EKErdal Kiliç

Erdal Kiliç

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Erdal Kiliç has a total of 31 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Toward Robust Unsupervised Multi-Class Chest X-Ray Clustering: Comparing Reconstruction-Driven and Self- Supervised Representation Learning

    by Salma Ouhsousou, Zinnet Duygu Akşehir, Erdal Kiliç

    Unsupervised clustering of medical images remains a challenging problem, particularly in radiology, where reliable annotations are scarce and visual differences between disease categories can be subtle. Many existing chest X-ray clustering studies rely on Convolutional autoencoders (CAEs) to learn latent features; however, reconstruction-based objectives tend to emphasize low-level image similarity rather than clinically meaningful structure. In this work, we present a controlled and systematic comparison between reconstruction-driven autoencoder representations and self-supervised transformer representations derived from DINO for multi-class chest X-ray clustering. All methods are evaluated under a unified experimental protocol across three dataset scales, including a balanced 4,000-image development dataset and a strict cross-dataset generalization setting. We further examine the influence of dimensionality reduction by comparing linear projection (PCA-32) and nonlinear manifold learning (UMAP-32),and assess clustering robustness using K-Means and Gaussian Mixture Models under a strictly inductive protocol, with Spectral Clustering included as a secondary exploratory reference. Across all configurations, DINO-based embeddings consistently yield stronger cluster compactness, separation, and alignment with clinical categories than autoencoder features. Nonlinear projection with UMAP further enhances cluster structure, while performance remains stable when models trained on one dataset are transferred to an independent dataset without refitting. In contrast, the choice of clustering algorithm has comparatively limited impact when high-quality representations are used, indicating that representation geometry is the primary driver of performance. Our results demonstrate that while CAEs primarily capture pixel-level textures, DINO-based representations encode higher-level semantic structures. Under a strict cross-dataset evaluation protocol, the proposed hybrid strategy (Strategy B) substantially improved clustering quality compared to direct feature fusion (Strategy A), increasing the Silhouette score from 0.056 to 0.564 and the Rand Index (RI) from 0.762 to 0.860 on an external dataset. These findings highlight the potential of self-supervised vision transformers as a robust representation foundation for future unsupervised clinical image analysis and decision support systems.

  • Open Access

    A Dataset-Driven AutoML Framework for Clustering of Chest X-Ray Images

    by Salma Ouhsousou, Zinnet Duygu Akşehir, Oğuz Emre Kural, Soumaya Ouhsousou, Erdal Kiliç

  • Open Access

    Turkish Optical Character Recognition Under the Lens: A Systematic Review of Language-Specific Challenges, Dataset Scarcity, and Open-Source Limitations

    by Míraç Göksu Öztürk, Durmus Özkan Sahin, Erdal Kiliç

    This systematic literature review explores the progress, challenges, and opportunities in the field of Optical Character Recognition (OCR) for the Turkish language. Despite significant advancements, the development of robust Turkish OCR systems faces several obstacles, such as a lack of publicly available datasets, limited open-source solutions, and the underutilization of cutting-edge deep learning techniques. These challenges hinder the creation of OCR systems that can match the capabilities of those developed for languages like English. Focusing on 38 peer-reviewed studies published between 2019 and 2023, this paper provides the first systematic review of Turkish OCR research, offering a comprehensive analysis of the current methods, datasets, and evaluation metrics across both modern Turkish (Latin script) and Ottoman Turkish (Arabic script) contexts. Our findings highlight that while Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM), and Convolutional Recurrent Neural Networks (CRNN) architectures are frequently used, Transformer-based and end-to-end models remain underexplored in Turkish OCR. We also identify data scarcity and the lack of reproducible benchmark datasets as key barriers. By analyzing current research trends, pinpointing challenges, and emphasizing opportunities for future advancements, this review aims to be a valuable resource for researchers and practitioners in Turkish language text recognition. Our study contributes to the field by offering a structured overview of existing methods and proposes practical recommendations for improving dataset availability, encouraging open-source collaboration, and adopting more advanced model architectures.


  • Open Access

    Using Kolmogorov–Arnold Networks in Transformer Model: A Study on Low-Resource Neural Machine Translation

