Endüstri Mühendisliği Bölümü Koleksiyonu

Bu koleksiyon için kalıcı URI

https://hdl.handle.net/20.500.12939/2083

Listeleniyor 1 - 20 / 56

A two-stage stochastic programming model for comprehensive risk response action selection: A case study in Industry 4.0
(Elsevier Ltd, 2024) Hajipour, Vahid; Di Caprio, Debora; Santos-Arteaga, Francisco J.; Amirsahami, Amirali; Vazifeh Noshafagh, Samira
Effective project risk management is critical in environments where both micro-level and macro-level risks are present. Traditional models often focus on micro-level risks, neglecting broader macroeconomic uncertainties such as geopolitical instability and supply chain disruptions. This research introduces a two-stage stochastic programming model designed to optimize the selection of Risk Response Actions (RRAs) under uncertainty while addressing both types of risk. The model incorporates “here-and-now” decisions at the planning stage and “wait-and-see” decisions as uncertainties unfold, enabling adaptive risk management throughout the project lifecycle. To solve the model efficiently, we employ an evolutionary algorithm combined with Sample Average Approximation (SAA) to handle the computational complexity of multiple scenarios. The model is applied to a real-world case study involving the integration of IoT and ERP systems in a smart factory in Iran, a project characterized by significant macroeconomic and geopolitical risks. Our key contribution lies in providing a comprehensive risk response strategy selection model that simultaneously addresses micro- and macro-level risks while incorporating strategic flexibility through outsourcing decisions. The results demonstrate that our model outperforms traditional deterministic models, offering enhanced resilience against macro-level risks and improved project performance under uncertainty. These findings provide valuable insights for project managers aiming to increase resilience and adaptability in volatile environments. By integrating both internal and external risk factors, our model offers a robust tool for managing complex projects, enhancing decision-making and project outcomes in uncertain conditions.
New hybrid EC-PROMETHEE method with multiple iterations of random weight ranges: step-by-step application in Python
(Elsevier B.V., 2024) Basilio, Marcio Pereira; Pereira, Valdecy; Yiğit, Fatih
The decision-making process consists of finding the best solution to an analyzed problem. This search is carried out in the face of countless interactions when analyzing an alternative criterion by criterion, under which weights are assigned that distinguish the degree of importance they have for the decision-makers. The definition of weight for each criterion gives rise to three lines of thought on the subject. There are objective, subjective, and hybrid methods. This discussion concerns the degree to which experts define the criteria weights. Based on this discussion, we developed a hybrid method to integrate the Entropy and CRITIC methods with the PROMETHEE method, called EC-PROMETHEE. The innovation of this method is that the combination of the Entropy and CRITIC methods does not result in a single set of weights. In reality, the weights generated by each method are used to define each criterion's upper and lower limits. The range of weights generated for each criterion is emulated "n" times and builds a set of weights that are applied to the ranking definition process. The model generates "n" rankings, defining a single ranking. In this article, we demonstrate a step-by-step application of a tool developed in Python called EC-PROMETHEE and use it as an example of the problem of choosing rotary-wing airplanes for application in the military police service. ➢ The method reduces discretion in determining the weights of the criteria; ➢ The innovation lies in the use of a range of weights for criteria; ➢ Consistency in defining the final ranking.
A hybrid approach for the multi-criteria-based optimization of sequence-dependent setup-based flow shop scheduling
(Multidisciplinary Digital Publishing Institute (MDPI), 2024) Yiğit, Fatih; Basilio, Marcio Pereira; Pereira, Valdecy
A key challenge in production management and operational research is the flow shop scheduling problem, characterized by its complexity in manufacturing processes. Traditional models often assume deterministic conditions, overlooking real-world uncertainties like fluctuating demand, variable processing times, and equipment failures, significantly impacting productivity and efficiency. The increasing demand for more adaptive and robust scheduling frameworks that can handle these uncertainties effectively drives the need for research in this area. Existing methods do not adequately capture modern manufacturing environments’ dynamic and unpredictable nature, resulting in inefficiencies and higher operational costs; they do not employ a fuzzy approach to benefit from human intuition. This study successfully demonstrates the application of Hexagonal Type-2 Fuzzy Sets (HT2FS) for the accurate modeling of the importance of jobs, thereby advancing fuzzy logic applications in scheduling problems. Additionally, it employs a novel Multi-Criteria Decision-Making (MCDM) approach employing Proportional Picture Fuzzy AHP (PPF-AHP) for group decision-making in a flow shop scheduling context. The research outlines the methodology involving three stages: group weight assessment through a PPF-AHP for the objectives, weight determination using HT2FS for the jobs, and optimization via Genetic Algorithm (GA), a method that gave us the optimal solution. This study contributes significantly to operational research and production scheduling by proposing a sophisticated, hybrid model that adeptly navigates the complexities of flow shop scheduling. The integration of HT2FS and MCDM techniques, particularly PPF-AHP, offers a novel approach that enhances decision-making accuracy and paves the way for future advancements in manufacturing optimization.
