Tracking the states of a nonlinear and nonstationary system in the weight-space of artificial neural networks

We propose a novel interpretation and usage of Neural Network (NN) in modeling physiological signals, which are allowed to be nonlinear and/or nonstationary. The method consists of training a NN for the k-step prediction of a physiological signal, and then examining the connection-weight-space (CWS) of the NN to extract information about the signal generator mechanism. We de. ne a novel feature, Normalized Vector Separation (gamma(ij)), to measure the separation of two arbitrary states i and j in the CWS and use it to track the state changes of the generating system. The performance of the method is examined via synthetic signals and clinical EEG. Synthetic data indicates that gamma(ij) can track the system down to a SNR of 3.5 dB. Clinical data obtained from three patients undergoing carotid endarterectomy of the brain showed that EEG could be modeled (within a root-means-squared-error of 0.01) by the proposed method, and the blood perfusion state of the brain could be monitored via gamma(ij), with small NNs having no more than 21 connection weight altogether.

Injuries associated with continuous miners, shuttle cars, load-haul-dump and personnel transport in New South Wales underground coal mines

In the three years to June 2005, 959 injuries associated with continuous miners (CMs), shuttle cars (SCs), load–haul–dump and personnel transport (PT) were reported by NSW underground coal mines, comprising 23% of all injuries reported. The present paper reports an analysis of the narrative field accompanying these reports to determine opportunities for controlling injury risks. The most common combinations of activity and mechanism were: strain while handling CM cable (96 injuries); caught between or struck by moving parts while bolting on a CM (86 injuries); strains while bolting on CM (54 injuries); and slipping off a CM during access, egress or other activity (60 injuries). For the other equipment considered, the common injury mechanism was the vehicle running over a pothole or other roadway abnormality causing the driver or passengers to be injured (169 injuries). Potential control measures include: monorails for CM services; hydraulic cable reelers; handrails on CM platforms; redesign of CM platforms and bolting rigs to reduce reach distances during drilling and bolting; improvements to guarding of bolting controls; standardisation and shape coding of bolting controls; two handed fast feed; improvements in underground roadway maintenance, vehicle suspension, visibility and seating; and pedestrian proximity warning devices.

Tracking the states of a nonlinear system in the weight-space of a feed-forward neural network

Nonlinear, non-stationary signals are commonly found in a variety of disciplines such as biology, medicine, geology and financial modeling. The complexity (e.g. nonlinearity and non-stationarity) of such signals and their low signal to noise ratios often make it a challenging task to use them in critical applications. In this paper we propose a new neural network based technique to address those problems. We show that a feed forward, multi-layered neural network can conveniently capture the states of a nonlinear system in its connection weight-space, after a process of supervised training. The performance of the proposed method is investigated via computer simulations.