Partitioning of unstructured grid meshes using Boltzmann machine neural networks

Properly adapted Boltzmann machine neural networks are used to devise effective unstructured grid partitioners that are capable of providing equally loaded grid subsets with minimum interface, for concurrent data-handling on parallel computers. The partitioning scheme is based on recursive bisections so that the outcome always consists of 2ⁿ partitions. Two different techniques are introduced to speed up the—otherwise costly—partitioning process and several variants are considered. In particular, a transformation of bipolar Hopfield-type neural networks is developed providing an effective multi-scale approach. Results on a number of test cases are presented in order to assess the performance of the proposed techniques.     

Surface processing methods for point sets using finite elements

We present a framework for processing point-based surfaces via partial differential equations (PDEs). Our framework efficiently and effectively brings well-known PDE-based processing techniques to the field of point-based surfaces. At the core of our method is a finite element discretization of PDEs on point surfaces. This discretization is based on the local assembly of PDE-specific mass and stiffness matrices, using a local point coupling computation. Point couplings are computed using a local tangent plane construction and a local Delaunay triangulation of point neighborhoods. The definition of tangent planes relies on moment-based computation with proven scaling and stability properties. Once local stiffness matrices are obtained, we are able to easily assemble global matrices and efficiently solve the corresponding linear systems by standard iterative solvers. We demonstrate our framework by several types of PDE-based surface processing applications, such as segmentation, texture synthesis, bump mapping, and geometric fairing.     

Binary classification using ensemble neural networks and interval neutrosophic sets

This paper presents an ensemble neural network and interval neutrosophic sets approach to the problem of binary classification. A bagging technique is applied to an ensemble of pairs of neural networks created to predict degree of truth membership, indeterminacy membership, and false membership values in the interval neutrosophic sets. In our approach, the error and vagueness are quantified in the classification process as well. A number of aggregation techniques are proposed in this paper. We applied our techniques to the classical benchmark problems including ionosphere, pima-Indians diabetes, and liver-disorders from the UCI machine learning repository. Our approaches improve the classification performance as compared to the existing techniques which applied only to the truth membership values. Furthermore, the proposed ensemble techniques also provide better results than those obtained from only a single pair of neural networks.     

Fairing point sets using curvature

Planar curves “suggested” by sequences of points are considered. A method is discussed for refining the sequence iteratively so that the fairness of the curve is improved while maintaining the basic form and features. This involves the use of intrinsic coordinates and works by smoothing the curvature plot and then integrating twice to recover the curve. Modifications are made during this process to ensure that individual subsegments run correctly between their end points and join smoothly.     

Recursive dynamic node creation in multilayer neural networks

The derivations of a novel approach for simultaneous recursive weight adaptation and node creation in multilayer backpropagation neural networks are presented. The method uses time and order update formulations in the orthogonal projection method to derive a recursive weight updating procedure for the training process of the neural network and a recursive node creation algorithm for weight adjustment of a layer with added nodes during the training process. The proposed approach allows optimal dynamic node creation in the sense that the mean-squared error is minimized for each new topology. The effectiveness of the algorithm is demonstrated on several benchmark problems (the multiplexer and the decoder problems) as well as a real world application for detection and classification of buried dielectric anomalies using a microwave sensor.     

Searching sets of properties with neural networks

In this paper we develop an algorithm in the framework of neural networks. Specifically we consider the problem of detecting a subset of elements of a set Ω which possess a given property.     

Surface defect detection of voltage-dependent resistors using convolutional neural networks

Surface defect detection is an important way to improve the production quality of voltage-dependent resistors (VDRs). To improve the accuracy and efficiency of VDR surface quality detection, an end-to-end surface quality detection method based on deep convolutional neural networks (CNNs) was proposed. The method includes four stages: data preparation, convolution neural network design, CNN training, and testing. First, images of VDRs were acquired from three perspectives, i.e., the front, back, and side, and then training, validation and testing sets were obtained. Second, the proposed CNN models for VDR surface defect detection were constructed. Third, during the training stage, the images with class labels from the established training sets were input to the proposed network for training and validation. Finally, in the testing stage, test images from a total of 408 samples of two VDR models were used to test the trained network. The sensitivity, specificity, accuracy, precision and F measure of the proposed algorithm were compared with those of state-of-the-art methods, and the experimental results showed that the proposed method has a high recognition speed and accuracy and meets the requirements of online real-time detection.

