Search

The application domains of biological and ecological systems provide many opportunities and challenges for the technologies of modelling and control. These domains feature prominently amongst the activities of the IFAC community. This paper, written by authors who have had close connections with IFAC activities in these domains, provides insights as to achievements that have been made and challenges which need to be addressed during this first decade of the 21st century. Applications focus on agricultural systems, the biomedical domain and on environmental systems.

The interpretation of image information of plants can be possibly done based on image features extracted from the original pictorial image, This research work focused its interest on techniques of non-parametric image extraction, Two different types of non-parametric image features were discussed. First, the textural analysis which can be recognized as one of conventional non-parametric image feature extractors was examined. Secondly, The finite element method was introduced as an information processing tool for image feature extraction. The finite element application in image processing features a unique image data compression which is apparently similar to the function of human retina.

It is possible to cultivate plants under an artificial gravity field generated by a centrifugal device in space. In order to determine an optimal magnitude of gravity, there is a need to investigate the relationship between plant growth and gravity, including not only reduced gravity but also gravity greater than 1G. A prototype centrifugal phytotron was designed and fabricated in order to investigate the relationship between plant growth and increased gravity. This device enables us to cultivate plants over the long term by controlling environmental conditions in the phytotron such as temperature, relative humidity, CO2 concentration and light intensity. The results of our experiment indicate that plant seeds can germinate and grow even under an artificial gravity which changes sinusoidally from 2G to 4G

The finite element method was utilized in image feature extraction. Non-linear relationships between plant moisture content and the finite element image features were identified by using a neural network in order to predict water status of plant from digital image of a wilting plant. In this paper, bio-response feedback control strategies for developing an intelligent water management system in plant production were discussed. A non-invasive sensing technique for monitoring plant moisture conditions were proposed.

1. 1. Mn2+ (5 mM) completely inhibited the K+ (10–60 mM)-induced ileal tonic tension to the baseline, however, the tension and Mn2+ uptake increased progressively, depending on the K+ concentration of above 35 mM. 2. 2. The L-type Ca2+ channel blocker, D-600 and nifedipine inhibited the tension development and Mn2+ uptake after addition of Mn2+ in the high-K+ (60 mM) medium, however, T-type Ca2+ channel blocker, Ni2+ and amiloride had no effect on it. 3. 3. D-600 and nifedipine inhibited the tension development and Mn2+ uptake in the presence of 5 mM Mn2+ in the Ca2+-free, high-K+ (60mM) medium. 4. 4. The results suggest that Mn2+ penetrates via L-type Ca2+ channels in the ileal cell membrane in a state of prolonged depolarization and activates the contractile elements.

The finite element neural network (FENN) was applied to a non-invasive technique to monitor the plant water status of greenhouse-grown chrysanthemums. The governing differential equation (Poisson's equation) was utilized for neural information processing. The solution of the Poisson's equation was obtained using the finite element technique. A Kalman filter was used as a learning algorithm of the FENN. It was demonstrated as a practical example of the FENN applications that the FENN provided a means of estimating the leaf water potentials (correlated outputs of the FENN) of a greenhouse-grown chrysanthemum from the digital image data of its lead (correlated inputs of the FENN).

A spatial neural network (FENN) has been developed. The FENN is structured in a physical space unlike other conventional artificial neural networks of which structure represent only mathematical connections of neural elements. The FENN structure is formed by the finite clement used in the finite element method. The governing differential equation (Poisson's equation) was utilized for neural information processing. Kalman filter was used as a learning algorithm of the FENN. In this paper, a practical aspect of the FENN in the field of plant factory is discussed in relation to the sensor fusion technique for environmental control

The hierarchical neural network can be used to model biological systems such as plant growth, photosynthesis, evapotranspiration, etc. The development of back-propagation algorithm for neuron training has made it possible to use the layered network for simulating such non-linear systems. Modeling of such biological systems using the neural network often requires large number of layers and units in the network architecture because of the complexity of the system. The back propagation algorithm, however, often fails to achieve satisfactory identification of the system in the sense that output error minimization characteristics of the steepest descent scheme of the back propagation algorithm does not fit the problems involving large number of estimation parameters (synapse weights). An attempt of implementing Kalman filter algorithm (Kalman, 1960) in the procedure for training the neural network was made and evaluated. The performance of Kalman filter neuro-computing algorithm was compared to commonly used back propagation algorithm. Simulation of growth of radish sprouts under influence of changes in temperature and concentration of nutrient solution was attempted by two different neural network models, i.e., Kalman filter model and back propagation model. Results revealed a superior effectiveness of Kalman filter algorithm over the standard back propagation algorithm in the parameter estimation.