Endüstri Mühendisliği Bölümü Koleksiyonu

Permanent URI for this collectionhttps://hdl.handle.net/20.500.11779/1942

Browse

Filters

2014 - 201928

Settings

Start date: 2014End date: 2019

Search Results

Now showing 1 - 10 of 28
  • Conference Object
    Dialogue Enhancement Using Kernel Additive Modelling
    (Institute of Electrical and Electronics Engineers Inc., 2015-05-01) Liutkus, A.; Kırbız, Serap; Cemgil, A. Taylan
    It is a major problem for the sound engineers to find the right balance between the dialogue signals and the ambient sources. This problem also makes one of the main causes of the audience concerns. The audience wants to arrange the sound balance based on their personal preferences, listening environment and their hearing. In this work, a method is proposed for enhancing the dialogue signals in stereo recordings that consist of more than one source. The kernel additive modelling that has been used successfully in sound source separation is used to extract the dialogues and the ambient sources from the movie sounds. The separated dialogue and ambient sources can later be upmixed by the user to make a personal mix. The separation performance of the proposed method is evaluated on the sounds generated by mixing the sources which were taken from the only dialogue and only music parts of the movies. It has been shown that the Kernel Additive Modelling (KAM) based method can be successfully used for dialogue enhancement. © 2015 IEEE.
  • Article
    Stokastik Süreler İçeren Kapasite Kısıtlı Parti Büyüklüğü Belirleme Problemi
    (EJOSAT - DergiPark, 2019-08-31) Taş, Duygu
    Bu makalede üretim ve kurulum süreleri stokastik olan kapasite kısıtlı çok ürünlü dinamik parti büyüklüğü belirleme problemi ele alınmıştır. Bu problemde tüm sürelerin stokastik olduğu durum göz önünde bulundurularak hem verimli hem de güvenilir üretim planları elde edilmektedir. Ele alınan problemin amacı klasik üretim maliyetleri ve ek mesai maliyetlerinden oluşan toplam maliyeti en küçüklemektir. Klasik maliyetler, üretim, kurulum ve envanter tutmaktan kaynaklanmaktadır. Ek mesai maliyetleri ise makinenin zaman kapasitesini aşacak şekilde kullanılmasından dolayı ortaya çıkmaktadır. Öncelikle, belirli bir üretim ve kurulum planı için beklenen ek mesai süresini kesin olarak hesaplayan bir prosedür önerilmiştir. Problemi etkin bir şekilde çözmek için tabu algoritmasına dayanan bir çözüm yaklaşımı geliştirilmiştir. Bu yaklaşım üç aşamadan oluşmaktadır: Başlangıç, iyileştirme ve planlama. Algoritmanın ilk aşamasında olurlu planlar üreten bir başlangıç metodu önerilmiştir. Bulunan planlar makalede önerilen tabu arama metoduyla iyileştirilmektedir. Planlama aşamasında, yerel arama metodunun bulduğu çözümleri iyileştirmek için bir doğrusal programlama modeli geliştirilmiştir. Çözüm yöntemimizin performansı literatürde yayınlanmış alt sınırlar kullanılarak onaylanmıştır. Ayrıca, sonuçlar tabu arama yöntemimizin makul sürelerde çok iyi çözümler elde ederek iyi performans sergilediğini göstermektedir.
  • Article
    Citation - WoS: 12
    Citation - Scopus: 19
    Minimizing the Misinformation Spread in Social Networks
    (Taylor and Francis, 2019-11-21) Güney, Evren; Kuban, İ. Kuban Altınel; Tanınmış, Kübra; Aras, Necati; Altinel, I. Kuban
    The Influence Maximization Problem has been widely studied in recent years, due to rich application areas including marketing. It involves finding k nodes to trigger a spread such that the expected number of influenced nodes is maximized. The problem we address in this study is an extension of the reverse influence maximization problem, i.e., misinformation minimization problem where two players make decisions sequentially in the form of a Stackelberg game. The first player aims to minimize the spread of misinformation whereas the second player aims its maximization. Two algorithms, one greedy heuristic and one matheuristic, are proposed for the first player’s problem. In both of them, the second player’s problem is approximated by Sample Average Approximation, a well-known method for solving two-stage stochastic programming problems, that is augmented with a state-of-the-art algorithm developed for the influence maximization problem.
  • Article
    Citation - WoS: 6
    Citation - Scopus: 6
    A Strong Integer Programming Formulation for Hybrid Flowshop Scheduling
