Search

Recently, a mathematical model of pandemic influenza was proposed including typical control strategies such as antivirals, vaccination and school closure; and considering explicitly the effects of immunity acquired from the early outbreaks on the ulterior outbreaks of the disease. In such model the algebraic expression for the basic reproduction number (without control strategies) and the effective reproduction number (with control strategies) were derived and numerically estimated. A drawback of this model of pandemic influenza is that it ignores the effects of the differential susceptibility due to immunosuppression and the effects of the complexity of the actual contact networks between individuals. We have developed a generalized model which includes such effects of heterogeneity. Specifically we consider the influence of the air network connectivity in the spread of pandemic influenza and the influence of the immunosuppresion when the population is divided in two immune classes. We use an algebraic expression, namely the Tutte polynomial, to characterize the complexity of the contact network. Until now, The influence of the air network connectivity in the spread of pandemic influenza has been studied numerically, but not algebraic expressions have been used to summarize the level of network complexity. The generalized model proposed here includes the typical control strategies previously mentioned (antivirals, vaccination and school closure) combined with restrictions on travel. For the generalized model the corresponding reproduction numbers will be algebraically computed and the effect of the contact network will be established in terms of the Tutte polynomial of the network.

Multi-granularity optical cross-connects (MG-OXC) is proposed as a promising technique to reduce the cost of the optical nodes in the wavelength division multiplexing (WDM) optical networks. In this paper, we use the on-line Maximize the Number of Waveband Route (MNWR) algorithm to evaluate the performance and optimize the design of multi-granularity optical WDM networks based on two different MG-OXCs: the serial MG-OXCs and the interconnecting MG-OXCs. The numerical results show that our optimal design can significantly reduce the network complexity and the blocking probability.

A modular neural network classifier has been applied to the problem of automatic target recognition using forward- looking infrared (FLIR) imagery. The classifier consists of several independently trained neural networks operating on features extracted from a local portion of a target image. The classification decisions of the individual networks are combined to determine the final classification. Experiments show that decomposition of the input features results in performance superior to a fully connected network in terms of both network complexity and probability of classification. Performance of the classifier is further improved by the use of multi-resolution features and by the introduction of a higher level neural network on the top of expert networks, a method known as stacked generalization. In addition to feature decomposition, we implemented a data decomposition classifier network and demonstrated improved performance. Experimental results are reported on a large set of FLIR images.© (1998) COPYRIGHT SPIE--The International Society for Optical Engineering. Downloading of the abstract is permitted for personal use only.

The detection and disposal of anti-personnel landmines is one of the most difficult and intractable problems faced in ground conflict. This paper first presents current detection methods which use a separated aperture microwave sensor and an artificial neural-network pattern classifier. Several data-specific pre-processing methods are developed to enhance neural-network learning. In addition, a generalized Karhunen-Loeve transform and the eigenspace separation transform are used to perform data reduction and reduce network complexity. Highly favorable results have been obtained using the above methods in conjunction with a feedforward neural network. Secondly, a very promising idea relating to future research is proposed that uses acoustic modulation of the microwave signal to provide an additional independent feature to the input of the neural network. The expectation is that near-perfect mine detection will be possible with this proposed system.© (1996) COPYRIGHT SPIE--The International Society for Optical Engineering. Downloading of the abstract is permitted for personal use only.

A novel neural network for distortion-invariant pattern recognition is described. Image regions of interest are determined using a detection stage, each region is then enhanced (the steps used are detailed), features are extracted (new Gabor wavelet features are used), and these features are used to classify the contents of each input region. A new feature space trajectory neural network (FST NN) classifier is used. A new 8 class database is used, a new multilayer NN to calculate the distance measures necessary is detailed, its low storage and on-line computational load requirements are noted. The ability of the adaptive FST algorithm to reduce network complexity while achieving excellent performance is demonstrated. The clutter rejection ability of this neural network to reject false alarm inputs is demonstrated, and time-history processing to further reduce false alarms is discussed. Hardware and commercial realizations are noted.© (1995) COPYRIGHT SPIE--The International Society for Optical Engineering. Downloading of the abstract is permitted for personal use only.

