Endüstri Mühendisliği Bölümü Koleksiyonu

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

Browse

Now showing 1 - 7 of 7

Analysis of a New Business Model To Fundraise Non-Governmental Organizations Using Fuzzy Cognitive Maps
(IOS Press, 2020) Aytore, Can; Sergi, Duygu; Ucal Sari, Irema; 02.01. Department of Industrial Engineering; 02. Faculty of Engineering; 01. MEF University
Fundraising is one of the most critical issues for non-governmental organizations (NGOs) to carry out their projects. In this paper, a search engine project which aims to find additional financial sources and increase donations for NGOs is proposed. The proposed search engine project is analyzed using fuzzy cognitive maps (FCMs) to define and manage factor influences on the success of the project. FCMs are useful tools to define long term effects of important factors for a system. First casual relations of the factors are determined and then using sigmoid function for learning algorithm, the equilibrium state for the system is obtained. It is found that the factors generating monetary values are the most important ones for the project to be successful in long term.
Citation - WoS: 3
Citation - Scopus: 5
Consumer Loans' First Payment Default Detection: a Predictive Model
(TUBITAK SCIENTIFIC & TECHNICAL RESEARCH COUNCIL, 2020) Sevgili, Türkan; Koç, Utku; 02.01. Department of Industrial Engineering; 02. Faculty of Engineering; 01. MEF University
A default loan (also called nonperforming loan) occurs when there is a failure to meet bank conditions and repayment cannot be made in accordance with the terms of the loan which has reached its maturity. In this study, we provide a predictive analysis of the consumer behavior concerning a loan’s first payment default (FPD) using a real dataset of consumer loans with approximately 600,000 records from a bank. We use logistic regression, naive Bayes, support vector machine, and random forest on oversampled and undersampled data to build eight different models to predict FPD loans. A two-class random forest using undersampling yielded more than 86% on all performance measures: accuracy, precision, recall, and F1-score. The corresponding scores are even as high as 96% for oversampling. However, when tested on the real and balanced dataset, the performance of oversampling deteriorates as generating synthetic data for an extremely imbalanced dataset harms the training procedure of the algorithms. The study also provides an understanding of the reasons for nonperforming loans and helps to manage credit risks more consciously.
Citation - WoS: 49
Citation - Scopus: 52
Extension of Capital Budgeting Techniques Using Interval-Valued Fermatean Fuzzy Sets
(IOS Press, 2022) Sergi, Duygu; Sarı, İrem Uçal; Senapati, Tapan; 02.01. Department of Industrial Engineering; 02. Faculty of Engineering; 01. MEF University
Capital budgeting requires dealing with high uncertainty from the unknown characteristics of cash flow, interest rate, and study period forecasts for future periods. Many fuzzy extensions of capital budgeting techniques have been proposed and used in a wide range of applications to deal with uncertainty. In this paper, a new fuzzy extension of the most used capital budgeting techniques is proposed. In this content, first interval-valued Fermatean fuzzy sets (IVFFS s) are defined, and the algebraic and aggregation operations are determined for interval-valued Fermatean fuzzy (IVFF) numbers. The formulations of IVFF net present value, IVFF equivalent uniform annual value, and IVFF benefit-cost ratio (B/C) methods are generated. To validate the proposed methods, proposed formulations are illustrated with a hypothetical example, and the results are compared with classical fuzzy capital budgeting techniques.
Citation - WoS: 1
Facial Emotion Recognition Using Residual Neural Networks
(2024) Kırbız, Serap; 02.05. Department of Electrical and Electronics Engineering; 02. Faculty of Engineering; 01. MEF University
Facial 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%.
Citation - Scopus: 3
Selection of the Best Face Recognition System for Check in and Boarding Services
(Springer, 2022) Ucal Sarı, İrem; Sergi, Duygu; Kuchta, Dorota; 02.01. Department of Industrial Engineering; 02. Faculty of Engineering; 01. MEF University
Check-in and boarding services are one of the most human oriented pre-flight services in aviation industry. The process of using face recognition systems increase with the aviation 4.0 concept, decreases need for manpower and increases the efficiency of the processes. Therefore, problems, developments and challenges of face recognition in terms of aviation 4.0 are discussed in this chapter to determine the best face recognition system for check in and boarding systems. Analytic hierarchy process and grey relational analysis are used to analyze current system providers. To handle the ambiguity in the linguistic evaluations, fuzzy Z- numbers are used. 10 face recognition system providers are evaluated according to five criteria with the proposed methodology and the results are discussed. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.
Citation - WoS: 1
Citation - Scopus: 2
Simple Nonlinear Optimization-Based Selection of Insulation Material and Window Type in Turkey: Effect of Heating and Cooling Base Temperatures
(2017) Ağralı, Semra; Uçtuğ, Fehmi Görkem; 02.01. Department of Industrial Engineering; 02. Faculty of Engineering; 01. MEF University
The energy-savings of four hypothetical households in different climatic regions of Turkey were calculated via a nonlinear mixed integer optimization model. The ideal insulation material, its optimum thickness, and the ideal window type were determined. The standard degree days method was used with five different base temperatures for heating and five different base temperatures for cooling. The climatic conditions of the region, the properties of the insulation options, the unit price of fuel and electricity and the base temperature are used as model inputs, whereas the combination of selected insulation material with its optimum thickness and window type are given as model outputs. Stone Wool was found to be the ideal wall insulation material in all scenarios. The optimum window type was found to depend on the heating or cooling requirements of the house, as well as the lifetime of insulation. The region where the energy saving actions are deemed most feasible has been identified as Erzurum (Region 4), followed by Antalya (Region 1). Finally, the effect of changing the base temperature on energy savings was investigated and the results showed that an approximate average increase of $15/degrees C in annual savings is possible. Our model can be used by any prospective home-owner who would like to maximize their energy savings.
Citation - WoS: 8
Citation - Scopus: 8
Zaman Pencereli ve Değişken Başlama Zamanlı Bir Araç Rotalama Problemi için Sütun Türetme Temelli Matsezgiseller
(DergiPark, 2019) Küçükaydın, Hande; 02.01. Department of Industrial Engineering; 02. Faculty of Engineering; 01. MEF University
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.

Browse

Browsing Endüstri Mühendisliği Bölümü Koleksiyonu by Scopus Q "Q3"