Yazar "Doğan, Onur" seçeneğine göre listele
Listeleniyor 1 - 20 / 30
Sayfa Başına Sonuç
Sıralama seçenekleri
Öğe Catastrophic household expenditure for healthcare in Turkey: Clustering analysis of categorical data(MDPI, 2019) Doğan, Onur; Kaya, Gizem; Kaya, Aycan; Beyhan, HidayetThe amount of health expenditure at the household level is one of the most basic indicators of development in countries. In many countries, health expenditure increases relative to national income. If out-of-pocket health spending is higher than the income or too high, this indicates an economical alarm that causes a lower life standard, called catastrophic health expenditure. Catastrophic expenditure may be affected by many factors such as household type, property status, smoking and drinking alcohol habits, being active in sports, and having private health insurance. The study aims to investigate households with respect to catastrophic health expenditure by the clustering method. Clustering enables one to see the main similarity and difference between the groups. The results show that there are significant and interesting differences between the five groups. C4 households earn more but spend less money on health problems by the rate of 3.10% because people who do physical exercises regularly have fewer health problems. A household with a family with one adult, landlord and three people in total (mother or father and two children) in the cluster C5 earns much money and spends large amounts for health expenses than other clusters. C1 households with elementary families with three children, and who do not pay rent although they are not landlords have the highest catastrophic health expenditure. Households in C3 have a rate of 3.83% health expenditure rate on average, which is higher than other clusters. Households in the cluster C2 make the most catastrophic health expenditure.Öğe Categorization of customer complaints in food industry using machine learning approaches(2022) Kılınç, Deniz; Doğan, Onur; Bozyiğit, FatmaCustomer feedback is one of the most critical parameters that determine the market dynamics of product development. In this direction, analyzing product-related complaints helps sellers to identify the quality characteristics and consumer focus. There have been many studies conducted on the design of Machine Learning (ML) systems to address the causes of customer dissatisfaction. However, most of the research has been particularly performed on English. This paper contributes to developing an accurate categorization of customer complaints about package food products, written in Turkish. Accordingly, various ML algorithms using TF-IDF and word2vec feature representation strategies were performed to determine the category of complaints. Corresponding results of Linear Regression (LR), Naive Bayes (NB), k Nearest Neighbour (kNN), Support Vector Machine (SVM), Random Forest (RF), and Extreme Gradient Boosting (XGBoost) classifiers were provided in related sections. Experimental results show that the best-performing method is XGBoost with TF-IDF weighting scheme and it achieves %86 F-measure score. The other considerable point is word2vec based ML classifiers show poor performance in terms of F-measure compared to the TF-IDF term weighting scheme. It is also observed that each experimented TF-IDF based ML algorithm gives a more successful prediction performance on the optimal subsets of features selected by the Chi Square (CH2) method. Performing CH2 on TF-IDF features increases the F-measure score from 86% to 88% in XGBoost.Öğe A comprehensive study of machine learning methods on diabetic retinopathy classification(Atlantis Press, 2021) Gürcan, Ömer Faruk; Beyca, Ömer Faruk; Doğan, OnurDiabetes is one of the emerging threats to public health all over the world. According to projections by the World Health Organization, diabetes will be the seventh foremost cause of death in 2030 (WHO, Diabetes, 2020. https://www.afro.who.int/healthtopics/diabetes). Diabetic retinopathy (DR) results from long-lasting diabetes and is the fifth leading cause of visual impairment, worldwide. Early diagnosis and treatment processes are critical to overcoming this disease. The diagnostic procedure is challenging, especially in low-resource settings, or time-consuming, depending on the ophthalmologist's experience. Recently, automated systems now address DR classification tasks. This study proposes an automated DR classification system based on preprocessing, feature extraction, and classification steps using deep convolutional neural network (CNN) and machine learning methods. Features are extracted from a pretrained model by the transfer learning approach. DR images are classified by several machine learning methods. XGBoost outperforms other methods. Dimensionality reduction algorithms are applied to obtain a lower-dimensional representation of extracted features. The proposed model is trained and evaluated on a publicly available dataset. Grid search and calibration are used in the analysis. This study provides researchers with performance comparisons of different machine learning methods. The proposed model offers a robust solution for detecting DR with a small number of images. We used a transfer learning approach, which differs from other studies in the literature, during the feature extraction. It provides a data-driven, cost-effective solution, which includes comprehensive preprocessing and fine-tuning processes. (C) 2021 The Authors. Published by Atlantis Press B.V.