    (Taylor & Francis, 2019-09-09) Ağralı, Semra; Ünal, A. Tamer; Taşkın, Z. Caner
    We consider a hybrid flowshop scheduling problem that includes parallel unrelated discrete machines or batch processing machines in different stages of a production system. The problem is motivated by a bottleneck process within the production system of a transformer producer located in the Netherlands. We develop an integer programming model that minimises the total tardiness of jobs over a finite planning horizon. Our model is applicable to a wide range of production systems organised as hybrid flowshops. We strengthen our integer program by exploiting the special properties of some constraints in our formulation. We develop a decision support system (DSS) based on our proposed optimisation model. We compare the results of our initial optimisation model with an improved formulation as well as with a heuristic that was in use at the company before the implementation of our DSS. Our results show that the improved optimisation model significantly outperforms the heuristic and the initial optimisation model in terms of both the solution time and the strength of its linear programming relaxation.
  • Article
    Citation - WoS: 8
    Citation - Scopus: 8
    Zaman Pencereli ve Değişken Başlama Zamanlı Bir Araç Rotalama Problemi için Sütun Türetme Temelli Matsezgiseller
    (DergiPark, 2019-06-25) Küçükaydın, Hande
    In this study, a vehicle routing problem with time windows is investigated, where the costs depend on the total duration of vehicle routes and the starting time from the depot for each vehicle is determined by a decision maker. In order to solve the problem, two column generation based mat-heuristics are developed, where the first one makes use of the iterated local search and the second one uses the variable neighbourhood search. In order to assess the accuracy of the mat-heuristics, they are first compared with an exact algorithm on small instances taken from the literature. Since their performance are quite satisfactory, they are further tested on 87 large instances by running each algorithm 3 times for each instance. The computational results prove that the mat-heuristic using the variable neighbourhood search outperforms the other one. Hence, this enables to obtain a good feasible solution in a very short time when it is not possible to solve large instances with an exact solution method in a reasonable CPU time.
  • Article
    Citation - WoS: 2
    Citation - Scopus: 5
    Increasing Procurement Efficiency Through Optimal E-Commerce Enablement Scheduling
    (Emerald Group Publishing Ltd., 2019-06-03) Özlük, Özgür; Cholette, Susan; Clark, Andrew G
    Purpose: This study aims to show how cost savings can be achieved through optimizing the scheduling of e-commerce enablements. The University of California is one of the largest, most prestigious public education and research systems in the world, yet diminished state support is driving the search for system-wide cost savings. Design/methodology/approach: This study documents the preparation for and rollout of an e-procurement system across a subset of campuses. A math programing tool was developed for prioritizing the gradual rollout to generate the greatest expected savings subject to resource constraints. Findings: The authors conclude by summarizing the results of the rollout, discussing lessons learned and their benefit to decision-makers at other public institutions. Originality/value: The pilot program comprising three campuses has been predicted to yield $1.2m in savings over a one-year period; additional sensitivity analysis with respect to savings, project timelines and other rollout decisions illustrate the robustness of these findings.
  • Article
    Citation - WoS: 65
    Citation - Scopus: 72
    Carbon Price Forecasting Models Based on Big Data Analytics
    (Taylor and Francis Ltd., 2019-02-17) Çanakoğlu, Ethem; Ağralı, Semra; Yahşi, Mustafa
