Yazar "Argun, İrem Düzdar" seçeneğine göre listele
Listeleniyor 1 - 12 / 12
Sayfa Başına Sonuç
Sıralama seçenekleri
Öğe An Approach to the use of Wi-Fi Signals for Hospital Indoor Location Detection: Performance Comparison of Classification Algorithms(Ieee, 2019) Sabah, Levent; Argun, İrem DüzdarDetecting the location in the indoor is relatively difficult compared to the outdoor places. Location detection in outdoor places GPS-enabled devices and signals from at least 3 different satellites are easy to implement due to various difficulties (such as forested areas, high-rise buildings). On the other hand, In indoor places like hospital, airports, car parks, mines; Wi-Fi, Beacon and Radio Frequency (RF) signals are used for position detection. In this study, on a sample data set consisting of signals from 7 different access points in a closed area, analyzes were made by using machine learning algorithms on the correct position determination. With the obtained values and the comparisons made, it was seen that the location could be determined by using the access point signals in the indoor. In this pre - study, it is aimed to reduce adverse conditions with rapid and high accuracy location detection in emergency situations which may occur in hospital buildings where time is crucial.Öğe Classification of a bank data set on various data mining platforms(Institute of Electrical and Electronics Engineers Inc., 2018) Başarslan, Muhammet Sinan; Argun, İrem DüzdarThe process of extracting meaningful rules from big and complex data is called data mining. Data mining has an increasing popularity in every field today. Data units are established in customer-oriented industries such as marketing, finance and telecommunication to work on the customer churn and acquisition, in particular. Among the data mining methods, classification algorithms are used in studies conducted for customer acquisition to predict the potential customers of the company in question in the related industry. In this study, bank marketing data set in UCI Machine Learning Data Set was used by creating models with the same classification algorithms in different data mining programs. Accuracy, precision and f- measure criteria were used to test performances of the classification models. When creating the classification models, the test and training data sets were randomly divided by the holdout method to evaluate the performance of the data set. The data set was divided into training and test data sets with the 60-40%, 75, 25% and 80-20% separation ratios. Data mining programs used for these processes are the R, Knime, RapidMiner and WEKA. And, classification algorithms commonly used in these platforms are the k-nearest neighbor (k-nn), Naive Bayes, and C4.5 decision tree. © 2018 IEEE.Öğe Comparing of Results and Implemantation of Clustering Methods of Data Mining Software with a Data Set(Ieee, 2017) Argun, İrem Düzdar; Temür, GünayIn data mining, the process of grouping similar data among each other in an evaluation made by the same kind of data is called clustering. Clusters are usually computed by algorithms that take advantage of relational or remote neighborhood relations to each other. A large number of clustering methods are used in practice. In this study, the differences between open source software used in data mining and results obtained by clustering methods of Oracle, Knime, Weka and RapidMiner programs are tabulated. As a source for this study, clustering analysis based article presentations by M. Turanli, U.H. Ozden and S. Turedi have been handled. For the evaluation, in 2006, economic similarities of 29 countries from candidate and member countries from the EU in terms of proprtion of inflation, Gross National Product, Internet Usage, Unemployment, Lifetime Education Indicators and Imports and Exports were tried to be clustered. Clustering operations were performed separately as 2-3-4 clusters in each program. In the clustering process, the euclidean distance is set for calculation and the number of iterations is 99 in each program. The obtained results were written in tabular form and the results were interpreted.