Wyniki wyszukiwania - BazTech

Ograniczanie wyników

3 Scherer M.

Znaleziono wyników: 3

Liczba wyników na stronie

Wyniki wyszukiwania

Sortuj według:

Ogranicz wyniki do:

Multi-layer neural networks for sales forecasting

Scherer M.

Journal of Applied Mathematics and Computational Mechanics

2018

Vol. 17, nr 1

61--68

Predicting business operations on the basis of previous events plays an important role in managing a company. In the paper, we predict monthly sales volume of a textile warehouse by mathematical tools. To this end we use a feedforward artificial neural network trained on past data. The network predicted the volume with high accuracy. For the examined company, such prediction is very important as nearly the entire range of products is imported from different countries and the goods have to be ordered in advance.

Management of reverse logistics processes with Microsoft Dynamics NAV

Scherer M.

Production Engineering Archives

2017

Vol. 15

11--14

Appropriate management of waste streams is a very important part of business operations as it is reflected in the reduction in the flow and use of materials. It also minimizes negative impact on the environment. The article discusses the capabilities of Microsoft Dynamics NAV in the management of reverse logistics processes. We also developed a system supporting reverse logistics as a module for Microsoft Dynamics NAV. It automatically counts waste dividing them into appropriate groups. At the time of writing there was no direct support for waste management in the Dynamics NAV system.

Waste flows management by their prediction in a production company

Scherer M.

Journal of Applied Mathematics and Computational Mechanics

2017

Vol. 16, nr 2

135--144

In this paper we apply neuro-fuzzy systems to predict waste production in a company. Waste is produced by companies at every phase of their business, e.g. at the stage of supply, production and distribution. We used data on the production waste of one of the typical Polish manufacturing companies operating in the automotive industry. We predicted monthly waste production by data-driven learning of neuro-fuzzy systems. Neuro-fuzzy systems share with artificial neural-networks the ability to learn from data and the interpretability with fuzzy systems. In the experiments we achieved a high rate of prediction.