İnan, Emrah
Loading...
Profile URL
Name Variants
İnan, E.
Inan, Emrah
İnan, E
Inan, E.
Inan, E
Inan, Emrah
İnan, E
Inan, E.
Inan, E
Job Title
Email Address
emrahinan@iyte.edu.tr
Main Affiliation
03.04. Department of Computer Engineering
Status
Current Staff
ORCID ID
Scopus Author ID
Turkish CoHE Profile ID
Google Scholar ID
WoS Researcher ID
Sustainable Development Goals
1NO POVERTY
0
Research Products
2ZERO HUNGER
0
Research Products
3GOOD HEALTH AND WELL-BEING
1
Research Products
4QUALITY EDUCATION
0
Research Products
5GENDER EQUALITY
0
Research Products
6CLEAN WATER AND SANITATION
0
Research Products
7AFFORDABLE AND CLEAN ENERGY
0
Research Products
8DECENT WORK AND ECONOMIC GROWTH
0
Research Products
9INDUSTRY, INNOVATION AND INFRASTRUCTURE
1
Research Products
10REDUCED INEQUALITIES
0
Research Products
11SUSTAINABLE CITIES AND COMMUNITIES
0
Research Products
12RESPONSIBLE CONSUMPTION AND PRODUCTION
0
Research Products
13CLIMATE ACTION
0
Research Products
14LIFE BELOW WATER
0
Research Products
15LIFE ON LAND
0
Research Products
16PEACE, JUSTICE AND STRONG INSTITUTIONS
0
Research Products
17PARTNERSHIPS FOR THE GOALS
0
Research Products
Documents
23
Citations
107
h-index
5
Documents
13
Citations
61
Scholarly Output
11
Articles
3
Views / Downloads
2126/929
Supervised MSc Theses
1
Supervised PhD Theses
0
WoS Citation Count
0
Scopus Citation Count
1
Patents
0
Projects
0
WoS Citations per Publication
0.00
Scopus Citations per Publication
0.09
Open Access Source
5
Supervised Theses
1
| Journal | Count |
|---|---|
| -- 9th International Artificial Intelligence and Data Processing Symposium, IDAP 2025 -- 2025-09-06 through 2025-09-07 -- Malatya -- 215321 | 2 |
| -- 2025 Innovations in Intelligent Systems and Applications Conference, ASYU 2025 -- 2025-09-10 through 2025-09-12 -- Bursa -- 214381 | 2 |
| Dokuz Eylül Üniversitesi Mühendislik Fakültesi Fen ve Mühendislik Dergisi | 1 |
| Fibers and Polymers | 1 |
| Journal of Computational Science | 1 |
Current Page: 1 / 2
Scopus Quartile Distribution
Competency Cloud
11 results
Scholarly Output Search Results
Now showing 1 - 10 of 11
Publication Prediction of Associations Between Nanoparticle, Drug and Cancer Using Variational Graph Autoencoder(2024) İnan, EmrahPredicting implicit drug-disease associations is critical to the development of new drugs, with the aim of minimizing side effects and development costs. Existing drug-disease prediction methods typically focus on either single or multiple drug-disease networks. Recent advances in nanoparticles particularly in cancer research show improvements in bioavailability and pharmacokinetics by reducing toxic side effects. Thus, the interaction of the nanoparticles with drugs and diseases tends to improve during the development phase. In this study, it presents a variational graph autoencoder model to the cell-specific drug delivery data, including the class interactions between nanoparticle, drug, and cancer types as a knowledge base for targeted drug delivery. The cell-specific drug delivery data is transformed into a bipartite graph where relations only exist between sequences of these class interactions. Experimental results show that the knowledge graph enhanced Variational Graph Autoencoder model with VGAE-ROC-AUC (0.9627) and VGAE-AP (0.9566) scores performs better than the Graph Autoencoder model.Article Contrastive Retrieval Methodology for Turkish Metaphor Detection and Identification(Assoc Computing Machinery, 2025) Inan, EmrahMetaphorical expressions, as a form of figurative language, are individually limited in their use. However, whenboth literal and non-literal meanings are considered, they are frequently used in web content. Hence, producinga balanced dataset to learn superior representations is a challenging task, and metaphor detection suffers froma limited training dataset. To alleviate this problem, we present a retrieval-based contrastive learning approachwhich first identifies candidate metaphors in the input text and then detects metaphorical expressions as aclaim verification task in the inherently unbalanced setting of this study. Furthermore, we adapt contrastivelearning to make it easier to distinguish between the literal and figurative meanings of the same expression.For the experimental setup, we extract non-literal and literal expressions along with their meanings andsample sentences from a Turkish dictionary. In the metaphor detection subtask, performance evaluation shows that sparse and dense search variations using the Turkish-e5-Large model achieve a Recall@10 (R@10) scoreof 0.614. Moreover, the SimCSE-TR-Contr-Sample-Meaning model achieves the highest Recall@10 (R@10)of 0.9739 on the generated test dataset for the metaphor identification subtask. In the real-world scenario,it achieves a competitive R@10 score of 0.8684, and these results clearly demonstrate that our model cangeneralise to this real-world scenarioConference Object A Semantic Search Engine for Turkish and English Research Resources(Institute of Electrical and Electronics Engineers Inc., 2025) Karabacak, O.; Inan, E.Research resources are growing in volume at an exponential rate across disciplines and languages. This exponential increase has created a pressing need for intelligent search systems that can help researchers efficiently access relevant academic material. To overcome this issue, this study introduces a bilingual semantic search engine designed to retrieve academic articles written in both Turkish and English. The primary