Institution
Adana Science and Technology University
Education•Adana, Turkey•
About: Adana Science and Technology University is a education organization based out in Adana, Turkey. It is known for research contribution in the topics: Aroma & Exergy. The organization has 219 authors who have published 548 publications receiving 7007 citations.
Topics: Aroma, Exergy, Diesel fuel, Thin film, Computer science
Papers
More filters
••
TL;DR: In this article, the authors proposed a hybrid Artificial Neural Network (ANN) model for stock market prediction, which combines Harmony Search (HS) and GA for selecting the most relevant technical indicators, such as simple moving average of close price, momentum close price etc.
Abstract: Integrating metaheuristics and ANN for improved stock price prediction.Both topology of ANN and the number of inputs are optimized.The number of the input variables is reduced to almost its half.HS-ANN has better generalization ability than GA-ANN model.Proposed methodologies outperformed both in statistical and financial terms. Stock market price is one of the most important indicators of a country's economic growth. That's why determining the exact movements of stock market price is considerably regarded. However, complex and uncertain behaviors of stock market make exact determination impossible and hence strong forecasting models are deeply desirable for investors' financial decision making process. This study aims at evaluating the effectiveness of using technical indicators, such as simple moving average of close price, momentum close price, etc. in Turkish stock market. To capture the relationship between the technical indicators and the stock market for the period under investigation, hybrid Artificial Neural Network (ANN) models, which consist in exploiting capabilities of Harmony Search (HS) and Genetic Algorithm (GA), are used for selecting the most relevant technical indicators. In addition, this study simultaneously searches the most appropriate number of hidden neurons in hidden layer and in this respect; proposed models mitigate well-known problem of overfitting/underfitting of ANN. The comparison for each proposed model is done in four viewpoints: loss functions, return from investment analysis, buy and hold analysis, and graphical analysis. According to the statistical and financial performance of these models, HS based ANN model is found as a dominant model for stock market forecasting.
241 citations
••
TL;DR: In this paper, a review of current and past studies to assess the optical and thermal performances of parabolic trough solar collectors, modeling approaches and the potential improvements proposed on behalf of the parabolic-trough solar collector design is presented.
206 citations
••
TL;DR: A geographic information system (GIS)-based MCDA approach and fuzzy analytical hierarchy process (AHP) and technique for order preference by similarity to ideal solution (TOPSIS) methods are applied to choose the optimal EVCS sites.
162 citations
••
TL;DR: In this paper, the electrical percolation thresholds of different carbon-based nano-and micro-scale materials in cementitious composites were investigated under uniaxial compressive loading.
Abstract: An experimental study was carried out to understand the electrical percolation thresholds of different carbon-based nano- and micro-scale materials in cementitious composites. Multi-walled carbon nanotubes (CNTs), graphene nanoplatelets (GNPs) and carbon black (CB) were selected as the nano-scale materials, while 6 and 12 mm long carbon fibers (CF6 and CF12) were used as the micro-scale carbon-based materials. After determining the percolation thresholds of different electrical conductive materials, mechanical properties and piezoresistive properties of specimens produced with the abovementioned conductive materials at percolation threshold were investigated under uniaxial compressive loading. Results demonstrate that regardless of initial curing age, the percolation thresholds of CNT, GNP, CB and CFs in ECC mortar specimens were around 0.55%, 2.00%, 2.00% and 1.00%, respectively. Including different carbon-based conductive materials did not harm compressive strength results; on the contrary, it improved overall values. All cementitious composites produced with carbon-based materials, with the exception of the control mixtures, exhibited piezoresistive behavior under compression, which is crucial for sensing capability. It is believed that incorporating the sensing attribute into cementitious composites will enhance benefits for sustainable civil infrastructures.
134 citations
••
TL;DR: In this paper, the performance of a parabolic trough solar collector using single-walled carbon nanotubes (SWCNTs)-Therminol® VP-1 nanofluid were numerically investigated and presented.
118 citations
Authors
Showing all 246 results
Name | H-index | Papers | Citations |
---|---|---|---|
Hasim Kelebek | 28 | 113 | 2383 |
Gürkan Yıldırım | 25 | 50 | 1529 |
Zafer Erbay | 24 | 51 | 1800 |
S. Yılmaz | 18 | 36 | 750 |
Mehmet Tumay | 17 | 104 | 1055 |
Abdullah Yesil | 16 | 49 | 902 |
Hasan Kurtaran | 14 | 39 | 1383 |
Gözde Baydemir | 14 | 26 | 981 |
Naghdali Choupani | 14 | 53 | 545 |
Abdullah Algin | 14 | 42 | 518 |
Erinç Uludamar | 14 | 31 | 647 |
Mustafa Akyol | 13 | 53 | 795 |
Osman Sivrikaya | 13 | 40 | 569 |
A. Ersoy | 13 | 25 | 832 |
Mustafa Laman | 13 | 42 | 594 |