A delay decomposition approach to delay-dependent passivity analysis for interval neural networks with time-varying delay

This paper is concerned with delay-dependent passivity analysis for interval neural networks with time-varying delay. By decomposing the delay interval into multiple equidistant subintervals, new Lyapunov-Krasovskii functionals (LKFs) are constructed on these intervals. Employing these new LKFs, a new passivity criterion is proposed in terms of linear matrix inequalities, which is dependent on the size of the time delay. Finally, some numerical examples are given to illustrate the effectiveness of the developed techniques.     

A hybrid fault diagnosis approach using neural networks

A hybrid fault diagnosis method is proposed in this paper which is based on the parity equations and neural networks. Analytical redundancy is employed by using parity equations. Neural networks then are used to maximise the signal- to- noise ratio of the residual and to isolate different faults. Effectiveness of the method is demonstrated by applying it to fault detection and isolation for a hydraulic test rig. Real data simulation shows that the sensitivity of the residual to the faults is maximised, whilst that to the unknown input is minimised. The simulated faults are successfully isolated by a bank of neural nets.     

A new approach to artificial neural networks

A novel approach to artificial neural networks is presented. The philosophy of this approach is based on two aspects: the design of task-specific networks, and a new neuron model with multiple synapses. The synapses' connective strengths are modified through selective and cumulative processes conducted by axo-axonic connections from a feedforward circuit. This new concept was applied to the position control of a planar two-link manipulator exhibiting excellent results on learning capability and generalization when compared with a conventional feedforward network. In the present paper, the example shows only a network developed from a neuronal reflexive circuit with some useful artifices, nevertheless without the intention of covering all possibilities devised.     

A neural networks approach to minority game

The minority game (MG) comes from the so-called “El Farol bar” problem by W.B. Arthur. The underlying idea is competition for limited resources and it can be applied to different fields such as: stock markets, alternative roads between two locations and in general problems in which the players in the “minority” win. Players in this game use a window of the global history for making their decisions, we propose a neural networks approach with learning algorithms in order to determine players strategies. We use three different algorithms to generate the sequence of minority decisions and consider the prediction power of a neural network that uses the Hebbian algorithm. The case of sequences randomly generated is also studied. Research supported by Local Project 2004–2006 (EX 40%) Università di Foggia. A. Sfrecola is a researcher financially supported by Dipartimento di Scienze Economiche, Matematiche e Statistiche, Università degli Studi di Foggia, Foggia, Italy.     

Effective data mining using neural networks

Classification is one of the data mining problems receiving great attention recently in the database community. The paper presents an approach to discover symbolic classification rules using neural networks. Neural networks have not been thought suited for data mining because how the classifications were made is not explicitly stated as symbolic rules that are suitable for verification or interpretation by humans. With the proposed approach, concise symbolic rules with high accuracy can be extracted from a neural network. The network is first trained to achieve the required accuracy rate. Redundant connections of the network are then removed by a network pruning algorithm. The activation values of the hidden units in the network are analyzed, and classification rules are generated using the result of this analysis. The effectiveness of the proposed approach is clearly demonstrated by the experimental results on a set of standard data mining test problems     

A variational approach to intensity approximation for remote sensing images using dynamic neural networks

Abstract: In remote sensing image processing, image approximation, or obtaining a high‐resolution image from a corresponding low‐resolution image, is an ill‐posed inverse problem. In this paper, the regularization method is used to convert the image approximation problem into a solvable variational problem. In regularization, the constraints on smoothness and discontinuity are considered, and the original ill‐posed problem is thereby converted to a well‐posed optimization problem. In order to solve the variational problem, a Hopfield‐type dynamic neural network is developed. This neural network possesses two states that describe the discrepancy between a pixel and adjacent pixels, the intensity evolution of a pixel and two kinds of corresponding weights. Based on the experiment in this study with a Landsat TM image free of added noise and a noisy image, the proposed approach provides better results than other methods. The comparison shows the feasibility of the proposed approach.     

A hybrid approach to vehicle routing using neural networks and genetic algorithms

A competitive neural network model and a genetic algorithm are used to improve the initialization and construction phase of a parallel insertion heuristic for the vehicle routing problem with time windows. The neural network identifies seed customers that are distributed over the entire geographic area during the initialization phase, while the genetic algorithm finds good parameter settings in the route construction phase that follows. Computational results on a standard set of problems are also reported.     

