Identifying the interactions of multi-criteria in Turkish discourse segmentation

Investigating the performance of segmentation methods with deep learning models for sentiment analysis on turkish informal texts Kurt, Fatih; Karagöz, Pınar; Department of Information Systems (2018) This work investigates segmentation approaches for informal short texts in morphologically rich languages in order to e ectively classify the sentiment. The two building blocks of the proposed work in this thesis are segmentation and deep neural network model building. Segmentation focuses on preprocessing of text with di erent methodologies. These methodologies are grouped under four distinct approaches; namely, morphological, sub-word, tokenization, and hybrid approaches. There is mostly multiple numbers ...
Configuration of Neural Networks for the Analysis of Seasonal Time Series Taşkaya Temizel, Tuğba (2005-08-25) Time series often exhibit periodical patterns that can be analysed by conventional statistical techniques. These techniques rely upon an appropriate choice of model parameters that are often difficult to determine. Whilst neural networks also require an appropriate parameter configuration, they offer a way in which non-linear patterns may be modelled. However, evidence from a limited number of experiments has been used to argue that periodical patterns cannot be modelled using such networks. In this paper, ...
Modelling the evolution of demand forecasts in a production-distribution system Yücer, Cem Tahsin; Meral, Fatma Sedef; Department of Industrial Engineering (2006) In this thesis, we focus on a forecasting tool, Martingale Model of Forecast Evolution (MMFE), to model the evolution of forecasts in a production-distribution system. Additive form is performed to represent the evolution process. Variance-Covariance (VCV) matrix is defined to express the forecast updates. The selected demand pattern is stationary and it is normally distributed. It follows an Autoregressive Order-1 (AR(1)) model. Two forecasting procedures are selected to compare the MMFE with. These are MA...
Development of a screening model for polymer flooding in multi-layer reservoirs ZarePakzad, Negar; Durgut, İsmail; Artun, Emre; Department of Petroleum and Natural Gas Engineering (2018) Polymer flooding is a chemical enhanced oil recovery method which aims to increase oil production from a water flooded oil reservoir by increase in water viscosity and reduction in water-oil mobility ratio. These changes result in significant increase in sweep efficiency of water comparing with water-only flooding technique. The objective of this study is to analyze the behavior of multilayer reservoirs under polymer flooding process, considering effects of reservoir characteristics, polymer properties and ...
Developing an impact evaluation framework for product designers inspired by the capability approach: a case study on the Philips Chulha Marel, Floris van der; Işık, Figen; Keyson, David V.; Department of Industrial Design (2012) Within the field of Product Design there is an increasing interest in designing with emerging markets. Considering how long people have already been concerned with increasing global living standards it is surprising how little has been achieved. This suggests our current methods are insufficient. The Capability Approach (CA) by Amartya Sen offers a new way of assessing inequality and poverty, focusing on what people have reason to value to be or do. Products can be means to achieve these beings and doings. ...

Citation Formats

M. T. Yöndem, “Identifying the interactions of multi-criteria in Turkish discourse segmentation,” Ph.D. - Doctoral Program, Middle East Technical University, 2001.