Morphological and structural complexity analysis of low-resource English-Turkish language pair using neural machine translation models

Acı, Mehmet | Vuran Sarı, Nisa | Acı, Çiğdem

Neural machine translation (NMT) has achieved remarkable success in high-resource language pairs; however, its effectiveness for morphologically rich and low-resource languages like Turkish remains underexplored. As a highly agglutinative and morphologically complex language with limited high-quality parallel data, Turkish serves as a representative case for evaluating NMT systems on low-resource and linguistically challenging settings. Its structural divergence from English makes it a critical testbed for assessing tokenization strategies, attention mechanisms, and model generalizability in neural translation. This study investigates the comparative performance of two prominent NMT paradigms—the Transformer architecture, and recurrent-based sequence-to-sequence (Seq2Seq) models with atten...

A hybrid CNN-GRU model with XAI-Driven interpretability using LIME and SHAP for static analysis in malware detection

Sarı, Nisa Vuran | Acı, Mehmet

The increasing sophistication of evolving malware types and attack techniques has rendered traditional antivirus solutions inadequate, particularly in mitigating zero-day threats. To address this challenge, Machine Learning (ML) and Deep Learning (DL)-based approaches have been developed, demonstrating significant efficacy and high accuracy in malware classification. However, the black box nature of these models raises significant concerns in terms of transparency and interpretability. This study presents a comprehensive evaluation of Ensemble Learning and Deep Learning methods for static analysis-based malware classification, which allows joint analysis of Application Programming Interface (API) calls and Dynamic Link Library (DLL) data. In the study, a specially designed Convolutional Ne...

Empowering Entrepreneurial Mindsets With AI

Özsungur, Fahri

OVERVIEW OF THE SUBJECT MATTER Artificial Intelligence (AI) has evolved from a futuristic concept to an integral part of our daily lives and business operations. This book explores the intersection of AI and entrepreneurship, delving into how AI influences entrepreneurial activities, business strategies, and various sectors of the economy. By examining AI's role in enhancing business operations, fostering innovation, and addressing challenges such as sustainability and market analysis, this book provides a comprehensive understanding of AI's transformative impact on modern entrepreneurship. Where the Topic Fits in the World Today In today's rapidly evolving technological landscape, AI is reshaping industries and creating new opportunities for innovation and growth. Entrepreneurs are at the...

Evaluation of the Effectiveness of Orthopedic Face Mask Treatment Using Artificial Intelligence on Two-Dimensional Photographs

Merve, Cengiz Saniye

Aim. The aim of this study is to evaluate the changes in the parameters measured in two-dimensional frontal and profile photographs taken at the beginning (T0) and at the end (T1) of orthopedic face mask (FM) treatment in patients with skeletal Class III malocclusion, using artificial intelligence (AI). Material and methods. A total of 23 patients with skeletal Class III malocclusion receiving orthopedic FM treatment were included in the study. Eight parameters were evaluated in this study: Nasolabial Angle, Mentolabial Angle, Chin Projection Angle, Frankfurt Horizontal–A'B' angle, Upper Lip/Lower Lip Ratio, Midface/Lower Face Ratio, Upper Lip–E-Line, Lower lip – E-line. Results. Except for the Nasolabial Angle, significant changes were observed in all parameters between the T0 a...

Artificial Intelligence in Digital Public Relations: A Delphi Study

Çataldaş, ibrahim

Digitalization has brought many new technologies. One of these technologies is artificial intelligence, which has started a new change process in public relations. Some digital public relations duties are currently being performed using artificial intelligence, but it is still unclear what role this technology will play in the field's future. In this study, artificial intelligence is discussed in the context of digital public relations. In this vein, the primary purpose of this study is to identify new technologies and trends that may affect the future transformation of public relations. According to the purpose of the study, expert opinions were used by applying the Delphi technique in the research part. The goal of the first round of this research, which consists of two rounds, was ...

Bulanık Kümeleme ve Destek Vektörleri ile Sinir Ağı Güçlendirme Uygulamaları

Vuran, Nisa | Acı, Mehmet | Korucu, Gizen Mutlu | Acı, Çiğdem

Bu çalışmada, sinir ağlarının kullanımında Regülerize Edilmiş Bulanık Kümeleme Sinir Ağı’nın (RFCNN) gürültülü ve uyumsuz veriler karşısında dayanıklılığının arttırılması amaçlanmıştır. Geleneksel sinir ağları, gürültülü verilerle çalışırken performans düşüşleri yaşamaktadır. Bu sorunu ele almak için, destek vektör tabanlı (Support Vector, SV) tabanlı Hiyerarşik Bulanık C-Ortalamalar (Hierarchical Fuzzy C-Means, HFCM) ve Bulanık C-Ortalamalar (Fuzzy C-Me-ans, FCM) kümeleme tekniklerini L2-norm düzenleme ile birleştirerek daha da-yanıklı bir model geliştirilmesi hedeflenmiştir. Çalışmada, SV tabanlı kümeleme tekniklerinin aykırı değerlerin etkilerini azaltarak modelin performansını iyileştiği gösterilmiştir. L2-norm düzenlemesi, modelin aşırı uyumunu önlemek ve varyans-önyargı dengesini sağ...

Sağlık Görüntülerinin Sınıflandırılmasında Derin Nöral Bulanık Ağının Performansı

Vuran, Nisa | Acı, Mehmet | Korucu, Gizen Mutlu | Acı, Çiğdem

Çevrimiçi Aktif Öğrenme ile Geliştirilen Bulanık Sinirsel Sınıflandırıcı Analizi

Vuran, Nisa | Acı, Mehmet | Korucu, Gizen Mutlu | Acı, Çiğdem

Detection of Malware by Static Analysis Using Machine Learning Methods

Vuran, Nisa | Acı, Mehmet

The increase in cyber-attacks has also started to threaten the use of internet and information technologies. This situation emphasizes the importance of detecting malicious software that is responsible for cyber-attacks. Nowadays, there are studies on the development of machine learning methods for malicious software detection. Malicious software detectors are the primary tools in defense against malicious software. The quality of such a detector is determined by the techniques it uses. Malware analysis methods such as machine learning, deep learning, and static and dynamic analysis are among these techniques. This study presents malware analysis and classification techniques. For malware detection, well-known algorithms for machine learning including such K-Nearest Neighbors, Naive Bayes,...

Navigating Organizational Behavior in the Digital Age With AI

Özsungur, Fahri

Artificial Intelligence (AI) has evolved from a futuristic concept into a powerful force that is transforming industries and organizations across the globe. The impact of AI on organizational behavior, leadership, talent management, ethics, and strategic decision-making is profound, especially within the corporate landscape. As organizations adapt to the digital age, understanding how AI reshapes key areas of management is critical for staying competitive and innovative. Navigating Organizational Behavior in the Digital Age With AI provides a comprehensive exploration of AI's integration within organizations, covering its influence on decision-making, conflict resolution, performance management, diversity, and ethics. This book offers valuable insights into AI's role in shaping modern work...