Intelligent data structures selection using neural networks

It is well known that abstract data types represent the core for any software application, and a proper use of them is an essential requirement for developing a robust and efficient system. Data structures are essential in obtaining efficient algorithms, having a major importance in the software development process. Selecting and creating the appropriate data structure for implementing an abstract data type can greatly impact the performance and the efficiency of the software systems. It is not a trivial problem for a software developer, as it is hard to anticipate all the use scenarios of the deployed application, and a static selection before the system’s execution is, generally, not accurate. In this paper, we are focusing on the problem of dynamic selection of efficient data structures for abstract data types implementation using a supervised learning approach. In order to dynamically select the most suitable representation for an aggregate according to the software system’s current execution context, a neural network will be used. We experimentally evaluate the proposed technique on a case study, emphasizing the advantages of the proposed model in comparison with existing similar approaches.     

Scenery image recognition and interpretation using fuzzy inference neural networks

In this paper, we propose a new image recognition and interpretation system. The proposed system is composed of three processes: (1) regional segmentation process; (2) image recognition process; and (3) image interpretation process. As a pre-processing in the regional segmentation process, an input image is divided into some proper regions using techniques based on K-means algorithm. In both the image recognition and the interpretation processes, fuzzy inference neural networks (FINNs) working in parallel are employed to achieve a high level of recognition and interpretation. Scenery images are used and it is confirmed that the system has an average of 71.9% accuracy rate in the recognition process and good results in the interpretation process without heuristic knowledge. In addition, it is also confirmed that the proposed system has an ability to extract proper rules for the image recognition and interpretation.     

A global optimum approach for one-layer neural networks

The article presents a method for learning the weights in one-layer feedforward neural networks minimizing either the sum of squared errors or the maximum absolute error, measured in the input scale. This leads to the existence of a global optimum that can be easily obtained solving linear systems of equations or linear programming problems, using much less computational power than the one associated with the standard methods. Another version of the method allows computing a large set of estimates for the weights, providing robust, mean or median, estimates for them, and the associated standard errors, which give a good measure for the quality of the fit. Later, the standard one-layer neural network algorithms are improved by learning the neural functions instead of assuming them known. A set of examples of applications is used to illustrate the methods. Finally, a comparison with other high-performance learning algorithms shows that the proposed methods are at least 10 times faster than the fastest standard algorithm used in the comparison.     

A neural networks algorithm for data path synthesis

This paper presents a deterministic parallel algorithm to solve the data path allocation problem in high-level synthesis. The algorithm is driven by a motion equation that determines the neurons firing conditions based on the modified Hopfield neural network model of computation. The method formulates the allocation problem using the clique partitioning problem, an NP-complete problem, and handles multicycle functional units as well as structural pipelining. The algorithm has a running time complexity of O(1) for a circuit with n operations and c shared resources. A sequential simulator was implemented on a Linux Pentium PC under X-Windows. Several benchmark examples have been implemented and favorable design comparisons to other synthesis systems are reported.     

A new approach for automated parts recognition using time series analysisand neural networks

This paper presents a new approach for automated parts recognition. It is based on the use of the signature and autocorrelation functions for feature extraction and a neural network for the analysis of recognition. The signature represents the shapes of boundaries detected in digitized binary images of the parts. The autocorrelation coefficients computed from the signature are invariant to transformations such as scaling, translation and rotation of the parts. These unique extracted features are fed to the neural network. A multilayer perceptron with two hidden layers, along with a backpropagation learning algorithm, is used as a pattern classifier. In addition, the position information of the part for a robot with a vision system is described to permit grasping and pick-up. Experimental results indicate that the proposed approach is appropriate for the accurate and fast recognition and inspection of parts in automated manufacturing systems.     

Classification approach for reliability-based topology optimization using probabilistic neural networks

This research explores the usage of classification approaches in order to facilitate the accurate estimation of probabilistic constraints in optimization problems under uncertainty. The efficiency of the proposed framework is achieved with the combination of a conventional topology optimization method and a classification approach- namely, probabilistic neural networks (PNN). Specifically, the implemented framework using PNN is useful in the case of highly nonlinear or disjoint failure domain problems. The effectiveness of the proposed framework is demonstrated with three examples. The first example deals with the estimation of the limit state function in the case of disjoint failure domains. The second example shows the efficacy of the proposed method in the design of stiffest structure through the topology optimization process with the consideration of random field inputs and disjoint failure phenomenon, such as buckling. The third example demonstrates the applicability of the proposed method in a practical engineering problem.     

A blackboard system approach to electromagnetic sensor data interpretation

Abstract: A prototype system for automated defect classification and characterisation of automotive or other components involving two separate inspection sensors, vision and electromagnetic, was developed. This paper concentrates on the development work and issues related to the electromagnetic sensor. In particular, the issues relating to knowledge acquisition and knowledge representation are discussed. For instance, one of the problems which arose during the development work was that it appeared that the reasoning carried out unconsciously by a human was more complex than had been realised and not easily encapsulated as high level knowledge. A blackboard architecture was used to integrate the different areas of expertise required for each sensor to interpret the results of the inspections. The main issue here was in the effective use of the blackboard architecture for intelligent data fusion at all levels to improve interpretation.     