We have applied a feed-forward neural network to the task of resolving closely-spaced objects (CSO). Traditional algorithmic methods are computationally expensive or numerically unstable, and techniques based on ad hoc rules are too subjective. Our approach relies on the principle that a sufficiently complex neural network can approximate an arbitrary function to an arbitrary degree of accuracy. We train a neural network to approximate the multi- dimensional function that maps from detector signal space to CSO parameter space, using an aggressive Hessian-based training algorithm and training set examples synthesized from the known inverse function. We find two important empirical results: we can simultaneously identify when the training set size is sufficient to adequately represent the mapping function, and when the network has achieved optimum generalization capability, for a given degree of network complexity. Thus we can predict the network and training set sizes necessary to achieve a given mission performance. Finally, we show how such a network can be used to provide sub-pixel resolution capabilities for missions observing both single objects and CSOs, as part of a real-time 2D sensor processor.© (1994) COPYRIGHT SPIE--The International Society for Optical Engineering. Downloading of the abstract is permitted for personal use only.

Statistical models of neural networks predict that the difference in training and testing error will be linear in network complexity and quadratic in the feature noise of the training set. Models of this kind have been applied to the Boltzmann pruning of a large MLP (3786 weights) trained on 10,000 and tested on 10,000 Karhunen-Loeve (K-L) features sets derived from images of handprinted characters and to a fingerprint classification problem which has 17,157 weights and is trained and tested on 2,000 K-L feature sets. Using the information content to optimize network size, the pruned networks have achieved high rates of recognition and at the same time been reduced in size by up to 90%. In the pruning process the product of the network capacity and the recognition error can be used effectively to select an optimum pruned network. If, in addition to conventional Boltzmann weight reduction, a weight reduction method which takes the variance content of the K-L by weighting the features using the K-L eigenvalues is used, networks with optimal size and information content can be constructed.

Optimization of large neural networks is essential in improving the network speed and generalization power, while at the same time reducing the training error and the network complexity. Boltzmann methods have been used as a statistical method for combinatorial optimization and for the design of learning algorithm. In the networks studied here, the Adaptive Resonance Theory (ART) serves as a connection creation operator and the Boltzmann method serves as a competitive connection annihilation operator. By combining these two methods it is possible to generate small networks that have similar testing and training accuracy and good generalization from small training sets. Our findings demonstrate that for a character recognition problem the number of weights in a fully connected network can be reduced by over 80%. We have applied the Boltzmann criteria to differential pruning of the connections which is based on the weight contents rather than on the number of connections.

Tracking single pixel targets in real time is a difficult task. In a previous paper the authors described a filter that detects possible trajectories in high-noise images. A trajectory image is generated and then used by a Hough transform network to detect lines as well as their end point (the target location at the last frame of the sequence used to generate the image). The Hough transform requires too much processing time when implemented in conventional computers. In this paper, a completely different architecture implementable in analog VLSI form which performs the operation in an extremely short time is proposed. The network uses intrinsic properties of the transform in order to map points in the image plane to corresponding points in the parameter plane. Simple summers are used to `connect'' all possible image lines to cells in parameter plane. A peak detecting neural net is then used to detect high count cells in the parameter plane. The technique, developed for straight lines, can easily be extended to second order curves at the cost of increased network complexity. The network has been simulated with simulated target trajectories superimposed on real background images (clouds, etc).© (1991) COPYRIGHT SPIE--The International Society for Optical Engineering. Downloading of the abstract is permitted for personal use only.

Current trends in both long haul transmission and optical networks indicate no slowing down in the move towards increased capacity and network complexity. These requirements have highlighted the limitations of the digital techniques that are the backbone of the current technology. Optical amplifiers offer potential solutions to many of these. This paper reviews the operation of these amplifiers, the current state of their development, and the future prospects for deployment.