Scopus İndeksli Açık & Kapalı Erişimli Yayınlar
Permanent URI for this communityhttps://hdl.handle.net/11727/10752
Browse
13 results
Search Results
Item A Self-tuning Heuristic for the Design of Communication Networks(2015) Dengiz, Berna; Alabas-Uslu, CigdemThis paper addresses the design of communication networks that has a large application area. The problem is to design a minimum cost network subject to a given reliability level. Complexity of the problem is twofold: (1) finding a minimum-cost network topology that every pair of nodes can communicate with each other and (2) computing overall reliability to provide the reliability constraint. Over the last two decades, metahemistic algorithms have been widely applied to solve this problem due to its NP-hardness. In this study, a self-tuning heuristic (STH), which is a new approach free from parameter tuning, is applied to the design of communication networks. Extensive computational results confirm that STH generates superior solutions to the problem in comparison to some well-known local search metaheuristics, and also more sophisticated metaheuristics proposed in the literature. The practical advantage of STH lies in both its effectiveness and simplicity in application to the design problem.Item A Self-adaptive Local Search Algorithm for the Classical Vehicle Routing Problem(2011) Alabas-Uslu, Cigdem; Dengiz, BernaThe purpose of this study is introduction of a local search heuristic free from parameter tuning to solve classical vehicle routing problem (VRP). The VRP can be described as the problem of designing optimal delivery of routes from one depot to a number of customers under the limitations of side constraints to minimize the total traveling cost. The importance of this problem comes from practical as well as theoretical point of view. The proposed heuristic, self-adaptive local search (SALS), has one generic parameter which is learnt throughout the search process. Computational experiments confirm that SALS gives high qualified solutions to the VRP and ensures at least an average performance, in terms of efficiency and effectiveness, on the problem when compared with the recent and sophisticated approaches from the literature. The most important advantage of the proposed heuristic is the application convenience for the end-users. SALS also is flexible that can be easily applied to variations of VRP. (C) 2011 Elsevier Ltd. All rights reserved.Item A Genetic Algorithm for the Redundancy Allocation Problem with Repairable Components(2022) Sahin, Merve Uzuner; Dengiz, Orhan; Dengiz, BernaThe complexity of the structures of modern engineering systems in the communication and electronic fields, the demand for high reliable system evaluation methods has increased. While improving the system's reliability, the cost is also on the upswing. Redundancy allocation is important approach for designing telecommunication systems. The reliability is increased by increasing number of redundant components in a system. The Redundancy Allocation Problem (RAP) is the design of new systems with higher reliability using redundant components in parallel arrangement. This paper presents a genetic algorithm (GA) with discrete event simulation (DES) to solve RAP with repairable components. The promising proposed approach is illustrated and investigated by some RAP benchmark/test problems involving repairable systems.Item Applications of Deep Learning Techniques to Wood Anomaly Detection(2022) Celik, Yaren; Guney, Selda; Dengiz, Berna; Xu, J; Altiparmak, F.; Hassan, MHA; Marquez, FPGWood products and structures have an important place in today's industry. They are widely used in many fields. However, there are various difficulties in production systems where wood raw material is under many processes. Some difficulty and complexity of production processes result in high variability of raw materials such as a wide range of visible structural defects that must be checked by specialists on line or of line. These issues are not only difficult and biased in manual processes, but also less effective and misleading. To overcome the drawbacks of the manual quality control processes, machine vision-based inspection systems are in great of interest recently for quality control applications. In this study, the wood anomaly has been detected by using deep learning. As it will be a distinction-based method on image processing, the Convolution Neural Network (CNN), which is one of the most suitable methods, has been used for anomaly detection. In addition, it will be tried to obtain the most suitable one among different CNN architectures such as ShuffleNet, AlexNet, GoogleNet for the problem. MobileNet, SqueezeNet, GoogleNet, ShuffleNet among considered methods show promising results in classifying normal and abnormal wood products.Item Analysis of the Robustness of the Operational Performance Using a Combined Model of the Design of Experiment and Goal Programming Approaches for a Flexible Manufacturing Cell(2023) Ic, Yusuf Tansel; Yurdakul, Mustafa; Dengiz, Berna; Sasmaz, TurgutA combined model of a 2(k) design of experiment (DOE) and goal programming (GP) approaches is presented to determine optimum levels of input variables and analyze their robustness for a multiobjective performance of a flexible manufacturing cell (FMC) in this study. Two main performance metrics, namely, manufacturing lead time (MLT) and surface roughness (SR), are considered performance outputs for the FMC. Machine sequence, robot speed, tool type, and material type are selected as the four input variables on the input side of the proposed model. The