Search

In this paper, a fault detection scheme for application to large-scale data acquisition systems is presented. The detection scheme has to process up to several hundreds of different measurements at a time and check them for consistency. The fault detection scheme works in three steps: First, principal component analysis of training data is used to determine non-sparse areas of the measurement space. Fault detection is accomplished by checking whether a new data record lies in a cluster of training data or not. Therefore, in a second step the distribution function of the available data is estimated using kernel regression techniques. In order to reduce the degrees of freedom and to determine clusters of data efficiently, in a third step the distribution function is approximated by a neural network. In order to use as few basis functions as possible a new training algorithm for ellipsoidal basis function networks is presented: New neurons are placed such that they approximate the distribution function in the vicinity of their centers up to the second order. This is accomplished by adapting the spread parameters using Taylor''s theorem. Thus, the amount of necessary parameters and the computational effort for online supervision can be reduced dramatically. An important requirement for the fault detection scheme is that it is able to automatically adapt itself to new data. The present paper also addresses this feature. It is demonstrated how a gradient optimization with algebraic constraints can be applied to adapt a pre-existing network to new data points. Numerical examples with real data show that the proposed method produces excellent results. [Copyright &y& Elsevier]

Abstract: Neural networks (NNs) represent a familiar artificial intelligence approach widely applied in many fields and to a wide range of issues. The back propagation network (BPN) is one of the most well-known NNs, comprising multilayer perceptrons (MLPs) with an error back propagation learning algorithm. BPN typically employs associate multiplicative weightings for layer connections. For single connections, BPN combines neuron inputs linearly to neuron outputs. In this study, the author develops and embeds high order connections (exponent multipliers) into the BPN. The resultant proposed hybrid high order neural network (HHONN) is intended to be applicable to both linear and high order connections. HHONN allows an additional connection type for BPN, which permits BPN to adapt to different scenarios. In this paper, learning equations for both weighting and high order connections are introduced in their general forms. A feedforward neural network with a topology of two hidden layers and one high order connection was developed and studied to confirm the improved performance of developed HHONN models. Case studies, including two basic tests (a function approximation and the TC problem) and squat wall strength learning, were used to verify HHONN performance. Results showed that, when the high order connection was employed anywhere except the eventual connection, HHONN delivered better results than achievable using traditional BPN. Such results show that HHONN successfully introduces high order connections into BPN. [Copyright &y& Elsevier]

Abstract: This paper presents an overview of a data analysis method based on self-organizing maps (SOM), a well-known unsupervised neural network learning algorithm, which was applied to a lead-free wave soldering process. The aim of the study was to determine whether the neural network modeling method could be a useful and time-saving way to analyze data from a discrete manufacturing process, such as wave soldering, which is a widely used technique in the electronics industry to solder components on printed circuit boards. The data variables were mostly various process parameters, but also some solder defect numbers were present in the data as a measure of the product quality. The data analysis procedure went as follows. At first, the process data were modeled using the SOM-algorithm. Next, the neuron reference vectors of the formed map were clustered to reveal the desired dominating elements of each territory of the map. At the final stage, the clusters were utilized as sub-models to indicate variable dependencies in these sub-models. The results show that the method presented here can be a good way to analyze this type of process data because interesting interactions between certain process parameters and solder defects were found by means of this data-driven modeling method. [Copyright &y& Elsevier]

Abstract: A given observation in time series does not only depend on preceding one but also previous ones in general. Therefore, high order fuzzy time series approach might obtain better forecasts than does first order fuzzy time series approach. Defining fuzzy relation in high order fuzzy time series approach are more complicated than that in first order fuzzy time series approach. A new proposed approach, which uses feed forward neural networks to define fuzzy relation in high order fuzzy time series, is introduced in this paper. The new proposed approach is applied to well-known enrollment data for the University of Alabama and obtained results are compared with other methods proposed in the literature. It is found that the proposed method produces better forecasts than the other methods. [Copyright &y& Elsevier]

Abstract: This paper presents a new approach to the tracking of multiple objects in CCTV surveillance using a combination of simple neural cost functions based on Self-Organizing Maps, and a greedy assignment algorithm. Using a reference standard data set and an exhaustive search algorithm for benchmarking, we show that the cost function plays the most significant role in realizing high levels of performance. The neural cost function’s context-sensitive treatment of appearance, change of appearance and trajectory yield better tracking than a simple, explicitly designed cost function. The algorithm matches 98.8% of objects to within 15 pixels. [Copyright &y& Elsevier]