A neural network approach for data masking

In this letter we present a neural network based data masking solution, in which the database information remains internally consistent yet is not inadvertently exposed in an interpretable state. The system differs from the classic data masking in the sense that it can understand the semantics of the original data and mask it using a neural network which is a priori trained by some rules. Our adaptive data masking (ADM) concentrates on data masking techniques such as shuffling, substitution, masking and number variance in an intelligent fashion with the help of adaptive neural network. The very nature of being adaptive makes data masking easier and content agnostic, and thus finds place in various vertical domains and systems.     

A genetic algorithm to refine input data selection for air temperature prediction using artificial neural networks

The accurate prediction of air temperature is important in many areas of decision-making including agricultural management, transportation and energy management. Previous research has focused on the development of artificial neural network (ANN) models to predict air temperature from one to twelve hours in advance. The inputs to these models included a constant duration of prior data with a fixed resolution for all environmental variables for all prediction horizons. The overall goal of this research was to develop more accurate ANN models that could predict air temperature for each prediction horizon. The specific objective was to determine if the ANN model accuracy could be improved by applying a genetic algorithm (GA) for each prediction horizon to determine the preferred duration and resolution of input prior data for each environmental variable. The ANN models created based on this GA based approach provided smaller errors than the models created based on the existing constant duration and fixed data resolution approach for all twelve prediction horizons. Except for a few cases, the GA generally included a longer duration for prior air temperature data and shorter durations for other environmental variables. The mean absolute errors (MAEs) for the evaluation input patterns of the one-, four-, eight-, and twelve-hour prediction models that were based on this GA approach were 0.564 °C, 1.264 °C, 1.766 °C and 2.018 °C, respectively. These MAEs were improvements of 3.98%, 4.59%, 2.55% and 1.70% compared to the models that were created based on the existing approach for the same corresponding prediction horizons. Thus, the GA based approach to determine the duration and resolution of prior input data resulted in more accurate ANN models than the existing ones for air temperature prediction. Future work could examine the effects of various GA and fitness evaluation parameters that were part of the approach used in this study.     

Symbolic interpretation of artificial neural networks

Hybrid intelligent systems that combine knowledge-based and artificial neural network systems typically have four phases, involving domain knowledge representation, mapping of this knowledge into an initial connectionist architecture, network training and rule extraction, respectively. The final phase is important because it can provide a trained connectionist architecture with explanation power and validate its output decisions. Moreover, it can be used to refine and maintain the initial knowledge acquired from domain experts. In this paper, we present three rule extraction techniques. The first technique extracts a set of binary rules from any type of neural network. The other two techniques are specific to feedforward networks, with a single hidden layer of sigmoidal units. Technique 2 extracts partial rules that represent the most important embedded knowledge with an adjustable level of detail, while the third technique provides a more comprehensive and universal approach. A rule-evaluation technique, which orders extracted rules based on three performance measures, is then proposed. The three techniques area applied to the iris and breast cancer data sets. The extracted rules are evaluated qualitatively and quantitatively, and are compared with those obtained by other approaches     

A neural network approach for a robot task sequencing problem

This paper presents a neural network approach with successful implementation for the robot task-sequencing problem. The problem addresses the sequencing of tasks comprising loading and unloading of parts into and from the machines by a material-handling robot. The performance criterion is to minimize a weighted objective of the total robot travel time for a set of tasks and the tardiness of the tasks being sequenced. A three-phased parallel implementation of the neural network algorithm on Thinking Machine's CM-5 parallel computer is also presented which resulted in a dramatic increase in the speed of finding solutions. To evaluate the performance of the neural network approach, a branch-and-bound method and a heuristic procedure have been developed for the problem. The neural network method is shown to give good results and is especially useful for solving large problems on a parallel-computing platform.     

Nonlinear curve fitting to stopping power data using RBF neural networks

This paper presents a novel approach for fitting experimental stopping power data to a simple empirical formula. The unknown complex nonlinear stopping power function is approximated by a Radial Basis Function (RBF) neural network with an additional linear neuron. The fitting coefficients are determined by learning algorithms globally. The experiments using the proposed method have been conducted on a benchmark dataset (titanium heat) and a set of stopping power data with implicit noise (MeV projectiles of Li, B, C, O, Al, Si, Ar, Ti and Fe in elemental carbon materials) from high energy physics measurements. The results not only showed the effectiveness of our method but also showed the significant improvement of fitting accuracy over other methods, without increasing computational complexity. The proposed approach allows us to obtain a fast and accurate interpolant that well suits to the situations where no stopping power data exist. It can be used as a standalone method or implemented as a sub-system that can be efficiently embedded in an intelligent system for ion beam analysis techniques.