Browsing by Author "Sütçü, Muhammed"

Now showing 1 - 7 of 7

Analysis of under-five mortality by diseases in countries with different levels of development: a comparative analysis
(Prusa Medikal Yayıncılık, 2023) Sütçü, Muhammed; Güner, Pınar; Ersöz, Nur Şebnem; 0000-0002-8523-9103; 0000-0001-5979-0375; 0000-0003-3343-9936; AGÜ, Mühendislik Fakültesi, Endüstri Mühendisliği Bölümü; Sütçü, Muhammed; Güner, Pınar; Ersöz, Nur Şebnem
Objectives: The right to health is critical for children because they are sensitive beings who are more susceptible to disease and health problems. It would be beneficial to compare child mortality rates in countries with different levels of development and to conduct studies to address them by taking into account their causes. This study aims to analyze the situation of developed, developing and least developed countries in terms of causes under-5 child mortality (U5CM) determined by World Health Organization and to identify the similarities or differences of under-five mortality. Methods: Child mortality rates per 1,000 live births between 2000 and 2017 years in between different age groups (0-27 days and 1-59 months) by causes (disease-specific) were obtained from World Health Organization for a total 15 countries including developed, developing and least developed countries. Regression analysis was performed to identify which causes have more impact on child mortality. In addition, the relationship between diseases was calculated using Euclidean distance, and diseases were clustered using k-means clustering algorithm for each country. Results: As a result of mathematical and statistical analysis, it was seen that causes of child mortality have a significant relation with the development level of country where a child was born. Conclusions: It has been observed that the causes of child mortality in countries with different levels of development vary depending on different factors such as geographical conditions, air quality population and access to medicine.
Electricity Load Forecasting Using Deep Learning and Novel Hybrid Models
(Sakarya University, 2022) Sütçü, Muhammed; Şahin, Kübra Nur; Koloğlu, Yunus; Çelikel, Mevlüt Emirhan; Gülbahar, İbrahim Tümay; 0000-0002-8523-9103; 0000-0001-9786-6270; 0000-0001-6198-569X; 0000-0001-9264-4345; 0000-0001-9192-0782; AGÜ, Mühendislik Fakültesi, Endüstri Mühendisliği Bölümü; Sütçü, Muhammed; Şahin, Kübra Nur; Koloğlu, Yunus; Çelikel, Mevlüt Emirhan; Gülbahar, İbrahim Tümay
Load forecasting is an essential task which is executed by electricity retail companies. By predicting the demand accurately, companies can prevent waste of resources and blackouts. Load forecasting directly affect the financial of the company and the stability of the Turkish Electricity Market. This study is conducted with an electricity retail company, and main focus of the study is to build accurate models for load. Datasets with novel features are preprocessed, then deep learning models are built in order to achieve high accuracy for these problems. Furthermore, a novel method for solving regression problems with classification approach (discretization) is developed for this study. In order to obtain more robust model, an ensemble model is developed and the success of individual models are evaluated in comparison to each other
Movie Recommendation Systems Based on Collaborative Filtering: A Case Study on Netflix
(Erciyes Üniversitesi, 2021) Sütçü, Muhammed; Erdem, Oğuzkan; Kaya, Ecem; 0000-0002-4634-7638; 0000-0002-8547-7929; 0000-0002-8523-9103; AGÜ, Mühendislik Fakültesi, Endüstri Mühendisliği Bölümü; Sütçü, Muhammed; Erdem, Oğuzkan
User ratings on items like movies, songs, and shopping products are used by Recommendation Systems (RS) to predict user preferences for items that have not been rated. RS has been utilized to give suggestions to users in various domains and one of the applications of RS is movie recommendation. In this domain, three general algorithms are applied; Collaborative Filtering that provides prediction based on similarities among users, Content-Based Filtering that is fed from the relation between item-user pairs and Hybrid Filtering one which combines these two algorithms. In this paper, we discuss which methods are more efficient in movie recommendation in the framework of Collaborative Filtering. In our analysis, we use Netflix Prize dataset and compare well-known Collaborative Filtering methods which are Singular Value Decomposition, Singular Value Decomposition++, KNearest Neighbour and Co-Clustering. The error of each method is calculated by using Root Mean Square Error (RMSE). Finally, we conclude that K-Nearest Neighbour method is more successful in our dataset.