Locating hydrogen fuel stations: A comparative study for Istanbul
(Elsevier Ltd, 2023) Gündüz, Saliha Büşra; Geçici, Ebru; Güler, Mehmet Güray
World's energy sources are depleting while the need for alternative energy resources is increasing. Hydrogen energy is an essential alternative and its use in transportation sector through Hydrogen Fuel Cell Vehicles (HFCV) is increasing day by day. For HFCV to become widely used, however, it is necessary to establish a good infrastructure, i.e., hydrogen should be accessible. In this study, we investigate the problem of locating Hydrogen Refueling Stations (HRS) in İstanbul, the most crowded city of Turkey. The problem is addressed with multi-period set covering model and the different population densities in the city are integrated with a modification of this model. Due to the long computational time required by the multi-period set-covering model, two heuristics, namely the iterative model and the reduced model, are proposed. The results indicate that for a geographically distinct city like İstanbul, using Euclidean distance may yield very drastic conclusions, hence should be avoided. It is also shown that the HRS are densely located in areas with high population, and one should trade-off between the total distance to be travelled by the drivers and being served by one of the closest stations. In a multi-period setting where stations are opened incrementally, the findings from two different heuristics favor different stakeholders: the iterative model offers advantages from the perspective of decision-makers, while the multi-period model with an optimality gap is advantageous from the perspective of customers. We also introduce the partial coverage model, which serves as a combination of set covering and p-median models, to analyze the transition if the demand is fulfilled incrementally, not completely. It turns out that less number of stations are sufficient to meet high demand, but the number increases significantly if all demand should be satisfied.
A novel type-2 hexagonal fuzzy logic approach for predictive safety stock management for a distribution business
(2023) Yiğit, Fatih
Safety stock is an important method to overcome variability in inventory management. The classical approach to safety stock decisions relies on historical demand and lead time statistical data, which may not capture the uncertainty and complexity of the real world. Human knowledge and experience are valuable assets for making better decisions, especially when facing unpredictable situations. The fuzzy method is widely used for employing human intuition for decisions. When fuzzy opinions are input, decisions can be made proactively rather than reactively while benefiting from future predictions. The paper aims to integrate human intuition using Hexagonal Type-2 Fuzzy Sets (HT2FS) for safety stock management. HT2FS is a generalization of Interval Type-2 Fuzzy Sets that can represent more uncertainty in the membership functions. Predictions may be integrated into the safety stock models using human intuition. The proposed model uses novel fuzzy approaches to integrate human intuition into the traditional safety stock model. Applying fuzzy sets to safety stock management allowed experts' opinions under fuzzy logic to be integrated into decision-making. The proposed novel approach uses the centre of gravity method of Polygonal Interval Type-2 Fuzzy sets for defuzzification, which is a computationally efficient method that can handle any shape of the footprint of uncertainty. A mathematical model is developed to validate fuzzy opinions that may replace historical data. The data is received from a real-life case, and human intuition is integrated using an expert's input. After the validation, a real-life numerical example has been considered to illustrate the model and its validity compared to the classical model. The outcomes show that the proposed model may contribute to the classical models, mainly when experts' inputs offer good predictions. When expert opinion on HT2FS is used for a real-life case, the results show that the expert's better representation of future variances lowers total cost by 2.8%. The results, coupled with the sensitivity analysis, underline that the proposed approach may contribute to the literature on safety stock management.
