arXiv subjects

Omer Aydin

Publications and source records attributed to Omer Aydin.

11 recordsLinked to original sources

arXiv2025

Improving LLM Reliability with RAG in Religious Question-Answering: MufassirQAS

Religious teachings can sometimes be complex and challenging to grasp, but chatbots can serve as effective assistants in this domain. Large Language Model (LLM) based chatbots, powered by Natural Language Processing (NLP), can connect related topics and provide well-supported responses to intricate questions, making them valuable tools for religious education. However, LLMs are prone to hallucinations as they can generate inaccurate or irrelevant information, and these can include sensitive content that could be offensive, inappropriate, or controversial. Addressing such topics without inadvertently promoting hate speech or disrespecting certain beliefs remains a significant challenge. As a solution to these issues, we introduce MufassirQAS, a system that enhances LLM accuracy and transparency using a vector database-driven Retrieval-Augmented Generation (RAG) approach. We built a dataset comprising fundamental books containing Turkish translations and interpretations of Islamic texts. This database is leveraged to answer religious inquiries while ensuring that responses remain reliable and contextually grounded. Our system also presents the relevant dataset sections alongside the LLM-generated answers, reinforcing transparency. We carefully designed system prompts to prevent harmful, offensive, or disrespectful outputs, ensuring that responses align with ethical and respectful discourse. Moreover, MufassirQAS provides supplementary details, such as source page numbers and referenced articles, to enhance credibility. To evaluate its effectiveness, we tested MufassirQAS against ChatGPT with sensitive questions, and our system demonstrated superior performance in maintaining accuracy and reliability. Future work will focus on improving accuracy and refining prompt engineering techniques to further minimize biases and ensure even more reliable responses.

cs.CL↗

arXiv2025

Deciphering the Crypto-shopper: Knowledge and Preferences of Consumers Using Cryptocurrencies for Purchases

The fast-growing cryptocurrency sector presents both challenges and opportunities for businesses and consumers alike. This study investigates the knowledge, expertise, and buying habits of people who shop using cryptocurrencies. Our survey of 516 participants shows that knowledge levels vary from beginners to experts. Interestingly, a segment of respondents, nearly 30%, showed high purchase frequency despite their limited knowledge. Regression analyses indicated that while domain knowledge plays a role, it only accounts for 11.6% of the factors affecting purchasing frequency. A K-means cluster analysis further segmented the respondents into three distinct groups, each having unique knowledge levels and purchasing tendencies. These results challenge the conventional idea linking extensive knowledge to increased cryptocurrency usage, suggesting other factors at play. Understanding this varying crypto-shopper demographic is pivotal for businesses, emphasizing the need for tailored strategies and user-friendly experiences. This study offers insights into current crypto-shopping behaviors and discusses future research exploring the broader impacts and potential shifts in the crypto-consumer landscape.

cs.CY↗

arXiv2025

Generative AI in Academic Writing: A Comparison of DeepSeek, Qwen, ChatGPT, Gemini, Llama, Mistral, and Gemma

DeepSeek v3, developed in China, was released in December 2024, followed by Alibaba's Qwen 2.5 Max in January 2025 and Qwen3 235B in April 2025. These free and open-source models offer significant potential for academic writing and content creation. This study evaluates their academic writing performance by comparing them with ChatGPT, Gemini, Llama, Mistral, and Gemma. There is a critical gap in the literature concerning how extensively these tools can be utilized and their potential to generate original content in terms of quality, readability, and effectiveness. Using 40 papers on Digital Twin and Healthcare, texts were generated through AI tools based on posed questions and paraphrased abstracts. The generated content was analyzed using plagiarism detection, AI detection, word count comparisons, semantic similarity, and readability assessments. Results indicate that paraphrased abstracts showed higher plagiarism rates, while question-based responses also exceeded acceptable levels. AI detection tools consistently identified all outputs as AI-generated. Word count analysis revealed that all chatbots produced a sufficient volume of content. Semantic similarity tests showed a strong overlap between generated and original texts. However, readability assessments indicated that the texts were insufficient in terms of clarity and accessibility. This study comparatively highlights the potential and limitations of popular and latest large language models for academic writing. While these models generate substantial and semantically accurate content, concerns regarding plagiarism, AI detection, and readability must be addressed for their effective use in scholarly work.

