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.

A controlled trial of sip-feed supplements in elderly orthopaedic patients

The potential nutritional and clinical benefits of sip-feed supplements were investigated by means of a controlled trial in elderly female patients admitted for orthopaedic surgery. A nutritional risk assessment procedure (Nutritional Risk Questionnaire, NRQ) was used to identify patients who might benefit from supplementation. Patients identified as high risk who did not receive supplements showed significant losses in triceps skinfold thickness (TSF) and mid-upper arm muscle circumference (MUAMC) measurements during hospitalization. Such changes were not observed in high-risk supplemented patients, but significant losses of MUAMC were also recorded in a group of patients who failed to comply with the supplement. No differences in biochemical parameters, muscle function, or clinical outcome were observed between supplemented and unsupplemented and non-compliant patients. The problems of poor compliance to sip-feed supplements and failure to observe clinical benefit in supplemented patients are discussed.