Browsing by Author "Bilgili, Erdem"

Now showing 1 - 2 of 2
  • Thumbnail Image
    ItemOpen Access
    Design and development of an emulated human cognition using novel 3D neural networks
    (Cranfield University Press, 2013-09-19) Ziarati, Martin; Ziarati, Reza; Akdemir, Başak; Bilgili, Erdem
    This paper describes the development of an Emulated Human Cognition (EHC) which is designed and based on a replicated human brain with a right- and a left- hand lobe, one a deductive side and the other a generic one. Right-hand lobe consists of a newly designed Artificial Neural Network (ANN) with a multi-hidden layer topology. Left-hand lobe is a newly designed 3-dimensional cellular neural network. The input variables presented to the EHC are immediately analysed for it to decide which lobe should be activated. The EHC, when fully developed, has almost an unlimited memory capacity and is capable of immediate recall of any data in its almost unlimited memory locations. EHC has been used in several applications where neural networks have been used to establish relationship between two or more sets of variables. In this paper the EHC has been used to forecast demand for a given product.
  • Thumbnail Image
    ItemOpen Access
    Development of a neural network mathematical model for demand forecasting in fluctuating markets
    (Cranfield University Press, 2013-09-19) Ziarati, Martin; Bilgili, Erdem; Singh, Lakhvir; Akdemir, Başak; Ziarati, Reza
    Research has shown that Neural Networks (NNs) when trained appropriately are the best forecasting system compared to conventional techniques. Research has shown that there is no system to accurately forecast sudden changes in demand for a given product. This paper reports on the development of a recovery method when a sudden change in demand has taken place. This error in forecasting demand leads to either excessive inventories of the product or shortages of it and can lead to substantial financial losses for the company producing or marketing the product. Two recovery methods have been developed and described in this paper: RZ recovery and Exponential Smoothing (ES). In the RZ recovery once a sudden change has taken place, a ‘soft’ Poke-Yoke (PY) system is setup warning the company that the normal forecasting system can no longer be relied upon and a recovery system needs to be initiated, with re-forecasting initiated.