TR Dizin İndeksli Yayınlar / TR Dizin Indexed Publications Collection
Permanent URI for this collectionhttps://hdl.handle.net/11147/7149
Browse
3 results
Search Results
Article Sales History-Based Demand Prediction Using Generalized Linear Models(Süleyman Demirel Üniversitesi, 2019) Özenboy, Başar; Tekir, Selma; Tekir, Selma; 03.04. Department of Computer Engineering; 03. Faculty of Engineering; 01. Izmir Institute of TechnologyIt’s vital for commercial enterprises to accurately predict demand by utilizing the existing sales data. Such predictive analytics is a crucial part of their decision support systems to increase the profitability of the company.In predictive data analytics, the branch of regression modeling is used to predict a numerical response variable like sale amount. In this category, linear models are simple and easy to interpret yet they permit generalization to very powerful and flexible families of models which are called Generalized linear models (GLM). The generalization potential over simple linear regression can be explained twofold: First, GLM relax the assumption of normally distributed error terms. Moreover, the relationship of the set of predictor variables and the response variable could be represented by a set of link functions rather than the sole choice of the identity function. This work models the sales amount prediction problem through the use of GLM. Unique company sales data are explored and the response variable, sale amount is fitted to the Gamma distribution. Then, inverse link function, which is the canonical one in the case of gamma-distributed response variable is used. The experimental results are compared with the other regression models and the classification algorithms. The model selection is performed via the use of MSE and AIC metrics respectively. The results show that GLM is better than the linear regression. As for the classification algorithms, Random Forest and GLM are the top performers. Moreover, categorization on the predictor variables improves model fitting results significantly.Article Art as a Political Act: the Russian Agit-Props of the 1920s(Süleyman Demirel Üniversitesi, 2020) Savaşır, Gökçeçiçek; Güleç, Ece; 01. Izmir Institute of TechnologyEmerged in the mid-19th century, the mechanical reproduction techniques changed the definitions of work of art, artist, and social role of art. These transformations have triggered an extensive sociocultural revolution during the 20th century. Art turned out to be an instrument for guiding the masses; and the communist ideology politicized aesthetics as a strategy of the power. The Russian Constructivists of the 1920s utilized agitation and propaganda techniques (agit-props) in their art for creating an aesthetic language for the political propaganda. This study argues that the Russian avantgarde aiming to bring art into everyday life and urban space became an instrument for aestheticization of politics. The scope is limited to the agit-props appropriated by the Bolshevik power. Dwelling on textual and visual documents from literature, it scrutinizes the topic with a historical interpretation research method. It aims to discuss the agit-props within the framework of politics and aesthetic revolution in everyday life and urban space.Article Methylene Blue Removal of Fixed-Bed Column Reactor With Pumice and Nzvi-Pumice: Experimental and Modeling Study(Süleyman Demirel Üniversitesi, 2019) Genişoğlu, Mesut; Gören, Ayşegül Yağmur; Gören, Ayşegül Yağmur; Recepoğlu, Yaşar Kemal; Ökten, Hatice Eser; Genişoğlu, Mesut; Recepoğlu, Yaşar Kemal; Ökten, Hatice Eser; 03.07. Department of Environmental Engineering; 03.02. Department of Chemical Engineering; 03. Faculty of Engineering; 01. Izmir Institute of TechnologyNano zero-valent iron (nZVI) emerges as a low cost and eco-friendly adsorbent to treat textile wastewater, which is rich in dye content. However nZVI particles can easily agglomerate in aqueous environment due to electrostatic interaction, decreasing their treatment efficiency. Therefore pumice, a low-cost and naturally found porous material with lower specific surface area (2m2/gr), can be used as support material to reduce agglomeration of nZVI. Treatment efficiencies of pumice/nZVI packing (10:0 and 9:1 (w/w)) in column reactor for specified initial methylene blue concentrations (25, 50, 75 and 100 mg/L) were investigated in this study. Adsorption capacities of the adsorbents were calculated as 2.8 and 4.2 mg/g-adsorbent, respectively at 100 mg/L initial methylene blue concentration. Mixed bed column performed significantly better than its pumice-only counterpart for low initial concentrations. Thomas adsorption model was applied to experimental results with a moderate to high predictive power.