Öğe Comparison of Open Source Data Mining Tools: Naive Bayes Algorithm Example(Ieee, 2019) Özkan, Sibel Barın; Apaydın, Sultan Muhammed Fatih; Özkan, Yasin; Argun, İrem DüzdarData Mining is a set of processes that use many disciplines together in the process of analyzing large data. It is the concept of data mining that combines computer technologies, statistical analysis techniques, database technologies and many disciplines. There are many commercial and open source programs to implement Data Mining applications. In this study, open source data mining programs WEKA, Orange, Knime is described. A sample is analyzed with the classification algorithm in all of these programs. In this study, it was aimed to determine the difference between these 3 open source Data Mining programs with Naive Bayes classification algorithm by taking Bay iris, breast cancer, wine, monk, balance es data sets from UCI Machine Learning Repository database. With this study, there are suggestions for making comparisons according to the outputs from the programs.Öğe Electric vehicle charge station layout planning: A case study in Istanbul Technical University campus(John Wiley & Sons Ltd, 2023) Müyesseroğlu, Arzu; Argun, İrem Düzdar; Kayakutlu, GülgünWhile the popularity of electric vehicles is rising, several studies have been conducted on the challenges surrounding charging stations. The choice of charging station layout planning is evaluated in this study, which is based on available parking capacity and potential vehicle users on campus. Its goal is to figure out how various data and different coverage methods affect optimal selection. These models aim to serve the regions within a specified distance with the least possible number of stations. The data are collected with geographic information system, and the Voronoi diagram is used to solve the models. The findings of the models have been compared, and station sites that were deemed suitable for the campus have been determined. Evaluation of three models allows the most appropriate solution for the campus to set up five stations and use a 700-m service distance. In this study, an opportunity was created to observe how the added parameters affect the optimization model and the results.Öğe Financial Performance Analysis of Firms in the Energy Sector with Multi-Criteria Decision-Making Methods(Ieee, 2022) Argun, İrem Düzdar; Altınoluk, HazalToday, in the energy sector, as in all other sectors, there are some risks and a competitive environment. Performance measurements have great importance in the analysis of how well-prepared they are against current risks and in order for businesses to continue to take place in the competitive environment without losing value. Financial performance analysis, on the other hand, covers the general analysis made to determine the strategic path to be drawn by determining the financial risks that businesses may face. Based on this, financial performance analysis of energy companies in the Borsa Istanbul (BIST) energy sector were made in this study. As a result of the analysis, the companies were compared both within themselves and with each other. In the study, the values obtained from the financial statements of the companies with the Ratio Analysis method were converted into numerical data to be used as criteria by means of various formulas. At the stage of obtaining the weights of the determined criteria, first of all, the criteria were evaluated by the experts in the energy sector through a questionnaire and then the weights were obtained by using the Analytical Hierarchy Process (AHP) method. In the analysis phase, the Ranking Technique in terms of Similarity to the Ideal Solution (TOPSIS) and Multi-Criteria Optimization and Compromise Solution (VIKOR) methods were used. The study was carried out within the scope of 2015-2019 data of 10 energy companies in the energy sector. As a result of the study, it is aimed to evaluate the financial performance analysis of the companies, as well as to test the usability of Multi-Criteria Decision Making methods in this field and to present the results to the literature by comparing them with each other.Öğe Initial Seed Value Effectiveness on Performances of Data Mining Algorithms(2021) Timuçin, Tunahan; Argun, İrem DüzdarAfter 2000s, Computer capacities and features are increased and access to data made easy. However, the produced and recorded data should be meaningful. Transformation of unprocessed data into meaningful information can be done with the help of data mining. In this study, classification methods from data mining applications are studied. First, the parameters that make the results of the same data set different were investigated on 4 different data mining tools (Weka, Rapid Miner, Knime, Orange), It has been tested with 3 different algorithms (K nearest neighborhood, Naive