Search

In natural language processing (NLP), transformer based models have surpassed recurrent neural networks (RNN) as state of the art, being introduced specifically to address the limitations of RNNs originating from its sequential nature. As a similar sequence modeling problem, transformer methods can be readily adapted for deep learning time series prediction. This paper proposes a sparse transformer based approach for electricity load prediction. The layers of a transformer addresses the shortcomings of RNNs and CNNs by applying the attention mechanism on the entire time series, allowing any data point in the input to influence any location in the output of the layer. This allows transformers to incorporate information from the entire sequence in a single layer. Attention computations can also be parallelized. Thus, transformers can achieve faster speeds, or trade this speed for more layers and increased complexity. In experiments on public datasets, the sparse transformer attained comparable accuracy to an RNN-based SOTA method (Liu et al., 2022) while being up to 5× faster during inference. Moreover, the proposed model is general enough to forecast the load from individual households to city levels as shown in the extensive experiments conducted. [ABSTRACT FROM AUTHOR]

Abstract: This paper presents a novel hybrid GMDH-type algorithm which combines neural networks (NNs) with an approximation scheme (self-organizing polynomial neural network: SOPNN). This composite structure is developed to establish a new heuristic approximation method for identification of nonlinear static systems. NNs have been widely employed to process modeling and control because of their approximation capabilities. And SOPNN is an analysis technique for identifying nonlinear relationships between the inputs and outputs of such systems and builds hierarchical polynomial regressions of required complexity. Therefore, the combined model can harmonize NNs with SOPNN and find a workable synergistic environment. Simulation results of the nonlinear static system are provided to show that the proposed method is much more accurate than other modeling methods. Thus, it can be considered for efficient system identification methodology. [Copyright &y& Elsevier]

In the last decades, several tools and various methodologies have been proposed by the researchers for developing effective medical decision support systems. Moreover, new methodologies and new tools are continued to develop and represent day by day. Diagnosing of the heart disease is one of the important issue and many researchers investigated to develop intelligent medical decision support systems to improve the ability of the physicians. In this paper, we introduce a methodology which uses SAS base software 9.1.3 for diagnosing of the heart disease. A neural networks ensemble method is in the centre of the proposed system. This ensemble based methods creates new models by combining the posterior probabilities or the predicted values from multiple predecessor models. So, more effective models can be created. We performed experiments with the proposed tool. We obtained 89.01% classification accuracy from the experiments made on the data taken from Cleveland heart disease database. We also obtained 80.95% and 95.91% sensitivity and specificity values, respectively, in heart disease diagnosis. [Copyright &y& Elsevier]

Abstract: One of the phenomena that can be observed when using neural networks for time series prediction is that the quality of the forecasts obtained is correlated with the dimensionality of the data. Higher data dimensionality leads, in most cases, to higher prediction errors. This phenomenon is connected by some authors to the decrease in variance of the distances between the data points, which occurs when the lengths of the predicted vectors increase. In this paper, a proof is given that the variance of the distances between data points also decreases with the so-called correlation dimension of the data. Therefore, a drop in forecast quality might be expected not only when the lengths of the data vectors are increased, but also when using vectors of the same length to represent data of increasing dimensionality. We also present some experimental results that illustrate the dependence between data dimensionality and the variance of the distances between the data points, and the forecast error obtained when using a multilayer perceptron to predict future values of some time series. [Copyright &y& Elsevier]

Abstract: The construction of computational models with provision for effective learning and added reasoning is a fundamental problem in computer science. In this paper, we present a new computational model for integrated reasoning and learning that combines intuitionistic reasoning and neural networks. We use ensembles of neural networks to represent intuitionistic theories, and show that for each intuitionistic theory and intuitionistic modal theory there exists a corresponding neural network ensemble that computes a fixed-point semantics of the theory. This provides a massively parallel model for intuitionistic reasoning. In our model, the neural networks can be trained from examples to adapt to new situations using standard neural learning algorithms, thus providing a unifying foundation for intuitionistic reasoning, knowledge representation, and learning. [Copyright &y& Elsevier]

Abstract: In this paper, two methods are reviewed and compared for designing reduced order controllers for distributed parameter systems. The first involves a reduction method known as LQG balanced truncation followed by MinMax control design and relies on the theory and properties of the distributed parameter system. The second is a neural network based adaptive output feedback synthesis approach, designed for the large scale discretized system and depends upon the relative degree of the regulated outputs. Both methods are applied to a problem concerning control of vibrations in a nonlinear structure with a bounded disturbance. [Copyright &y& Elsevier]

This paper presents a technique based on artificial neural networks (ANN) to estimate pollutant rates of emission from industrial stacks, on the basis of pollutant concentrations measured on the ground. The ANN is trained on data generated by the ISCST3 model, widely accepted for evaluation of dispersion of primary pollutants as a part of an environmental impact study. Simulations using theoretical values and comparison with field data are done, obtaining good results in both cases at predicting emission rates.The application of this technique would allow the local environment authority to control emissions from industrial plants without need of performing direct measurements inside the plant. [Copyright &y& Elsevier]

Jet engines are nonlinear dynamical systems for which an exact mathematical model cannot be used for estimator design, because it is either not available or so complex that it does not fit the necessary assumptions. Thus, classical analytical tools for studying standard system properties like observability, which is very important in estimator design, cannot be directly applied. Generally, for practical jet engine applications, the designer faces two closely related problems: first, given a non-measurable parameter, find the minimal set of estimator inputs that facilitates achieving a satisfactory estimation performance (input selection); second, given a predetermined set of inputs, derive an “observability” measure that characterizes the estimation feasibility of a specific non-measurable parameter. In this paper, techniques for solving these two problems are developed and applied to estimator design for jet engine thrust, stall margins, and an unmeasurable state. [Copyright &y& Elsevier]

This paper investigates the asymmetric costs of false positive and negative errors to enhance the IDS performance. The proposed method utilizes the neural network model to consider the cost ratio of false negative errors to false positive errors. Compared with false positive errors, false negative errors incur a greater loss to organizations which are connected to the systems by networks. This method is designed to accomplish both security and system performance objectives. The results of our empirical experiment show that the neural network model provides high accuracy in intrusion detection. In addition, the simulation results show that the effectiveness of intrusion detection can be enhanced by considering the asymmetric costs of false negative and false positive errors. [Copyright &y& Elsevier]