature selection problems.
  • Master Thesis
    Makine Öğrenmesi Yöntemleri ile Zararlı Yazılım Tespiti
    (Konya Teknik Üniversitesi, 2020) Güleş, Şeyma; Koçer, Barış
    Teknolojinin gelişmesi ile birlikte hayatımızla ayrılmaz bir parça haline gelen bilgisayar sistemlerinin kullanımı giderek artmaktadır. Bu artış birçok siber güvenlik probleminin ortaya çıkmasına sebep olmuştur. Siber güvenlik açıklarının sonucunda kullanıcıların bilgisayar sistemlerine giren kötü amaçlı yazılımlar birçok zarara sebep olmaktadır. Bu zararları engelleyebilmek amacıyla kötü amaçlı yazılım tespit sistemleri geliştirilmiştir. Kötü amaçlı yazılımların herhangi bir zarara sebep olmadan önce tespit edilebilmesi bilgi sistemleri için hayati önem taşımaktadır. Bu çalışmada makine öğrenmesi yöntemleri ile bilgisayar sistemlerinin telemetri bilgileri kullanılarak kötü amaçlı bir yazılımın sistem üzerinde var olup olmadığının tahmini yapılmıştır. Çalışmada kullanılan veri seti Microsoft tarafından bilgisayarların telemetri bilgileri toplanarak oluşturulmuştur. Veri setinin ilk bir milyon veri satırı Bilgi Kazancı, Ki-Kare özellik seçme yöntemleri ile birlikte Naive Bayes, Karar Ağacı, Random Forest, Adaboost, LightGBM sınıflandırma algoritmaları ile 10 çapraz doğrulama tekniği kullanılarak test edilmiştir. Ayrıca Microsoft Kötü Amaçlı Yazılım Tahmini veri setini çalışmasında kullanan Lin'in (2019) veri ön işleme adımlarından sonra elde ettiği veri seti Naive Bayes, Karar Ağacı, Random Forest, Adaboost, LightGBM sınıflandırma algoritmaları ile test edilmiştir.
  • Article
    Ohe-Rwnet: A Novel Neural Network-Based Vectorization Method for Fake Review Detection
    (Springer Heidelberg, 2026-01-01) Gules, Seyma; Gunduz, Mesut; Kiran, Mustafa Servet
    Advancements in internet technologies have enabled many activities to be carried out in online environments. In recent years, with the increase in online shopping, online reviews have played a significant role in influencing users' product preferences. Although such reviews sometimes provide accurate and objective information, in some cases, they can be misleading. So, this has made fake review detection an important research area today. Although various studies have been conducted in the literature on this subject, the growing prevalence of fake reviews highlights the need for more effective and innovative approaches. In this study, a novel vectorization method called OHE-RWNet is proposed for fake review detection. The proposed approach models semantic relationships between words using neural networks and converts words into machine-processable numerical representations by considering the target concept of spam in context. The OHE-RWNet approach is compared with widely used vectorization techniques, including One-Hot Encoding (OHE), Bag-of-Words (BoW), Term Frequency-Inverse Document Frequency (TF-IDF), Word2Vec, Global Vectors for Word Representation (GloVe), and Bidirectional Encoder Representations from Transformers (BERT) on seven different datasets. Experimental results demonstrate that the proposed method exhibits superior and competitive performance compared to the techniques considered.

Research Topics

Domains
Physical SciencesSocial Sciences
Fields
Computer ScienceSocial Sciences
Subfields
Artificial IntelligenceComputational Theory and MathematicsSociology and Political ScienceSignal ProcessingInformation Systems
Specific Research Areas
Metaheuristic Optimization Algorithms Research
Advanced Multi-Objective Optimization Algorithms
Misinformation and Its Impacts
Advanced Malware Detection Techniques
Spam and Phishing Detection

Sustainable Development Goals

SDG data is not available
This researcher does not have a Scopus ID.
This researcher does not have a WoS ID.

Publication Collaboration

Affiliation Name Count
Konya Technical University 2
1 / 1
Data obtained from OpenAlex
JournalCount
Applied Sciences-Basel1
International Journal of Machine Learning and Cybernetics1
Current Page: 1 / 1
Scholarly Output

3

Articles

2

Views / Downloads

12/48

Supervised MSc Theses

1

Supervised PhD Theses

0

WoS Citation Count

1

Scopus Citation Count

1

Patents

0

Projects

0

WoS Citations per Publication

0.33

Scopus Citations per Publication

0.33

Open Access Source

2

Supervised Theses

1

Scopus Quartile Distribution

Competency Cloud

GCRIS Competency Cloud