Browsing by Author "Fatih Yetkin, E."

Now showing 1 - 4 of 4

Evaluating Cognitive and Emotional Engagement in AI-Assisted Virtual Reality Through EEG
(Bulgarian Academy of Sciences, Institute of Mathematics and Informatics, 2025) Fatih Yetkin, E.; Ballı, Tuğçe
Citation - WoS: 19
Citation - Scopus: 33
A Hybrid Approach With Gan and Dp for Privacy Preservation of Iiot Data
(IEEE-Inst Electrical Electronics Engineers Inc, 2023) Hindistan, Yavuz Selim; Yetkin, E. Fatih; Fatih Yetkin, E.
There are emerging trends to use the Industrial Internet of Things (IIoT) in manufacturing and related industries. Machine Learning (ML) techniques are widely used to interpret the collected IoT data for improving the company's operational excellence and predictive maintenance. In general, ML applications require high computational resource allocation and expertise. Manufacturing companies usually transfer their IIoT data to an ML-enabled third party or a cloud system. ML applications need decrypted data to perform ML tasks efficiently. Therefore, the third parties may have unacceptable access rights during the data processing to the content of IIoT data that contains a portrait of the production process. IIoT data may include hidden sensitive features, creating information leakage for the companies. All these concerns prevent companies from sharing their IIoT data with third parties. This paper proposes a novel method based on the hybrid usage of Generative Adversarial Networks (GAN) and Differential Privacy (DP) to preserve sensitive data in IIoT operations. We aim to sustain IIoT data privacy with minimal accuracy loss without adding high additional computational costs to the overall data processing scheme. We demonstrate the efficiency of our approach with publicly available data sets and a realistic IIoT data set collected from a confectionery production process. We employed well-known privacy six assessment metrics from the literature and measured the efficiency of the proposed technique. We showed, with the help of experiments, that the proposed method preserves the privacy of the data while keeping the Linear Regression (LR) algorithms stable in terms of the R-Squared accuracy metric. The model also ensures privacy protection for hidden sensitive data. In this way, the method prevents the production of hidden sensitive data from the sub-feature sets.
Citation - Scopus: 1
RESTORATIVE: Improving Accessibility to Cultural Heritage with AI-Assisted Virtual Reality
(Bulgarian Academy of Sciences, Institute of Mathematics and Informatics, 2025) Fatih Yetkin, E.; Pişkin, Şenol; Peker, Hasan; Ballı, Tuğçe
Citation - WoS: 3
Citation - Scopus: 5
A Scalable Unsupervised Feature Selection With Orthogonal Graph Representation for Hyperspectral Images
(IEEE-Inst Electrical Electronics Engineers Inc, 2023) Taskin, Gulsen; Yetkin, E. Fatih; Camps-Valls, Gustau; Fatih Yetkin, E.
Feature selection (FS) is essential in various fields of science and engineering, from remote sensing to computer vision. Reducing data dimensionality by removing redundant features and selecting the most informative ones improves machine learning algorithms' performance, especially in supervised classification tasks, while lowering storage needs. Graph-embedding (GE) techniques have recently been found efficient for FS since they preserve the geometric structure of the original feature space while embedding data into a low-dimensional subspace. However, the main drawback is the high computational cost of solving an eigenvalue decomposition problem, especially for large-scale problems. This article addresses this issue by combining the GE framework and representation theory for a novel FS method. Inspired by the high-dimensional model representation (HDMR), the feature transformation is assumed to be a linear combination of a set of univariate orthogonal functions carried out in the GE framework. As a result, an explicit embedding function is created, which can be utilized to embed out-of-samples into low-dimensional space and provide a feature relevance score. The significant contribution of the proposed method is to divide an $n$ -dimensional generalized eigenvalue problem into $n$ small-sized eigenvalue problems. With this property, the computational complexity (CC) of the GE is significantly reduced, resulting in a scalable FS method, which could be easily parallelized too. The performance of the proposed method is compared favorably to its counterparts in high-dimensional hyperspectral image (HSI) processing in terms of classification accuracy, feature stability, and computational time.