Abstract
Computers have transformed the design of everything from cars to coffee cups. Now the food industry faces the same revolution, with intelligent computer models being used in the design, production and marketing of food products. The combined market capitalisation of the world’s biggest food, cosmetics, tobacco, clothing and consumer electronics companies is $2 trillion, forming the world’s 500 richest companies. Many of these “fast‐moving consumer goods” companies now apply intelligent computer models to the design, production and marketing of their products. Manufacturers aim to develop and produce high volumes of these commodities with minimum costs, maximum consumer appeal, and of course, maximum profits. Products have limited lifetimes following the fashions of the consumer‐driven marketplace. With food and drink, little is known about many of the underlying characteristics and processes. Product development and marketing must therefore be rapid, flexible and use raw data alongside existing expert knowledge. Intelligent systems, such as neural networks, fuzzy logic and genetic algorithms, mimic human skills such as the ability to learn from incomplete information, to adapt to changing circumstances, to explain their decisions and to cope with novel situations. These systems are being used to tackle a growing range of problems, from credit card fraud detection and stock market prediction to medical diagnosis and weather forecasting. This paper introduces intelligent systems and highlights their use in all aspects of the food and drink industry, from ingredient selection, through product design and manufacture, to packaging design and marketing.
Subject
Food Science,Business, Management and Accounting (miscellaneous)
Reference39 articles.
1. Bimbenet, J. and Trystram, G. (1992), “Process control in the food industry”, Food and Bioproducts Processing, Vol. 70 No. C3, pp. 115‐25.
2. Bishop, C.M. (1995), Neural Networks for Pattern Recognition, Clarendon Press, Oxford.
3. Burges, C.J.C. (1998), “A tutorial on support vector machines for pattern recognition”, Data Mining and Knowledge Discovery, Vol. 2 No. 2, pp. 121‐67.
4. Clark, P. and Boswell, R. (1991), “Rule induction with CN2: some recent improvements”, in Proceedings of the Fifth European Working Session on Learning, Springer, Berlin, pp. 151‐63.
5. Corney, D. (2000), “Designing food with Bayesian belief networks”, in Parmee, I. (Ed.), Evolutionary Design and Manufacture – ACDM2000, Springer‐Verlag, pp. 83‐94.
Cited by
15 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献