goal is to improve the accuracy and relevance of academic information retrieval by using modern Natural Language Processing techniques. Instead of relying on traditional keyword-based search methods, the system leverages transformer-based sentence embedding models. To capture semantic meaning more effectively, MiniLM-L6v2, paraphrase-multilingual-MiniLM-L12-v2 and multilingual-e5-base models were chosen for their multilingual capabilities and sentence-level embedding performance. To assess the quality of search results, Mean Average Precision (MAP) and Normalized Discounted Cumulative Gain (nDCG) were used. These metrics were calculated for each model across both language groups. Evaluation results show that the multilingual-e5-base model consistently outperformed the other models in both MAP and nDCG scores, demonstrating superior semantic understanding and multilingual alignment. The system also features a simple and responsive Streamlit-based interface that allows for real-time querying and result display. © 2025 IEEE.Conference Object Citation - Scopus: 1Applying Weighted Graph Embeddings To Turkish Metaphor Detection(Institute of Electrical and Electronics Engineers Inc., 2024) İnan, EmrahMetaphor is a common literary mechanism that allows abstract concepts to be conceptualised using more concrete terminology. Existing methods rely on either end-to-end models or hand-crafted pre-processing steps. Generating well-defined training datasets for supervised models is a time-consuming operation for this type of problem. There is also a lack of pre-processing steps for resource-poor natural languages. In this study, we propose an approach for detecting Turkish metaphorical concepts. Initially, we collect non-literal concepts including their meaning and reference sentences by employing a Turkish dictionary. Secondly, we generate a graph by discovering super-sense relations between sample texts including target metaphorical expressions in Turkish WordNet. We also compute weights for relations based on the path closeness and word occurrences. Finally, we classify the texts by leveraging a weighted graph embedding model. The evaluation setup indicates that the proposed approach reaches the best F1 and Gmean scores of 0.83 and 0.68 for the generated test sets when we use feature vector representations of the Node2Vec model as the input of the logistic regression for detecting metaphors in Turkish texts. © 2024 IEEE.Article Making Hierarchically Aware Decisions on Short Findings for Automatic Summarisation(Elsevier, 2025) Inan, EmrahAn impression in a typical radiology report emphasises critical information by providing a conclusion and reasoning based on the findings. However, the findings and impression sections of these reports generally contain brief texts, as they highlight crucial observations derived from the clinical radiograph. In this scenario, abstractive summarisation models often experience a degradation in performance when generating short impressions. To address this challenge in the summarisation task, our work proposes a method that combines well-known fine-tuned text classification and abstractive summarisation language models. Since fine-tuning a language model requires an extensive, well-defined training dataset and is a time-consuming task dependent on high GPU resources, we employ prompt engineering, which uses prompt templates to programme language models and improve their performance. Our method first predicts whether the given findings text is normal or abnormal by leveraging a fine-tuned language model. Then, we apply a radiology-specific BART model to generate the summary for abnormal findings. In the zero-shot setting, our method achieves remarkable results compared to existing approaches on a real-world dataset. In particular, our method achieves scores of 37.43 for ROUGE-1, 21.72 for ROUGE-2, and 35.52 for ROUGE-L.Master Thesis Moresysgoal: Movie Recommendation System Using Technique Supplemented by Content With Goal Programming(Izmir Institute of Technology, 2012) İnan, Emrah; Aytaç, İsmail SıtkıIn recent years, internet grows at an accelerating rate. In addition, a new flow of information, which has various types of data, takes place at internet. Therefore, the end users may not find the relevant information satisfying their interests. As a result, recommendation systems, one of the approaches, appeared to help users for this manner. MoresysGOAL is one of the examples for these systems, and stands for movie recommendation system with goal programming. It aims to improve the state-of-art collaborative filtering algorithms unless they have enough dense dataset. Hence, MoresysGOAL has a successful combination of content-based and collaborative filtering approaches for increasing performance of the recommendation system. This thesis focuses on serving a successful solution to users considering two parts. The first part is related to the similarity calculation of the contents are supplemented by goal programming. Moreover, the proposed system has the content information of the movies which also play a role to support collaborative filtering algorithms. These collaborative methods form the second part by means of predicting movies to satisfy user tastes. Lastly, MoresysGOAL is a web-based application for recommending prediction lists of movies to the end users.Conference Object Aspect-Based Medical Record Classification Using Large Language Model Guided Knowledge Graph(Institute of Electrical and Electronics