Abstract
The direct investment and joint ventures of clothing manufacturers in developing regions have grown rapidly over the last few decades. Manufacturers have encountered difficulties when selecting the plant location however, because their decisions are based on subjective judgments and inconsistent assessments rather than on a clear classification system. Variances between potential plants cannot always be represented in terms of objective value, such as country risk and community facilities. Clothing manufacturers must also consider more intangible factors such as the social environment and political stability when deciding the most appropriate site for production. Classification methods are a more efficient and less time-consuming way of organizing a number of sites into different levels of appropriateness, thereby allowing clothing manufacturers to make more informed and objective decisions about plant locations. This chapter investigates two recent types of classification technique; unsupervised and supervised artificial neural networks. The limitations of the adaptive resonance theory of the unsupervised artificial neural network are demonstrated in this chapter and a comparison of the performance of the three types of supervised artificial neural network, back propagation, learning vector quantization and probabilistic neural network are presented. The supervised artificial neural network has proved to be an effective classifier in which the probabilistic neural network performs better than in the other networks on the site selection problem.
Original language | English |
---|---|
Title of host publication | Optimizing Decision Making in the Apparel Supply Chain Using Artificial Intelligence (AI) |
Subtitle of host publication | From Production to Retail |
Publisher | Elsevier Inc. |
Pages | 41-54 |
Number of pages | 14 |
ISBN (Print) | 9780857097798 |
DOIs | |
Publication status | Published - 1 Jan 2013 |
Keywords
- Artificial neural network
- Clothing manufacture
- Plant location
ASJC Scopus subject areas
- General Engineering