Prediction of Parkinson's disease tremor onset using artificial neural networks

In this paper we present the initial results using an artificial neural network to predict the onset of Parkinson's Disease tremors in a human subject. Data for the network was obtained from implanted deep brain electrodes. A tuned artificial neural network was shown to be able to identify the pattern of the onset tremor from these real time recordings.

Identification of Parkinson’s disease tremor onset using artificial neural networks

In this paper we consider the possibility of using an artificial neural network to accurately identify the onset of Parkinson’s Disease tremors in human subjects. Data for the network is obtained by means of deep brain implantation in the human brain. Results presented have been obtained from a practical study (i.e. real not simulated data) but should be regarded as initial trials to be discussed further. It can be seen that a tuned artificial neural network can act as an extremely effective predictor in these circumstances.

Cross-resistance following artificial selection for increased defense against parasitoids in Drosophila melanogaster

An increase in resistance to one natural enemy may result in no correlated change, a positive correlated change, or a negative correlated change in the ability of the host or prey to resist other natural enemies. The type of specificity is important in understanding the evolutionary response to natural enemies and was studied here in a Drosaphila-parasitoid system. Drosophila melanogaster lines selected for increased larval resistance to the endoparasitoid wasps Asobara tabida or Leptopilina boulardi were exposed to attack by A. tabida, L. boulardi and Leptopilina heterotama at 15 degrees C, 20 degrees C, and 25 degrees C. In general, encapsulation ability increased with temperature, with the exception of the lines selected against L. boulardi, which showed the opposite trend. Lines selected against L, boulardi showed large increases in resistance against all three parasitoid species, and showed similar levels of defense against A. tabida to the lines selected against that parasitoid. In contrast, lines selected against A. tabida showed a large increase in resistance to A. tabida and generally to L. heterotoma, but displayed only a small change in their ability to survive attack by L. boulardi. Such asymmetries in correlated responses to selection for increased resistance to natural enemies may influence host-parasitoid community structure.

Persistent, symptomless, systemic, and seed-borne infection of lettuce by Botrytis cinerea

Experiments are presented which show that Botrytis cinerea, the cause of gray mould disease, is often present in symptomless lettuce plants as a systemic, endophytic, infection which may arise from seed. The fungus was isolated on selective media from surface sterilized sections of roots, stem pieces and leaf discs from symptomless plants grown in a conventional glasshouse and in a spore-free air-flow provided by an isolation propagator. The presence of B. cinerea was confirmed by immuno-labelling the tissues with the Botrytis-specific monoclonal antibody BC-12.CA4. As plants grew, infection spread from the roots to stems and leaves. Surface sterilization of seeds reduced the number of infected symptomless plants. Artificial infection of seedlings with dry conidia increased the rate of infection in some experiments. Selected isolates were genetically finger-printed using microsatellite loci. This confirmed systemic spread of the inoculating isolates but showed that other isolates were also present and that single plants hosted multiple isolates. This shows that B. cinerea commonly grows in lettuce plants as an endophyte, as has already been shown for Primula. If true for other hosts, the endophytic phase may be as important a component of the species population as the aggressive necrotrophic phase.

Mechanisms of partial plant resistance to diamondback moth (Plutella xylostella) in brassicas

Artificial diet studies were used to differentiate among physical and chemical mechanisms affecting the suitability to diamondback moth (Plutella xylostella L.), of 16 food substrates obtained by growing four different brassicas in the glasshouse or field and measuring the pest's performance on either leaf discs or a diet incorporating leaf powders. Leaves of Chinese cabbage and the cabbage cultivar 'Minicole' were, respectively, the most and least suitable leaves for the insect, but this ranking was reversed on artificial diet. Leaves of glasshouse-grown plants were more suitable than those of plants grown in the fields. Differences in the suitability of leaves to diamondback moth appeared to be largely determined by leaf toughness and surface wax load. Concentrations of individual glucosinolates in the brassicas probably acted as phagostimulants, so increasing their intrinsic susceptibility to diamondback moth, but the effect of the physical factors appeared more important.

Artificial keys for botanical identification using a multilayer perceptron neural network (MLP)

In this paper, practical generation of identification keys for biological taxa using a multilayer perceptron neural network is described. Unlike conventional expert systems, this method does not require an expert for key generation, but is merely based on recordings of observed character states. Like a human taxonomist, its judgement is based on experience, and it is therefore capable of generalized identification of taxa. An initial study involving identification of three species of Iris with greater than 90% confidence is presented here. In addition, the horticulturally significant genus Lithops (Aizoaceae/Mesembryanthemaceae), popular with enthusiasts of succulent plants, is used as a more practical example, because of the difficulty of generation of a conventional key to species, and the existence of a relatively recent monograph. It is demonstrated that such an Artificial Neural Network Key (ANNKEY) can identify more than half (52.9%) of the species in this genus, after training with representative data, even though data for one character is completely missing.

Using self-organising feature maps for the control of artificial organisms

Variations on the standard Kohonen feature map can enable an ordering of the map state space by using only a limited subset of the complete input vector. Also it is possible to employ merely a local adaptation procedure to order the map, rather than having to rely on global variables and objectives. Such variations have been included as part of a hybrid learning system (HLS) which has arisen out of a genetic-based classifier system. In the paper a description of the modified feature map is given, which constitutes the HLSs long term memory, and results in the control of a simple maze running task are presented, thereby demonstrating the value of goal related feedback within the overall network.

Object detecting artificial retina

This paper describes the novel use of agent and cellular neural Hopfield network techniques in the design of a self-contained, object detecting retina. The agents, which are used to detect features within an image, are trained using the Hebbian method which has been modified for the cellular architecture. The success of each agent is communicated with adjacent agents in order to verify the detection of an object. Initial work used the method to process bipolar images. This has now been extended to handle grey scale images. Simulations have demonstrated the success of the method and further work is planned in which the device is to be implemented in hardware.