Yazar "Ipek, Asli Boru" seçeneğine göre listele

Listeleniyor 1 - 3 / 3
  • [ X ]
    Öğe
    Comparison of harmony search derivatives for artificial neural network parameter optimisation: stock price forecasting
    (Inderscience Enterprises Ltd, 2022) Ozcalici, Mehmet; Dosdogru, Ayse Tugba; Ipek, Asli Boru; Gocken, Mustafa
    This study has been conducted on forecasting, as accurately as possible, the next day's stock price using harmony search (HS) and its variants [improved harmony search (IHS), global-best harmony search (GHS), self-adaptive harmony search (SAHS), and intelligent tuned harmony Search (ITHS) together with artificial neural network (ANN)]. The advantage of the proposed models are that the useful information in the original stock data is found by input variable selection and simultaneously the most proper number of hidden neurons in hidden layer is discovered to mitigate overfitting/underfitting problem in ANN. The results have shown that forecasts made by HS-ANN, IHS-ANN, GHS-ANN, SAHS-ANN, and ITHS-ANN demonstrate a tendency to achieve hit rates above 89%, which is considerably better than previously proposed forecasting models in literature. Hence, ANN models provide more valuable forecasting results for investors to hedge against potential risk in stock markets.
  • [ X ]
    Öğe
    Determining the factor levels for a green supply chain using response surface methodology based discrete event simulation
    (Emerald Group Publishing Ltd, 2024) Dosdogru, Ayse Tugba; Sahin, Yeliz Buruk; Gocken, Mustafa; Ipek, Asli Boru
    Purpose This study aims to optimize the levels of factors for a green supply chain (GSC) while concurrently gaining valuable insights into the dynamic interrelationships among several factors, leading to reductions in CO2 emissions and the maximization of the average service level, thereby enhancing overall supply chain performance. Design/methodology/approach Response surface methodology (RSM) is employed as a technique for multiple response optimization. This study uses a supply chain simulation model that includes decision variables related to the level of inventory control parameters and vehicle capacity. The desirability approach is adopted to achieve optimization objectives by focusing on minimizing CO2 emissions and maximizing service levels while simultaneously determining the optimum levels of considered decision variables. Findings The high R-2 values of 97.38% for CO(2 )and 97.28% for service level, along with adjusted R-2 values reasonably close to predicted values, affirm the models' capability to predict responses accurately. Key significant model terms for CO2 encompassed reorder point, order up to quantity, vehicle capacity, and their interaction effects, while service level is notably influenced by reorder point, order up to quantity, and their interaction effects. The study successfully achieved a high level of desirability value of %99.1 and the validated performance levels confirmed that the results fall within the prediction interval. Originality/value This study introduces a metamodel framework designed to optimize various design parameters for a GSC combining discrete event simulation (DES) and RSM in the form of a simulation optimization model. In contrast to the literature, the current study offers an exhaustive and in-depth analysis of the structural elements of the supply chain, particularly the inventory control parameters and vehicle capacity, which are crucial for comprehending its performance and environmental impact.
  • [ X ]
    Öğe
    Hybrid boosting algorithms and artificial neural network for wind speed prediction
    (Pergamon-Elsevier Science Ltd, 2022) Dosdogru, Ayse Tugba; Ipek, Asli Boru
    Energy sources are an important foundation for national economic growth. The future of energy sources depend on the energy controls. The reserves of fossil energy have declined significantly, and environmental pollution has increased dramatically due to excessive fossil fuel consumption. At this point, wind energy can be used as one of the key source of renewable energy. It has a remarkable importance among the low-carbon energy technologies. The primary aim of wind energy production is to reduce dependence on fossil fuels that affect environment adversely. Therefore, wind energy is analyzed to develop new energy resources. The main issue related to evaluation of the wind energy potential is wind speed prediction. Due to the high volatile and irregular nature of wind speed, wind speed prediction is difficult. To cope with complex data structure, this study presents the development of extreme gradient boosting (XGBoost), adaptive boosting (AdaBoost), and artificial neural network (ANN) within particle swarm optimization (PSO) parameter optimization for hourly wind speed prediction. To compare the proposed hybrid methods, various performance measures, the Pearson's test, and the Taylor diagram are used. The results showed that proposed hybrid methods provide reasonable prediction results for wind speed prediction. (c) 2021 Hydrogen Energy Publications LLC. Published by Elsevier Ltd. All rights reserved.