study shows that even with a limited number of experiments, one can determine optimum input levels for the multiobjective performance of the FMC and determine their robustness.Item A Multi-Objective Mathematical Model for Level of Repair Analysis with Lead Times and Multi-Transportation Modes(2022) Bicakci, Ismail; Ic, Yusuf Tansel; Karasakal, Esra; Dengiz, Berna; https://orcid.org/0000-0001-9274-7467; AGE-3003-2022In the event of failure of the product, level of repair analysis (LORA) is used to determine (1) whether the defective component should be discarded or repaired and (2) where this repair is made. In the literature, these repair operations are made with the aim of minimizing the total life cycle cost of the product. In this paper, we develop a multi-objective decision model that minimizes both the repair time (affected by lead times) and the repair costs. Our proposed model also considers the movement of the defective components to be performed by multiple transportation modes such as highway, railway, and airway. We use the epsilon constraint method to generate the Pareto frontier and analyze the trade-off between total repair costs and total repair time. We demonstrate the approach on an example problem.Item Analysis of the manufacturing flexibility parameters with effective performance metrics: a new interactive approach based on modified TOPSIS-Taguchi method(2022) Ic, Yusuf Tansel; Sasmaz, Turgut; Yurdakul, Mustafa; Dengiz, Berna; 0000-0001-9274-7467; AGE-3003-2022Flexibility is one of the most important strategy parameters to achieve a long-term successful performance for a manufacturing company. Studies in the literature aim to operate a manufacturing system at optimum levels of flexibility parameters under its own manufacturing environment. This study aims to present an interactive analysis framework based on TOPSIS and Taguchi parameter design principles for investigating the effects of different levels of flexibility parameters on the performance of a flexible manufacturing cell (FMC). The main performance metric used in this study is manufacturing lead time. Other important metrics to evaluate quality control and inspection policies are also investigated in this study. To conclude, a combined model of an interactive approach based on TOPSIS and Taguchi methods are used to assess the effectiveness of the flexibility parameters for a FMC.Item The development of a reviewer selection method: a multi-level hesitant fuzzy VIKOR and TOPSIS approaches(2021) Kocak, Serdar; Ic, Yusuf Tansel; Atalay, Kumru Didem; Sert, Mustafa; Dengiz, Berna; 0000-0001-9274-7467; AGE-3003-2022This paper proposes a new approach for the selection of reviewers to evaluate research and development (R&D) projects using a new integrated hesitant fuzzy VIKOR and TOPSIS methodology. A reviewer selection model must have a multi-level framework in which reviewer selection strategies and related objectives guide the second level of the reviewer performance ranking process. The model must measure reviewer performance related to the activities that are necessary for the R&D project evaluation to be successful. A novel model is presented in this paper. In the proposed methodology, the aim is to select a reviewer in a hierarchical decision-making structure. The selection criteria values and their weights were obtained using the hesitant fuzzy VIKOR method. For the selection of a suitable reviewer, the conventional TOPSIS model was used. We developed a simpler procedure for effectively performing the reviewer selection process. The new approach was tested with a real case study and satisfactory results were obtained. A comparative analysis is also included in the article for illustrative purposes.Item Obesity Level Estimation based on Machine Learning Methods and Artificial Neural Networks(2021) Celik, Yaren; Guney, Selda; Dengiz, BernaObesity is a growing societal and public health problem starting from 1980 that needs more attention. For this reason, new studies are emerging day by day, including those looking for obesity in children, especially the impact factors, and how to predict the emergence of the situation under these factors. In this study, different classification methods were applied for the estimation of obesity levels. Based on the evaluation criteria, the results were compared for different machine learning methods. When the Cubic SVM method was applied by selecting the appropriate features specific to the problem, 97.8% accuracy was obtained.Item Automated Tuberculosis Detection Using Pre-Trained CNN and SVM(2021) Oltu, Burcu; Guney, Selda; Dengiz, Berna; Agildere, MuhtesemTuberculosis (TB) is a dreadfully contagious and life-threatening disease if left untreated. Therefore, early and accurate diagnosis is critical for treatment. Today, invasive, expensive, or time-consuming tests are performed for diagnosis. Unfortunately, accurate TB diagnosis is still a major challenge. In the proposed study, a decision support system that can automatically separate normal and TB chest X-ray (CXR) images is presented for objective and accurate diagnosis. In the presented methodology, first various data augmentation methods were applied to the data set, then pre-trained networks (VGG16, MobileNet), were employed as feature extractors from augmented CXR's. Afterward, the extracted features for all images were fed into a support vector machine classifier. In training process, 5-fold cross-validation was applied. As a result of this classification, it was concluded that TB can be diagnosed with an accuracy of 96,6% and an area under the ROC curve (AUC) of 0,99.