cs.CY↗

arXiv2025

OpenAI ChatGPT interprets Radiological Images: GPT-4 as a Medical Doctor for a Fast Check-Up

OpenAI released version GPT-4 on March 14, 2023, following the success of ChatGPT, which was announced in November 2022. In addition to the existing GPT-3 features, GPT-4 can interpret images. To achieve this, the processing power and model have been significantly improved. The ability to process and interpret images goes far beyond the applications and effectiveness of artificial intelligence. In this study, we first explored the interpretation of radiological images in healthcare using artificial intelligence (AI). Then, we experimented with the image interpretation capability of the GPT-4. In this way, we addressed the question of whether artificial intelligence (AI) can replace a healthcare professional (e.g., a medical doctor) or whether it can be used as a decision-support tool that makes decisions easier and more reliable. Our results showed that ChatGPT is not sufficient and accurate to analyze chest X-ray images, but it can provide interpretations that can assist medical doctors or clinicians.

cs.CV↗

arXiv2024

Artificial Intelligence, VR, AR and Metaverse Technologies for Human Resources Management

Human Resources (HR) technology solutions encompass software and hardware tools designed to automate HR processes, gather, process, and analyze data, utilize it for strategic decision-making, and execute HR professionals' tasks while prioritizing security and privacy considerations. As with numerous other domains, Digital Transformation and emerging technologies have commenced integration into HR processes. These technologies are utilized by HR professionals and various stakeholders involved in HR operations. This study evaluates the utilization of Artificial Intelligence (AI), Virtual Reality (VR), Augmented Reality (VR), and the Metaverse within HR management, focusing on current trends and potential opportunities. A survey was conducted to gauge HR professionals' perceptions and critiques regarding these technologies. Participants were the HR department officers, academicians who specialized in HR and staff who had courses at diverse levels about HR. The acquired results were subjected to comparative analysis within this article.

cs.CY↗

arXiv2022

Authentication and Billing Scheme for The Electric Vehicles: EVABS

The need for different energy sources has increased due to the decrease in the amount and the harm caused to the environment by its usage. Today, fossil fuels used as an energy source in land, sea or air vehicles are rapidly being replaced by different energy sources. The number and types of vehicles using energy sources other than fossil fuels are also increasing. Electricity stands out among the energy sources used. The possibility of generating electricity that is renewable, compatible with nature and at a lower cost provides a great advantage. For all these reasons, the use of electric vehicles is increasing day by day. Various solutions continue to be developed for the charging systems and post-charge billing processes of these vehicles. As a result of these solutions, the standards have not yet been fully formed. In this study, an authentication and billing scheme is proposed for charging and post-charging billing processes of electric land vehicles keeping security and privacy in the foreground. This scheme is named EVABS, which derives from the phrase "Electric Vehicle Authentication and Billing Scheme". An authentication and billing scheme is proposed where data communication is encrypted, payment transactions are handled securely and parties can authenticate over wired or wireless. The security of the proposed scheme has been examined theoretically and it has been determined that it is secure against known attacks.

cs.CR↗

arXiv2021

Video or Image Transmission Security for ESP-EYE IoT device used in Business Processes

