An adaptive neural-wavelet model for short term load forecasting

This paper proposed a novel model for short term load forecast in the competitive electricity market. The prior electricity demand data are treated as time series. The forecast model is based on wavelet multi-resolution decomposition by autocorrelation shell representation and neural networks (multilayer perceptrons, or MLPs) modeling of wavelet coefficients. To minimize the influence of noisy low level coefficients, we applied the practical Bayesian method Automatic Relevance Determination (ARD) model to choose the size of MLPs, which are then trained to provide forecasts. The individual wavelet domain forecasts are recombined to form the accurate overall forecast. The proposed method is tested using Queensland electricity demand data from the Australian National Electricity Market. (C) 2001 Elsevier Science B.V. All rights reserved.

Neural adaptations to resistance training - Implications for movement control

It has long been believed that resistance training is accompanied by changes within the nervous system that play an important role in the development of strength. Many elements of the nervous system exhibit the potential for adaptation in response to resistance training, including supraspinal centres, descending neural tracts, spinal circuitry and the motor end plate connections between motoneurons and muscle fibres. Yet the specific sites of adaptation along the neuraxis have seldom been identified experimentally, and much of the evidence for neural adaptations following resistance training remains indirect. As a consequence of this current lack of knowledge, there exists uncertainty regarding the manner in which resistance training impacts upon the control and execution of functional movements. We aim to demonstrate that resistance training is likely to cause adaptations to many neural elements that are involved in the control of movement, and is therefore likely to affect movement execution during a wide range of tasks. We review a small number of experiments that provide evidence that resistance training affects the way in which muscles that have been engaged during training are recruited during related movement tasks. The concepts addressed in this article represent an important new approach to research on the effects of resistance training. They are also of considerable practical importance, since most individuals perform resistance training in the expectation that it will enhance their performance in-related functional tasks.

Probabilistic modelling of CO2 corrosion laboratory data using neural networks

The present paper addresses two major concerns that were identified when developing neural network based prediction models and which can limit their wider applicability in the industry. The first problem is that it appears neural network models are not readily available to a corrosion engineer. Therefore the first part of this paper describes a neural network model of CO2 corrosion which was created using a standard commercial software package and simple modelling strategies. It was found that such a model was able to capture practically all of the trends noticed in the experimental data with acceptable accuracy. This exercise has proven that a corrosion engineer could readily develop a neural network model such as the one described below for any problem at hand, given that sufficient experimental data exist. This applies even in the cases when the understanding of the underlying processes is poor. The second problem arises from cases when all the required inputs for a model are not known or can be estimated with a limited degree of accuracy. It seems advantageous to have models that can take as input a range rather than a single value. One such model, based on the so-called Monte Carlo approach, is presented. A number of comparisons are shown which have illustrated how a corrosion engineer might use this approach to rapidly test the sensitivity of a model to the uncertainities associated with the input parameters. (C) 2001 Elsevier Science Ltd. All rights reserved.

Neural compensation for compliant loads during rhythmic movement

An experiment was performed to characterise the movement kinematics and the electromyogram (EMG) during rhythmic voluntary flexion and extension of the wrist against different compliant (elastic-viscous-inertial) loads. Three levels of each type of load, and an unloaded condition, were employed. The movements were paced at a frequency of I Hz by an auditory metronome, and visual feedback of wrist displacement in relation to a target amplitude of 100degrees was provided. Electro-myographic recordings were obtained from flexor carpi radialis (FCR) and extensor carpi radialis brevis (ECR). The movement profiles generated in the ten experimental conditions were indistinguishable, indicating that the CNS was able to compensate completely for the imposed changes in the task dynamics. When the level of viscous load was elevated, this compensation took the form of an increase in the rate of initial rise of the flexor and the extensor EMG burst. In response to increases in inertial load, the flexor and extensor EMG bursts commenced and terminated earlier in the movement cycle, and tended to be of greater duration. When the movements were performed in opposition to an elastic load, both the onset and offset of EMG activity occurred later than in the unloaded condition. There was also a net reduction in extensor burst duration with increases in elastic load, and an increase in the rate of initial rise of the extensor burst. Less pronounced alterations in the rate of initial rise of the flexor EMG burst were also observed. In all instances, increases in the magnitude of the external load led to elevations in the overall level of muscle activation. These data reveal that the elements of the central command that are modified in response to the imposition of a compliant load are contingent, not only upon the magnitude, but also upon the character of the load.

