Search

Vaccination studies against the Covid-19 virus, which has affected our country and the whole world, bring along a major logistical problem for the mass vaccination of the modern world. Various vaccines produced by different methods such as mRNA and inactive virus method are made ready for mass production by companies. A well-planned distribution network is important for these vaccines with different shelf life under different conditions. In this study, the two-echelon location-routing model that will efficiently use the shelf life for Covid-19 mRNA vaccines, which are used in our country and need harsh storage conditions, is emphasized. In this respect, hubs and centers were determined with two different methods, and then time-limited capacitated vehicle routing problem mathematical model was developed for vehicle routes between the determined locations. As a result, two-stage deployment-routing model made it possible to successfully identify the appropriate delivery model for vaccines to be consumed before the shelf-life period. Scientists in the field of medicine state that such epidemics will be encountered again in the coming years. Therefore, the study will be developed further in the following years and will ensure that the vaccine distribution policy in the country is ready and effective in advance., Ülkemizi ve tüm dünyayı etkisi altına almış olan Covid-19 virüsüne karşı yapılan aşı çalışmaları, modern dünyanın kitlesel olarak aşılanabilmesi için büyük bir lojistik problemi de yanında getirmektedir. mRNA ve inaktif virüs yöntemi gibi farklı yöntemlerle üretilen çeşitli aşılar şirketler tarafından her geçen gün seri üretim için hazır hale getirilmektedir. Farklı koşullar altında farklı raf ömrü sürelerine sahip bu aşılar için iyi planlanmış bir dağıtım ağı büyük önem taşımaktadır. Bu çalışmada, ülkemizde kullanılan ve zorlu saklama koşullarına ihtiyaç duyan Covid-19 mRNA aşıları için raf ömrünü verimli şekilde kullanacak iki aşamalı yerleştirme-rotalama modeli üzerinde durulmaktadır. Bu açıdan çalışmada, iki farklı yöntem ile ara depolar ve ara depolara bağlı merkezler belirlenmiş, sonrasında ise belirlenen lokasyonlar arasındaki araç rotaları için probleme özgü zaman kısıtlı kapasiteli araç rotalama problemi matematiksel modeli geliştirilmiştir. Sonuç olarak ortaya çıkan iki aşamalı yerleştirme-rotalama modeli başarılı bir şekilde aşıların raf ömrü süresi dolmadan tüketilmesi için uygun dağıtım modelini tespit etmeyi mümkün kılmıştır. Tıp alanındaki bilim insanları, ilerleyen yıllarda da bu tarz salgınlarla tekrar karşılaşılacağını dile getirmektedir. Bu yüzden yapılan çalışma ileriki yıllarda daha da geliştirilerek ülkedeki aşı gibi acil ve kısa tüketim ömrüne sahip ürünlerin dağıtım politikasının önceden hazır ve etkin kılınmasını sağlayacaktır.

Official data, administered by National Statistic Institutes (NSIs), play crucial role for being a major element of the governmental economic and social decision-making process. This strategic role raises a significant necessity for statistical authorities to adopt new data tools to shift the statistical quality of the published data to a higher level. Data mining (DM) techniques and algorithms are promising tools to provide new ways to mine the crucial, complex, and voluminous official data to complement or substitute the traditional and lagged-behind tools that NSIs have been using. This study addresses this potential utilization of DM tools on official data with a specific problem in an important survey for official statistics: Household Budget Survey. Through this study, clustering techniques are employed to characterize the household types and association rule mining technique is used to mine consumption patterns for each differentiated type. It is aimed to integrate the proposed model into data preprocessing procedure of the NSI to be able to engage in the real time analyses and to contribute exactness and timeliness of the data. (C) 2017 Wiley Periodicals, Inc.

Increased use of railways in public transportation in recent years increases the importance of planning problems related to railway systems. Since the crew-related costs constitute the critical part of the operational costs, researches are focused on duty and crew scheduling problems. In this study, a multi objective 0-1 mixed integer programming model is established considering all operational and legal constraints of crew rostering problem which is one of the problems of railway planning process of Kayseri Transportation Inc. In the objective function of the proposed mathematical model, total number of machinists working, the sum of overtime amounts of the weekly working time of each machinist from the legal working time and the largest difference between average rest period and actual rest period are minimized. The effectiveness of the proposed model is evaluated by the comparison of the results obtained by the mathematical model and the current system for two different lines of the light rail system in Kayseri.