Internet of Things is the name of a communication network that is formed by physical objects such as RFID tags, sensors and some lightweight development platforms that have the ability to connect to the internet. While the devices can communicate among themselves in this network, they can also be part of a large network. The data produced by those physical objects which are the member of IoT network are processed by different methods and the outputs obtained are used in processes such as decision making and learning. With this aspect of the Internet of Things, it affects all areas of human life and its number is increasing day by day. These devices appear to have security gaps due to their limited resources, their wide range of usage area and incomplete security standards. These devices, which are located in people's living areas, manufacturing and business processes also cause difficulties in protecting privacy. In this study, a solution has been developed for the communication security of the internet of things called ESP-Eye which includes a camera, wireless communication module and face recognition software. The proposed solution was implemented on the ESP-Eye.

cs.OH↗

arXiv2021

Secure Charging and Payment System for Electric Land Vehicles with Authentication Protocol

It is obvious that fossil fuels are a limited resource and will be replaced by other energy sources in the future considering economic and en-vironmental problems. Electricity comes to the forefront among the sources that are candidates to replace fossil fuels. In the near future, electric land, air and sea vehicles will start to take more place in daily life. For this reason, systems for the charging systems of these devices and post-charge payments have been developed. There is no general standard on this issue yet. In this study, a charge and payment system, which is safe against known cyber-attacks for use in electric land ve-hicles, and which prioritizes privacy, is proposed. A system has been proposed to verify each other wired or wirelessly with an authentication protocol, where the data communication is encrypted, and the payment transactions are performed securely and invoiced to the vehicle owners.

cs.CR↗

arXiv2021

Digital Twin As A Cost Reduction Method

Many fields have been affected by the introduction of concepts such as sensors, industry 4.0, internet of things, machine learning and artificial intelligence in recent years. As a result of the interaction of cyber physical systems with these concepts, digital twin model has emerged. The concept of digital twin has been used in many areas with its emergence. The use of this model has made significant gains, especially in decision making processes. The gains in decision making processes contribute to every field and cause changes in terms of cost. In this study, the historical development of the concept of digital twin has been mentioned and general information about the usage areas of digital twin has been given. In the light of this information, the cost effect of the digital twin model, therefore its appearance from the cost accounting window and its use as a cost reduction method were evaluated. This study was carried out in order to shed light on the studies with the insufficient resources in the Turkish literature and the cost accounting perspective.

cs.OH↗

arXiv2021

Analysis of the Visitor Data of a Higher Education Institution Website

In todays world, the internet affects every aspect of human life; it has caused changes in corporate websites as well as in many other areas. Corporate websites should be more dynamic, more interactive, and more compatible with new technologies. The interaction of the website with users, search engines, and other devices has to be examined by experts, and improvements and changes should be made for this interaction. In this study, a higher education institution website was examined. Visitor data collected between 2013 and 2019 were used for the analysis. In the study, which includes a wide range of examinations and data, important findings from traffic analysis to development suggestions were included. In particular, useful information has been obtained through the compatibility of the site with mobile devices, optimization of pictures and videos, geographical features of users, language options, and density analysis of the content accessed over time.

cs.CY↗

arXiv2021

Classification of Documents Extracted from Images with Optical Character Recognition Methods

Over the past decade, machine learning methods have given us driverless cars, voice recognition, effective web search, and a much better understanding of the human genome. Machine learning is so common today that it is used dozens of times a day, possibly unknowingly. Trying to teach a machine some processes or some situations can make them predict some results that are difficult to predict by the human brain. These methods also help us do some operations that are often impossible or difficult to do with human activities in a short time. For these reasons, machine learning is so important today. In this study, two different machine learning methods were combined. In order to solve a real-world problem, the manuscript documents were first transferred to the computer and then classified. We used three basic methods to realize the whole process. Handwriting or printed documents have been digitalized by a scanner or digital camera. These documents have been processed with two different Optical Character Recognition (OCR) operation. After that generated texts are classified by using Naive Bayes algorithm. All project was programmed in Microsoft Visual Studio 12 platform on Windows operating system. C# programming language was used for all parts of the study. Also, some prepared codes and DLLs were used.

cs.CV↗