David Gillingwater

The assessment of aircraft noise is becoming an increasingly important task in ensuring sustainable airport development. Aircraft noise is influenced by many complex factors and traditional laboratory models are not sufficient to assess the exposure to noisy flights of specific local communities in proximity to an airport. In this paper neural network and fuzzy set methods have been integrated with

This paper presents a new method for explaining the reasoning results of a trained neural network. The method considers the most significant attribute first under the guidance of a relative strength of effect analysis and eliminates irrelevant points. Following the adaptive search in the dynamic state space, a set of relevant points are extracted and form the basis of the

... and k Lim win = o k-> - I=l lherefore, the increment of the number of nodes for the same input factor does not increase the initial weight of its corresponding traditional NN. According to theJaynes' Maximum Entropy Principle when we do not [14], we should assume that win = - ...

The past few years have seen the voluntary transport sector grow and diversify, despite the uncertainty faced over funding. Statutory involvement in voluntary transport provision has increased, with passenger transport authorities creating community transport policies and budgets and local councils undertaking authority‐wide reviews of special needs transport service provision. This article examines the voluntary‐statutory sector relationship and comments on the

Aircraft noise is influenced by many complex factors and it is difficult to devise an accurate mathematical model to simulate it with respect to operations at an airport. This paper presents an investigation in simulating airport noise using artificial neural networks. The results show that it is possible to establish a simple neural network model with monitored data for a specific airport and specific aircraft under local conditions.