Search

Abstract: The Hilbert transform defined via the Hartley transform in contrast with the well-known Fourier transform is mathematically illustrated with a couple of geophysical applications. Although, the 1-D Fourier and Hartley transforms are identical in amplitude with a phase difference of 45°, the Hilbert transform effectively differs when defined as a function of the Hartley transform in certain geophysical applications. It may be noted here that the Hilbert transform defined through Fourier and Hartley transforms while possessing the same magnitude differs in phase by 270°. It is derived and shown mathematically that the evaluation of depth of subsurface targets is directly equal to the abscissa of the point of intersection of the gravity (magnetic) field and the Hartley–Hilbert transform; however, it is not the case with the Fourier–Hilbert transform. The practical applications are illustrated with the interpretation of gravity anomaly due to an inclined sheet-like structure across the Mobrun ore body, Noranda, Quebec, Canada, and the vertical magnetic anomaly due to a cylindrical structure over a narrow band of quartzite magnetite, Karimnagar, India. The entire process can be automated. [Copyright &y& Elsevier]

Abstract: A code, TODGINV, to determine the parameters of 2D anticlinal and synclinal structures besides estimating linear regional gravity background is presented wherein the density contrast varies with depth based on a parabolic equation. The main program, TODGINV, is supported by five subroutines namely GANTCLINE, GSYNCLINE, PDSANT, PDSSYN and NOREQS. Forward modeling is realized through the subroutine GANTCLINE in case of an anticlinal structure while GSYNCLINE in case of a synclinal structure. PDSANT and PDSSYN compute the partial derivatives of anticlinal and synclinal structures, respectively, whereas NOREQS solves the system of normal equations. The efficiency of the code is illustrated with a set of synthetic gravity anomalies over an anticlinal and a synclinal structure both with and without regional background. Further, the code is exemplified with the gravity anomalies of the Pays De Bray anticline, France, and the results are found to be more consistent with borehole information rather than with those of Alessandrello et al. (1983, Automatic three-layer, three-dimensional deconvolution of the Pays De Bray anticline. Geophysical Prospecting 31, 608–626). [Copyright &y& Elsevier]

A program, INV2P5DSB, has been developed to simultaneously estimate the depth of a 2. 5-D sedimentary basin and regional background from observed gravity anomalies. The density contrast is assumed to be varying parabolically with depth above the basement interface. The main program is supported with two subroutines GRAV2P5D and SIMEQ and a function GPRM. The analysis of gravity anomalies due to a synthetic model of a 2. 5-D sedimentary basin with and without regional background illustrates that the code is insensitive to regional background. Interpretation of gravity anomalies over the Gediz graben, Western Anatolia with parabolic density function yields geologically plausible model. [Copyright &y& Elsevier]

Abstract: This paper presents a neural-aided controller that enhances the fault tolerant capabilities of a high performance fighter aircraft during the landing phase when subjected to severe winds and failures such as stuck control surfaces. The controller architecture uses a neural controller aiding an existing conventional controller. The neural controller uses a feedback error learning mechanism and employs a dynamic Radial Basis Function neural network called Extended Minimal Resource Allocating Network (EMRAN), which uses only on-line learning and does not need a priori training. The conventional controller is designed using a classical design approach to achieve the desired autonomous landing profile with tight touchdown dispersions called herein as the pillbox. This design is carried out for no failure conditions but with the aircraft being subjected to winds. The failure scenarios considered in this study are: (i) Single faults of either aileron or elevator stuck at certain deflections, and (ii) double fault cases where both the aileron and elevator are stuck at different deflections. Simulation studies indicate that the designed conventional controller has only a limited failure handling ability. However, neural controller augmentation considerably improves the ability to handle large faults and meet the strict touchdown dispersion requirements, thus enlarging the fault-tolerance envelope. [Copyright &y& Elsevier]

Abstract: An algorithm and associated codes are developed to determine the depths to bottom of a 21/2-D sedimentary basin in which the density contrast varies parabolically with depth. This algorithm estimates initial depths of a sedimentary basin automatically and modifies thereafter appropriately within the permissible limits in an iterative approach as described in the text. Efficacy of the method as well as the code is illustrated by interpreting a gravity anomaly of a synthetic model. Further, the applicability of the method is exemplified with the derived density–depth model of the Godavari sub-basin, India to interpret the gravity anomalies due to the basin. Interpretations based on parabolic density profile are more consistent with existing geological information rather than with those obtained with constant density profile. [Copyright &y& Elsevier]

A method to model 3-D sedimentary basins with density contrast varying with depth is presented along with a code GRAV3DMOD. The measured gravity fields, reduced to a horizontal plane, are assumed to be available at grid nodes of a rectangular/square mesh. Juxtaposed 3-D rectangular/square blocks with their geometrical epicenters on top coincide with grid nodes of a mesh to approximate a sedimentary basin. The algorithm based on Newton''s forward difference formula automatically calculates the initial depth estimates of a sedimentary basin assuming that 2-D infinite horizontal slabs among which, the density contrast varies with depth could generate the measured gravity fields. Forward modeling is realized through an available code GR3DPRM, which computes the theoretical gravity field of a 3-D block. The lower boundary of a sedimentary basin is formulated by estimating the depth values of the 3-D blocks within predetermined limits. The algorithm is efficient in the sense that it automatically generates the grid files of the interpreted results that can be viewed in the form of respective contour maps. Measured gravity fields pertaining to the Chintalpudi sub-basin, India and the Los Angeles basin, California, USA in which the density contrast varies with depth are interpreted to show the applicability of the method. [Copyright &y& Elsevier]