Öğe A corridor selection for locating autonomous vehicles using an interval-valued intuitionistic fuzzy AHP and TOPSIS method(Springer, 2020) Doğan, Onur; Deveci, Muhammet; Canitez, Fatih; Kahraman, CengizAutonomous vehicles (AVs) provide a new mobility option and have been becoming widespread around the world. They can be used not only as automobiles but also as public transport vehicles in the form of shuttles, buses and pods. One of the problem areas in implementing AVs as a public transport vehicle is to choose a suitable road for operating them. A fuzzy decision model combining analytic hierarchy process (AHP) and technique for order of preference by similarity to ideal solution (TOPSIS) techniques with intuitionistic fuzzy sets is used to solve this problem. The results show that the BRT corridor is the most suitable option for operating AVs according to the decision criteria. Furthermore, operating AVs on a BRT corridor provides an unprecedented service provision approach.Öğe Customer churn prediction using deep learning(Springer Science and Business Media Deutschland GmbH, 2021) Seymen, Ömer Faruk; Doğan, Onur; Hızıroğlu, AbdülkadirChurn studies have been used for years to achieve profitability and to establish a sustainable customer-company relationship. Deep learning is one of the contemporary methods used in churn analysis due to its ability to process huge amounts of customer data. In this study, a deep learning model is proposed to predict whether customers in the retail industry will churn in the future. The model was compared with logistic regression and artificial neural network models, which are also frequently used in the churn prediction studies. The results of the models were compared with accuracy classification tools, which are precision, recall and AUC. The results showed that the deep learning model achieved better classification and prediction success than other compared models. © 2021, The Author(s), under exclusive license to Springer Nature Switzerland AG.Öğe Diagnosis of COVID-19 using deep CNNs and particle swarm optimization(Springer Science and Business Media Deutschland GmbH, 2022) Gürcan, Ömer Faruk; Atıcı, Uğur; Biçer, Mustafa Berkan; Doğan, OnurCoronavirus pandemic (COVID-19) is an infectious illness. A newly explored coronavirus caused it. Currently, more than 112 million verified cases of COVID-19, containing 2,4 million deaths, are reported to WHO (February 2021). Scientists are working to develop treatments. Early detection and treatment of COVID-19 are critical to fighting disease. Recently, automated systems, specifically deep learning-based models, address the COVID-19 diagnosis task. There are various ways to test COVID-19. Imaging technologies are widely available, and chest X-ray and computed tomography images are helpful. A publicly available dataset was used in this study, including chest X-ray images of normal, COVID-19, and viral pneumonia. Firstly, images were pre-processed. Three deep learning models, namely DarkNet-53, ResNet-18, and Xception, were used in feature extraction from images. The number of extracted features was decreased by Binary Particle Swarm Optimization. Lastly, features were classified using Logistic Regression, Support Vector Machine, and XGBoost. The maximum accuracy score is 99.7% in a multi-classification task. This study reveals that pre-trained deep learning models with a metaheuristic-based feature selection give robust results. The proposed model aims to help healthcare professionals in COVID-19 diagnosis. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.Öğe Exploration with process mining on how temperature change affects hospital emergency departments(Springer Science and Business Media Deutschland GmbH, 2021) Lull, Juan José; Doğan, Onur; Celda, Angeles; Mandingorra, Jesus; Lemus, Lenin; Pla, Miguel Ángel Mateo; Fernandez-Llatas, CarlosThe way patients are treated in Hospital Emergency Departments changes during the year, depending on many factors. One key component is weather temperature. Some seasonal maladies are tightly related to temperature, such as flu in cold weather or sunburn in hot weather. In this study, data from a hospital in Valencia was used to explore how harsh weather changes affect the emergency department, obtaining information about probable impacts of global warming effects in healthcare systems. Process mining techniques helped in the discovery of changes in the Emergency Departments. Some illnesses, such as heat stroke, are more prevalent during heatwaves, but more interestingly, the time to attend patients is also higher. Rapid changes in temperature are also analyzed through Process Mining techniques. © 2021, Springer Nature Switzerland AG.