Yazar "Kavak, Elif" seçeneğine göre listele

Listeleniyor 1 - 2 / 2
  • [ X ]
    Öğe
    Comparison of Nature-Inspired Optimization Models and Robust Machine-Learning Approaches in Predicting the Sustainable Building Energy Consumption: Case of Multivariate Energy Performance Dataset
    (MDPI, 2025) Keles, Mumine Kaya; Keles, Abdullah Emre; Kavak, Elif; Gorecki, Jaroslaw
    Accurate prediction of building energy loads is essential for smart buildings and sustainable energy management. While machine learning (ML) approaches outperform traditional statistical models at capturing nonlinear relationships, most studies primarily optimize prediction accuracy, overlooking the importance of computational efficiency and feature compactness, which are critical in real-time, resource-constrained environments. This study aims to evaluate whether hybrid nature-inspired feature-selection techniques can enhance the accuracy and computational efficiency of ML-based building energy load prediction. Using the UCI Energy Efficiency dataset, eight ML models (LightGBM, CatBoost, XGBoost, Decision Tree, Random Forest, Extra Trees, Linear Regression, Support Vector Regression) were trained under feature subsets obtained from the Butterfly Optimization Algorithm (BOA), Grey Wolf Optimization Algorithm (GWO), and a hybrid BOA-GWO approach. Model performance was evaluated using three metrics (MAE, RMSE, and R2), along with training time, prediction time, and the number of selected features. The results show that gradient-boosting models consistently yield the highest accuracy, with CatBoost achieving an R2 of 0.99 or higher. The proposed hybrid BOA-GWO method achieved competitive accuracy with fewer features and reduced training time, demonstrating its suitability for efficient ML deployment in smart building environments. Rather than proposing a new metaheuristic algorithm, this study contributes by adapting a hybrid BOA-GWO feature-selection strategy to the building energy domain and evaluating its benefits under a multi-criteria performance framework. The findings support the practical adoption of hybrid feature-selection-supported ML pipelines for intelligent building systems, energy management platforms, and IoT-based real-time applications.
  • [ X ]
    Öğe
    Estimation of parameters affecting water quality using data mining algorithms
    (Adana Alparslan Türkeş Bilim ve Teknoloji Üniversitesi, 2025) Kavak, Elif; Kaya Keleş, Mümine
    Achieving a sustainable life is one of the most important issues today. In order for future generations to achieve this life, the United Nations (UN) has published the Sustainable Development Goals (SDGs). Among these, the 6th SDG under the title of "Clean Water and Sanitation" is of critical importance in terms of human health, hygiene and protection of ecosystems. Therefore, it reveals the necessity of sustainable management and effective monitoring of water resources. In this context, data mining applications and regression models were developed in the study carried out in order to monitor water quality and predict future changes. Within the scope of the study, five separate data sets were created by bringing together the parameters affecting water quality obtained from drinking water analyses of Adana, Mersin, İzmir, Sakarya and İstanbul provinces of Turkey. Water Quality Index (WQI) was calculated using various physical and chemical parameters. Various algorithms such as Linear Regression (LR), Support Vector Regression (SVR), Artificial Neural Networks (ANN), Decision Tree (DT), Random Forest (RF), Ridge Regression (RR) and Lasso were evaluated comparatively. As a result of the study, it was seen that ANN, SVR and LR models were effective for water quality management among the models evaluated with two different evaluation metrics.