    by Bilge Kagan Yazar, Erdal Kiliç

    Neural machine translation is one of the most significant research area with the widespread use of deep learning. However, unlike other problems, machine translation includes at least two languages. Due to this situation, the amount of data between the languages to be translated is an important factor for translation success. On the other hand, low-resource languages have problems with the amount of data, which poses a significant challenge to the success of machine translation. Transformer models have achieved great success by modeling long-term dependencies with the self-attention mechanism. However, the feed forward layers (FFN) that follow each self-attention layer constitute almost all the non-embedding parameters of the model. On the other hand, studies in the literature have been conducted on the necessity of these FFN layers in the Transformer model and on different alternatives that can be used. Kolmogorov-Arnold networks (KAN) have recently come to the forefront as a new neural network architecture that has achieved success on many problems. The KAN structure can better learn patterns in complex data using learnable activation functions instead of fixed ones. Accordingly, this study proposes using KAN layers instead of FFN layers in the Transformer model for the low-resource translation problem. It is aimed to overcome the low-resource problem and to present a new alternative within the Transformer model employing the adaptive activation functions of KANs. In traditional Transformer models, FFN layers consist of two linear transformations and ReLU activation functions. In the proposed structure, firstly, the KAN structure is used instead of FFN layers in the Transformer model without any changes in the model dimensions. Then, experiments are conducted with lower-dimensional KAN layers and various parameter sets. The study is carried out using Turkish-English and Kazakh-English language pairs. Obtained findings reveal that using KAN layers instead of FFN layers in the Transformer model has a positive effect on the translation success and that KAN layers used in similar or lower dimensions significantly increase the success of the Transformer model.


  • Open Access

    Improving Low-Resource Kazakh-English and Turkish-English Neural Machine Translation Using Transfer Learning and Part of Speech Tags

    by Bilge Kağan Yazar, Erdal Kiliç

    This study presents a novel translation framework by combining transfer learning and part-of-speech (POS) tagging methods to improve the performance of low-resource neural machine translation models using Kazakh-English and Turkish-English language pairs. It is aimed to maximize the effectiveness of transfer learning by taking advantage of the structural similarities of Turkish and Kazakh languages and to obtain more accurate and consistent translation results by integrating grammatical and syntactic information into the model with POS tags. For Kazakh, POS tags were generated using the RoBERTa model, while for Turkish, the Zemberek library was employed, and these tags were used as an additional feature in Transformer-based models. The findings show that using transfer learning and POS tags alone increases the performance, but when these two methods are used together, more meaningful and consistent results are obtained. The results obtained in the study are examined with BLEU, chrF, and METEOR metrics, and detailed analyses are made. The models created for the Kazakh-English translation direction are compared with different models, and it is seen that much better results are obtained with the methods used. For the Turkish-English translation direction, the results were examined using Tatoeba and TED2020 corpora of different sizes. In particular, significant improvements were observed in the experiments conducted on the Tatoeba corpus, and significant increases were obtained in the examined metrics. In this context, the methods applied in the study achieved successful results for low-resource languages, and the generalizability of the proposed approach was demonstrated with the use of different corpora and language pairs.


  • A Systematic Survey of Machine Learning and Deep Learning Models Used in Industrial Internet of Things Security

    by Ersin Enes Eryılmaz, Sedat Akleylek, Yankı Ertek, Erdal Kılıç

    IIoT “Industrial Internet of Things” refers to a subset of Internet of Things technology designed for industrial processes and industrial environments. IIoT aims to make manufacturing facilities, energy systems, transportation networks, and other industrial systems smarter, more efficient and connected. IIoT aims to reduce costs, increase productivity, and support more sustainable operations by making industrial processes more efficient. In this context, the use of IIoT is increasing in production, energy, healthcare, transportation, and other sectors. IoT has become one of the fastest-growing and expanding areas in the history of information technology. Billions of devices communicate with the Internet of Things with almost no human intervention. IIoT consists of sophisticated analysis and processing structures that handle data generated by internet-connected machines. IIoT devices vary from sensors to complex industrial robots. Security measures such as patch management, access control, network monitoring, authentication, service isolation, encryption, unauthorized entry detection, and application security are implemented for IIoT networks and devices. However, these methods inherently contain security vulnerabilities. As deep learning (DL) and machine learning (ML) models have significantly advanced in recent years, they have also begun to be employed in advanced security methods for IoT systems. The primary objective of this systematic survey is to address research questions by discussing the advantages and disadvantages of DL and ML algorithms used in IoT security. The purpose and details of the models, dataset characteristics, performance measures, and approaches they are compared to are covered. In the final section, the shortcomings of the reviewed manuscripts are identified, and open issues in the literature are discussed.


  • Top Cited Papers
    Open Access

    Low-Resource Neural Machine Translation: A Systematic Literature Review

    by Bılge Kağan Yazar, Durmuş Özkan Şahın, Erdal Kiliç

    In this study, a systematic literature review was conducted to examine the significant works in the literature on low-resource neural machine translation. Within the scope of the study, three research questions were identified to examine the low-resource neural machine translation literature. According to the inclusion and exclusion criteria, 45 studies were selected for review. After the relevant studies were identified, three research questions were aimed to be answered. The first research question is to identify the study directions and language pairs used in low-resource neural machine translation. The second research question aims to identify which deep learning methods are used in low-resource neural machine translation and which metrics are used to evaluate these methods. The third research question is to determine the bilingual and monolingual corpora used in the studies and the preferred development environments. In addition, the studies with the most commonly used language pairs were analyzed, and directions for future studies were made.


  • Collecting Health Information with LoRa Technology

    by Zinnet Duygu Akşehir, Sedat Akleylek, Erdal Kiliç, Burçe Şirin, Korhan Cengiz