Browsing by Author "Dag,H."
Now showing 1 - 4 of 4
- Results Per Page
- Sort Options
Conference Object Citation Count: 0Enhancing Malware Classification: A Comparative Study of Feature Selection Models with Parameter Optimization(Institute of Electrical and Electronics Engineers Inc., 2024) Dağ, Hasan; Dag,H.This study assesses the impact of seven feature selection algorithms (Minimum Redundancy Maximum Relevance (MRMR), Mutual Information (MI), Chi-Square (Chi), Leave One Feature Out (LOFO), Feature Relevance-based Unsupervised Feature Selection (FRUFS), A General Framework for Auto-Weighted Feature Selection via Global Redundancy Minimization (AGRM), and BoostARoota) across two malware datasets (Microsoft and API call sequences) using three machine learning models (Extreme Gradient Boosting (Xgboost), Random Forest, and Histogram-Based Gradient Boosting (Hist Gradient Boosting)). The analysis reveals that no feature selection algorithm uniformly outperforms the others as their effectiveness varies based on the dataset and model characteristics. Specifically, BoostARoota demonstrated significant compatibility with the Microsoft dataset, especially after parameter optimization, whereas its performance varied with the API call sequences dataset, suggesting the need for customized parameter selection. This study highlights the necessity of tailored feature selection approaches and parameter adjustments to optimize machine learning model performance across different datasets. © 2024 IEEE.Conference Object Citation Count: 0Garbage in, Garbage Out: A Case Study on Defective Product Prediction in Manufacturing(Institute of Electrical and Electronics Engineers Inc., 2023) Dağ, Hasan; Ucar,B.E.; Saygut,I.; Duzgun,B.; Demirkiran,F.; Dag,H.Despite their potential business value and invest-ments, data science projects often fail owing to a lack of preparedness, implementation challenges, and poor data quality. This study aimed to develop a machine learning model for predicting defective products in the dyeing process within the manufacturing domain. However, inadequate importance given to data by the involved factory, insufficient data quality, and the lack of the necessary technical infrastructure for data science projects have hindered attaining desired results. This study emphasizes to academic researchers and industry experts the significance of data quality and technical infrastructure, highlights how these deficiencies can impact the success of a data science project, and provides several recommendations. © 2023 IEEE.Conference Object Citation Count: 0Optimizing Collective Building Management through a Machine Learning-based Decision Support System(Institute of Electrical and Electronics Engineers Inc., 2023) Dağ, Hasan; Kiran,H.; Dogan,E.; Dag,H.; Ozyuruyen,B.; Cakar,T.This study presents the design, implementation, and evaluation of a Decision Support System (DSS) developed for Collective Building Management. Given the potential advantages of machine learning techniques in this domain, the research explores how these techniques can be used to improve collective building management. The dataset consists of 824,932 records and 15 attributes, after preprocessing the data to fill in missing values with the median. The random forest algorithm was chosen for model training and achieved a performance rate of 71.2%. This model can be used to optimize decision processes in collective building management. The proposed prototype is notable for its ability to automatically generate operational plans. In conclusion, machine learning-based DSSs are effective tools for collective building management. © 2023 IEEE.Conference Object Citation Count: 0Towards Better Cyber Security Consciousness: The Ease and Danger of OSINT Tools in Exposing Critical Infrastructure Vulnerabilities(Institute of Electrical and Electronics Engineers Inc., 2023) Ecevit, Mert İlhan; Dağ, Hasan; Naqvi,N.Z.; Creutzburg,R.; Dag,H.This article explores open-source intelligence (OS-INT) to identify the vulnerabilities and loopholes in power grid systems, focusing on an electrical distribution company operating in Turkey. The study emphasizes the potential risks of sharing publicly available information on social media accounts, websites, reports, and press releases which most companies overlook. It highlights that individuals or adversaries can exploit this information to harm companies and countries that may not be fully aware of these vulnerabilities. OSINT tools can efficiently gather interpretable data on a company, which companies unknowingly share. By refining the collected data, the study aims to understand the technologies used, their software versions, and any associated vulnerabilities. Web scraping tools extract data from the company's website, which may contain critical information about updates, ongoing systems, and technologies. The article provides a comprehensive understanding of the potential risks and vulnerabilities associated with sharing sensitive information and the various OSINT tools and techniques that can be used to identify and address these vulnerabilities. The importance of vigilance against the potential harm that remote or unrelated individuals can inflict using OSINT capabilitiesis underscored. This study shows how easy it is to detect vulnerabilities in a critical infrastructure system using OSINT tools. © 2023 IEEE.