Slowed conduction and ventricular tachycardia after targeted disruption of the cardiac sodium channel gene Scn5a

Voltage-gated sodium channels drive the initial depolarization phase of the cardiac action potential and therefore critically determine conduction of excitation through the heart. In patients, deletions or loss-of-function mutations of the cardiac sodium channel gene, SCN5A, have been associated with a wide range of arrhythmias including bradycardia (heart rate slowing), atrioventricular conduction delay, and ventricular fibrillation. The pathophysiological basis of these clinical conditions is unresolved. Here we show that disruption of the mouse cardiac sodium channel gene, Scn5a, causes intrauterine lethality in homozygotes with severe defects in ventricular morphogenesis whereas heterozygotes show normal survival. Whole-cell patch clamp analyses of isolated ventricular myocytes from adult Scn5a(+/-) mice demonstrate a approximate to50% reduction in sodium conductance. Scn5a(+/-) hearts have several defects including impaired atrioventricular conduction, delayed intramyocardial conduction, increased ventricular refractoriness, and ventricular tachycardia with characteristics of reentrant excitation. These findings reconcile reduced activity of the cardiac sodium channel leading to slowed conduction with several apparently diverse clinical phenotypes, providing a model for the detailed analysis of the pathophysiology of arrhythmias.

The 2000 Ogura Lecture: Olfactory neural cells: An untapped diagnostic and therapeutic resource

Objective. This is an over-view of the cellular biology of upper nasal mucosal cells that have special characteristics that enable them to be used to diagnose and study congenital neurological diseases and to aid neural repair. Study Design: After mapping the distribution of neural cells in the upper nose, the authors' investigations moved to the use of olfactory neurones to diagnose neurological diseases of development, especially schizophrenia. Olfactory-ensheating glial cells (OEGs) from the cranial cavity promote axonal penetration of the central nervous system and aid spinal cord repair in rodents. The authors sought to isolate these cells from the more accessible upper nasal cavity in rats and in humans and prove they could likewise promote neural regeneration, making these cells suitable for human spinal repair investigations. Methods: The schizophrenia-diagnosis aspect of the study entailed the biopsy of the olfactory areas of 10 schizophrenic patients and 10 control subjects. The tissue samples were sliced and grown in culture medium. The ease of cell attachment to fibronectin (artificial epithelial basement membrane), as well as the mitotic and apoptotic indices, was studied in the presence and absence of dopamine in those cell cultures. The neural repair part of the study entailed a harvesting and insertion of first rat olfactory lamina propria rich in OEGs between cut ends of the spinal cords and then later the microinjection of an OEG-rich suspension into rat spinal cords previously transected by open laminectomy. Further studies were done in which OEG insertion was performed up to 1 month after rat cord transection and also in monkeys. Results: Schizophrenic patients' olfactory tissues do not easily attach to basement membrane compared with control subjects, adding evidence to the theory that cell wall anomalies are part of the schizophrenic lesion of neurones. Schizophrenic patient cell cultures had higher mitotic and apoptotic indices compared with control subjects. The addition of dopamine altered these indices enough to allow accurate differentiation of schizophrenics from control patients, leading to, possibly for the first time, an early objective diagnosis of schizophrenia and possible assessment of preventive strategies. OEGs from the nose were shown to be as effective as those from the olfactory bulb in promoting axonal growth across transected spinal cords even when added I month after injury in the rat. These otherwise paraplegic rats grew motor and proprioceptive and fine touch fibers with corresponding behavioral improvement. Conclusions. The tissues of the olfactory mucosa are readily available to the otolaryngologist. Being surface cells, they must regenerate (called neurogenesis). Biopsy of this area and amplification of cells in culture gives the scientist a window to the developing brain, including early diagnosis of schizophrenia. The Holy Grail of neurological disease is the cure of traumatic paraplegia and OEGs from the nose promote that repair. The otolaryngologist may become the necessary partner of the neurophysiologist and spinal surgeon to take the laboratory potential of paraplegic cure into the day-to-day realm of clinical reality.