Yazar "Simsir, Fuat" seçeneğine göre listele

Listeleniyor 1 - 5 / 5
  • Küçük Resim Yok
    Öğe
    Demand forecasting with color parameter in retail apparel industry using artificial neural networks (ANN) and support vector machines (SVM) methods
    (Pergamon-Elsevier Science Ltd, 2020) Guven, Ilker; Simsir, Fuat
    In this study, product variety has been taken into account and sales forecasting has been performed by using artificial intelligence to minimize error rate, in the retail garment industry. In this context, artificial intelligence models such as artificial neural networks (ANN) and support vector machines (SVM) have been established and inferences from the datasets have been made. During the establishment of the models, datasets have been prepared with and without color details of the products, for nine different products as separately and one combined dataset which consists all products, then the forecast process was carried out. Thus 20 different models were established and compared. Along with color detail, other variables that may have an effect on the sales performance such as weather, gender, special days etc., have been added to proposed models. In the comparison of methods root mean square error has been taken into consideration. As a result of this study, it has been determined that ANN outperformed SVM on seven datasets out of ten for the datasets without color and their performances were even for the datasets with color. The reliability of this study has been increased by comparing the results of the methods.
  • Küçük Resim Yok
    Öğe
    Machine Learning Algorithms with Intermittent Demand Forecasting: An Application in Retail Apparel with Plenty of Predictors
    (E.U. Printing And Publishing House, 2021) Guven, Ilker; Uygun, Ozer; Simsir, Fuat
    Demand forecasting is a key factor for apparel retail stores to sustain their business, especially where there are variety of products and intermittent demand. In this study, two of the most popular machine learning methods, random forest (RF) and k-nearest neighbour (KNN), have been used to forecast retail apparel's intermittent demand. Numerous variables that may have an effect on the sales, have been taken into account one of which is defined as special day that might trigger intermittency in the demand. During the forecast application, four different datasets were used to provide reliability. 28 different variables were used to increase accuracy of the forecasting and experience of the behaviours of the algorithms. Root mean square error (RMSE) was used to evaluate performance of the methods and as a result of this study, RF showed better performance in all four datasets comparing to KNN.
  • Küçük Resim Yok
    Öğe
    A metaheuristic solution approach to capacitied vehicle routing and network optimization
    (Elsevier - Division Reed Elsevier India Pvt Ltd, 2019) Simsir, Fuat; Ekmekci, Dursun
    The vehicle routing problem (VRP) is one of the problem types that are sought after for a long time by trying out different techniques and attracting attention in terms of optimization. In most VRP types, route cost is associated with distance, and a shorter distance solution is considered a more successful solution. While the shortest distance goal provides significant advantages in terms of cost and time to businesses, this makes it attractive for further research. When examining the types of problems having different directions and areas devised from different points of view on vehicle routing, it can be said that the closest approach to practical application is the vehicle routing problem with simultaneous delivery and pickup (VRPSDP). In this study, a solution proposal is presented for the VRPSDP using the Artificial Bee Colony (ABC) algorithm and the application is tested with the benchmark problem data sets commonly used for VRPSDP in the literature. When the results are compared with the least cost route solutions in the literature, it is observed that despite the few parameters, the proposed method can produce low-cost solutions very close to the most successful solutions in the literature. (C) 2019 Karabuk University. Publishing services by Elsevier B.V.
  • Küçük Resim Yok
    Öğe
    A new model based on Artificial Bee Colony algorithm for preventive maintenance with replacement scheduling in continuous production lines
    (Elsevier - Division Reed Elsevier India Pvt Ltd, 2019) Ozcan, Selcuk; Simsir, Fuat
    Rails are produced in continuous production lines and most of the equipment in this line are huge. Thus, preventive maintenance in these lines is performed by replacing the parts. Since the part replacement in this kind of production lines halts production, it decreases production outputs. An effective scheduling reduces the downtime to the lowest possible levels. In this study, we propose a replacement scheduling model for a rail production line. The replacement scheduling problem is discussed for 1349 parts annually. The problem was studied for the first time in the literature both in size and in the way, it was handled. A new model is proposed integrating Bin Packing solution method into the replacement scheduling problem assuming the replacements as an item. Bottom Left (BL) Bin Packing algorithm is used to assign the replacements in two solution methods. Firstly, the classical Time-Based Replacement (TBR) method was analysed and the downtime was calculated. Secondly, the Flexible Time-Based Replacement (FTBR) method was developed integrating Artificial Bee Colony (ABC) algorithm. When the results are examined for both solutions, FTBR provided a decrease of approximately 12% in downtime compared to TBR. This improvement means 21 328 tons of rail production. As a result, the proposed solution method can be easily applied for any replacement scheduling problem. (C) 2019 Karabuk University. Publishing services by Elsevier B.V.
  • Küçük Resim Yok
    Öğe
    Selecting Display Products for Furniture Stores Using Fuzzy Multi-criteria Decision Making Techniques
    (Springer International Publishing Ag, 2018) Uygun, Ozer; Guven, Ilker; Simsir, Fuat; Aydin, Mehmet Emin
    Efficient marketing in which the right products are supplied to the right consumer plays a crucial role for a profitable business in the age of highly accessible and competitive global market. This fact enforces producers to clearly identify and analyze the needs of consumers and to display their products respecting locality based on customers' needs. The position of the business is strengthened within the market and its competiveness increases by supplying and displaying the products suitable to regional consumers' preferences. In this study, an integral fuzzy multi criteria decision making technique is proposed for an effective decision making process to select the most suitable display products to the consumers' needs and preferences. The approach has been applied to identify the most suitable set of modular furniture products to be displayed at a local store that locates in Bursa city of Turkey. The approach uses Fuzzy DEMATEL method to work out the interrelations of chosen criteria, which are weighted with Fuzzy ANP and finally suggest a rank-based list of products with Fuzzy PROMETHEE. The results are verified with the expert view and found very useful.