TR-Dizin İndeksli Yayınlar Koleksiyonu

Permanent URI for this collectionhttps://gcris.yasar.edu.tr/handle/123456789/11291

Browse

Now showing 1 - 5 of 5

Citation - WoS: 1
Citation - Scopus: 1
An Empirical Evaluation of Feature Selection Stability and Classification Accuracy
(GAZI UNIV, 2024-06-01) Mustafa Buyukkececi; Mehmet Cudi Okur; Büyükkeçeci, Mustafa; Okur, Mehmet
The performance of inductive learners can be negatively affected by high -dimensional datasets. To address this issue feature selection methods are used. Selecting relevant features and reducing data dimensions is essential for having accurate machine learning models. Stability is an important criterion in feature selection. Stable feature selection algorithms maintain their feature preferences even when small variations exist in the training set. Studies have emphasized the importance of stable feature selection particularly in cases where the number of samples is small and the dimensionality is high. In this study we evaluated the relationship between stability measures as well as feature selection stability and classification accuracy using the Pearson 's Correlation Coefficient (also known as Pearson 's Product -Moment Correlation Coefficient or simply Pearson's r ). We conducted an extensive series of experiments using five filter and two wrapper feature selection methods three classifiers for subset and classification performance evaluation and eight real -world datasets taken from two different data repositories. We measured the stability of feature selection methods using a total of twelve stability metrics. Based on the results of correlation analyses we have found that there is a lack of substantial evidence supporting a linear relationship between feature selection stability and classification accuracy. However a strong positive correlation has been observed among several stability metrics.
Citation - WoS: 5
Citation - Scopus: 5
Electrical Energy Demand Prediction: A Comparison Between Genetic Programming and Decision Tree
(GAZI UNIV, 2020-03-01) Ali Danandeh Mehr; Farzaneh Bagheri; Mir Jafar Sadegh Safari; Mehr, Ali Danandeh; Safari, Mir Jafar Sadegh; Danandeh Mehr, Ali; Bagheri, Farzaneh
Several recent studies have used various data mining techniques to obtain accurate electrical energy demand forecasts in power supply systems. This paper for the first time compares the efficiency of the decision tree (DT) and classic genetic programming (GP) data mining models developed for electrical energy demand forecasting in Nicosia Northern Cyprus. The models were trained and tested using daily electricity consumptions measured during the period 2011-2016 and were compared in terms of three statistical performance indices including coefficient of determination mean absolute percentage error and concordance coefficient. The prediction results showed that the proposed models can be effectively applied to forecasts of electrical energy demand. The results also indicated that the GP is slightly superior to DT in terms of the performance indices.
Enhancing lighting efficiency in deep-plan classroom: Artificial lighting and daylighting
(GAZI UNIV, 2025-03-27) Ecenur Kizilorenli; Yonca Yaman; Ilknur Uygun
Insufficient light distribution throughout the classroom has a negative impact on students. Therefore it is crucial to implement effective daylighting and artificial lighting strategies in educational buildings. To address this issue a combination of a horizontal daylight tubes and an overhang was proposed for a classroom at the selected university. The aim was to enhance the availability of daylight reduce glare and improvement of the artificial lighting system performance. The goal is to achieve a Spatial Daylight Autonomy (sDA) of at least 55% and an Annual Sunlight Exposure (ASE) of no more than 10% in the designated analysis area as stipulated by the daylight assessment criteria outlined in LEEDv4 standards. In addition to the improvements in the daylight performance of the classroom an artificial lighting system was proposed to replace the existing system which creates homogeneous and sufficient lighting. Reducing the energy consumption of the proposed system is also among the desired targets while evaluating the proposed systems Rhinoceros and ClimateStudio were used for daylight simulations and DIALux was used for artificial lighting simulations. The results show that proposed solutions were successful as intended. The sDA value for the zone with the lowest initial value was improved from 1.6% to 59.1% while the ASE value for the zone with the highest initial value was improved from 16.1% to 9.7%. Additionally energy consumption was reduced by 72.34%.
Citation - Scopus: 2
Scenario-Based Cellular Automata and Artificial Neural Networks in Urban Growth Modeling
(GAZI UNIV, 2023-03-01) Nur Sipahioglu; Gulen Cagdas; Cagdas, Gulen; Sipahioğlu, Nur
The speed at which cities are growing and developing today cannot be disregarded. Human activities and natural causes are both contributors to urban growth. The relationship between these factors is complex and the complexity makes it difficult for the human mind alone to understand cities. A model that helps reveal the complexity is needed for urban studies. Main objective of this study is to understand the effects of urban planning strategies on the future of the city by utilizing a Cellular Automata and Artificial Neural Networks based simulation model. Driving factors of urban growth according to development scenarios were used in the simulation process. Six different development scenarios were formulated according to the strategic plan of Izmir. Land use and driving factor data used in simulating scenarios were acquired from EarthExplorer and OpenStreetMap databases and produced in QGIS. Future Land Use Simulation Model (FLUS) based on Cellular Automata (CA) and Artificial Neural Networks (ANN) was used. The results were assessed both by using FRAGSTATS which helped calculate fractal dimensions and visual analysis. Fractal dimension results of each scenario showed that the simulation model respected the overall urban complexity. A closer look at each scenario indicated the diverse local growth possibilities for different scenarios. The results show that urban simulation models when used as decision support tools promise a more inclusive and explicit planning process.
Theoretical Exergoenvironmental Analysis of a Tunnel Furnace and Drying System in a Brick Production
(GAZI UNIV, 2024-03-01) Gurhan Tahtali; Hayati Olgun; Mustafa Gunes; Arif Hepbasli
The performance of a tunnel furnace and a tunnel dryer in a brick production was exergoenvironmentally assessed. The real production data of a brick factory in Turkey with a daily production capacity of 392 tons of fired bricks were used in the analysis. The exergoenvironmental factor of the control volume was calculated as 0.87. The specific exergoenvironmental cost of the control volume was determined to be 559.55 euro/h 3.39 eurocent/ kg fired brick and 1.94 eurocent/MJ. The specific exergoeconomic cost and the environmental damage prevention cost were obtained to be 0.41 euro cent/MJ and 1.53 euro cent/MJ respectively. Because the ratio of exergoenvironmental cost to sales price of 2.41 euro cent / kg fired brick was 1.41 (above 1) it was concluded that the brick production in Turkey was not sustainable in terms of exergoenvironmental analysis.

Browse

Browsing TR-Dizin İndeksli Yayınlar Koleksiyonu by Publisher "GAZI UNIV"