New hybrid EC-Promethee method with multiple iterations of random weight ranges: applied to the choice of policing strategies
(Multidisciplinary Digital Publishing Institute (MDPI), 2023) Basilio, Marcio Pereira; Pereira, Valdecy; Yiğit, Fatih
The decision-making process is part of everyday life for people and organizations. When modeling the solutions to problems, just as important as the choice of criteria and alternatives is the definition of the weights of the criteria. This study will present a new hybrid method for weighting criteria. The technique combines the ENTROPY and CRITIC methods with the PROMETHE method to create EC-PROMETHEE. The innovation consists of using a weight range per criterion. The construction of a weight range per criterion preserves the characteristics of each technique. Each weight range includes lower and upper limits, which combine to generate random numbers, producing “t” sets of weights per criterion, allowing “t” final rankings to be obtained. The alternatives receive a value corresponding to their position with each ranking generated. At the end of the process, they are ranked in descending order, thus obtaining the final ranking. The method was applied to the decision support problem of choosing policing strategies to reduce crime. The model used a decision matrix with twenty criteria and fourteen alternatives evaluated in seven different scenarios. The results obtained after 10,000 iterations proved consistent, allowing the decision maker to see how each alternative behaved according to the weights used. The practical implication observed concerning traditional models, where a single final ranking is generated for a single set of weights, is the reversal of positions after “t” iterations compared to a single iteration. The method allows managers to make decisions with reduced uncertainty, improving the quality of their decisions. In future research, we propose creating a web tool to make this method easier to use, and propose other tools are produced in Python and R.
Blockchain-based framework for supply chain traceability
(World Scientific, 2023) Korkmaz, Elif Baǧnu; Erkayman, Burak
Alcohol counterfeiting, which negatively affects people's lives in terms of economic, health, and social aspects, is one of the crucial problems that arise in many countries. For this reason, information should be made visible and traceable in all current flows of manufactured products from the raw material supplier to the retailer. In this study, a blockchain-based system architecture is proposed to ensure the traceability of raki (an anise-flavored Turkish drink), which is heavily counterfeited in Turkey. The information that adds value to the product is recorded in blocks in the blockchain, which is the building block of the system architecture, and this recorded information can be viewed by the relevant stakeholders. Product traceability is carried out with two smart contracts. With the Asset Registration Smart Contract (ARSC), assets are identified in the digital layer and the lot ID is assigned to the assets. The security of these smart contracts is ensured by storing recorded information in the blockchain, where it cannot be deleted or changed. Hyperledger Fabric, a blockchain platform, is used in the proposed architecture. In addition, QR codes integrated into the system act as a bridge between the physical and digital layers, directing consumers to the blockchain layer for traceability. Thus, the consumer will be able to see all the stages of the product that have transparently reached him and will be able to notice any counterfeiting event that may occur. In this context, it is foreseen that the proposed architecture will prevent raki counterfeiting as much as possible and provide transparency and traceability in all processes from raw material to bottle. This paper is arranged as follows. In Sec. 1, the problem is defined, the solution for the problem is explained, information is given about the technologies proposed for the solution, and current studies on the subject are discussed. In Sec. 2, the system architecture created for traceability is explained in detail. Section 3 describes the results.
Classification of XTEKS companies during COVID-19 pandemic using fuzzy-analytic hierarchy process and fuzzy-C-means
(Springer Science and Business Media Deutschland GmbH, 2023) Yiğit, Fatih
Assessment of companies is vital for an accurate investment decision. Financial ratios are essential performance indicators. However, there is no consensus in their comparison among all financial ratios. Expert opinions are an indispensable resource for such assessment. This study uses an integrated approach to benefit from expert opinions. Clustering is an important area of unsupervised learning. Clustering, when assigned to classes, can also be used for classification. It is vital to classify data to apply for decision-making. This study applies the Fuzzy Analytic Hierarchy Process (FAHP) and Fuzzy C-Means (FCM) for clustering and classification as a part of machine learning. Financial ratios are widely used to compare different companies. This study focuses on companies under the "Textile Leather Index" registered in the Istanbul Stock Exchange (BIST) for applying the proposed model. The study employed current financial results and the positive and negative trends of the last year for classification. The results allow the decision-maker to choose the right company to invest in. Among 17 companies, 2 are classified as A class. To the best of our research, using trend values and integrating FAHP and FCM for classification is new in the literature.
