Mühendislik Fakültesi / Faculty of Engineering
Permanent URI for this collectionhttps://hdl.handle.net/11727/1401
Browse
18 results
Search Results
Item Goodness-of-fit and Randomness Tests for the Sun's Emissions True Random Number Generator(2014) Tanyer, Suleyman Gokhun; Atalay, Kumru Didem; Inam, Sitki Cagdas; 0000-0003-0820-9186; I-5023-2013; JHU-3888-2023Random number generators ( RNGs) are one of the key tools necessary for statistical analysis and optimization methods such as Monte Carlo, particle swarm optimization ( PSO) and the genetic algorithm. Various pseudo and true RNGs are available today, and they provide sufficient randomness. Unfortunately, they generate data that do not always represent the required distribution accurately, especially when the data length is small. This could possibly threaten the 'repeatability' of an academic study. A novel true RNG ( TRNG) using the method of uniform sampling ( MUS) is recently proposed. In this work, the Sun's RF emissions MUS-TRNG is comparatively tested with well known pseudo and true RNGs. It is observed that both randomness and very high goodness-of-fit qualities are possible.Item Randomness Tests For The Method Of Unıform Sampling Quasi-Random Number Generator (MUS-QRNG)(2014) Atalay, Kumru Didem; Tanyer, Suleyman Gokhun; https://orcid.org/0000-0001-9506-2391; I-5023-2013Random number generation is still an important research field in many scientific applications today. Cryptography, Monte Carlo simulations and commertial applications all rely on reference random data. Randomness tests and basic statistics share the same history. Randomness can be summarized as the unpredictability of future samples of a random number generator even in the presence of known all past values. Various randomness tests are developed and due to their individual contributions, usually a battery of tests are applied to verify a random number generator. In signal processing however, the error of a specific observed sample set to a given distribution could be much more important when it is used as the input for a system model. Recently, this distance of finite samples set to a given distribution is studied and a quantitative measure for quality is proposed Multi run computations like Monte Carlo simulations, often rely on accurate statistical data for high repetibility. Otherwise when the data is not accurate, the results could often rely on the source of random data generator. Many runs are often required to gain a confidence in the presence of those variances. In this work, recently proposed quasi-random number generator utilizing method of uniform sampling NUS) is tested using standard goodness-of-fitness tests. MUS-QRNG numbers are shown to have exact statistics and also their randomness test results are observed to be similar to well known reference generator of Matlab. MUS-QRNG is proposed for high quality random data generation.Item A New Hybrid Intuitionistic Approach for New Product Selection(2018) Atalay, Kumru Didem; Can, Gulin FeryalThis paper proposes a new hybrid approach for multi-criteria decision-making problems combining intuitionistic fuzzy analytic hierarchy process and intuitionistic fuzzy multi-objective optimization by ratio analysis. Analytic hierarchy process has an inherent ability for handling intangible problems and implements a simple scale to represent evaluations in the structure of pairwise comparisons. Multi-objective optimization by ratio analysis optimizes the solution of a problem having two or more conflicting objectives, taking into account certain constraints. In real-life decision problems, evaluations of decision makers related to performance of alternatives and criteria weights can be expressed by linguistic terms comprising vagueness and uncertainty. These uncertain, vague and hesitant judgments of decision makers can be described more comprehensively by using intuitionistic fuzzy set theory. The proposed approach is a powerful tool for dealing with information which consists of hesitancy and vagueness. An illustrative example related to new product selection for a company is also presented to demonstrate the implementation of the approach.Item A Case Study on Shopping Malls Attributes for Young Consumers(2016) Can, Gulin Feryal; Kurtulmusoglu, Feride Bahar; Atalay, Kumru DidemPurpose - This study aims to determine the mall criteria that are the most crucial for the youth market by determining the winning brand in comparison to other offerings to understand what is required to gain a competitive advantage and to differentiate a mall from its rivals. Design/methodology/approach - This study chose the Stochastic Multicriteria Acceptability Analysis-2 method to evaluate the mall preferences of young people. By using this method, the various criteria were evaluated for more than one alternative to find the best solution. JSMA program was used to analyze the data. The survey was administered using the mall intercept method to reduce sample bias. Findings - The study identifies that the criteria that have the highest impact on the mall preferences of young people are the mall campaigns for loyal customers; the traffic in the mall locality and the mall's parking facilities; the mall's facilities for disabled people; the quality of the mall locality; and the quality of the people visiting the mall. The study reveals that a mall's physical features, its facilities and the criteria related to employees have a very low impact on the mall choices of young people. The study further finds that the youth market has very low satisfaction levels for all of the identified criteria. This study reveals that this macro accessibility criterion is less relevant for the youth market than for the general population. Originality/value - Despite the importance of this market, there is insufficient research on the shopping behavior of young people. They have a considerable impact on the purchasing decisions of their families, significant disposable income and constitute the future market for the sector. This study uniquely enables the sequential ordering of customers' decision-making criteria and determines the effectiveness or impact of these criteria in the mall sector.Item Evaluation of Effect of Different Membership Functions on Risk Assessment(2018) Atalay, Kumru Didem; Can, Guelin Feryal; Eraslan, Ergun; 28330411This study aims to define the relationship between risk degrees and risk indexes on different functional structures with the assumption that risk degrees may not always present a linear relationship with the risk indexes. In this way, risk indexes suitable for expert evaluation of working conditions and computed using three different membership functions are determined. Among the membership functions used, one is preferred as linear and the others are preferred as non-linear. Additionally, a new fuzzy risk assessment (RA) algorithm is developed using these three membership functions. With this new fuzzy RA algorithm, a more flexible and precise process becomes available, while information loss during the determination