Öğe A framework for sustainable and data-driven smart campus(Scitepress, 2020) Köstepen, Zeynep Nur; Akkol, Ekin; Doğan, Onur; Bitim, Semih; Hızıroğlu, AbdülkadirAs small cities, university campuses contain many opportunities for smart city applications to increase service quality and use of public resources efficiency. Enabling technologies for Industry 4.0 play an important role in the goal of building a smart campus. The study contributes to the digital transformation process of.Izmir Bakircay University which is a newly established university in Turkey. The aim of the study is to plan a road map for establishing a smart and sustainable campus. A framework including an architectural structure and the application process, for the development of a smart campus have been revealed in the study. The system application is designed to be 3 stages. The system, which is planned to be built on the existing information systems of the university, includes data collection from sensors and data processing to support the management processes. The proposed framework expects to support some value-added operations such as increasing personnel productivity, increasing the quality of classroom training, reducing energy consumption, accelerating interpersonal communication and finding the fastest solution to the problems on campus. Therefore, not only a smart campus but also a system is designed for sustainability and maximum benefit from the facilities.Öğe From indoor paths to gender prediction with soft clustering(IOS Press, 2020) Doğan, Onur; Öztayşi, BaşarCustomer-based practices enable benefits to organizations in a contentious business. Offering individualized proposals increase customer loyalty to be able to afloat. Understanding customers is a vital difficulty to perform personalized recommendations. As a demographic feature, gender information essentially cannot be captured by human tracking technologies. Hence, several procedures are improved to predict undiscovered gender information. In the research, the followed indoor paths in a shopping mall are used to predict customer genders using fuzzy c-medoids, one of the soft clustering techniques. A Levenshtein-based fuzzy classification methodology is proposed the followed paths as string data. Although some studies focused on gender prediction, no research has centered on path-oriented. The novelty of the investigation is to analyze customer path data for the gender classes.Öğe Fuzzy association rule mining approach to identify e-commerce product association considering sales amount(Springer Heidelberg, 2022) Doğan, Onur; Kem, Furkan Can; Öztayşi, BaşarOnline stores assist customers in buying the desired products online. Great competition in the e-commerce sector necessitates technology development. Many e-commerce systems not only present products but also offer similar products to increase online customer interest. Due to high product variety, analyzing products sold together similar to a recommendation system is a must. This study methodologically improves the traditional association rule mining (ARM) method by adding fuzzy set theory. Besides, it extends the ARM by considering not only items sold but also sales amounts. Fuzzy association rule mining (FARM) with the Apriori algorithm can catch the customers' choice from historical transaction data. It discovers fuzzy association rules from an e-commerce company to display similar products to customers according to their needs in amount. The experimental result shows that the proposed FARM approach produces much information about e-commerce sales for decision-makers. Furthermore, the FARM method eliminates some traditional rules considering their sales amount and can produce some rules different from ARM.Öğe Gender prediction from classified indoor customer paths by fuzzy c-medoids clustering(Springer Verlag, 2020) Doğan, Onur; Öztayşi, BaşarCustomer oriented systems provides advantages to companies in competitive environment. Understanding customers is a fundamental problem to present individualized offers. Gender information, which is one of the demographic information of customers, mainly cannot be obtained by data collection technologies. Therefore, various techniques are developed to predict unknown genders of customers. In this study, customer genders are predicted from their paths in a shopping mall using fuzzy set theory. A fuzzy classification method based on Levenshtein distance is developed for string data that refer to the indoor customer paths. Although there are several ways to predict the gender, no study has focused on path-based gender classification. The originality of the study is to classify customer data into the gender classes using indoor paths. © 2020, Springer Nature Switzerland AG.