10 March 2022 in Journal of Advanced Research in Natural and Applied Sciences
In this study, financial prediction models have been developed over the silver / ounce parity using deep learning architectures. LSTM and ARIMA architectures, which are deep learning algorithms, are used. By loading the train-ing and test data into the established algorithms, the system was learned and a graphical estimation was requested on the silver / ounce parity for the next 10 days. Written algorithms can produce different results each time they are run. However, in the graphs we have taken as an example, the graph created with the ARIMA architecture has produced a more realistic result by specifying a range and making an upward forecast. The prediction chart we obtained with the LSTM architecture did not create a much decrease or upward forecast. However, as a feature of the LSTM algorithm, it clearly predicted the daily closing values, and did not specify an estimation as a range and direction as in the study with the ARIMA architec-ture. It should not be forgotten that these algorithms are dynamic and can give different results in predictions even when they are run with the same data. According to the results obtained in the research, although the LSTM architecture clearly stated the daily closing values as numbers, the estimation study made with the ARIMA architecture produced a result closer to the graph in terms of both interval and direction.
1 January 2014 in Journal of Industrial and Intelligent Information
Journal of Industrial and Intelligent Information
28 August 2020 in Arabian Journal for Science and Engineering
30 June 2023 in International Journal of Computational and Experimental Science and Engineering
Time is the most precious resource for any business simply because no one can bring time back. Therefore, there is a huge need to be able to control time accurately. Also, the competitiveness between companies increased the value of time. Many investments were allocated to build methodologies that help to use time effectively. Because it became a fact that the speed of work accomplishment is the main factor for being a considerable competitor. Planning for future projects usually relays on non-fixed but mostly expected data. It is more reliable to use fuzzy methods for this situation. In this study, Fuzzy PERT (FPERT) was used as a project management technique to plan the construction of a marble factory from the establishment phase to the plan of the machines that will be used later on. FPERT showed more realistic results than any classical method would. Out of 16 routes, the final result of the completion time was (90.9,122.1,151.9) days which was determined after triangular fuzzy numbers for the activity times in the entire project. This article aims to prove the efficiency of fuzzy methodologies especially FPERT to be conducted in future planned projects through this real-life case study.
31 January 2024 in Academic Platform Journal of Engineering and Smart Systems
With the increase in the need for electrical energy, production amount planning is of great importance in order not to experience restrictions in terms of use, to meet the required electricity production, and to evaluate the excess production efficiently. In this study, a generation forecasting model was created with the fuzzy logic method to determine the electricity generation strategy. The created model is aimed to determine the electrical energy that needs to be produced daily by using the previous day's production amount, temperature, and season data. Three separate sets of data were used to test the fuzzy logic model built using information from the General Directorate of Meteorology (GDM) and Energy Markets Operations Inc. (EMOI). Fuzzy Logic was used to predict the data and the accuracy rates were found to be high. An improvement was observed when the accuracy rates were compared with the accuracy rates obtained in the Multiple Linear Regression Model. The accuracy rates of the model were initially examined using the Fuzzy Logic approach on weekdays and weekends, followed by a seasonal analysis and an assessment of the model's performance. As a result of the analysis, it was observed that the model worked with high accuracy in the autumn season and on weekend days.
31 January 2023 in Uluslararası Muhendislik Arastirma ve Gelistirme Dergisi
İş değerlendirme; işletmelerdeki performans değerlendirme ve ücret yönetimine girdi oluşturmak amacıyla işlerin maharet, sorumluluk, iş koşulları vb. gibi faktörler çerçevesinde değerlendirilerek biçimsel ve sistematik olarak karşılaştırılmasıdır. Bu çalışmada Demir Çelik Sektörü’ne faaliyet gösteren bir işletmenin çelik üretim müdürlüğü birimindeki mevcut 48 adet mavi yaka işçilik pozisyonları değerlendirilmiştir. Öncelikle AHP yöntemi ile ikili karşılaştırma matrisleri oluşturulmuştur. Bunun sonucunda 48 adet mavi yaka işçilik pozisyonuna ait yakınlık katsayıları hesaplanarak sıralama elde edilmiştir. Topsis ve Bulanık Topsis sonucu ortaya çıkan işçilik pozisyonlarına ait puanlar; Ünite Amiri, Şef ve ilgili kısımdaki Formenin görüş ve kararı doğrultusunda puanlanan işçilik pozisyonlarının sıralaması ile karşılaştırılmıştır. Bu amaca uygun olarak da hedef, yapılan iş değerlendirme sonucu ortaya çıkan işlerin önem düzeyi ve sıralaması doğrultusunda, o işe uygun çalışanların belirlenmesi ve çalışanların performanslarının değerlendirilerek, proseste yapılabilecek olan iyileştirme çalışmalarının şirkete tavsiye olarak verilmesidir.