Bayes, Random Forest). In order to evaluate the performance of the data set while creating the classification models, the data set was divided into training data and test data as 80% -20%, 70% -30% and 60-40%. The accuracy, roc and precision values was used to test the performance of the classifying data. While classifying, the effect of algorithm parameters on the results is observed. The most important of these parameters is the initial seed value. The initial seed is a value using especially in classification algorithms that determines the initial placement of the data and directly affects the result. In this respect, it is very important to determine the initial seed value correctly. In this study, initial seed values between 0 and 100 were evaluated and it was shown that the classification could change the accuracy value approximately by 5%.Öğe Investigation of Shelf Life for Door Seal Mixture in Automotive Industry(2022) Cihan, Ahmet; Kantoğlu, Barış; Güner, Yusuf; Argun, İrem DüzdarThe door seals for vehicles in automotive industry, which are one of the most important components, provide insulation and damping. Quality of the product highly depends on the shelf life of the seal compound under required temperature. The most important parameters of the compound are its viscosity and scorch values. The aim of this study is to determine the most suitable shelf life in manufacturing and storage processes for seal compound. For stating the important factors affecting shelf life of frequently used main two types of seal compound, interviews are made with the producing firm. Then for both types of compound, series of controlled experiments are performed, and linear estimation models are developed with the help of the results of these experiments. In this study, the results of generated multi variable regression models are presented. It is seen that the generated estimation models can be employed by the producers, and the results of the experiments are overlapping with the results of studies performed in the literature.Öğe Life Long Economic Analysis for Industrial Microgrids: A Case Study in Turkey(Springer International Publishing Ag, 2018) Öztürk, Çağrı; Argun, İrem Düzdar; Kayalıca, M. ÖzgürMicrogrids are used prevalently in isolated sites as a solution for multiple resource usage and distributed energy generation. Industrial Zones are constructed as isolated sites, where expectations include reducing the energy costs, providing local energy supply with fewer fluctuations and reducing greenhouse gas emissions. To encourage the microgrids in a developing country of Small and Medium-sized Enterprises (SMEs) placed in industrial zones, pre-investment studies are to be run. This article aims at minimizing the total energy costs of an organized industrial zone in parallel with mitigation of emission for climate change. The costs depend on the number and power of the Wind Turbines (WT) and the capacity of Photovoltaic (PV) panels when renewable energy sources and power storage construct the resources. A Mixed Integer Nonlinear Programming (MINLP) model is proposed to optimize the number of installations to satisfy the current demand. Lifelong carbon emission and cost analysis are performed to minimize the total cost of ownership. In this initial study, uncertainties caused by the renewable energy supply are smoothed by limited use of one gas tribune and grid connection. A case study of the model is implemented for Gebze Industrial Zone. This project will contribute to the researches on microgrids for a long term optimization model.Öğe A New Product Design After Benckmarking Analysis Of Helis Gear Pumps And Optimization In Energy Consumption(2018) Argun, İrem Düzdar; Kantoğlu, Barış; Öztürk, BurakThe various types of helical gear pumps can be produced to transfer the gasoline, diesel, chemicals, and oil. Helical gear pumps are used by motor power in fuel selling and transfer points, and by gear shafts at mobile transfer trucks. These pumps are classified in three main groups as internal gear, pallet, and helical pumps. The common feature of them is sucking the liquid from the container placed under ground level and transferring it to the high levels. The lower flow rates, noisy working, and the quick corrosion of gear when the pump is running closing outlet valve are the disadvantages of these pumps produced in our country. The aim of this study is to design a new generation of helical gear pump which will eliminate or at least decrease