Fuzzy multi-criteria sorting models FMAVT-Sort and FTOPSIS-Sort: features and application within the case studies
(Springer Science and Business Media Deutschland, 2023) Radaev, Alexander; Haktanır, Elif; Yatsalo, Boris; Kahraman, Cengiz
The need to sort alternatives according to ordered categories, especially in problems consisting of a large number of alternatives, makes it effective to use of multi-criteria sorting methods. A family of fuzzy multi-criteria sorting models FMAVT-Sort and FTOPSIS-Sort based on a fuzzy extension of MAVT and TOPSIS methods respectively and the their features are presented. In the developed models, different approaches can be used both for calculating functions of fuzzy numbers and for ranking of fuzzy numbers. Case studies showing the application of the developed models to sort problems related to the Internet of Things and anti-COVID measures are presented.
A value-oriented Artificial Intelligence-as-a-Service business plan using integrated tools and services
(Elsevier Inc., 2023) Hajipour, Vahid; Hekmat, Siavash; Amini, Mohammad
The latest developments in Artificial Intelligence (AI) are the focal point in increasing the performance of other technologies and the evolution of Industry 4.0. Considering the benefits of AI in today's world, businesses must move towards using Integrated AI tools and services. This paper introduces a business model based on AI-as-a-Service (AIaaS), which provides an integrated bundle of AI products and services. The strategic approach, roadmap, and heuristic pricing model provided in this paper can be considered as a benchmark for AIaaS companies.
A novel model for the calculation of safety stock of perishables products with a total waste constraint
(University of Cincinnati, 2023) Yiğit, Fatih; Esnaf, Sakir
Perishable products cover a high percentage of all goods. The variability, long lead times, risk period, and high service level increase the safety stock level. An increase in safety stock will also increase the probability of perished products because of the increased probability of sales of less than stock during shelf life. This study proposes a model for calculating safety stocks of perishable products besides showing the effect of perishability on service level. The effects of long lead times, risk periods, high sales and lead-time variance, and short shelf life adversely affect perished products. The study investigates and proposes a novel model for calculating total expected waste and costs with a waste quantity constraint. A real-life example compares a proposed model with waste constraints and the traditional safety stock model based on costs and waste quantity. The case study shows the better results of the proposed models.
A three-stage fuzzy neutrosophic decision support system for human resources decisions in organizations
(Elsevier Inc., 2023) Yiğit, Fatih
This study proposes an integrated Decision Support System (DSS) with Multi-Criteria Decision-Making (MCDM) to evaluate trainers in organizations and choose the most suitable one(s) for a training program. The clustering stage determines the most appropriate number of trainees to be assigned to a trainer. The proposed model also considers the training budget and the constraint limiting the number of assignments. The proposed model has three stages: Delphi, the Interval-Valued Neutrosophic Analytic Hierarchy Process (IVN-AHP), and Fuzzy C-Means (FCM). The model’s input is expert opinions on various criteria, the candidate assessment score, and the bi-comparison of agreed criteria. Outputs are weights, and the members of each cluster represent possible candidates. We present a case study to demonstrate the applicability of the proposed DSS in a training program assessment. Additional applications of the proposed system include recruitment and promotion
A mathematical interpretation for outbreaks of bacterial meningitis under the effect of time-dependent transmission parameters
(Springer Science and Business Media B.V., 2023) Türkün, Can; Gölgeli, Meltem; Atay, Fatihcan M.
We consider a SIR-type compartmental model divided into two age classes to explain the seasonal exacerbations of bacterial meningitis, especially among children outside of the meningitis belt. We describe the seasonal forcing through time-dependent transmission parameters that may represent the outbreak of the meningitis cases after the annual pilgrimage period (Hajj) or uncontrolled inflows of irregular immigrants. We present and analyse a mathematical model with time-dependent transmission. We consider not only periodic functions in the analysis but also general non-periodic transmission processes. We show that the long-time average values of transmission functions can be used as a stability marker of the equilibrium. Furthermore, we interpret the basic reproduction number in case of time-dependent transmission functions. Numerical simulations support and help visualize the theoretical results.
