Browsing by Author "Soylemez, Ismet"

Now showing 1 - 7 of 7

Citation - WoS: 7
Citation - Scopus: 11
An Ant Colony Optimisation Algorithm for Balancing Two-Sided U-Type Assembly Lines With Sequence-Dependent Set-Up Times
(Springer India, 2018) Delice, Yilmaz; Aydogan, Emel Kizilkaya; Soylemez, Ismet; Ozcan, Ugur
Some practical arrangements in assembly lines necessitate set-up times between consecutive tasks. To create more realistic models of operations, set-up times must be considered. In this study, a sequence-dependent set-up times approach for two-sided u-type assembly line (TUAL) structures is proposed for the first time. Previous studies on TUAL have not included set-up times in their analyses. Furthermore, an algorithm based on the Ant Colony Optimization (ACO) algorithm, which is using a heuristic priority rule based procedure has been proposed in order to solve this new approach. In this paper, we look at the sequence-dependent set-up times between consecutive tasks and consecutive cycles, called the "forward set-up time'' and the "backward set-up time'', respectively. Additionally, we examine the "crossover set-up time'', which arises from a new sequence of tasks in a crossover station. In order to model more realistic assembly line configurations, it is necessary to include sequence-dependent set-up times when computing all of the operational times such as task starting times and finishing times as well as the total workstation time. In this study, the proposed approach aims to minimize the number of mated-stations as the primary objective and to minimize the number of total workstations as a secondary objective. In order to evaluate the efficiency of the proposed algorithm, a computational study is performed. As can be seen from the experimental results the proposed approach finds promising results for all literature-test problems.
Citation - WoS: 1
Citation - Scopus: 1
Strategic Investment in BIST100: A Machine Learning Approach Using Symbolic Aggregate Approximation Clustering
(Univ Cincinnati industrial Engineering, 2025) Nalici, Mehmet Eren; Soylemez, Ismet; Unlu, Ramazan
This study employs the Symbolic Aggregate Approximation (SAX) clustering method to enhance investor decision-making on the Borsa Istanbul (BIST100) by identifying companies exhibiting analogous stock movements. The data from 81 BIST100 companies over a three-year period has been analyzed, with a focus on risk minimization and strategic investment. The SAX method, integrated with a dendrogram, categorizes stocks into sector-based and non-sector-based clusters, providing insights for portfolio optimization. The results demonstrate the effectiveness of the method in identifying relevant stock patterns across sectors, aiding in more informed investment decisions. This approach highlights the need for considering multiple factors in investment strategies, offering a new perspective on stock market analysis with advanced clustering techniques.
Fluctuations in the European Housing Market: Forecasting the House Price Index Change with Time-Series Models
(Gazi Univ, 2025) Soylemez, Ismet; Nalici, Mehmet Eren; Unlu, Ramazan
This study presents a comparative analysis of a time series models for forecasting changes in the Housing Price Index (HPI) in 27 European countries. Accurate HPI forecasting is essential for the development of effective policies and investment strategies. The study uses quarterly data from Q4 2013 to Q3 2024. Methodologically, the stationarity of the data is tested using the Dickey-Fuller test and differencing is applied to non-stationary series. The ARIMA, Holt Linear Trend, Additive Damped Trend and Exponential Smoothing models are evaluated based on the lowest mean squared error (MSE) value for each country. The findings confirmed the heterogeneous structure of the European housing market, showing that no single model is suitable for all countries. The ARIMA model provided the most accurate results for nine countries, while the Holt Linear Trend and Additive Damped Trend models performed best in seven countries each. Forecasts for the period 2025-2026 are generated based on these results. This study highlights the importance of adopting country-specific and adaptable forecasting approaches to accommodate the varying dynamics of European housing markets.
