Endüstri Mühendisliği Bölümü Koleksiyonu
Permanent URI for this collectionhttps://hdl.handle.net/20.500.11779/1942
Browse
3 results
Search Results
Article Citation - WoS: 1Facial Emotion Recognition Using Residual Neural Networks(Aves, 2024-11-08) Kırbız, SerapFacial emotion recognition (FER) has been an emerging research topic in recent years. Recent automatic FER systems generally apply deep learning methods and focus on two important issues: lack of sufficient labeled training data and variations in images such as illumination, pose, or expression-related variations among different cultures. Although Convolutional Neural Networks (CNNs) are widely used in automatic FER, they cannot be used when the number of layers is large. Therefore, a residual technique is applied to CNNs and this architecture is named residual neural network. In this paper, an automatic facial emotion recognition method using residual networks with random data augmentation is proposed on a merged FER dataset consisting of 41,598 facial images of size 48 × 48 pixels from seven basic emotion classes. Experimental results show that ResNet34 with data augmentation performs better than CNN with a classification accuracy of 81%.Article Citation - Scopus: 2Nonlinear Benefit-Cost Optimization-Based Selection of Insulation Material and Window Type: a Case Study in Turkey(Amer Inst Physics, 2017-11-01) Ağralı, Semra; Uctuğ, Fehmi Görkem; Aǧrall, SemraIn this study, we maximize the energy savings of a hypothetical household by choosing an optimal insulation material with its optimal thickness and also the optimal window type. We develop a nonlinear mixed integer optimization model that maximizes the net present value of the benefits obtained by insulation over the lifespan of the house. Savings are calculated based on the gains from the electricity usage for air conditioning during cooling-required days and the fuel usage for heaters in heating-required days. The heat transfer calculations consider conductive, convective, and radiative components simultaneously. The optimization model takes the climate conditions of the region where the house is located, the consumer's desired indoor temperature, and the properties of the insulation options; then, it returns a combination of selected insulation materials with its optimum thickness and window type as output. We applied the optimization model developed to hypothetical houses in four different climatic regions of Turkey for different lifespans. For all reasonable lifespans, the model choses stonewool as the ideal insulation material. For high interest rates, single windows or double-glazed windows are preferable, but as the interest rate decreases and the net present value of the energy-savings increases, the model prefers triple-glazed windows as the ideal material. Erzurum, a city in climatic region 4, characterized by very cold winters and cool summers, was found to require the highest optimum insulation thickness, and the economic return resulting from the above-mentioned energy-saving actions was also found to be the highest in the case of Erzurum. In all the regions, the energy-saving investments were found to be feasible via applying the feasibility assessment techniques of net present value and payback period. The model developed in this study is applicable to any household as long as the required input data are available. Published by AIP Publishing.Article Citation - WoS: 24Citation - Scopus: 23Modeling of Carbon Credit Prices Using Regime Switching Approach(AIP Publishing, 2018-05-01) Çanakoğlu, Ethem; Ağralı, Semra; Adıyeke, Esra; Aǧralı, Semra; Adlyeke, Esra; Aǧrall, SemraIn this study, we analyze the price dynamics of carbon certificates that are traded under the European Union's Emissions Trading System (EU-ETS). With the aim of investigating the joint relations among carbon, electricity, and fuel prices, we model historical prices using several methods and incorporating structural changes, such as econometric time series, regime switching, and multivariate vector autoregression models. We compare the results of the structural model with the results of traditional Markov switching and autoregressive models with breaks and present performance analysis based on the mean average percentage error, root mean squared error, and coefficient of determination. According to these performance tests, models with regimes outperform the approaches where breaks are defined using ex ante dummy variables. Moreover, we conclude that among regime switching models, univariate models are better than multivariate counterparts for modeling carbon price series for the analysis of both in-sample and out-of-samples. Published by AIP Publishing.