Abstract: This paper is concerned with the state estimation problem for a class of Markovian neural networks with discrete and distributed time-delays. The neural networks have a finite number of modes, and the modes may jump from one to another according to a Markov chain. The main purpose is to estimate the neuron states, through available output measurements, such that for all admissible time-delays, the dynamics of the estimation error is globally asymptotically stable in the mean square. An effective linear matrix inequality approach is developed to solve the neuron state estimation problem. Both the existence conditions and the explicit characterization of the desired estimator are derived. Furthermore, it is shown that the traditional stability analysis issue for delayed neural networks with Markovian jumping parameters can be included as a special case of our main results. Finally, numerical examples are given to illustrate the applicability of the proposed design method. [Copyright &y& Elsevier]

Abstract: In this paper, the problem of exponential stability of uncertain cellular neural networks with discrete and distribute time-varying delays is considered. Based on the Lyapunov function method and convex optimization approach, a new delay-dependent stability criterion with an exponential convergence rate is derived in terms of LMI (linear matrix inequality). Three numerical examples are given to show the effectiveness of the proposed methods. [Copyright &y& Elsevier]

Abstract: This paper discusses a predictive modeling framework actualized in a learning agent that uses logged tutorial interactions to discover predictive characteristics of students. The agent automatically forms cluster models that are described in terms of student–system interaction attributes, i.e., in terms of the student’s knowledge state and behaviour and system’s tutoring actions. The agent utilizes the knowledge of its various clusters together with a weighting scheme to learn predictive models of high-level student information, specifically, the time it will take the student to respond to a problem and whether the response is correct, that can be utilized to support individualized adaptation. We investigated utilizing the Self-Organizing Map and AutoClass as clustering algorithms and the naïve Bayesian classifier and single layer neural network as weighting algorithms. Empirical results show that by utilizing cluster knowledge the agent’s predictions are acceptably strong for response time and accurate at the average for response correctness. Further investigation is needed to validate the scalability of the framework given other datasets and possibly migrate to other approaches that can obtain more meaningful cluster models, detect richer attribute relations, and provide better approximations to further improve prediction of response behaviour for a more informed pedagogical decision-making by the system. [Copyright &y& Elsevier]

Abstract: The paper presents a neural network model for evaluation of the magnetic/mechanical properties and the rate of corrosive wear of the polymer matrix hard magnetic composite materials with particles of the powdered rapid quenched Nd–Fe–B strip with addition of metallic powder: iron, aluminum, CuSn10 type cast copper–tin alloy and X2CrNiMo17-12-2 high-alloy steel. Simulation approach to model the magnetic/mechanical properties in function of the chemical composition employing a neural network technique was proposed. A neural network model of corrosion wear was established based on the research results from the investigations carried out in two corrosive environments. Simulation approach to model the corrosive wear in function of the chemical composition, nature of the corrosive environment and the test duration was proposed. The obtained results indicate that the developed neural networks are able to generalize which justified using these models to the simulation of magnetic/mechanical properties and corrosive wear of hard magnetic composite materials. [Copyright &y& Elsevier]

Abstract: This paper presents the implementation of an artificial neural network to predict surface heave resulting from shallow subsurface utility installations conducted with horizontal directional drilling. Data gathered from a full factorial field experimentation examining the effects of drilling techniques is utilized in the network development, with the attempt to understand the relationship between construction techniques and resulting surface heave. The developed model is compared to a multivariate linear regression analysis conducted on the raw data, and a sensitivity analysis utilizing the trained network connection weights is conducted to determine which factor has the greatest effect on surface heave development. Further examination of the behavior of the system is provided through a trend analysis which studied the effect of each drilling factor on the predicted surface heave. The results indicate that a neural network would adequately model the relationship between drilling techniques and the resulting surface heave. [Copyright &y& Elsevier]

This paper presents a novel architecture of neural networks designed for pattern recognition. The concept of induction graphs coupled with a divide-and-conquer strategy defines a neural network induction graph (NNIG). First, the NNIG concept is described and its properties detailed. It is based on a set of several little neural networks, each one discriminating only two classes. The specialization of each neural network simplifies their structure and improves the classification. The principle used to perform the decision of classification on an input pattern is explained. The latter enables to take into account dubious decisions identified by the NNIG. The last section presents experimental results. A significant gain in the global classification rate can be obtained by using an NNIG. The discussion is illustrated by tests on databases from the UCI machine learning database repository. The experimental results show that an NNIG can achieve a better learning, simpler neural networks and an improved performance in classification. A final illustration is presented on a real microscopical imaging problem for the classification of cells in serous cytology. [Copyright &y& Elsevier]