Citation - WoS: 3
Association Rules on Traffic Accident: Case of Ankara
(Ege Univ, Fac Economics & Admin Sciences, 2016) Soylemez, Ismet; Dogan, Ahmet; Ozcan, Ugur
In this study, association rules analysis of the data mining techniques are used for data of traffic accidents in 2010 and some rules are obtained. With this rules, what is the possibility of accident which resulted anybody injured for "different weather conditions (snowy, rainy etc.)", "where the accidents occurred (street, road etc.)" and "way situations (separated road or not)". Different algorithms are used to analyze the association rules. Apriori algorithm is selected for this study and SPSS Clementine 12.0 is used for this algorithm. Firstly, frequency of items are found. Then, items are grouped. In this study, data preprocessing is done and missing values are filled or rejected. In the second phase, outliers are rejected and data type is converted type of 1-0 (binary). In the third phase, Apriori algorithm is applied and results are evaluated.
Citation - WoS: 3
Long-Term Supplier Selection Problem: A Case Study
(Sciencepark Sci, Organization & Counseling Ltd, 2017) Senyigit, Ercan; Soylemez, Ismet; Atici, Ugur
The problem to select a supplier has taken the best supplier according to all combinations of sorting criteria. With regard to the supplier selection problem, the priority ranking of the criteria taken into consideration to solve this problem has a direct impact on the determination of the "optimum" supplier. This paper provides a case study made for the supplier selection problem involving all possible rankings in cable transfer pulleys used in rolling products by a company X which is active in a steel cable industry in Kayseri, Turkey. NG's model is used in the solution stage in the application. In this research, a new type of supplier selection problem called long-term supplier selection problem with a case study is proposed. Finally, solution of long-term supplier selection problem by a new approach is presented. According to the values obtained by scoring, it has been determined that a long-term agreement can be concluded with the supplier no. 4 (S4) and a long or medium-term agreement can be made with supplier no. 2 (S2). S1, S3 and S5 are determined as the suppliers with the worst performances. As a result, it has been shown to the company that working with S1, S3 and S5 suppliers will not generate any benefits.
Sustainable Economic Development Indicators: The Case of Turkey
(World Scientific Publ Co Pte Ltd, 2016) Soylemez, Ismet; Dogan, Ahmet; Ozcan, Ugur
Sustainable development indicators are a good road map for financial, social and economic targets of countries. This paper aims to show which indicators are affect sustainable development of Turkey for last twelve years. 132 sustainable development indicators determined by European Union Statistical Office (Eurostat). Sustainable development indicators are calculated by related unit, institution or establishment in the direction of definitions determined by Eurostat. These indicators are calculated by TUIK (Turkish Statistical Institute) for Turkey. Some indicators as follows: socio-economic development, sustainable consumption and production, climate change and energy, sustainable transport, financing for sustainable development. However, only economic indicators are presented and analyzed in the case study. Official development assistance has tenfold rise in the last 12 years. These indicators will show which areas at economic changes should be considered to the sustainable development of country.
High-Accuracy Identification of Durian Leaf Diseases: A Convolutional Neural Network Approach Validated with K-Fold Cross-Validation and Bayesian Optimization
(Springer, 2025) Soylemez, Ismet; Nalici, Mehmet Eren; Unlu, Ramazan
To address the economic losses caused by plant diseases in durian farming, this study presents an optimized deep learning model that diagnoses diseases from leaf images with high accuracy. The model's performance is maximized through Bayesian optimization and hyperparameter tuning, while its reliability is maximized through layered five-fold cross-validation. Training the convolutional neural network model on 2595 leaf images displaying six different states (five diseased and one healthy) resulted in an average test accuracy of 91.98%. This high, consistent success rate demonstrates the model's generalizability to different datasets without overfitting. While the 'Healthy' and 'Algal' classes were successfully detected with high F1-scores, there are difficulties distinguishing between the 'Blight' and 'Colletotrichum' classes due to visual similarities. This study establishes a new reference point for durian disease classification and makes a significant contribution to the development of reliable artificial intelligence-based diagnostic tools for precision agriculture.