The min-max function differentiation and training of fuzzy neural networks.

This paper discusses the Delta-rule and training of min-max neural networks by developing a differentiation theory for min-max functions, the functions containing min (wedge) and/or max (V) operations. We first prove that under certain conditions all min-max functions are continuously differentiable almost everywhere in the real number field R and derive the explicit formulas for the differentiation. These results are the basis for developing the Delta-rule for the training of min-max neural networks. The convergence of the new Delta-rule is proved theoretically using the stochastic theory, and is demonstrated with a simulation example.

Adaptive neural network control of nonlinear systems by state and output feedback.

This paper presents a novel control method for a general class of nonlinear systems using neural networks (NNs). Firstly, under the conditions of the system output and its time derivatives being available for feedback, an adaptive state feedback NN controller is developed. When only the output is measurable, by using a high-gain observer to estimate the derivatives of the system output, an adaptive output feedback NN controller is proposed. The closed-loop system is proven to be semi-globally uniformly ultimately bounded (SGUUB). In addition, if the approximation accuracy of the neural networks is high enough and the observer gain is chosen sufficiently large, an arbitrarily small tracking error can be achieved. Simulation results verify the effectiveness of the newly designed scheme and the theoretical discussions.

[Trauma score and injury severity score in evaluation of the trauma patients: a preliminary report of 1000 cases].

It is important to evaluate trauma patients with a properly graded severity system in the emergency management of these patients. In this study the Trauma and the Injury Severity Scores based on the evaluation of trauma patients at the emergency services of Mackay Memorial Hospital and Taipei Medical College Hospital, and the mortality rate of these patients is analyzed. There was not a single mortality in patients with a Trauma Score of 15 or 16 and no survival in the patients with Trauma Scores under 11. Eighty-three of 1000 patients (8.3%) had a Trauma Score under 16, and hospitalization was necessary for most of them. All the 22 fatal cases had an Injury Severity Score greater than 24. The mortality rate was 70.6% for the patients with an Injury Severity Score greater than 30. This was the first trial in Taiwan to evaluate patients with the Trauma Score in the hope of aiding medical and paramedical staffs in the selection hospitals to which to transfer patients. All patients having a Trauma Score under 14 should be transferred to well-equipped trauma centers and those with a better score to other hospitals. The Injury Severity Score is nowadays used widely in the world to evaluate the severity and to predict the outcome of the patients. By comparing and utilizing these two grading systems, a more accurate evaluation of the trauma patients can be expected.