Repository logoGCRIS

Scopus İndeksli Yayınlar Koleksiyonu

Permanent URI for this collectionhttps://hdl.handle.net/20.500.12573/395

Browse

Filters

2015 - 201922020 - 20254

Settings

COAR Access Rights: search.filters.coarAccessRights.metadata only accessSubject: search.filters.subject.Neural Networks

Search Results

Now showing 1 - 6 of 6
  • Conference Object
    Citation - Scopus: 1
    Drug Repositioning via Entity Transformation in Biomedical Knowledge Systems
    (Springer Science and Business Media Deutschland GmbH, 2025) Erkantarci, B.; Bakal, G.
    The drug discovery process for known diseases is crucial in bioinformatics, given the extensive clinical trials, regulatory approvals, and high costs. Computational in silico methods are essential to mitigate these challenges, as they help identify promising drug candidates, thereby reducing the time and cost associated with drug discovery. An effective strategy in this domain is drug repositioning, where existing drugs, already approved for one disease, are repurposed for treating another. This approach is advantageous as it leverages the established safety profiles of existing drugs, avoiding toxic effects on human metabolism. In this effort, we employed a translational entity embedding-based neural network model to advance drug repositioning efforts. We utilize the Semantic Medline Database (SemMedDB) as the primary source of biomedical entity relationships for model training. The model is validated using repoDB, a gold standard dataset for drug repositioning. Technically, the model will learn to minimize the vector distance between related entities. This distance will serve as the basis for predicting potential drug-disease pairs in drug repositioning, offering a novel computational method to expedite the drug discovery process. © 2025 Elsevier B.V., All rights reserved.
  • Conference Object
    Citation - WoS: 1
    Citation - Scopus: 8
    Short Term Electricity Load Forecasting: A Case Study of Electric Utility Market in Turkey
    (Institute of Electrical and Electronics Engineers Inc., 2015-04) Ishik, Muhammed Yasin; Göze, Tolga; Ozcan, Ihsan; Güngör, Vehbi Çağrı; Aydin, Zafer; Yasin, Muhammed
    With the recent developments in energy sector, the pricing of electricity is now governed by the spot market where a variety of market mechanisms are effective. After the new legislation of market liberalization in Turkey, competition-based on hourly price has received a growing interest in the energy market, which necessitated generators and electric utility companies to add new dimensions to their scope of operation: short-term load and price forecasting. The field has several opportunities though not free from challenges. The dynamic behavior of the market price has caused the electric load to become variable and non-stationary. Furthermore, the number of nodes, in which the load must be predicted, is not constant anymore and can no longer be estimated by experts alone. In this competitive scenario, statistical forecasting methods that can automatically and accurately process thousands of data samples are essential. The purpose of this study is to demonstrate the importance of short-term load forecasting, how it has received a growing interest in Turkey and to propose an artificial neural network that can forecast the short term electricity load. Through detailed performance evaluations, we demonstrate that our forecasting method is capable of predicting the hourly load accurately. © 2017 Elsevier B.V., All rights reserved.
  • Conference Object
    Modelling of Rock Comminution Using Statistical and Soft Computing Analyses – A Case Study on a Laboratory-Scale Jaw Crusher
    (Baski, 2022) Köken, E.
    The present study encompasses a quantitative investigation on rock comminution using statistical and soft computing analyses. For this purpose, physical and mechanical rock aggregate properties were determined for nine different rock types (R1-R9) in Turkey. Then, crushability tests were performed to determine the size reduction ratio (SRR) using a laboratory-scale jaw crusher. Based on statistical and soft computing analyses, five different predictive models (M1 to M5) were established to estimate the SRR in this study. Consequently, the SRR values are associated with water absorption by weight (w<inf>a</inf>), dry unit weight (γ<inf>d</inf>), and aggregate impact value (AIV) of the investigated rocks. However, the individual use of these independent variables results in undulating SRR estimations. Therefore, among the established predictive models, the empirical formulation based on artificial neural networks (ANN) (M5) was found to be the most reliable model with a correlation of determination value (R2) of 0.88. However, the predictive models stated in this study should be implemented to several portable jaw crushers to observe the similarities or difficulties in quantifying SRR as a function of rock properties in future studies. © 2022 Elsevier B.V., All rights reserved.
