Doktora Tezleri

Permanent URI for this collectionhttps://hdl.handle.net/20.500.12469/7776

Browse

Now showing 1 - 6 of 6

Analysis of the Stochastic Skiving Stock Problem
(Kadir Has Üniversitesi, 2022) KARACA, TOLGA KUDRET; Samanlıoğlu, Funda
This study addresses the stochastic version of the one-dimensional skiving stock problem (SSP), a rather recent combinatorial optimization challenge. The tradi tional SSP aims to determine the optimal structure that skives (combines) small items of various sizes side-by-side to form as many large items (products) as possible that satisfy a target width. This study considers a single-product and multi-product cases for the stochastic SSP. First, two-stage stochastic programming model is pre sented to minimize the total cost for the single product stochastic SSP which is under random demand. Integration of the Column Generation, Progressive Hedging Al gorithm, and Branch and Bound is proposed where Progressive Hedging Algorithm is embedded in each node of the search tree to obtain the optimal integer solution. Next, the single product stochastic model is extended to the multi-product, multi random variable model with the additional costs as a large size complex model. To examine this large-sized stochastic N P-hard problem, a two-stage stochastic programming approach is implemented. Moreover, as a solution methodology, this problem is handled in two phases. In the first phase, the Dragonfly Algorithm constructs minimal patterns as an input for the next phase. The second phase executes a Sample Average Approximation method that provides solutions for the stochastic production problem with large size scenarios. Results indicate that the two-phase heuristic approach provides good feasible solutions under numerous sce narios without requiring excessive execution time. Finally, a multi-objective case for the deterministic SSP is analyzed where the objectives are minimization of the trim loss (waste), number of items in each product by considering the quality aspect, and number of pattern changes as the set-up. Lexicographic method is preferred for the multi-objective approach where preferences are ranked according to their importance. Column generation and Integer programming are further used to solve the multi-objective problem. In addition, a heuristic is proposed for the same multi objective problem.
Building a Framework for Adopting Lean Principles To Achieve Sustainability in Solar Energy Firms: Turkiye as a Case Study
(Kadir Has Üniversitesi, 2022) Aldewachi, Bilal; Zeki Ayağ
The two terms lean, and sustainability have become one of the most important terms in the field of business because of their role in developing the work in line with increasing profits on the one hand and taking into account the future on the other. Solar energy firms are witnessing great competition to meet energy requirements and suffering from a huge amount of waste, which negatively affects in achieving sustainability. Hence, this study aims to build a framework for solar energy firms to achieve sustainability dimensions through adopting lean principles. The framework will help to solve problems that the solar energy sector is facing. The method in the study included reviewing the literature to examine the founding of the relation between lean and sustainability and using a questionnaire that was directed to the responsible people in Turkish solar energy companies. The results of the survey were analyzed to (1) Discover what the people in charge in solar energy firms think about lean and sustainability; (2) Measure the possible relationship between lean principles and sustainability dimensions by applying a linear regression and non-linear regression test; (3) Using the results of the second point to build the framework. The final results indicated a high level of the relative importance of the two terms from the perspective of the people in charge in the solar energy firms. Besides, the study found a relationship between adopting the two principles of lean, pull, and flow and achieving economic, social resources, and technology dimensions of sustainability; this finding is represented in a framework.
The Effect of Human-Computer Interaction (hci) Factors on Students' E-Learning Acceptance and Success During Covid-19 Pandemic
(Kadir Has Üniversitesi, 2022) Al-Sayid, Fareed; KIRKIL, GOKHAN
The purpose of this study is to investigate the effect of human-computer interaction (HCI) factors on the ease of use and usefulness of e-learning and their success (SS) at the time of the COVID-19 pandemic, to investigate if students' activities on systems moderate the relationship between the main constructs in the proposed model called "e-LASS," which goes beyond technology adoption, and to explore non-linear relationships between these constructs. Moreover, this study proposes a comprehensive model called "e-LASS2," integrating the main (Technology Acceptance Model- TAM) factors included in e-LASS and a unified theory of acceptance and use of technology (UTAUT) factors. To answer the questions that addressed these relations in the first and second parts, the researcher surveyed 103 students from Kadir Has University whose grade and activity logs were accessible, while the data related to the third part were collected via an online survey conducted on 232 students utilizing the Khas Learn system of Kadir Has University in Turkey. The results of the first and second parts show that most of the hypotheses have been proven, three comprehensive conceptual models were developed, the grades in the online courses improved students’ GPA, and the logs moderate the effects of HCI on TAM which together explained 54.9% of the variance in SS (student success), usefulness is the strongest determinant of SS, and non-linear models (cubic, quadratic, logarithmic, and s-curve) performed better in the description for the correlations when compared to linear models. The findings of the integrative approach in the third part reveal that the main predictors of students' success are behavior intention, ease of use, usefulness, visual design, and learner interface interactivity which explained 53.6% of perceived success in using the system.