these disadvantages. It is expected to minimize energy consumption, and to protect the corrosion of gears coming from the high pressure at this new design. The dimensions of this pump will be appropriated to the chassis of the truck and at minimum weight. For this reason, benchmarking study is applied; the by-pass system of the pumps that are currently produced, the fluid voids between the teeth, and faults in the inlet-outlet design, and a new type design has been proposed. Besides these the transfer capacity of the pump is increased from 400 l/min to 600 l/min. The energy requirement for 1 liter of liquid is compared with the other products to measure its energy efficiency. The result is also positive at this point of view. Then, this new design is protected by patent registration.Öğe Renewable Energy Investment Decision Evaluation for Local Authorities(Springer International Publishing Ag, 2022) Türkoğlu, Ecem; Çolak, Üner; Kayakutlu, Gülgün; Argun, İrem DüzdarCurrently, increasing urban population creates escalating problems such as housing, infrastructure, transportation, health, environment, safety, and energy consumption. Climate change, emission mitigation, and limited energy supply force urban managers to consider sound measures with the support of technological developments. It is based on data collection and accumulation using IoT, sensors, digital networks, and other means. Smart urbanism is a concept that considers predicting, designing, and creating solutions in a systematic, sustainable, and agile manner based on the data collected. Energy is an indispensable dimension in this context. Optimum energy management makes it smart energy with the inclusion clean and sustainable renewable energy resources as well as energy efficiency. This study is performed to analyze possible inclusion of geothermal, solar, and wind power. The analyses are based to reveal the best feasible alternative considering the parameters of location, climate, space availability, capital and operational expenditures as well as construction, operation, and maintenance. The Fuzzy Analytic Hierarchy Process (Fussy AHP) technique is used to evaluate the ranking. The proposed method uses fuzzy mathematics for solving problems containing uncertainties as well as less quantifiable. This study proposes a methodological framework for the analysis of competitiveness of alternative renewable energy generations in urban environments. The municipality of Balikesir is chosen for the case study presented in this work.Öğe Seri üretim boru bağlantı elemanlarının döküm işleminde optimizasyon(2017) Küçük, Özkan; Öztürk, Burak; Argun, İrem Düzdar; Varhan, Samed; Çetindağ, Hüseyin AlpBu çalışmada petrol ve doğalgaz hatlarında yaygın olarak kullanılan ½", ¾", 1", 1½", 2" çaplarındaki boru bağlantı elemanlarının tasarım ve üretiminde optimizasyonlar gerçekleştirilerek üretim verimliliğinin arttırılması araştırılmıştır. Yapılan çalışmalarda TS EN 10242 standart ölçülerine göre üretim ve inceleme yapılmıştır. Üretim verimliliğini etkileyen faktörler neden sonuç diyagramı yardımıyla incelenmiştir. Ürünlerin standartlara göre ortalama %12 daha ağır olduğu tespit edilmiş, modellerin yerleşiminde ise çeşitli hatalar saptanmıştır. 300400 mm'lik derece sisteminin boru bağlantı üretimi için uygun olmadığı gözlemlenmiştir. Bunun yanında yolluk ağırlığının fazla ve yolluk giriş tasarımının hatalı olduğu belirlenmiştir. Bu sorunların çözümü için model üretim yöntemlerinin oluşturduğu hatalar araştırılmıştır. Bu araştırmalar sonrasında üretimde yeni bir yöntem geliştirilerek optimizasyon sağlanmıştır. Ayrıca boru bağlantı elemanlarının model üzerindeki yerleşim planının dizilim parametreleri matematiksel formüllerle ifade edilmiştir. Elde edilen bu formüllere göre boru bağlantı elemanları için en iyi sonucu 420x500' lük derece sisteminin verdiği saptanmıştır. Kullanılan bu yöntem sonucu firmada seri üretimi gerçekleştirilen ½", ¾", 1", 1½", 2'' çaplarındaki boru bağlantı elemanları gözden geçirilip bu ürünlerde düzenlenmeye gidilmiştir. Bu sayede üretimin %90'ı optimize edilmiştir. Toplam yıllık hurda malzeme ağırlığı 246,660 kg'dan 188,496 kg'a düşürülmüştür. Ürünler TSE standart ölçülerine göre şekillendirilerek hata oranı azaltılmıştır ve malzeme ağırlıklarında %8-20 arasında düşüş sağlanmıştır. Geliştirilen yeni derece sistemi TÜBİTAK patent desteği almış ve 2013/00806 numaralı "Fittings malzemelerin dökümü için derece modeli'' adıyla Rusya'da incelenerek patente uygun görülmüştür
