Biomedical subjects

J Fulcher

Publications and source records attributed to J Fulcher.

5 recordsLinked to original sources

PubMed2000

Higherorder neural network group models for financial simulation.

Real world financial data is often discontinuous and non-smooth. If we attempt to use neural networks to simulate such functions, then accuracy will be a problem. Neural network group models perform this function much better. Both Polynomial Higher Order Neural network Group (PHONG) and Trigonometric polynomial Higher Order Neural network Group (THONG) models are developed. These HONG models are open box, convergent models capable of approximating any kind of piecewise continuous function, to any degree of accuracy. Moreover they are capable of handling higher frequency, higher order non-linear and discontinuous data. Results obtained using a Higher Order Neural network Group financial simulator are presented, which confirm that HONG group models converge without difficulty, and are considerably more accurate than neural network models (more specifically, around twice as good for prediction, and a factor of four improvement in the case of simulation).

Computer Simulation↗

PubMed1998

Multicentre evaluation of a commercial test for the rapid diagnosis of Clostridium difficile-mediated antibiotic-associated diarrhoea.

An immunoassay for the detection of Clostridium difficile toxin A in stool samples (Clearview C. DIFF A; Unipath, UK) was evaluated against the cell cytotoxicity assay using 407 stool samples from patients suspected to have, or considered at risk of, antibiotic-associated diarrhoea. Of the samples tested, 98 were positive and 280 were negative by both tests (sensitivity 83.1%, specificity 96.9%). Following resolution of the 29 discrepant results, the sensitivity and specificity of the immunoassay were 91% and 98%, respectively, and the sensitivity for the cell cytotoxicity assay was calculated as 91.5%, with a specificity of 99%. The Clearview C. DIFF A test proved to be a rapid simple assay for the detection of Clostridium difficile toxin A in stool samples. The test was equally suited to single or batch testing, required minimal sample handling, and provided results within 30 min of applying the sample to the test unit.

Animals↗

PubMed1997

Classification of user expertise level by neural networks.

A neural network approach to low-level user modeling is described, in the context of text editing tasks using the Jove editor. Knowledge of a user's expertise is extracted automatically, based on their interaction with Jove over a two week period. A MLP classifier which uses rprop learning and incorporates output data fuzzification is developed to classify users into one of five expertise levels. Classification into the correct level is achieved in around 80% of the cases, with misclassification being restricted to adjacent classes. The neurofuzzy system is seen to outperform not only the binary classifier of Beale [1989], but also production rule and inductive expert systems developed especially for comparison purposes in this study.

Artificial Intelligence↗

PubMed1997

Did British society change character in the 1920s or the 1980s.

This is a response to Runciman's reply to my critique of his 1993 article. I argue that although the First World War brought about many changes in British society, it did not initiate a new stage in its development, for these changes were largely an acceleration of existing tendencies. Runciman's argument that the similarities between the 1930s and the 1980s show that British capitalism was essentially the same in both periods does not allow for the different directions in which British society was moving in the 1930s and in the 1980s. His treatment of the 1980s changes as another phase in the political cycle fails to grasp what was new about the 1980s or locate these changes in their wider economic and global context.

Character↗

PubMed1995

An application of Hamiltonian neurodynamics using Pontryagin's Maximum (Minimum) Principle.

Classical optimal control methods, notably Pontryagin's Maximum (Minimum) Principle (PMP) can be employed, together with Hamiltonians, to determine optimal system weights in Artificial Neural dynamical systems. A new learning rule based on weight equations derived using PMP is shown to be suitable for both discrete- and continuous-time systems, and moreover, can also be applied to feedback networks. Preliminary testing shows that this PMP learning rule compares favorably with Standard BackPropagations (SBP) on the XOR problem.

Models, Theoretical↗