Merve Varol Arısoy

Dr. Merve Varol Arısoy

Information Systems Engineering, Mehmet Akif Ersoy University, Burdur, Turkey (Türkiye)
orcid

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

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

Representative Publications

View All Publications
4 December 2023 in Applied Sciences
Verified
Journal Article
Open access
PDF file
FYfatma yaprakdal
fatma yaprakdal
MAMerve Varol Arısoy
Merve Varol Arısoy
In the smart grid paradigm, precise electrical load forecasting (ELF) offers significant advantages for enhancing grid reliability and informing energy planning decisions. Specifically, mid-term ELF is a key priority for power system planning and operation. Although statistical methods were primarily used because ELF is a time series problem, deep learning (DL)-based forecasting approaches are more commonly employed and successful in achieving precise predictions. However, these DL-based techniques, known as black box models, lack interpretability. When interpreting the DL model, employing explainable artificial intelligence (XAI) yields significant advantages by extracting meaningful information from the DL model outputs and the causal relationships among various factors. On the contrary, precise load forecasting necessitates employing feature engineering to identify pertinent input features and determine optimal time lags. This research study strives to accomplish a mid-term forecast of ELF study load utilizing aggregated electrical load consumption data, while considering the aforementioned critical aspects. A hybrid framework for feature selection and extraction is proposed for electric load forecasting. Technical term abbreviations are explained upon first use. The feature selection phase employs a combination of filter, Pearson correlation (PC), embedded random forest regressor (RFR) and decision tree regressor (DTR) methods to determine the correlation and significance of each feature. In the feature extraction phase, we utilized a wrapper-based technique called recursive feature elimination cross-validation (RFECV) to eliminate redundant features. Multi-step-ahead time series forecasting is conducted utilizing three distinct long-short term memory (LSTM) models: basic LSTM, bi-directional LSTM (Bi-LSTM) and attention-based LSTM models to accurately predict electrical load consumption thirty days in advance. Through numerous studies, a reduction in forecasting errors of nearly 50% has been attained. Additionally, the local interpretable model-agnostic explanations (LIME) methodology, which is an explainable artificial intelligence (XAI) technique, is utilized for explaining the mid-term ELF model. As far as the authors are aware, XAI has not yet been implemented in mid-term aggregated energy forecasting studies utilizing the ELF method. Quantitative and detailed evaluations have been conducted, with the experimental results indicating that this comprehensive approach is entirely successful in forecasting multivariate mid-term loads.

16 September 2021 in International Journal of Engineering and Innovative Research
Verified
Journal Article
Open access
MAMerve Varol Arısoy
Merve Varol Arısoy
With the acceleration of digitalization in all areas of our lives, the need for biometric verification methods is increasing. The fact that biometric data is unique and biometric verification is stronger against phishing attacks compared to password-based authentication methods, has increased its preference rate. Signature verification, which is one of the biometric verification types, plays an important role in many areas such as banking systems, administrative and judicial applications. There are 2 types of signature verification, online and offline, for identifying the identity of the person and detecting signature forgery. Online signature verification is carried out during signing and temporal dynamic data are available regarding the person's signature. Offline verification is applied by scanning the image after signing, and this verification is limited to spatial data. Therefore, the offline signature verification process is considered a more challenging task. In this study, offline signature verification, independent of the writer, based on One-Shot Learning, was performed using Siamese Neural Network. Due to the fact that the Deep Convolution Neural Network requires a large amount of labeled data for image classification, real and fake signature distinction has been achieved by using the One-Shot Learning method, which can perform a successful classification by using less numbers of signature images. As a result of the experiments conducted on signature datasets, using the Siamese architecture, the proposed approach achieved percentage accuracy of 93.23, 92.11, 89.78, 91.35 verification in 4NSigComp2012, SigComp2011, 4NSigComp2010 and BHsig260 respectively.

28 March 2025 in Scientific Reports
Verified
Journal Article
Open access
PDF file
MAMerve Varol Arısoy
Merve Varol Arısoy
Ayhan ARISOYAyhan ARISOY
Ayhan ARISOY
IUIlhan Uysal
Ilhan Uysal
This study introduces the Medical Vision Attention Generation (MedVAG) model, a novel framework designed to facilitate the automated generation of medical reports. MedVAG integrates Vision Transformer (ViT)-based visual feature extraction and GPT-2 language modeling, enhanced by graph-based feature fusion and multiple attention mechanisms (co-attention, cross-attention, memory-guided attention), to ensure semantic coherence and diagnostic accuracy. Evaluated on IU X-Ray and COV-CTR datasets, the model achieved state-of-the-art performance across natural language generation metrics (BLEU, METEOR, ROUGE, CIDEr) and clinical effectiveness measures. Ablation studies highlighted the critical role of attention mechanisms and feature fusion in aligning visual and textual features. MedVAG demonstrates strong potential as an assistive technology, aiming to support radiologists by reducing workload and enhancing diagnostic accuracy.

31 August 2020 in Virtual Reality
Verified
Journal Article
Closed access
PDF file
MAMerve Varol Arısoy
Merve Varol Arısoy
Ecir Uğur KüçüksilleEcir Uğur Küçüksille
Ecir Uğur Küçüksille

13 February 2025 in Scientific Reports
Verified
Journal Article
Open access
PDF file
MAMerve Varol Arısoy
Merve Varol Arısoy
IUIlhan Uysal
Ilhan Uysal
Accurate classification of cherry varieties is crucial for their economic value and market differentiation, yet their genetic diversity and visual similarity make manual identification challenging, hindering efficient agricultural and trade practices. This study addresses this issue by proposing a novel deep learning-based hybrid model that integrates BiFPN with the YOLOv8n-cls framework, enhanced by Swin Transformer and Deformable Attention Transformer (DAT) techniques. The model was trained and evaluated on a newly constructed dataset comprising cherry varieties from Turkey’s Western Mediterranean region. Experimental results demonstrated the effectiveness of the proposed approach, achieving a precision of 91.91%, recall of 92.0%, F1-score of 91.93%, and an overall accuracy of 91.714%. The findings highlight the model’s potential to optimize harvest timing, ensure quality control, and support export classification, thereby contributing to improved agricultural practices and economic outcomes.

1 July 2022 in Neural Computing and Applications
Verified
Journal Article
Closed access
PDF file
MAMerve Varol Arısoy
Merve Varol Arısoy