     

Hebb-Hopfield neural networks based on one-dimensional sets of neuron states

Neural Networks (NN), which interconnection matrix is the Hebb matrix of Hopfield (HH) [2,3] are considered. Quasi-continuos sets of neuron states are being used for network matrix production. It is shown, that in this case minima of Hopfield energy are at the bottom of deep ditches, corresponding to the basic set of network activity states for the HH NN. The corresponding states can be made to be stable states of the network. When neuron threshold fatigue is introduced, depending of its recent activity state, the network activity becomes cyclic, moving with a constant rate in one of the two possible directions in the ring, depending on the initial conditions. The phenomena described present novel robust types of NN behavior, which have a high probability to be encountered in living neural systems.     

基于粗糙集的神经网络结构优化设计

神经网络的结构冗余的原因的基础上,提出了一种利用粗集优化网络结构的原理与方法,并用实例证明,与现有的权消去法,灵敏度剪枝法,相关性剪枝法等方法相比,该方法不仅优化了网络的拓扑结构,而且加快了网络的收敛速度,从而增强了BP神经网络的适应能力.     

Tetrahedralization of point sets using expanding spheres

The expanding sphere algorithm computes an alpha shape tetrahedralization of a point set. Starting with a seed tetrahedron, the circumscribing sphere is squeezed through each face until it either touches another point or exceeds a preset radius. If no point is found, that face of the tetrahedron is part of the surface of an object. If a point is found, a new tetrahedron is constructed. This process is iterated until all the faces of the tetrahedra have been processed and no more connected points can be found. If there are points left over, the process is iterated, creating additional objects. The algorithm generates a list of objects, with an alpha shape tetrahedralization and a surface triangulation for each. Any points that cannot be made part of a valid tetrahedron are also returned in the extra points list. The algorithm is efficient for uniformly distributed point sets, with a running time that is linear in the number of points for such sets. Since the operations are local, it is also robust.     

Coloring unstructured radio networks

During and immediately after their deployment, ad hoc and sensor networks lack an efficient communication scheme rendering even the most basic network coordination problems difficult. Before any reasonable communication can take place, nodes must come up with an initial structure that can serve as a foundation for more sophisticated algorithms. In this paper, we consider the problem of obtaining a vertex coloring as such an initial structure. We propose an algorithm that works in the unstructured radio network model. This model captures the characteristics of newly deployed ad hoc and sensor networks, i.e. asynchronous wake-up, no collision-detection, and scarce knowledge about the network topology. When modeling the network as a graph with bounded independence, our algorithm produces a correct coloring with O(Δ) colors in time O(Δ log n) with high probability, where n and Δ are the number of nodes in the network and the maximum degree, respectively. Also, the number of locally used colors depends only on the local node density. Graphs with bounded independence generalize unit disk graphs as well as many other well-known models for wireless multi-hop networks. They allow us to capture aspects such as obstacles, fading, or irregular signal-propagation. A preliminary version of this work has been published in [20] as Coloring Unstructured Radio Networks, In Proceedings of the 17th Symposium on Parallel Algorithms and Architectures (SPAA), Las Vegas, Nevada, 2005.     

Aeromagnetic compensation using neural networks

Airborne magnetic surveys in geophysical exploration can be subject to interference effects from the aircraft. Principal sources are the permanent magnetism of various parts of the aircraft, induction effects created by the earth's magnetic field and eddy-current fields produced by the aircraft's manoeuvres. Neural networks can model these effects as functions of roll, pitch, heading and their time derivatives, together with vertical acceleration, charging currents to the generator, etc., without assuming an explicit physical model. Separation of interference effects from background regional and diurnal fields can also be achieved in a satisfactory way.     

Dynamic modelling using neural networks

A neural network structure is presented that uses feedback of unmeasured system states to represent dynamic systems more efficiently than conventional feedforward and recurrent networks, leading to better predictions, reduced training requirement and more reliable extrapolation. The structure identifies the actual system states based on imperfect knowledge of the initial state, which is available in many practical systems, and is therefore applicable only to such systems. It also enables a natural integration of any available partial state-space model directly into the prediction scheme, to achieve further performance improvement. Simulation examples of three varied dynamic systems illustrate the various options and advantages offered by the state-feedback neural structure. Although the advantages of the proposed structure, compared with the conventional feedforward and recurrent networks, should hold for most practical dynamic systems, artificial systems can readily be created and real systems can surely be found for which one or more of these advantages would vanish or even get reversed. Caution is therefore recommended against interpreting the suggested advantages as strict theorems valid in all situations.     