A NEW RATIONAL CLASSIFICATION APPROACH BY THE NEW MIXED DATA BINARIZATION METHOD
(Süleyman Demirel Üniversitesi, 2023) Sütçü, Muhammed; Gülbahar, İbrahim Tümay; 0000-0001-9192-0782; AGÜ, Mühendislik Fakültesi, Endüstri Mühendisliği Bölümü; Sütçü, Muhammed; Gülbahar, İbrahim Tümay
Classification algorithm is a supervised learning technique that is used to identify the category of new observations. However, in some cases, quantitative and qualitative data must be used together. With this approach, we tried to overcome the problems encountered in using quantitative and qualitative data together. In this paper, we model a new classification technique by converting all types of data to binary data because in the real world, data are classified in different types such as binary, numeric, or categorical. By this way, we develop a more accurate and efficient mixed data binarization approach for multi-attribute data classification problems. First, we determine the classes from available dataset and then we classify the new instances into these predetermined classes by using the new proposed data binarization approach. We show how each step of this algorithm could be performed efficiently with a numeric example. Then, we apply the proposed approach on a well-known iris dataset and our model show promising results and improvements over previous approaches.
Optimal location determination of electric vehicle charging stations: A case study on Turkey's most preferred highway
(Bitlis Eren Üniversitesi, 2022) Sütçü, Muhammed; Gülbahar, İbrahim Tümay; 0000-0002-8523-9103; 0000-0001-9192-0782; AGÜ, Mühendislik Fakültesi, Endüstri Mühendisliği Bölümü; Sütçü, Muhammed; Gülbahar, İbrahim Tümay
Today, electric vehicles are seen as one of the most suitable and environmentally friendly alternatives to internal combustion engine vehicles. An important issue related to the dissemination of electric vehicles is the location of the vehicle charging network and specifically the optimum location selection of the charging stations. Generally, most of the studies focus on popular destinations such as city centers, shopping areas, bus stations, and airports. Although these places are often used in normal life, they can usually provide an adequate solution for daily charging needs due to the number of alternative charging stations. However, finding adequate charging stations is not possible in intercity travels especially in highways. In this paper, we proposed a decision model to determine the location of electric car charging stations in highways. We create an optimization model to decide the optimum locations for the charging stations that can meet the customer demands on the Istanbul-Ankara highway. The proposed model determines optimum charging stations that enable passengers traveling with their electric vehicles to travel in Istanbul-Ankara highway in the shortest time.
Parameter uncertainties in evaluating climate policies with dynamic integrated climate-economy model
(SPRINGER, 2024) Sütçü, Muhammed; 0000-0002-8523-9103; AGÜ, Mühendislik Fakültesi, Endüstri Mühendisliği Bölümü; Sütçü, Muhammed
Climate change is a complex issue with signifcant scientifc and socio-economic uncertainties, making it difcult to assess the efectiveness of climate policies. Dynamic Integrated Climate-Economy Models (DICE models) have been widely used to evaluate the impact of diferent climate policies. However, since climate change, long-term economic development, and their interactions are highly uncertain, an accurate assessment of investments in climate change mitigation requires appropriate consideration of climatic and economic uncertainties. Moreover, the results of these models are highly dependent on input parameters and assumptions, which can have signifcant uncertainties. To accurately assess the impact of climate policies, it is crucial to incorporate uncertainties into these models. In this paper, we explore the impact of parameter uncertainties on the evaluation of climate policies using DICE models. Our goal is to understand whether uncertainty signifcantly afects decision-making, particularly in global warming policy decisions. By integrating climatic and economic uncertainties into the DICE model, we seek to identify the cumulative impact of uncertainty on climate change. Overall, this paper aims to contribute to a better understanding of the challenges associated with evaluating climate policies using DICE models, and to inform the development of more efective policy measures to address the urgent challenge of climate change.
A variant SDDP approach for periodic-review approximately optimal pricing of a slow-moving a item in a duopoly under price protection with end-of-life return and retail fixed markdown policy
(Elsevier, 2023) Yildiz, Baris; Sutcu, Muhammed; 0000-0002-8523-9103; AGÜ, Mühendislik Fakültesi, Endüstri Mühendisliği Bölümü; Yıldız, Barış; Sütçü, Muhammed
In this paper, we examine a selling environment where a manufacturer-controlled retailer and an independent retailer sell a slow-moving A item. The manufacturer offers the independent retailer a price protection contract stipulating that the manufacturer reimburses the independent retailer in case of a reduction in the wholesale price. The price set by the independent retailer is assumed to be determined by Retail Fixed Markdown (RFM) policy. The manufacturer also offers the independent retailer a special discount rate for the replenishment orders and the retailers are assumed to follow (R, S) inventory replenishment policy. The manufacturer adopts a periodic-review pricing strategy and the mean demand observed by each retailer in a given period depends on the prices. We also take the customers choosing no-purchase option into account. We employ multinomial logit (MNL) models to forecast customers’ preferences based on retail prices. The retailers’ market shares are estimated by customized choice probability functions. We propose stochastic programming models to determine the manufacturer’s pricing strategy. Then, we propose a variant Stochastic Dual Dynamic Programming (SDDP) algorithm to determine the manufacturer’s approximately optimal pricing strategy by getting around three curses of dimensionality. Then, we move on to the observations on the impact of four critically important contractual parameters on the price, the market shares and the expected total net profits and finally discuss some possible approaches for the selection of the best compromise values of those contractual parameters.