Data mining which has attracted great interest in recent years is the process of extracting meaningful, accurate, interesting and hidden information from the databases. Among the various data mining tasks classification is the most widely used one which aims to predict the classes of future data objects. Classification has been successfully applied to many areas and one of these areas is the production sector. By analyzing the production-related data, a lot of knowledge can be achieved and productivity of the production firms can be increased. Artificial neural networks are one of the most promising classification methods with high accuracy rates. An artificial neural network is a mathematical or computational model based on biological neural networks. The conventional algorithms used for training neural networks are based on mathematical computations, are slow and usually trapped into local optima. In order to overcome these disadvantages meta-heuristic algorithms are successfully used in the literature for training neural networks. In this study, a new generation meta-heuristic algorithm Stochastic Fractal Search is adapted for training feed-forward neural networks in order to determine the causes of quality defects in a fabric production facility in Kayseri. Stochastic Fractal Search algorithm is inspired by the natural phenomenon of growth and uses a mathematical concept called fractal. The quality defect dataset consists of 2461 instances, 9 categorical, 8 continuous inputs and 5 classes which express the quality groups. Artificial neural network is trained with Stochastic Fractal Search algorithm and accuracy of the algorithm is compared with some classification algorithms from Weka data mining software and TACO-miner algorithm proposed by Özbakır and her colleagues. Obtained results and comparisons have shown that the Stochastic Fractal Search algorithm gives high accuracy rates and capable of training artificial neural networks on quality defect dataset.

Veri madenciliği, farklı bir çok alana başarı ile uygulanan bir tekniktir. Havacılık sektörü de bu alanlardan birisidir. Özellikle Türkiye’de gelişmekte olan hava yolu işletmelerinde de kullanılması mümkündür. Havacılık sektörü, çok büyük miktarlarda veri ve bilgi birikiminin olduğu bir alandır. Bu veriler pilot, bakım, kaza, parça söküm veya tehir raporları şeklinde kayıt altına alınmaktadır. Bu çalışmada, Türkiye’de bir hava yolu işletmesinin parça söküm raporları üzerinde veri madenciliği çalışması gerçekleştirilmiştir. Çalışmanın amacı, uçaklarda kullanılan parçaların, herhangi bir arıza oluşmadan önce düzeltici ve önleyici işlemlerin yapılması için ikaz seviyelerinin tespit edilmesine yönelik kural geliştirmektir. Sonuç olarak parçaların ikaz seviyelerini temsil edecek anlamlı bir kural elde edilmiş ve bulunan kurallar doğrulukları ve güvenilirlikleri bakımından test edilmiştir.

Arı Algoritması popülasyon tabanlı yeni bir arama algoritması olup sürü zekâsına dayalı metasezgisel yöntemlerden birisidir. Algoritma gerçek bal arılarının yiyecek arama davranışlarını modellemeye dayanmakta olup bilimsel yazında kombinatoryel ve genellikle de sürekli optimizasyon problemlerinin çözümünde kullanılmıştır. Diğer taraftan Genelleştirilmiş Atama Problemi NP-zor bir problem olup kombinatoryel tamsayılı optimizasyon problemi olarak formüle edilebilmektedir. Bu çalışmada öncelikle Arı Algoritması, Genelleştirilmiş Atama Problemi’nin çözümü için geliştirilmiş ve kaydırma, değiştirme, çift kaydırma ve çıkarım zinciri komşuluk yapılarının Arı Algoritması'nın performansı üzerindeki etkileri incelenmiştir. Bees Algorithm is a population based new search algorithm which is one of the meta heuristic techniques based on swarm intelligence. Bees Algorithm depends on to model natural behavior of real honey bees in food foraging and is used to obtain solutions for combinatorial and generally continuous optimization problems in the literature. On the other hand, Generalized Assignment Problem is known as an NP-Hard problem and can be formulated as a combinatorial integer optimization problem. In this study, firstly Bees Algorithm is modified to solve Generalized Assignment Problem and the effects of shift, swap, double shift, and ejection chain neighborhood structures on the performance of Bees Algorithm is analyzed.

Data mining methods have been successfully applied to different fields. Aviation industry is one of these fields. There is a large amount of knowledge and data accumulation in aviation industry. These data could be stored in the form of pilot reports, maintenance reports, incident reports, component reports or delay reports. This paper explains the data mining application on the component reports of an airline company in Turkey. In this study, we applied data mining functions on the component reports. The purpose of our application is to find out a rule about the warning level of the components to do correcting operation before any fault. As a result we found out a meaningful rule that presents the formulation of the warning level of the components. The rules found are tested in terms of their accuracy and reliability.