Models for Electricity Demand Forecasting, Classification, and Imbalance Reduction in Competitive Markets
(Kadir Has Üniversitesi, 2023) Yükseltan, Ergün; Yücekaya, Ahmet Deniz; Bilge, Ayşe
In liberalized energy markets, hourly forecasts of consumers and producers are crucial for efficiently using energy resources and reducing environmental impacts. In this study, the countries’ consumption in the ENTSO-E common network between 2006 and 2018 was analyzed using the time series method. With the created model, short, medium, and long-term demand forecasts are made using Fourier Series Expansion. In order to improve the error rate of short-term forecasts, a hybrid model was created with alternatively created feedback and autoregressive methods. While annual forecasts are made with an average error rate of 6%, the error rate in daily forecasts is around 4.5%. With the hybrid models created, hourly estimates can be made with approximately 1.5% and 1% error rates. Accurate estimations are of great importance in terms of the efficiency of energy markets, and the emergence of energy storage opportunities with the developing technology increases this importance. For this reason, the amount of imbalance was estimated by using the forecast result of the hybrid model in the Turkish Energy Market, and a strategy was developed to reduce the imbalance cost accordingly. With this strategy, simulations have been made for situations with and without storage, and the results have been shared.
The Rest Difference Problem in Round-Robin Tournaments
(Kadir Has Üniversitesi, 2022) Tuffaha, Tasbih; Çavdaroğlu, Burak
Fairness is a key consideration in designing tournament schedules. When two teams play against each other, it is only fair to let them rest the same amount of time before their game. In this study, we aim to reduce, if not eliminate, the difference between the rest durations of opposing teams in each game of a round-robin tournament. The rest difference problem proposed in this study constructs a timetable that determines both the round and the matchday of each game such that the total rest difference throughout the tournament is minimized. We provide a mixed-integer programming formulation and a matheuristic algorithm that solve the problem. Moreover, we de velop a polynomial-time exact algorithm for some special cases of the problem. This algorithm finds optimal schedules with zero total rest difference when the number of teams is a positive-integer power of 2 and the number of games in each day is even. Some theoretical results regarding tournaments with one-game matchdays are also provided.
Trend Forecast and Collection Management in Apparel Retail
(Kadir Has Üniversitesi, 2022) Arkan, Ramazan; Agca Aktunc, Esra; Yücekaya, Ahmet Deniz
This study addresses the new methods and some existing methods with a different approach for trend forecasting and using new trends in the collections in apparel retail industry. There are several approaches to determine the potential of fashion trends. This study describes several approaches for trend forecasting and develops methods for measuring the potential of new fashion trends with unknown potential and without sales data. Firstly, merchandise testing focuses on the process of testing products with new trends. It describes the test store selection, forecasting methods and analyze the accuracy of forecasting with real data. Secondly, Sales-Based Store Network of Stores model is presented to examine cross-store sales similarity and establishes a store network using Collaborative Filtering method as in recommendation systems. A clustering method like K-means is studied to cluster the stores using store network data. Moreover, Distribution of Collection into Store method focuses on distributing the main collection made for a category into each stores using some constraints such as capacity of stores, rates of product attributes in the main collection. Integer programming is used to distribute the collection. The sales potential of the new planned products is crucial. It is necessary to choose the products with highest potential among the hundreds of products. Prediction of products’ demand based on stores addresses a prediction model using sales data containing store features and product attributes with different forecasting methods with different parameters. Furthermore, store-based forecasts are used in Distribution of collection into stores method while selecting the best products for the stores.

Browse

Browsing Doktora Tezleri by Department "Enstitüler, Lisansüstü Eğitim Enstitüsü, Endüstri Mühendisliği Ana Bilim Dalı"