Person: GÖKTÜRK, Elvin Çoban
Loading...
Email Address
Birth Date
Name
Job Title
First Name
Elvin Çoban
Last Name
GÖKTÜRK
12 results
Publication Search Results
Now showing 1 - 10 of 12
Conference ObjectPublication Metadata only Advancing home healthcare through machine learning: Predicting service time for enhanced patient care(IEEE, 2023) Selçuk, Yağmur Selenay; Göktürk, Elvin Çoban; Industrial Engineering; GÖKTÜRK, Elvin Çoban; Selçuk, Yağmur SelenayProviding healthcare services at home is crucial for patients who require long-term care or face mobility or other health-related constraints that prevent them from traveling to healthcare facilities. Effective data analysis techniques are needed to optimize these services to understand patient needs and allocate resources efficiently. Machine learning algorithms can analyze big datasets generated from home healthcare services to identify patterns, trends, and predictive factors. By utilizing these techniques, predictive models for service time can be developed, leading to improved patient outcomes, increased efficiency, and reduced costs. This study explores the significance of various features in predicting service time for home healthcare services by analyzing real-life data using data analysis techniques. By developing a correlation matrix, healthcare providers can examine the relationships between features as well as their connections with the target value, thereby providing valuable managerial insights into improving the quality of home healthcare services through enhanced predictions of service time.ArticlePublication Metadata only Service center staffing with cross‐trained agents and heterogeneous customers(Wiley, 2019-04) Göktürk, Elvin Çoban; Heching, A.; Scheller-Wolf, A.; Industrial Engineering; GÖKTÜRK, Elvin ÇobanWe model a real-world service center with cross-trained agents serving customer requests that are heterogeneous with respect to complexity and priority levels: High priority requests preempt low priority requests and low-skilled agents can only serve less complex requests, while high skilled agents can serve all requests. Our main aim is to dynamically assign requests to agents considering the priority and complexity levels of requests. We model this system as a Markov chain that is infinite in multiple dimensions and thus is not amenable to exact analysis. We therefore apply approximation and bounding techniques to develop a tractable, novel algorithm using the Matrix Analytic Method. Our algorithm closely approximates the operations of the real-world service system under a simple but effective threshold-based request-assignment policy. Extensive computational results demonstrate the usefulness of our algorithm to minimize costs given an existing staffing configuration, as well as in helping to make long-term staffing decisions. In addition, our algorithm also has at least two orders of magnitude shorter computation times than each replication of simulation. Hence, it is both fast and accurate.ArticlePublication Metadata only Logic-based benders decomposition for planning and scheduling: a computational analysis(2016-12) Ciré, A. A.; Göktürk, Elvin Çoban; Hooker, J. N.; Industrial Engineering; GÖKTÜRK, Elvin ÇobanBook PartPublication Metadata only Drone routing for post-disaster damage assessment(Springer, 2021) Adsanver, Birce; Göktürk, Elvin Çoban; Koyuncu, Burcu Balçık; Industrial Engineering; GÖKTÜRK, Elvin Çoban; KOYUNCU, Burcu Balçık; Adsanver, BirceWe consider drones to support post-disaster damage assessment operations when the disaster-affected area is divided into grids and grids are clustered based on their attributes. Specifically, given a set of drones and a limited time for assessments, we address the problem of determining the grids to scan by each drone and the sequence of visits to the selected grids. We aim to maximize the total priority score collected from the assessed grids while ensuring that the pre-specified coverage ratio targets for the clusters are met. We adapt formulations from the literature developed for electric vehicle routing problems with recharging stations and propose two alternative mixed-integer linear programming models for our problem. We use an optimization solver to evaluate the computational difficulty of solving different formulations and show that both formulations perform similarly. We also develop a practical constructive heuristic to solve the proposed drone routing problem, which can find high-quality solutions rapidly. We evaluate the performance of the heuristic with respect to both mathematical models in a variety of instances with the different numbers of drones and grids.Book PartPublication Metadata only Demand-driven electricity supply options of electric vehicles: modelling, simulation, and management strategy of public charging stations(Springer, 2021-10-13) Göktürk, Elvin Çoban; Poyrazoğlu, Göktürk; Industrial Engineering; Electrical & Electronics Engineering; GÖKTÜRK, Elvin Çoban; POYRAZOĞLU, GöktürkIn this chapter, we discuss the challenges and research opportunities in the demand-driven electricity