Öğe Genders prediction from indoor customer paths by Levenshtein-based fuzzy kNN(Pergamon-Elsevier Science Ltd, 2019) Doğan, Onur; Öztayşi, BaşarCompanies have an advantage over the competitors if they can present customized offers to customers. Demographic information of customers is critical for the companies to develop individualized systems. While current technologies make it easy to collect customer data, the main problem is that demographic data are usually incomplete. Hence, several methods are developed to predict unknown genders of customers. In this study, customer genders are predicted from their paths in a shopping mall using fuzzy sets. A fuzzy classification method based on Levenshtein distance is developed for string data that refer to the indoor customer paths. Although there are several ways to predict the gender, no study has focused on path-based gender classification. The originality of the research is to classify customer data into the gender classes using indoor paths. (C) 2019 Elsevier Ltd. All rights reserved.Öğe Individual behavior modeling with sensors using process mining(MDPI, 2019) Doğan, Onur; Martinez-Millana, Antonio; Rojas, Eric; Sepulveda, Marcos; Munoz-Gama, Jorge; Traver, Vicente; Fernandez-Llatas, CarlosUnderstanding human behavior can assist in the adoption of satisfactory health interventions and improved care. One of the main problems relies on the definition of human behaviors, as human activities depend on multiple variables and are of dynamic nature. Although smart homes have advanced in the latest years and contributed to unobtrusive human behavior tracking, artificial intelligence has not coped yet with the problem of variability and dynamism of these behaviors. Process mining is an emerging discipline capable of adapting to the nature of high-variate data and extract knowledge to define behavior patterns. In this study, we analyze data from 25 in-house residents acquired with indoor location sensors by means of process mining clustering techniques, which allows obtaining workflows of the human behavior inside the house. Data are clustered by adjusting two variables: the similarity index and the Euclidean distance between workflows. Thereafter, two main models are created: (1) a workflow view to analyze the characteristics of the discovered clusters and the information they reveal about human behavior and (2) a calendar view, in which common behaviors are rendered in the way of a calendar allowing to detect relevant patterns depending on the day of the week and the season of the year. Three representative patients who performed three different behaviors: stable, unstable, and complex behaviors according to the proposed approach are investigated. This approach provides human behavior details in the manner of a workflow model, discovering user paths, frequent transitions between rooms, and the time the user was in each room, in addition to showing the results into the calendar view increases readability and visual attraction of human behaviors, allowing to us detect patterns happening on special days.Öğe Müşteri memnuniyetinin süreç odaklı değerlendirilmesi: Bir çağrı merkezinde süreç madenciliği uygulaması(2021) Doğan, Onur; Ayyar, Başak; Çağıl, GültekinFirmaların varlıklarını sürdürebilmeleri için müşteri odaklı bir yaklaşım sergilemeleri büyük avantaj sağlamaktadır. Müşteriler artık kendisine sunulanı değil, beklentilerini karşılayan ürün veya hizmeti satın almaktadır. Bu sebepten dolayı firmalar müşterileri dinlemek, onların ihtiyaç ve beklentilerini karşılamak amacıyla çeşitli stratejiler izlemektedirler. Bu stratejik birimlerden birisi de firma ile müşteri arasında iletişimi sağlayan çağrı merkezleridir. Firmalar çağrı merkezleri ile müşterilerin sorunlarını çözerek memnuniyet düzeyini arttırmaya çalışırlar. Bununla birlikte, müşteri memnuniyetinin yönetilebilir, ölçülebilir ve karşılaştırılabilir olması için memnuniyet anketi uygulamaktadırlar. Bu çalışmanın amacı, müşteri memnuniyet anketlerinin de göz önüne alındığı süreç madenciliği yardımıyla müşteri memnuniyetinin değerlendirilmesidir. Firmanın IT sisteminde tutulan çağrı merkezi bölümüne ait 11 günlük (18 – 28 Mart 2019) tarihleri arasındaki 42185 olay günlüğü (event log) süreç madenciliği için kullanılmıştır. Öncelikle memnuniyet anketine katılan ve katılmayan müşterilerin sistem içindeki akışı çıkarılmıştır. Ardından ankete katılan müşteriler arasında 5 (çok memnunum) puan verenlerin ve diğer müşterilerin süreçleri incelenmiştir. Çalışmada ulaşılan sonuçlardan biri, çağrı sırasında bekletilen müşterilerin daha yüksek puan vermesidir. Bu sonuç müşterilerin bekletilmekten ziyade ihtiyacının karşılanmasına daha çok önem verdiğini göstermektedir. Bu açıdan çalışma, firmanın süreç odaklı yönetimine, süreç iyileştirme çalışmalarına, strateji çalışmalarına yol gösterebilecek özelliktedir.