Job-shop scheduling using neural networks

Job-shop scheduling cannot easily be analytically accomplished, so, it is done by computer simulation using heuristic priority rules. The SLACK rule for calculating the margins of jobs to their due-dates is effective in meeting the due-dates. However, the calculated margins are not precise because the actual margin is shortened due to conflicts with other jobs. The authors propose a method for estimating the margins by using a neural network. It is found that the method is effective for improving the average lateness to due-dates but not the maximum lateness. This paper proposes a method for adding a second neural network for judging the reliability of the estimated margins composed to the first one and for switching to the margins calculated by the SLACK rule when the reliability is low. The proposed method is verified by scheduling simulations to be effective in decreasing the maximum lateness to due-dates as much as the average lateness.     

TCM decoding using neural networks

This paper presents a neural decoder for trellis coded modulation (TCM) schemes. Decoding is performed with Radial Basis Function Networks and Multi-Layer Perceptrons. The neural decoder effectively implements an adaptive Viterbi algorithm for TCM which learns communication channel imperfections. The implementation and performance of the neural decoder for trellis encoded 16-QAM with amplitude imbalance are analyzed.     

Portfolio selection using neural networks

In this paper we apply a heuristic method based on artificial neural networks (NN) in order to trace out the efficient frontier associated to the portfolio selection problem. We consider a generalization of the standard Markowitz mean-variance model which includes cardinality and bounding constraints. These constraints ensure the investment in a given number of different assets and limit the amount of capital to be invested in each asset. We present some experimental results obtained with the NN heuristic and we compare them to those obtained with three previous heuristic methods. The portfolio selection problem is an instance from the family of quadratic programming problems when the standard Markowitz mean-variance model is considered. But if this model is generalized to include cardinality and bounding constraints, then the portfolio selection problem becomes a mixed quadratic and integer programming problem. When considering the latter model, there is not any exact algorithm able to solve the portfolio selection problem in an efficient way. The use of heuristic algorithms in this case is imperative. In the past some heuristic methods based mainly on evolutionary algorithms, tabu search and simulated annealing have been developed. The purpose of this paper is to consider a particular neural network (NN) model, the Hopfield network, which has been used to solve some other optimisation problems and apply it here to the portfolio selection problem, comparing the new results to those obtained with previous heuristic algorithms.     

Invariant and attracting sets of Hopfield neural networks with delay

This paper studies invariant and attracting sets of Hopfield neural networks system with delay. Sufficient criteria are given for the invariant and attracting sets. In particular, we provide an estimate of the existence range of attractors by using invariant and attracting sets. Moreover, when the system has an equilibrium point, we obtain the sufficient conditions of global asymptotic stability of the equilibrium point. Several examples are also worked out to demonstrate the advantages of our results.     

Attracting and quasi-invariant sets of non-autonomous neural networks with delays

In this paper, a class of non-autonomous neural networks with delays is considered. By using the properties of spectral radius of nonnegative matrix, two new integral inequalities are established. Based on the integral inequalities, some new sufficient conditions for the existence of quasi-invariant and attracting sets of the non-autonomous neural networks with delays are obtained. The framework of the quasi-invariant and attracting sets is also given. The results extend and improve the earlier publications. One example is presented to illustrate the effectiveness of our conclusion.     

Surface meshing of underwater maps from highly defective point sets

Owing to the many possible errors that may occur during real‐world mapping, point set maps often present a huge amount of outliers and large levels of noise. We present two robust surface reconstruction techniques dealing with corrupted point sets without resorting to any prefiltering step. They are based on building an unsigned distance function, discretely evaluated on an adaptive tetrahedral grid, and defined from an outlier‐robust splat representation. To extract the surface from this volumetric view, the space is partitioned into two subsets, the surface of interest being at the boundary separating them. While both methods are based on a similar graph definition derived from the above‐mentioned grid, they differ in the partitioning procedure. First, we propose a method using S‐T cuts to separate the inside and outside of the mapped area. Second, we use a normalized cut approach to partition the volume using only the values of the unsigned distance function. We prove the validity of our methods by applying them to challenging underwater data sets (sonar and image based), and we benchmark their results against the approaches in the state of the art.