supply options of electric vehicles (EVs) at public charging stations (CSs). EVs have gained increased attention in recent years due to the need for clean energy sources and growing global warming discussions. Major automakers have already stated that RandD efforts for gasoline and diesel vehicles will be ceased by 2025. Even if, these may result in the rapid adoption of EVs in upcoming years, there are still open problems with the public CSs restricting the widespread use of EVs. In this study, we discuss some of the strategic, tactical, and operational level problems related to public CSs. We explain an existing mathematical model computing the location of public CSs and discuss possible extensions. Once the locations of public CSs are fixed, we explain how to model a public CS by simulation varying the number and type of chargers. We also report the energy consumption and utilization of chargers and introduce different charging policies (with/without valet service). We also discuss different pricing models and remaining open problems on how to best design public CSs.ArticlePublication Metadata only The effect of few historical data on the performance of sample average approximation method for operating room scheduling(Wiley, 2023-01) Göktürk, Elvin Çoban; Kayış, Enis; Dexter, F.; Industrial Engineering; GÖKTÜRK, Elvin Çoban; KAYIŞ, EnisWe model the scheduling problem of a single operating room for outpatient surgery, with uncertain case durations and an objective function comprising waiting time, idle time, and overtime costs. This stochastic scheduling problem has been studied in diverse forms. One of the most common approaches used is the sample average approximation (SAA). Our contribution is to study the use of SAA to solve this problem under few historical data using families of log t distributions with varying degrees of freedom. We analyze the results of the SAA method in terms of optimality convergence, the effect of the number of scenarios, and average computational time. Given the case sequence, computational results demonstrate that SAA with an adequate number of scenarios performs close to the exact method. For example, we find that the optimality gap, in units of proportional weighted time, is relatively small when 500 scenarios are used: 99% of the instances have an optimality gap of less than 2.6 7% (1.74%, 1.23%) when there are 3 (9, many) historical samples. Increasing the number of SAA scenarios improves performance, but is not critical when the case sequence is given. However, choosing the number of SAA scenarios becomes critical when the same method is used to choose among sequencing heuristics when there are few historical data. For example, when there are only three (nine, many) historical samples, 99% of the instances have less than 25.38% (13.15%, 6.87%) penalty in using SAA with 500 scenarios to choose the best sequencing heuristic.Book PartPublication Metadata only Post-disaster damage assessment using drones in a remote communication setting(Springer, 2023) Yücesoy, Ecem; Göktürk, Elvin Çoban; Koyuncu, Burcu Balçık; Industrial Engineering; GÖKTÜRK, Elvin Çoban; KOYUNCU, Burcu Balçık; Yücesoy, EcemAfter a disaster event, obtaining fast and accurate information about the damaged built-in structure is crucial for planning life-saving response operations. Unmanned aerial vehicles (UAVs), known otherwise as drones, are increasingly utilized to support damage assessment activities as a part of humanitarian operations. In this study, we focus on a post-disaster setting where the drones are utilized to scan a disaster-affected area to gather information on the damage levels. The affected area is assumed to be divided into grids with varying criticality levels. We consider en-route recharge stations to address battery limitations and remote information transmission to a single operation center. We address the problem of determining the routes of a set of drones across a given assessment horizon to maximize the number of visited grids considering their criticality levels and transmit the collected assessment information as quickly as possible along the routes. We propose a mixed integer linear programming formulation to solve this problem and also adapt it to a setting where the information transmission is only possible at the end of the routes for comparison purposes. We propose performance metrics to evaluate the performance of our model and present results on small-sized instances with sensitivity analysis. We present results that highlight the tradeoff between attained coverage (visiting more grids) and response time (the timing of information transmission in the scanned areas). Moreover, we show the advantage of en-route data transmission compared to the setting with data transmission at the end of the routes.ArticlePublication Metadata only The effect of multiple operating room scheduling on the sterilization schedule of reusable medical devices(Elsevier, 2020-09) Göktürk, Elvin Çoban; Industrial Engineering; GÖKTÜRK, Elvin ÇobanWe study scheduling problems of operating rooms (ORs) and sterilization