Öğe Natural gas consumption behavior of companies by clustering analysis(Pergamon-Elsevier Science Ltd, 2021) Doğan, OnurWe have still consumed natural gas as a restricted source of energy in our daily life. Moreover, the consumption of natural gas energy will continue to increase by the year. Although many studies have focused on electrical energy consumption, natural gas is another significant energy source that can be examined. Since companies consume much more gas, their gas consumption data are examined in this study. The study contributes to the literature by applying intuitionistic fuzzy c-means (IFCM) methodology to the natural gas industry. The main motivation and advantage of the methodology is two-fold. Because of its fuzziness, one data point can be assigned into more than one cluster, similar to real-world cases. Because of its intuitionistic side, it considers membership, non-membership and hesitant degrees. These two strengths of IFCM improves the clustering accuracy. IFCM clustering was used to arrange the companies with respect to the consumption amount to increase the understandability because 1049 companies' consumption data were collected. A calendar view was developed to visualize the consumption amounts in the clusters. The changes in consumption amounts were presented in different weather temperatures. Whereas some clustered companies were directly affected by temperature changes, others were not affected. The companies in the clusters were analyzed with respect to two main criteria: regularity and complexity. The findings showed while high levels in routine are related to manufacturing companies, high complexity level is an indicator of being active in the service industry.Öğe Prioritizing Digital Health: Key Municipal Services Identified Through Fuzzy Methods(İzmir Bakırçay Üniversitesi, 2024) Erdoğan, Aleyna; Turcan, Gizem; Doğan, Onur; Coşkun, ErmanThe integration of digital technologies into healthcare systems within municipalities has elicited a transformative change in the delivery of health services. This paper explores the importance of the digitalization of health services in municipalities and represents relatively selected the most important services by employing fuzzy methods. By examining existing literature and employing a combination of qualitative and quantitative methods, including the Pythagorean Fuzzy CRITIC (PF-CRITIC) and Interval Valued Pythagorean Fuzzy WASPAS (IVPF-WASPAS) methods, this research evaluates the importance of digital transformation of several health services in municipalities. Key findings highlight that mobile health services and medical center services are the two most important municipal health activities regarding digital transformation. Through evidence-based strategies, municipalities can harness the power of digitalization to develop patient-centered, efficient, and responsive healthcare services. Therefore, this study contributes to a more inclusive approach to digitalization in healthcare, aiming to obtain the opinions of individuals who have experience with health activities in municipalities.Öğe Process mining application for analysis of customer’s different visits in a shopping mall(Springer Verlag, 2020) Doğan, Onur; Fernandez-Llatas, Carlos; Öztayşi, BaşarIndoor customers may have different purposes to visit a shopping mall. Understanding the visiting aims results in better customer relationship management. One of the ways to explain the customer purpose is to discover customer paths. Customers mainly visit stores related to their purposes. The main problem is to discover customer paths from paths. Since customers have changeable mood and there are many stores in a shopping mall, customer paths are generally too complex to evaluate. To overcome that problem, we use process mining technique. Process mining is a technique that has some algorithms to discover business processes from event logs in the databases. In this study, we consider the visited stores as an activity in a process. PALIA Suite, a process mining tool that includes several clustering methods for processes, is used to discover and cluster indoor customer paths to evaluate differences among the visits. © 2020, Springer Nature Switzerland AG.