Motor-imagery tasks generate event related synchronization and de-synchronization in certain subject-specific frequency ranges of the subject’s ElectroEncephaloGraphy (EEG) signals. The selection of frequency ranges for each subject is important for obtaining better classification accuracy of motor-imagery based Brain Computer Interface (BCI). Further, the spatial filters extracted corresponding to the selected spectral ranges also influence the classification accuracy. In this paper, a subject-specific spatio-spectral filter selection approach using a cognitive fuzzy inference system for classification of the motor-imagery tasks in a two step approach is presented. The cognitive fuzzy inference system (CFIS) employs an evolving interval type-2 system to classify the non-stationary features. The classifier employs a meta-cognitive sequential algorithm to determine both the structure and parameters of the CFIS. In the first step, the CFIS classifier is used to find the desired spectral filters by eliminating those frequency bands that do not affect the classification performance. In the second step, CFIS is used to eliminate those spatial filters which do not affect the performance. The performance of CFIS based spatio-spectral scheme has been evaluated using two publicly available BCI competition data sets and compared with other existing algorithms like FBCSP, DCSP and BSSFO. The results indicate that the proposed approach outperforms the CSP method by approximately 15–18% and other algorithms like FBCSP, DCSP by 8–10%. Compared to a recently proposed algorithm BSSFO, it achieves an improvement of 2%, but is simpler in comparison to BSSFO. The main impact of the work is its ability to handle non-stationarity using interval type-2 sets and provide good classification performance. In general, the proposed CFIS algorithm can be applied in the field of expert and intelligent systems where it is necessary to deal with non-stationary signals. [ABSTRACT FROM AUTHOR]

Abstract: In this paper, we present a novel approach for the identification of brain regions responsible for Alzheimer’s disease using the Magnetic Resonance (MR) images. The approach incorporates the recently developed Self-adaptive Resource Allocation Network (SRAN) for Alzheimer’s disease classification using voxel-based morphometric features of MR images. SRAN classifier uses a sequential learning algorithm, employing self-adaptive thresholds to select the appropriate training samples and discard redundant samples to prevent over-training. These selected training samples are then used to evolve the network architecture efficiently. Since, the number of features extracted from the MR images is large, a feature selection scheme (to reduce the number of features needed) using an Integer-Coded Genetic Algorithm (ICGA) in conjunction with the SRAN classifier (referred to here as the ICGA–SRAN classifier) have been developed. In this study, different healthy/Alzheimer’s disease patient’s MR images from the Open Access Series of Imaging Studies data set have been used for the performance evaluation of the proposed ICGA–SRAN classifier. We have also compared the results of the ICGA–SRAN classifier with the well-known Support Vector Machine (SVM) and Extreme Learning Machine (ELM) classifiers. The study results clearly show that the ICGA–SRAN classifier produces a better generalization performance with a smaller number of features, lower misclassification rate and a compact network. The ICGA–SRAN selected features clearly indicate that the variations in the gray matter volume in the parahippocampal gyrus and amygdala brain regions may be good indicators of the onset of Alzheimer’s disease in normal persons. [Copyright &y& Elsevier]

Abstract: This paper presents a meta-cognitive learning algorithm for a single hidden layer complex-valued neural network called “Meta-cognitive Fully Complex-valued Relaxation Network (McFCRN)”. McFCRN has two components: a cognitive component and a meta-cognitive component. A Fully Complex-valued Relaxation Network (FCRN) with a fully complex-valued Gaussian like activation function () in the hidden layer and an exponential activation function in the output layer forms the cognitive component. The meta-cognitive component contains a self-regulatory learning mechanism which controls the learning ability of FCRN by deciding what-to-learn, when-to-learn and how-to-learn from a sequence of training data. The input parameters of cognitive components are chosen randomly and the output parameters are estimated by minimizing a logarithmic error function. The problem of explicit minimization of magnitude and phase errors in the logarithmic error function is converted to system of linear equations and output parameters of FCRN are computed analytically. McFCRN starts with zero hidden neuron and builds the number of neurons required to approximate the target function. The meta-cognitive component selects the best learning strategy for FCRN to acquire the knowledge from training data and also adapts the learning strategies to implement best human learning components. Performance studies on a function approximation and real-valued classification problems show that proposed McFCRN performs better than the existing results reported in the literature. [Copyright &y& Elsevier]

Abstract: This paper presents a performance enhancement scheme for the recently developed extreme learning machine (ELM) for multi-category sparse data classification problems. ELM is a single hidden layer neural network with good generalization capabilities and extremely fast learning capacity. In ELM, the input weights are randomly chosen and the output weights are analytically calculated. The generalization performance of the ELM algorithm for sparse data classification problem depends critically on three free parameters. They are, the number of hidden neurons, the input weights and the bias values which need to be optimally chosen. Selection of these parameters for the best performance of ELM involves a complex optimization problem. In this paper, we present a new, real-coded genetic algorithm approach called ‘RCGA-ELM’ to select the optimal number of hidden neurons, input weights and bias values which results in better performance. Two new genetic operators called ‘network based operator’ and ‘weight based operator’ are proposed to find a compact network with higher generalization performance. We also present an alternate and less computationally intensive approach called ‘sparse-ELM’. Sparse-ELM searches for the best parameters of ELM using K-fold validation. A multi-class human cancer classification problem using micro-array gene expression data (which is sparse), is used for evaluating the performance of the two schemes. Results indicate that the proposed RCGA-ELM and sparse-ELM significantly improve ELM performance for sparse multi-category classification problems. [ABSTRACT FROM AUTHOR]

Investigates real-time performance of a minimal radial basis function network called the minimal resource allocation network on a time varying signal identification problem. Ability of the network to grow and prune the hidden neurons to ensure a parsimonious structure; Suitability for real-time signal processing applications; Analysis of network's computation load.