    After the establishment of the European Union's Emissions Trading System (EU-ETS) carbon pricing attracted many researchers. This paper aims to develop a prediction model that anticipates future carbon prices given a real-world data set. We treat the carbon pricing issue as part of big data analytics to achieve this goal. We apply three fundamental methodologies to characterize the carbon price. First method is the artificial neural network, which mimics the principle of human brain to process relevant data. As a second approach, we apply the decision tree algorithm. This algorithm is structured through making multiple binary decisions, and it is mostly used for classification. We employ two different decision tree algorithms, namely traditional and conditional, to determine the type of decision tree that gives better results in terms of prediction. Finally, we exploit the random forest, which is a more complex algorithm compared to the decision tree. Similar to the decision tree, we test both traditional and conditional random forest algorithms to analyze their performances. We use Brent crude futures, coal, electricity and natural gas prices, and DAX and S&P Clean Energy Index as explanatory variables. We analyze the variables' effects on carbon price forecasting. According to our results, S&P Clean Energy Index is the most influential variable in explaining the changes in carbon price, followed by DAX Index and coal price. Moreover, we conclude that the traditional random forest is the best algorithm based on all indicators. We provide the details of these methods and their comparisons.
  • Article
    Citation - WoS: 6
    Citation - Scopus: 6
    Optimal Keyword Bidding in Search-Based Advertising With Budget Constraint and Stochastic Ad Position
    (Taylor & Francis, 2019-04-20) Özlük, Özgür; Selçuk, Barış; Küçükaydın, Hande
    This paper analyses the search-based advertising problem from an advertiser’s view point, and proposes optimal bid prices for a set of keywords targeted for the advertising campaign. The advertiser aims to maximise its expected potential revenue given a total budget constraint from a search-based advertising campaign. Optimal bid prices are formulated by considering various characteristics of the keywords such that the expected revenue from a keyword is a function of the ad’s position on the search page, and the ad position is a stochastic function of both the bid price and the competitive landscape for that keyword. We explore this problem analytically and numerically in an effort to generate important managerial insights for campaign setters.
  • Article
    Citation - WoS: 8
    Citation - Scopus: 8
    Risk Averse Investment Strategies for a Private Electricity Generating Company in a Carbon Constrained Environment
    (Taylor & Francis, 2019-04-12) Çanakoğlu, Ethem; Ağralı, Semra; Adıyeke, Esra
    We study a private electricity generating company that plans to enter a partially regulated market that operates under an active cap and trade system. There are different types of thermal and renewable power plants that the company considers to invest in over a predetermined planning horizon. Thermal power plants may include a carbon capture and storage technology in order to comply with the carbon limitations. We develop a time-consistent multi-stage stochastic optimization model for this investment problem, where the objective is to minimize the conditional value at risk (CV@R) of the net present value of the profit obtained through the planning horizon. We implement the model for a hypothetical generating company located in Turkey. The results show that the developed model is appropriate for determining risk averse investment strategies for a company that operates under carbon restricted market conditions.
  • Conference Object
    Capacity Allocation and Pricing Policies for Cloud Computing Service Providers
    (Curran Associates Inc., 2018) Ünlüyurt T.; Özgür Özlük; Afghah, R.; Ünlüyurt, T.; Özlük, Ö.
    The cloud computing is regarded as a paradigm shift in today’s IT world. As cloud computing resources behave like perishable products, revenue management techniques can be applied to increase cloud service provider's total revenue. In this paper, we propose various methods for pricing and capacity allocation. We consider three types of instances offered by the service provider; subscription, on-demand and spot instances. We introduce three allocation and pricing policies and propose different models. We simulate these models on a randomly generated dataset and evaluate the models for different capacities. The results we obtain indicate the sensitivity of revenue to varying policies and demonstrate the potential profit increase for cloud service providers. © 2018, Curran Associates Inc. All rights reserved.