Öğe Process mining methodology for digital processes under smart campus concept(2022) Cengiz, Esra; Doğan, OnurDigital transformation affects universities as well as many industries. Universities are increasingly using various digital resources and systems to manage their knowledge. The smart campus, on the other hand, supports informed decision-making by integrating these resources and systems. Process mining provides real insights for digital transformation, allowing processes to be examined more transparently. This study aims to examine the proposed project implementation processes related to the smart university with the process mining methodology. For this purpose, 32 completed projects submitted to İzmir Bakırçay University Scientific Research Projects Coordinatorship (BAPK) with the proposed methodology adapted from Deming's continuous improvement cycle were examined. The data are taken from two different pages in the project automation system. According to the research findings, Projects are grouped into three categories: Guided Projects (GDM, 5 projects), Graduate Thesis Projects (TEZ, 5 projects), and Career Start Support Projects (KBP, 22 projects). 40.6% (13 projects) of the applications went directly to the project review stage, while 19 (59.4%) needed procedural correction. Considering the time from the creation of the application of 32 projects to the signing of the contract, it is seen that the arithmetic average of the cycle time is 15.1 weeks, and the median average is 52.5 days. The notable difference between arithmetic and median mean is that very few projects are of long duration. Procedural adjustments affect project evaluation cycle time by an additional 14 days. The carelessness or lack of knowledge of the applicants extends the cycle time of the process from 15 days to 53 days. The total duration of unnecessary waiting time in the process is 17 days. This study primarily proposes that non-digital processes should be digitized as soon as possible.Öğe Process mining technology selection with spherical fuzzy AHP and sensitivity analysis(Pergamon-Elsevier Science Ltd, 2021) Doğan, OnurProcess mining (PM) supports organizations by improving their processes using event log data collected from information technology systems. Its primary purposes are discovering actual process models, monitoring and comparing actual and desired workflows, and enhancing processes by considering the discovered model and desired flow. Because process mining gains attraction day by day, various technology companies developed process mining tools to support organizations managing their business processes with data science. Technology selection is a complicated multi-criteria decision-making (MDCM) problem under several criteria and experts' evaluation, including uncertainty and subjectivity. Spherical fuzzy set is a powerful concept to cope with uncertainty by presenting a wider decision-making area and identifying hesitancy. A fuzzy MDCM approach based on spherical fuzzy AHP is offered in this study to manage the problem of selecting process mining technology under uncertain and ambiguous conditions. Then, one-at-a-time sensitivity analysis is applied to reduce the decision-makers' subjectivity. This study results in that Price, Process Discovery, Process Analysis&Analytics are the most relevant criteria to decide PM technology. It is interesting that even although Operational Support is one of the less important criteria, it may change the decision on selecting the best PM technology.Öğe Process-centric customer analytics: Understanding visit purposes of predicted age groups with discovered paths(Old City Publishing Inc, 2020) Doğan, Onur; Öztayşi, Başar; Fernandez-Llatas, CarlosIn a general manner, customer relationship management engages in understanding customer needs and meet them. Most of the investments are either far from customer needs or based on a primitive data collection method. However, customers mainly do not behave with the same ideas to shop in the retail domain. Several studies aim to understand the visiting purposes of customers using various methods. This study seeks to uncover the visit purposes of customers from their paths. Due to customers' unpredictable moods and plenty of stores in the shopping mall, the discovered paths are usually too complicated to analyze. Process mining that can overcome this obstacle is a method that creates process flows from event logs in the databases. In this study, the visited stores were seen as an activity in a business process. PALIA, a discovery algorithm in process mining, was applied to find and cluster customer paths. This study contributes to the literature by examining customer needs from their indoor paths, which were created by the PALIA algorithm. It facilitates to analyze discrepancies among the visits for the same customer. Moreover, the discovered paths are considered according to the age groups predicted by Levenshtein fuzzy kNN (L-FkNN).
