No abstract

No abstract

This paper presents a machine-learning-based approach for the structural health monitoring (SHM) of in-situ timber utility poles based on guided wave (GW) propagation. The proposed non-destructive testing method combines a new multi-sensor testing system with advanced statistical signal processing techniques and state-of-the-art machine learning algorithms for the condition assessment of timber utility poles. Currently used pole inspection techniques have critical limitations including the inability to assess the underground section. GW methods, on the other hand, are techniques potentially capable of evaluating nonaccessible areas and of detecting internal damage. However, due to the lack of solid understanding on the GW propagation in timber poles, most methods fail to fully interpret wave patterns from field measurements. The proposed method utilises an innovative multisensor testing system that captures wave signals along a sensor array and it applies machine learning algorithms to evaluate the soundness of a pole. To validate the new method, it was tested on eight in-situ timber poles. After the testing, the poles were dismembered to determine their actual health states. Various state-of-the-art machine learning algorithms with advanced data pre-processing were applied to classify the poles based on the wave measurements. It was found that using a support vector machine classifier, with the GW signals transformed into autoregressive coefficients, achieved a very promising maximum classification accuracy of 95.7±3.1% using 10-fold cross validation on multiple training and testing instances. Using leave-one-out cross validation, a classification accuracy of 93.3±6.0% for bending wave and 85.7±10.8% for longitudinal wave excitation was achieved.

No abstract

This paper investigates the efficacy of the genetic-based learning classifier system XCS, for the classification of noisy, artefact-inclusive human electroencephalogram (EEG) signals represented using large condition strings (108bits). EEG signals from three participants were recorded while they performed four mental tasks designed to elicit hemispheric responses. Autoregressive (AR) models and Fast Fourier Transform (FFT) methods were used to form feature vectors with which mental tasks can be discriminated. XCS achieved a maximum classification accuracy of 99.3% and a best average of 88.9%. The relative classification performance of XCS was then compared against four non-evolutionary classifier systems originating from different learning techniques. The experimental results will be used as part of our larger research effort investigating the feasibility of using EEG signals as an interface to allow paralysed persons to control a powered wheelchair or other devices.