  • Book Part
    Hosting Capacity Calculation Methods
    (Elsevier, 2025) Oguzhan, Ceylan; Alper, Savasci
    In this chapter, we focus on hosting capacity (HC) calculations, by giving the methods to determine the maximum amount of distributed energy resources (DER) that can be integrated into power distribution network(s) without compromising reliability or performance. We detail methodologies such as power flow-based approaches, probabilistic techniques, and machine learning algorithms, with sample applications of HC calculations. Initially, we focus on power flow-based methods based on simulating power distribution network(s) to assess system voltage, current flow, and stability impacts from DER installations. Then, we will give the probabilistic approaches that use uncertainties in renewable generation and consumer demand, based on statistical techniques and Monte Carlo simulations aiming to reflect these variability. Machine learning (ML) techniques will also be given based on analyzing large data sets, detecting patterns, and predicting system responses. These kinds of methods include regression analysis and neural networks trained on historical data for optimized HC predictions. It should be stated that HC is impacted by several factors, such as network topology, load profiles, and DER characteristics, and these as well will be discussed. We will provide a practical example of an HC calculation on a 141-node distribution network using a step-by-step algorithm in Matpower, with simulation results based on an iterative deterministic method. Then, we will give the broader implications of HC assessments for grid modernization and energy policy, highlighting how accurate calculations support a more decentralized, sustainable, and resilient energy future. © 2025 Elsevier B.V., All rights reserved.
  • Conference Object
    Citation - Scopus: 5
    Development of Knowledge Based Response Correction for a Reconfigurable N-Shaped Microstrip Antenna Design
    (Institute of Electrical and Electronics Engineers Inc., 2015-08) Aoad, Ashrf; Simsek, Murat; Aydin, Zafer
    This study presents the use of prior knowledge of inverse artificial neural network (ANN) to model and optimize a reconfigurable N-shaped microstrip antenna. Three accurate prior knowledge inverse ANNs with large amount training data are proposed where the frequency information is incorporated into the structure of ANN. The complexity of the input/output relationship is reduced by using prior knowledge. Three separate methods of incorporating knowledge in the second step of the training process with a multilayer perceptron (MLP) in the first step are demonstrated and their results are compared to EM simulation. © 2023 Elsevier B.V., All rights reserved.
  • Article
    Citation - WoS: 11
    Citation - Scopus: 12
    Developing New Empirical Formulae for the Resilient Modulus of Fine-Grained Subgrade Soils Using a Large Long-Term Pavement Performance Dataset and Artificial Neural Network Approach
    (Sage Publications inc, 2021-12-17) Fedakar, Halil Ibrahim
    Artificial neural network (ANN) has been successfully used for developing prediction models for resilient modulus (M-r). However, no reliable M-r formula derived from these models has been proposed in previous studies, although engineers/researchers need empirical formulae for hand calculation of M-r. Therefore, this study aimed to propose reliable empirical formulae for the M-r of fine-grained soils using ANN. For this purpose, thousands of ANN models were developed using the long-term pavement performance (LTPP) and external datasets. The input parameters were the percentage of soil particles passing through #200 sieve (P200), silt percentage (SP), clay percentage (CP), liquid limit (LL), plasticity index (PI), maximum dry density ([rho(dry)](max)), optimum moisture content (w(opt)), confining pressure (sigma(c)), and nominal maximum axial stress (sigma(z)). The ANN models were compared with several constitutive models. The results indicate that the constitutive models failed to predict the M-r, and the best M-r predictions were obtained by the ANN-C9 (P200, SP, CP, LL, PI, sigma(c), and sigma(z)), ANN-C10 (P200, SP, CP, [rho(dry)](max), w(opt), sigma(c), and sigma z), and ANN-C11 (P200, SP, CP, LL, PI, [rho(dry)](max), w(opt), sigma(c), and sigma(z)) models. Thus, the structures of these ANN models were formulated and proposed as the new empirical formulae for the M-r of fine-grained soils. Sensitivity analysis was also performed on these ANN models. It was determined that (rho(dry))(max) is the most influential parameter in the ANN-C10 model, and LL is the most influential parameter in the ANN-C9 and ANN-C11 models. On the other hand, sigma(c) and sigma(z) are the least influential parameters.