Engineers Inc., 2025) Işik, E.; Inan, E.Traditional sentiment analysis approaches typically evaluate a text as a whole and assign it a single sentiment label, such as positive or negative. Although this method works well for many tasks, there are cases where it is more beneficial to understand sentiment related to specific aspects. To address this issue, Aspect-Based Sentiment Analysis (ABSA) focuses on analysing sentiment at the aspect level, treating it as a more detailed form of opinion mining. In this study, we proposed a method that initially identifies aspect terms as an extraction sub-task of anatomy terms by leveraging biomedical knowledge graphs. In the second subtask, we leverage well-known large language models to predict the sentiment polarities of these extracted aspect terms. The experimental results for each subtask demonstrate that the RaTE-NER-Deberta model yields the best performance in the anatomy aspect identification subtask, achieving precision, recall, and F1 scores of 65.385, 64.151, and 64.762, respectively. After identifying anatomical entities in the input texts using this model, we proceed with the classification task. The deberta-v3-base-absa-v1.1 model, a specialized version for aspect-based sentiment analysis, delivers the highest results, with a precision of 91.38, recall of 80.30, and an F1 score of 85.48. © 2025 IEEE.Conference Object Adapting Language Models to Sentiment Analysis for Automatically Translated and Labelled Turkish News Texts(Institute of Electrical and Electronics Engineers Inc., 2025) Serficeli, S.C.; Udunman, B.; Inan, E.The proliferation of news sources makes it difficult to track current events and social events in real time. In order to interpret social events in this context quickly and effectively, it is important to translate news texts provided in different natural languages into Turkish and to perform sentiment analysis on them. The aim of this study is to translate multilingual news texts into Turkish and perform sentiment analysis on these texts. The generated labels were compared and the data that were given the same label by all models were separated as automatically labelled data. This automatic labelling process ensured that the data for which different models produced consistent results were reliably labelled. When the results were evaluated, F1 score of 0.946 was achieved for sentiment analysis using the automatic labelling mechanism for texts translated into Turkish. © 2025 IEEE.Conference Object A Data Coding and Screening System for Accident Risk Patterns: A Learning System(WITPress, 2011) Geçer Sargın, Feral; Geçer Sargın, Feral; Duvarcı, Yavuz; Duvarcı, Yavuz; İnan, E.; İnan, E.; Kumova, Bora İsmail; Kumova, Bora İsmail; Atay Kaya, İlgi; Atay Kaya, İlgiAccidents on urban roads can occur for many reasons, and the contributing factors together pose some complexity in the analysis of the casualties. In order to simplify the analysis and track changes from one accident to another for comparability, an authentic data coding and category analysis methods are developed, leading to data mining rules. To deal with a huge number of parameters, first, most qualitative data are converted into categorical codes (alpha-numeric), so that computing capacity would also be increased. Second, the whole data entry per accident are turned into ID codes, meaning each crash is possibly unique in attributes, called 'accident combination', reducing the large number of similar value accident records into smaller sets of data. This genetical code technique allows us to learn accident types with its solid attributes. The learning (output averages) provides a decision support mechanism for taking necessary cautions for similar combinations. The results can be analyzed by inputs, outputs (attributes), time (years) and the space (streets). According to Izmir's case results; sampled data and its accident combinations are obtained for 3 years (2005 - 2007) and their attributes are learned. © 2011 WIT Press.Article Digital Transformation in Leather Color Fastness Evaluation: Computer-Assisted Grey Scale Analysis(Korean Fiber Soc, 2025) Efendioglu, Nilay Ork; Mutlu, Mehmet Mete; Inan, Emrah; Ozgunay, HasanLeather is a critical material in the fashion industry, where it is required to meet specific customer demands for color, specifications, and performance, especially regarding color fastness. Traditional methods for assessing color fastness rely on subjective evaluations conducted by professional experts using grey scale standards. However, human evaluation can be inconsistent due to various factors, such as lighting conditions and individual perception. In this study, leather samples were first subjected to expert evaluations and scored using the grey scale system. These evaluations were then compared with color measurement data obtained through a spectrophotometer, which was processed using custom-designed software (written in the Python programming language). This software provided precise grey scale values based on the color measurements, enabling accurate digital assessments. The results of the comparative analysis showed that the computer-assisted grey scale assessment could be completed in a significantly shorter time frame with a minimal margin of error, offering a more reliable and efficient alternative to traditional evaluation methods. This approach not only enhances the accuracy of color assessments but also streamlines the evaluation process in the leather industry.