Sustainable development of art industry and a statistical analysis of the factors that influence the gallery prices of contemporary artworks
(John Wiley and Sons Ltd, 2022) Turan, Fikret Korhan; Tosun, Zeynep
Although art industry has developed significantly, the factors influencing artwork prices and their specific effects are not fully known. With this research, to guide curators, gallery owners, collectors and art investors, as well as artists, first the factors that may influence artwork prices are determined. Then, using a data set from a contemporary art gallery in Istanbul, which of these factors are significant and in which ways they alter the prices are investigated. While previous studies are typically based on auction prices, promoting the economic sustainability of artists, this study employs gallery prices, and different from the existing efforts, it examines the joint impact of the artwork specific factors such as production technique and the number of editions, together with the artist specific factors including gender, education level and the field of study. Statistical findings suggest that there is no significant difference between the prices of artworks created by the artists who have a formal education in fine arts and those who do not. However, it is found that artists, particularly the female ones, can increase the prices of their artworks by having a graduate level education. Also, it is observed that increasing the number of editions negatively affects artwork prices, and the artworks created in print techniques have significantly lower prices than the artworks produced in other techniques. Though, it is detected that print artworks are less affected from the price reductions induced by the increase in the number of editions, compared to the artworks produced in other techniques.
Maturing the scrum framework for software projects portfolio management: a case study-oriented methodology
(Institute of Electrical and Electronics Engineers Inc., 2022) Vazifeh-Noshafagh, Samira; Hajipour, Vahid; Jalali, Sajjad; Di Caprio, Debora; Santos-Arteaga, Francisco Javier
In the modern era, information technology-based solution providers are encountering a growing request for satisfying the versatile requirements of their customers in terms of software applications. To this end, specific approaches have been designed to streamline the way of accomplishing software projects in an efficient manner, i.e., agile-oriented frameworks. Even though previous studies have highlighted variations of such a framework, the literature has not addressed the adaptations required in response to the gradual maturity of a wide-ranging case study dealing with software applications. Following a case study-oriented methodology, this paper focuses on elaborating a set of workable maneuvers to mature the Scrum framework when applied to portfolio management. Particularly, we highlight how Scrum should be adapted from its basic setting to a vision and goal-oriented configuration or Scrumban under certain conditions. As a maturing practice, we propose a heuristic scoring technique to determine the sprint length of subprojects with different characteristics in the context of a portfolio. The study also introduces a multi-level refinement structure to enhance the monitoring of the teams' performance under the proposed mature framework. The results obtained display a considerable spike in the realization rate of release planning in light of the actual performance.
Optimal matchday schedule for Turkish professional soccer league using nonlinear binary integer programming
(2022) Göçgün, Yasin; Bakır, Niyazi Onur
Sports scheduling problems are interesting optimization problems that require the decision of who play with whom, where and when to play. In this work, we study the sports scheduling problem faced by the Turkish Football Federation. Given the schedule of games for each round of the season, the problem is to determine the match days with the goal of having a fair schedule for each team. The criteria we employ to establish this fairness are achieving an equal distribution of match days between the teams throughout the season and the ideal assignment of games to different days in each round of the tournament. The problem is formulated as a nonlinear binary integer program and is solved optimally for each week. Our results indicate that significant improvements over the existing schedule can be achieved if the optimal solution is implemented.