of reusable medical devices (RMDs) where RMDs are the tools that have to be sterilized in order to be reused in the other surgeries. During their sterilization, RMDs are batched and reprocessed extensively by sterilization machines to prevent possible nosocomial infections. Unlike other renewable resources, such as, nurses or anesthesiologists, RMDs do not become available for the next coming surgeries right after the surgery they are used is finished. Inadequate number of RMDs causes postponement of surgeries or delays in the starting times of surgeries. To study the effect of multiple operating room scheduling on the sterilization schedule of RMDs, we integrate scheduling of ORs and sterilization of RMDs by a mixed integer linear programming model to minimize the total cost that consists of the costs of sterilization, postponement of surgeries, and makespan. First, we solve the proposed model to compute the best solution found within a computation time limit. Then, we solve disaggregated versions of the problem: first step aims to schedule surgeries without considering RMDs, and second step aims to schedule RMD sterilization given the computed surgery schedule used as the earliest time surgeries may start. In the first disaggregated version, additional surgery postponement are not permitted in the second step (during RMD sterilization schedule), whereas, in the second disaggregated version additional surgery postponements are permitted. We also propose a batch-based heuristic where the problem is decomposed into two stages: assigning surgeries to ORs and batches by a mixed integer linear programming model, and then, scheduling surgeries based on the assignments computed by the previous stage via an iterative algorithm. In addition, we also model the real life practice of utilizing fixed sterilization times and a rule-of-thumb is also proposed based on sorting with respect to RMD requirements and surgery durations. We analyze the performance of these methods and we conclude that the proposed integrated mixed integer linear programming model performs better than the other methods over 375 instances with varying number of ORs and surgeries. Our computational results show that real life practice of scheduling sterilization with fixed time intervals results in an average gap of 20.2%, whereas, first and second disaggregated methods result in average gaps of 9.0% and 3.7%, respectively. In addition, 311 instances out of 375 instances could not be solved by the first disaggregated method. Our results demonstrate the usefulness of integrating OR scheduling problem and sterilization of RMDs, and it is also demonstrated that hospital administrations can not only decrease their total costs but also prevent delays due to inadequate number of RMDs required by their surgeries.ArticlePublication Metadata only A stochastic value estimation tool for electric vehicle charging points(Elsevier, 2021-07-15) Poyrazoğlu, Göktürk; Göktürk, Elvin Çoban; Industrial Engineering; Electrical & Electronics Engineering; GÖKTÜRK, Elvin Çoban; POYRAZOĞLU, GöktürkA stochastic value estimation tool serves as a planning tool with embedded modules for electrical and financial valuation of electric vehicle charging points. The tool is developed in stochastic nature for selected service and technology options. The tool is also valuable as a research tool to create a data set for a possible charging station with details of vehicle brands, state-of-charge at the arrival, charge duration, and waiting time. A case study for one of the biggest shopping malls in Istanbul, Turkey, where welcomes 350-400 electric vehicles per day is analyzed. The results are discussed on performance metrics such as the average waiting time in the queue, utilization of the station and each socket, profit, customer satisfaction, energy, and power consumption.ArticlePublication Open Access A predictive multistage postdisaster damage assessment framework for drone routing(Wiley, 2024-01) Adsanver, Birce; Göktürk, Elvin Çoban; Koyuncu, Burcu Balçık; Industrial Engineering; GÖKTÜRK, Elvin Çoban; Adsanver, BirceThis study focuses on postdisaster damage assessment operations supported by a set of drones. We propose a multistage framework, consisting of two phases applied iteratively to rapidly gather damage information within an assessment period. In the initial phase, the problem involves determining areas to be scanned by each drone and the optimal sequence for visiting these selected areas. We have adapted an electric vehicle routing formulation and devised a variable neighborhood descent heuristic for this phase. In the second phase, information collected from the scanned areas is employed to predict the damage status of the unscanned areas. We have introduced a novel, fast, and easily implementable imputation policy for this purpose. To evaluate the performance of our approach in real-life disasters, we develop a case study for the expected 7.5 magnitude earthquake in Istanbul, Turkey. Our numerical study demonstrates a significant improvement in response time and priority-based metrics.