Combination of artificial neural-network forecasters for prediction of natural gas consumption.

The focus of this paper is on combination of artificial neural-network (ANN) forecasters with application to the prediction of daily natural gas consumption needed by gas utilities. ANN forecasters can model the complex relationship between weather parameters and previous gas consumption with the future consumption. A two-stage system is proposed with the first stage containing two ANN forecasters, a multilayer feedforward ANN and a functional link ANN. These forecasters are initially trained with the error backpropagation algorithm, but an adaptive strategy is employed to adjust their weights during on-line forecasting. The second stage consists of a combination module to mix the two individual forecasts produced in the first stage. Eight different combination algorithms are examined, they are based on: averaging, recursive least squares, fuzzy logic, feedforward ANN, functional link ANN, temperature space approach, Karmarkar's linear programming algorithm and adaptive mixture of local experts (modular neural networks). The performance is tested on real data from six different gas utilities. The results indicate that combination strategies based on a single ANN outperform the other approaches.

A spatial correlation based method for neighbor set selection in random field image models.

Random field (RF) models have widespread application in image modeling and analysis. The effectiveness of these models is largely dependent on the choice of neighbor sets, which determine the spatial interactions that are represented by the model. We consider the problem of selecting these neighbor sets for simultaneous autoregressive and Gauss-Markov random field models, based on the correlation structure of the image to be modeled. A procedure for identifying appropriate neighbor sets is proposed, and experimental results which demonstrate the viability of this method are presented.

A physics-based coordinate transformation for 3-D image matching.

Many image matching schemes are based on mapping coordinate locations, such as the locations of landmarks, in one image to corresponding locations in a second image. A new approach to this mapping (coordinate transformation), called the elastic body spline (EBS), is described. The spline is based on a physical model of a homogeneous, isotropic three-dimensional (3-D) elastic body. The model can approximate the way that some physical objects deform. The EBS as well as the affine transformation, the thin plate spline [1], [2] and the volume spline [3] are used to match 3-D magnetic resonance images (MRI's) of the breast that are used in the diagnosis and evaluation of breast cancer. These coordinate transformations are evaluated with different types of deformations and different numbers of corresponding (paired) coordinate locations. In all but one of the cases considered, using the EBS yields more similar images than the other methods.

ANNSTLF-a neural-network-based electric load forecasting system.

A key component of the daily operation and planning activities of an electric utility is short-term load forecasting, i.e., the prediction of hourly loads (demand) for the next hour to several days out. The accuracy of such forecasts has significant economic impact for the utility. This paper describes a load forecasting system known as ANNSTLF (artificial neural-network short-term load forecaster) which has received wide acceptance by the electric utility industry and presently is being used by 32 utilities across the USA and Canada. ANNSTLF can consider the effect of temperature and relative humidity on the load. Besides its load forecasting engine, ANNSTLF contains forecasters that can generate the hourly temperature and relative humidity forecasts needed by the system. ANNSTLF is based on a multiple ANN strategy that captures various trends in the data. Both the first and the second generation of the load forecasting engine are discussed and compared. The building block of the forecasters is a multilayer perceptron trained with the error backpropagation learning rule. An adaptive scheme is employed to adjust the ANN weights during online forecasting. The forecasting models are site independent and only the number of hidden layer nodes of ANN's need to be adjusted for a new database. The results of testing the system on data from ten different utilities are reported.

Recognition and pose estimation of unoccluded three-dimensional objects from a two-dimensional perspective view by banks of neural networks.

This paper describes a neural network (NN) based system for recognition and pose estimation of an unoccluded three-dimensional (3-D) object from any single two-dimensional (2-D) perspective view. The approach is invariant to translation, orientation, and scale. First, the binary silhouette of the object is obtained and normalized for translation and scale. Then, the object is represented by a set of rotation invariant features derived from the complex orthogonal pseudo-Zernike moments of the image. The recognition scheme combines the decisions of a bank of multilayer perceptron NN classifiers operating in parallel on the same data. These classifiers have different topologies and internal parameters, but are trained on the same set of exemplar perspective views of the objects. Next, two pose parameters, elevation and aspect angles, are obtained by a novel two-stage NN system consisting of a quadrant classifier followed by NN angle estimators. Performance is tested on clean and noisy data bases of military ground vehicles. Comparative studies with three other classifiers (a single NN, the weighted nearest-neighbor classifier, and a binary decision tree) are carried out.

Estimation of single sweep steady-state visual evoked potentials by adaptive line enhancement.

An adaptive line enhancer (ALE) is used to obtain estimates of the single sweep steady-state visual evoked potential (SSVEP). The method is seen to enhance the estimated signal-to-noise ratio of the single sweep SSVEP by as much as 10 dB.

Stereopsis by constraint learning feed-forward neural networks.

A neural network (NN) approach to the problem of steropsis is presented. The correspondence problem (finding the correct matches between pixels of the epipolar lines of the stereo pair from among all the possible matches) is posed as a noniterative many-to-one mapping. Two multilayer feedforward NNs are utilized to learn and code this nonlinear and complex mapping using the backpropagation learning rule and a training set. The first NN is a conventional fully connected net while the second is a sparsely connected NN with a fixed number of hidden layer nodes. All the applicable constraints are learned and internally coded by the NNs enabling them to be more flexible and more accurate than previous methods. The approach is successfully tested on several random-dot stereograms. It is shown that the nets can generalize their learned mappings to cases outside their training sets and to noisy images. Advantages over the Marr-Poggio algorithm are discussed, and it is shown that the NNs performances are superior.