Sürdürülebilir insan kaynağı yönetimi : Belirsiz fayda fonksiyonlu doğrusal-olmayan atama programı ile çalışan memnuniyetinin arttırılması
(2022) Turan, Fikret Korhan; Çoruh, Gül
Kurumların sahip olduğu en önemli kaynak şüphesiz insandır ve insan kaynağını en doğru şekilde yönetebilmek kurumlara zaman ve paradan tasarruf sağlar. İnsan kaynağı yönetiminin en önemli adımlarından biri ise iş-personel eşleştirme sürecidir. Bu süreçte başarı için işe yerleştirilecek adayın teknik yeterliliğinin yanı sıra görev alacağı pozisyon ile ilgili memnuniyet ve beklentilerini de düşünmek gerekir. Bu bağlamda, sunulan çalışma ile güncel bir yaklaşım olan sürdürülebilir insan kaynağı yönetimi altında, çalışan memnuniyetini arttıracak bir iş-personel atama karar destek modelinin geliştirilmesi amaçlanmıştır. Geliştirilen karar destek modelinde çalışan memnuniyetini ölçmede fayda teorisi ve fonksiyonlarından yararlanılırken, optimal iş-personel eşleştirmesini gerçekleştirmede belirsiz fayda fonksiyonlu doğrusal olmayan atama programı kullanılmıştır. Geliştirilen karar destek modeli ile hem çalışan memnuniyetinin ekonomik, sosyal ve çevresel faktörlere göre çoğunlukla doğrusal olmayan bir şekilde değişiklik göstermesi durumu, hem de çalışan memnuniyetinde olabilecek belirsizlikler aynı anda hesaba katılarak, önceki modellerden daha gerçekçi bir yaklaşım sunulmuştur. Geliştirilen karar destek modelinin uygulaması kurgusal bir örnek üzerinden gösterilmiş, Monte Carlo benzetimi kullanılarak elde edilen sonuçlar duyarlılık analizi ile istatistiksel bağımsızlık ve bağımlılık durumları altında incelenmiştir. Bu sayede çalışmanın özgün tarafı detaylı olarak irdelenmiştir.
Classification of non-pharmaceutical anti-COVID ınterventions based on novel FTOPSIS-sort models
(Springer Science and Business Media Deutschland GmbH, 2022) Radaev, Alexander; Haktanır, Elif; Yatsalo, Boris; Kahraman, Cengiz
Assigning alternatives to predefined ordered categories under multicriteria conditions is the essence of multi-criteria sorting problematic. The family of fuzzy multi-criteria sorting models with the common name FTOPSIS-Sort are introduced based on the fuzzy extension of Multi-Criteria Decision Analysis (MCDA) ordinary method TOPSIS with the use of different approaches to assess functions of fuzzy numbers and different fuzzy ranking methods. The features of adjusting Fuzzy TOPSIS (FTOPSIS) models to sorting problematic are presented. The developed FTOPSIS-Sort models are implemented for multi-criteria sorting of non-pharmaceutical interventions against COVID-19.
Risk analysis of digital transformation with an ıntegrated picture fuzzy QFD and FMEA methodology
(Springer Science and Business Media Deutschland GmbH, 2022) Haktanır, Elif
Digital transformation takes more place in our lives day by day and changes both our individual lives and the way we do business. In addition to the numerous benefits it provides, it also has some risks that are accepted by everyone. In this study, these risks are analyzed with an integrated QFD (Quality Function Deployment) and FMEA (Failure Mode and Effects Analysis) methodology. The indecisiveness of the decision makers is handled with picture fuzzy sets. The novelty that the developed method adds to the literature is that it analyzes risk connectivity, one of the risk parameters, with the correlation matrix of QFD. The integrated approach uses nine risk parameters instead of the three risk parameters used in the classical FMEA method. In this way, the relationship pattern between the risks is included in the calculation and a more appropriate approach to real-life applications is suggested.
Digital transformation in textile ındustry and a study to determine the conceptual awareness level of textile firms regarding ındustry 4.0
(Tekstil Mühendisleri Odası, 2022) Turan, Fikret Korhan; Olgun, Buğra Artun
It is expected that as a new production model, Industry 4.0 will tremendously alter organizational life and work methods in many sectors in the near future by triggering digital transformation in manufacturing techniques. Thus, this research aims to determine the general level of conceptual awareness in textile sector regarding Industry 4.0 practices and the factors that are influential on it. With this aim, the employees of textile firms in Istanbul are contacted and a survey is conducted with the participation of 358 volunteers. Based on the results obtained from the statistical analysis of collected data, it is found that the Industry 4.0 conceptual awareness level of the firms in Turkish textile sector is found to be at moderate level; and this level can significantly vary depending on the firm's operating period, size (the number of employees), production structure (whether it works as a contract manufacturer) and export status (whether it does export). Further, from an individual perspective, it is observed that while the level of Industry 4.0 conceptual awareness changes significantly with respect to the employee's age, education level, position and working duration in the firm, it does not differ significantly according to the employee's gender.

Güncel Gönderiler