A Novel Radial Basis Function Neural Network with High Generalization Performance for Nonlinear Process Modelling

A radial basis function neural network (RBFNN), with a strong function approximation ability, was proven to be an effective tool for nonlinear process modeling. However, in many instances, the sample set is limited and the model evaluation error is fixed, which makes it very difficult to construct an optimal network structure to ensure the generalization ability of the established nonlinear process model. To solve this problem, a novel RBFNN with a high generation performance (RBFNN-GP), is proposed in this paper. The proposed RBFNN-GP consists of three contributions. First, a local generalization error bound, introducing the sample mean and variance, is developed to acquire a small error bound to reduce the range of error. Second, the self-organizing structure method, based on a generalization error bound and network sensitivity, is established to obtain a suitable number of neurons to improve the generalization ability. Third, the convergence of this proposed RBFNN-GP is proved theoretically in the case of structure fixation and structure adjustment. Finally, the performance of the proposed RBFNN-GP is compared with some popular algorithms, using two numerical simulations and a practical application. The comparison results verified the effectiveness of RBFNN-GP.

Construction of Nominal Ionospheric Gradient Using Satellite Pair Method Based on GNSS CORS Observation in Indonesia

Ground-Based Augmentation System (GBAS) is a GNSS augmentation system that meets International Civil Aviation Organization (ICAO) requirements to support precision approach and landing. GBAS is based on the local differential GNSS technique with reference stations located around the airport to provide necessary integrity and accuracy. The performance of the GBAS system can be affected by the gradient in the ionospheric delay between the aircraft and the reference stations. A nominal ionospheric gradient, which is bounded by a conservative error bound, is represented by a parameter σvig. σvig was commonly determined using station pair to GNSS Continuous Operating Reference Station (CORS) data. The station pair method is susceptible to doubling of receiver bias error and is not suitable with the CORS conditions in Indonesia. We propose a satellite pair method that is found to be more suitable for the CORS network over Indonesia which is centered in Java and Sumatra islands. The value of σvig (4.48 mm/km) is obtained using this method along with the preliminary results of a comparison of σvig from Java and Sumatra islands.

New error bound for linear complementarity problem of $ S $-$ SDDS $-$ B $ matrices

<abstract><p>$ S $-$ SDDS $-$ B $ matrices is a subclass of $ P $-matrices which contains $ B $-matrices. New error bound of the linear complementarity problem for $ S $-$ SDDS $-$ B $ matrices is presented, which improves the corresponding result in ^{[<xref ref-type="bibr" rid="b1">1</xref>]}. Numerical examples are given to verify the corresponding results.</p></abstract>