Location: Crop Production Systems Research Unit
Title: Advances in Artificial Neural Networks - Methodological Development and Application Author
Submitted to: Algorithms
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: July 30, 2009
Publication Date: August 3, 2009
Citation: Huang, Y. 2009. Advances in Artificial Neural Networks - Methodological Development and Application. Algorithms. 2(3):973-1007 Interpretive Summary: Artificial neural networks are the outcome of studies of human brain in mimic of biological neuron system for mathematical and empirical modeling of data from engineering and scientific research. Compared to conventional statistical analysis, artificial neural networks are a “model-free” method that does not require assuming the model form before modeling input and output process data. This method provides a powerful tool to characterize a broad range of input and output relationships, linear and nonlinear. Artificial neural networks have been extensively studied and applied during the last three decades in engineering and scientific research. Based on structures and training algorithms, many different networks are available, such as multilayer perceptron networks using backpropagation training algorithm, radial basis function networks with input data clustering, recurrent and feedback networks with backpropagation with time, and unsupervised Kohonen self-organizing network. Artificial neural networks have been integrated with other advanced methods such as fuzzy logic and wavelet analysis to provide robust solutions for some applications. As an advanced development, support vector machines have emerged as a set of high-performance supervised generalized linear classifiers to solve the problems in parallel with artificial neural networks. In agricultural and biological engineering, the interest of ANNs has been growing greatly in the last fifteen years in studies of soil and water regimes related to crop growth, analysis of the operation of food processing, and support of decision-making in precision farming. Starting from early 2000s, studies and applications of support vector machines have been growing steadily as well.
Technical Abstract: Artificial neural networks as a major soft-computing technology have been extensively studied and applied during the last three decades. Research on backpropagation training algorithms for multilayer perceptron networks has spurred development of other neural network training algorithms for other networks such as radial basis function, recurrent network, feedback network, and unsupervised Kohonen self-organizing network. These networks, especially the multilayer perceptron network with a backpropagation training algorithm, have gained recognition in research and applications in various scientific and engineering areas. In order to accelerate the training process and overcome data over-fitting, research has been conducted to improve the backpropagation algorithm. Further, artificial neural networks have been integrated with other advanced methods such as fuzzy logic and wavelet analysis, to enhance the ability of data interpretation and modeling and to avoid subjectivity in the operation of the training algorithm. In recent years, support vector machines have emerged as a set of high-performance supervised generalized linear classifiers in parallel with artificial neural networks. A review on development history of artificial neural networks is presented and the standard architectures and algorithms of artificial neural networks are described. Furthermore, advanced artificial neural networks will be introduced with support vector machines, and limitations of ANNs will be identified. The future of artificial neural network development in tandem with support vector machines will be discussed. With the network structures and training algorithms, the applications of artificial neural networks will be reviewed as well, especially in the field of agricultural and biological engineering.