of the risk index of danger sources is prevented. As a result, non-linear increasing membership function is selected as most suitable for the expression of the relationship between risk degrees and risk indexes.Item A New Stochastic MCDM Approach Based on COPRAS(2018) Ayrim, Yelda; Atalay, Kumru Didem; Can, Gulin FeryalThis study proposes a novel integrated Complex Proportional Assessment (COPRAS) approach by using stochastic decision process named as Stochastic COPRAS (COPRAS-S) to increase the evaluation performance of COPRAS. In COPRAS-S, criteria importance weights and the performance values of alternatives are determined by generating random numbers from uniform distribution in a range of minimum and maximum values of a limited number of decision-maker evaluations. Thus, the numbers of experts are increased and decision-making process is performed in an effective way because different opinions are incorporated. In addition, randomness feature brought with vagueness in decision is modeled in this process. A special normalization approach based on standard deviation is also implemented in COPRAS-S. In this way, cost and benefit type criteria are evaluated in a different way. This proposed stochastic structure for COPRAS is a practical and powerful tool that strengthens the decision.Item Development of a Decision Support System for Selection of Reviewers to Evaluate Research and Development Projects(2023) Kocak, Serdar; Ic, Yusuf Tansel; Sert, Mustafa; Atalay, Kumru Didem; Dengiz, BernaThe evaluation of Research and Development (R&D) projects consists of many steps depending on the government funding agencies and the support program. It is observed that the reviewer evaluation reports have a crucial impact on the support decisions of the projects. In this study, a decision support system (DSS), namely R&D Reviewer, is developed to help the decision-makers with the assignment of the appropriate reviewer to R&D project proposals. It is aimed to create an artificial intelligence-based decision support system that enables the classification of Turkish R&D projects with natural language processing (NLP) methods. Furthermore, we examine the reviewer ranking process by using fuzzy multi-criteria decision-making methods. The data in the database is processed primarily to classify the R&D projects and the word embedding model NLP, "Word2Vec". Also, we designed the Convolutional Neural Network (CNN) model to select the features by using the automatic feature learning approach. Moreover, we incorporate a new integrated hesitant fuzzy VIKOR and TOPSIS methodology into the developed DSS for the reviewer ranking process.Item Estimating the COVID-19 Death Counts Using a Hesitant Fuzzy Linear Regression Depend on Race, Age and Location(2022) Dengiz, Asiye Ozge; Atalay, Kumru DidemThe COVID-19 pandemic that has struck the world has caused social and economic problems in people's lives. Many countries are trying to reduce the impact of the pandemic by taking precautions to prevent the spread of the virus and reduce the number of deaths. Despite the precautions, many people have contracted the virus and a significant number have lost their lives. This suggests that some factors about the exact mechanism of how people contract the virus and get sick are still unclear. Therefore, many researchers wonder if there are other factors that make people more susceptible to the COVID-19 virus. In this study, hesitant fuzzy linear regression (HFLR) models are applied depending on variables such as age, race, and place of residence that are thought to influence COVID-19 deaths. HFLR provides an alternative approach to statistical regression for modeling situations with incomplete information. The models include input and output variables as hesitant fuzzy elements (HFEs). The relationship between the considered variables and the number of deaths is examined using data related to people living in different states of the United States. In addition, HFLR is used as an estimation model due to the uncertainty in the data obtained from the Centers for Disease Control and Prevention (CDC). The proposed HFLR models are used both to estimate COVID-19 deaths and to determine the effects of selected variables on COVID-19 deaths. In this way, countries can estimate the risk of death for individuals given these factors and determine what precautions to take for high-risk groups.Item Risk Analysis and Process Improvement for Medical Devices with Integrated Method DEA and FMEA(2022) Yamandir, Merve Nil; Dinler, Esra; Atalay, Kumru DidemRisk analysis is the identification of factors, conditions, activities, systems, components that are important concerning risk. Evaluating the systems in terms of risk plays a critical role in the production of products that are especially important for human health. The washing process of the medical devices at the production stage is important in terms of ensuring the acceptable sterility assurance level of the product before sterilization. In this process, the risk factors that may affect human health emerge. Risk Priority Number (RPN) which is used in the Failure Mode and Effect Analysis (FMEA) is calculated for each factor and it is considered to be equally important in general. Sometimes it can be difficult to clearly show the importance of these effects. These invisible effects cause great costs for companies, and they can also affect human health at risk. In this study, risk analysis of the washing process in a company producing medical devices is performed. Risk prioritization is made by scaling risk types and their effects by Data Envelopment Analysis (DEA) method to eliminate the disadvantages in question. As a result of the study, the prioritization of risk types with different methods is compared.Item A new hybrid method to determine the hazardous risk factors(2022) Dinler, Esra; Atalay, Kumru Didem; Guler, EzgiIn risk analysis, the quantification of risk, the modeling of identified risk, and how to make decisions are all topics considered. Risk analysis activity that companies must comply with and perform at a minimum level to produce medical devices. Manufacturers should consider all risks that the device may contain to indicate that the medical device is safe. Manufacturers must also justify that this device should be manufactured because the benefit of the device is greater than the risk. This study proposes a method to measure the risk factors of the medical devices on the patient. Accordingly, a mathematical model is developed, the model is applied to a device manufactured in a company, and the results are obtained. The aggregated method developed in this study, based on the Taguchi loss function and using the hesitant fuzzy the technique for order preference by similarity to ideal solution (HF-TOPSIS) method, ensures that the risks that may occur for the patient are minimized and the risk types to be taken into account are determined. In addition, the order of importance of the risk types obtained with the proposed method in the study is compared with the TOPSIS method.