Evolutionary Selection of Features forNeural Sleep/Wake Discrimination

摘要

In biomedical signal analysis, artificial neural networks are often used for pattern classification because of their capability fornonlinear class separation and the possibility to efficiently implement them on a microcontroller. Typically, the network topology isdesigned by hand, and a gradient-based search algorithm is used to find a set of suitable parameters for the given classification task.In many cases, however, the choice of the network architecture is a critical and difficult task. For example, hand-designed networksoften require more computational resources than necessary because they rely on input features that provide no information or areredundant. In the case of mobile applications, where computational resources and energy are limited, this is especially detrimental.Neuroevolutionary methods which allow for the automatic synthesis of network topology and parameters offer a solution to theseproblems. In this paper, we use analog genetic encoding (AGE) for the evolutionary synthesis of a neural classifier for a mobilesleep/wake discrimination system. The comparison with a hand-designed classifier trained with back propagation shows that theevolved neural classifiers display similar performance to the hand-designed networks, but using a greatly reduced set of inputs,thus reducing computation time and improving the energy efficiency of the mobile system.