Referral patterns in a global store-and-forward telemedicine system

We examined the nature of the referral patterns in the email telemedicine network operated by the Swinfen Charitable Trust with a view to informing long-term resource planning. Over the first six years of operation, 62 hospitals from 19 countries registered with the Trust in order to be able to refer cases for specialist advice; 55 of these hospitals (89%) actually referred cases during this period. During the first six years of operation, nearly 1000 referrals were submitted and answered, from a wide range of specialty areas. Between July 2002 and March 2005 the referral rate rose from 127 to 318 cases per year. The median length of time required to provide a specialist's response was 2.3 days during the first 12 months and 1.8 days during the last 12 months. Five hospitals submitted cases for more than four years (together sending a total of 493 cases). Their activity data showed a trend to declining referral rates over the four-year period, which may represent successful knowledge transfer. There is some evidence that over the last three years the growth in demand has been exponential, while the growth in resources available (i.e. specialists) has been linear, a situation which cannot continue for very long before demand outstrips supply.

The Australian insolvency regime revisited: a precis of the next leap forward

Australian corporate insolvency laws contained within Chapter 5 of the Corporations Act are currently being reviewed with respect to four principal areas identified by Australian Government Treasury. The four themes of review include employee ‘benefit’ enhancements; seeking to deter misconduct of company officers; rules around insolvency practitioner disclosure with respect to their remuneration and related independence issues; and some minor proposed changes to the voluntary administration procedure, widely regarded as requiring only minor adjustment. At this time, the draft legislation is not available for general release and is being discussed within the Australian Government appointed Insolvency Law Advisory Group. The next steps are public comment for review of draft legislation and then operation of the legislative change. These are expected to occur in 2007. This paper seeks to outline the likely issues associated with the expected reforms of the Australian insolvency regime.

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.

Curvature-driven smoothing: a learning algorithm for feed-forward networks

The performance of feed-forward neural networks in real applications can be often be improved significantly if use is made of a-priori information. For interpolation problems this prior knowledge frequently includes smoothness requirements on the network mapping, and can be imposed by the addition to the error function of suitable regularization terms. The new error function, however, now depends on the derivatives of the network mapping, and so the standard back-propagation algorithm cannot be applied. In this paper, we derive a computationally efficient learning algorithm, for a feed-forward network of arbitrary topology, which can be used to minimize the new error function. Networks having a single hidden layer, for which the learning algorithm simplifies, are treated as a special case.

Regularization and complexity control in feed-forward networks

In this paper we consider four alternative approaches to complexity control in feed-forward networks based respectively on architecture selection, regularization, early stopping, and training with noise. We show that there are close similarities between these approaches and we argue that, for most practical applications, the technique of regularization should be the method of choice.

Topographic mappings and feed-forward neural networks

This thesis is a study of the generation of topographic mappings - dimension reducing transformations of data that preserve some element of geometric structure - with feed-forward neural networks. As an alternative to established methods, a transformational variant of Sammon's method is proposed, where the projection is effected by a radial basis function neural network. This approach is related to the statistical field of multidimensional scaling, and from that the concept of a 'subjective metric' is defined, which permits the exploitation of additional prior knowledge concerning the data in the mapping process. This then enables the generation of more appropriate feature spaces for the purposes of enhanced visualisation or subsequent classification. A comparison with established methods for feature extraction is given for data taken from the 1992 Research Assessment Exercise for higher educational institutions in the United Kingdom. This is a difficult high-dimensional dataset, and illustrates well the benefit of the new topographic technique. A generalisation of the proposed model is considered for implementation of the classical multidimensional scaling (¸mds}) routine. This is related to Oja's principal subspace neural network, whose learning rule is shown to descend the error surface of the proposed ¸mds model. Some of the technical issues concerning the design and training of topographic neural networks are investigated. It is shown that neural network models can be less sensitive to entrapment in the sub-optimal global minima that badly affect the standard Sammon algorithm, and tend to exhibit good generalisation as a result of implicit weight decay in the training process. It is further argued that for ideal structure retention, the network transformation should be perfectly smooth for all inter-data directions in input space. Finally, there is a critique of optimisation techniques for topographic mappings, and a new training algorithm is proposed. A convergence proof is given, and the method is shown to produce lower-error mappings more rapidly than previous algorithms.

Combining the wavelet transform and forecasting models to predict gas forward prices

This paper presents a forecasting technique for forward energy prices, one day ahead. This technique combines a wavelet transform and forecasting models such as multi- layer perceptron, linear regression or GARCH. These techniques are applied to real data from the UK gas markets to evaluate their performance. The results show that the forecasting accuracy is improved significantly by using the wavelet transform. The methodology can be also applied to forecasting market clearing prices and electricity/gas loads.

Energy forward price prediction with a hybrid adaptive model

This paper presents a forecasting technique for forward electricity/gas prices, one day ahead. This technique combines a Kalman filter (KF) and a generalised autoregressive conditional heteroschedasticity (GARCH) model (often used in financial forecasting). The GARCH model is used to compute next value of a time series. The KF updates parameters of the GARCH model when the new observation is available. This technique is applied to real data from the UK energy markets to evaluate its performance. The results show that the forecasting accuracy is improved significantly by using this hybrid model. The methodology can be also applied to forecasting market clearing prices and electricity/gas loads.

Improved multi-beam neural network scatterometer forward models

Current methods for retrieving near surface winds from scatterometer observations over the ocean surface require a foward sensor model which maps the wind vector to the measured backscatter. This paper develops a hybrid neural network forward model, which retains the physical understanding embodied in ¸mod, but incorporates greater flexibility, allowing a better fit to the observations. By introducing a separate model for the mid-beam and using a common model for the fore- and aft-beams, we show a significant improvement in local wind vector retrieval. The hybrid model also fits the scatterometer observations more closely. The model is trained in a Bayesian framework, accounting for the noise on the wind vector inputs. We show that adding more high wind speed observations in the training set improves wind vector retrieval at high wind speeds without compromising performance at medium or low wind speeds.