A Long Memory Process Based Parametric Modeling and Recognition of PD Signal

We address the problem of recognition and retrieval of relatively weak industrial signal such as Partial Discharges (PD) buried in excessive noise. The major bottleneck being the recognition and suppression of stochastic pulsive interference (PI) which has similar time-frequency characteristics as PD pulse. Therefore conventional frequency based DSP techniques are not useful in retrieving PD pulses. We employ statistical signal modeling based on combination of long-memory process and probabilistic principal component analysis (PPCA). An parametric analysis of the signal is exercised for extracting the features of desired pules. We incorporate a wavelet based bootstrap method for obtaining the noise training vectors from observed data. The procedure adopted in this work is completely different from the research work reported in the literature, which is generally based on deserved signal frequency and noise frequency.

Time Series Classification for Online Tamil Handwritten Character Recognition – A Kernel Based Approach

In this paper, we consider the problem of time series classification. Using piecewise linear interpolation various novel kernels are obtained which can be used with Support vector machines for designing classifiers capable of deciding the class of a given time series. The approach is general and is applicable in many scenarios. We apply the method to the task of Online Tamil handwritten character recognition with promising results.

Language identification using parallel sub-word recognition

Parallel sub-word recognition (PSWR) is a new model that has been proposed for language identification (LID) which does not need elaborate phonetic labeling of the speech data in a foreign language. The new approach performs a front-end tokenization in terms of sub-word units which are designed by automatic segmentation, segment clustering and segment HMM modeling. We develop PSWR based LID in a framework similar to the parallel phone recognition (PPR) approach in the literature. This includes a front-end tokenizer and a back-end language model, for each language to be identified. Considering various combinations of the statistical evaluation scores, it is found that PSWR can perform as well as PPR, even with broad acoustic sub-word tokenization, thus making it an efficient alternative to the PPR system.

Experiments on three-dimensional wire-frame object recognition

Some experimental results on the recognition of three-dimensional wire-frame objects are presented. In order to overcome the limitations of a recent model, which employs radial basis functions-based neural networks, we have proposed a hybrid learning system for object recognition, featuring: an optimization strategy (simulated annealing) in order to avoid local minima of an energy functional; and an appropriate choice of centers of the units. Further, in an attempt to achieve improved generalization ability, and to reduce the time for training, we invoke the principle of self-organization which utilises an unsupervised learning algorithm.

Pattern recognition and cellular immune responses to novel Mycobacterium tuberculosis-antigens in individuals from Belarus

Background: Tuberculosis (TB) is an enduring health problem worldwide and the emerging threat of multidrug resistant (MDR) TB and extensively drug resistant (XDR) TB is of particular concern. A better understanding of biomarkers associated with TB will aid to guide the development of better targets for TB diagnosis and for the development of improved TB vaccines. Methods: Recombinant proteins (n = 7) and peptide pools (n = 14) from M. tuberculosis (M.tb) antigens associated with M.tb pathogenicity, modification of cell lipids or cellular metabolism, were used to compare T cell immune responses defined by IFN-gamma production using a whole blood assay (WBA) from i) patients with TB, ii) individuals recovered from TB and iii) individuals exposed to TB without evidence of clinical TB infection from Minsk, Belarus. Results: We identified differences in M.tb target peptide recognition between the test groups, i.e. a frequent recognition of antigens associated with lipid metabolism, e.g. cyclopropane fatty acyl phospholipid synthase. The pattern of peptide recognition was broader in blood from healthy individuals and those recovered from TB as compared to individuals suffering from pulmonary TB. Detection of biologically relevant M.tb targets was confirmed by staining for intracellular cytokines (IL-2, TNF-alpha and IFN-gamma) in T cells from non-human primates (NHPs) after BCG vaccination. Conclusions: PBMCs from healthy individuals and those recovered from TB recognized a broader spectrum of M.tb antigens as compared to patients with TB. The nature of the pattern recognition of a broad panel of M.tb antigens will devise better strategies to identify improved diagnostics gauging previous exposure to M.tb; it may also guide the development of improved TB-vaccines.

Interrelation of grain boundary microstructure and texture in a hot rolled Ni-rich NiTi alloy

This investigation deals with the evolution of grain boundary microstructure and crystallographic texture during hot rolling of a Ni-rich NiTi alloy. Electron backscattered diffraction studies revealed the occurrence of several coincidence site lattice (CSL) boundaries. The origin of these boundaries has been identified. The crystallographic texture of the deformed sample consists mainly of (1 1 1)parallel to normal direction fiber. The texture components on the fiber exhibit some correlation with the type of CSL boundary. (C) 2012 Acta Materialia Inc. Published by Elsevier Ltd. All rights reserved.

Microstructure and texture evolution during beta extrusion of boron modified Ti-6A1-4V alloy

Boron addition to conventional titanium alloys below the eutectic limit refines the cast microstructure and improves mechanical properties. The present work explores the influence of hypoeutectic boron addition on the microstructure and texture evolution in Ti-6Al-4V alloy under beta extrusion. The beta extruded microstructure of Ti-6Al-4V is characterized by shear bands parallel to the extrusion direction. In contrast, the extruded Ti-6Al-4V-0.1B alloy shows a regular beta worked microstructure consisting of fine prior beta grains and acicular alpha-lamellae with no signs of the microstructural instability. Crystallographic texture after extrusion was almost identical for the two alloys indicating the similarity in their transformation behavior, which is attributed to complete dynamic recrystallization during beta processing. Microstructural features as well as crystallographic texture indicate dominant grain boundary related deformation processes for the boron modified alloy that leads to homogeneous deformation without instability formation. The absence of shear bands has significant technological importance as far as the secondary processing of boron added alloys in (alpha + beta)-phase field are concerned. (C) 2012 Elsevier B.V. All rights reserved.

Texture and Microstructural Evolution in Pearlitic Steel During Triaxial Compression

This article presents the deformation behavior of high-strength pearlitic steel deformed by triaxial compression to achieve ultra-fine ferrite grain size with fragmented cementite. The consequent evolution of microstructure and texture has been studied using scanning electron microscopy, electron back-scatter diffraction, and X-ray diffraction. The synergistic effect of diffusion and deformation leads to the uniform dissolution of cementite at higher temperature. At lower temperature, significant grain refinement of ferrite phase occurs by deformation and exhibits a characteristic deformation texture. In contrast, the high-temperature deformed sample shows a weaker texture with cube component for the ferrite phase, indicating the occurrence of recrystallization. The different mechanisms responsible for the refinement of ferrite as well as the fragmentation of cementite and their interaction with each other have been analyzed. Viscoplastic self-consistent simulation was employed to understand deformation texture in the ferrite phase during triaxial compression.

Human action recognition using a fast learning fully complex-valued classifier

In this paper, we use optical flow based complex-valued features extracted from video sequences to recognize human actions. The optical flow features between two image planes can be appropriately represented in the Complex plane. Therefore, we argue that motion information that is used to model the human actions should be represented as complex-valued features and propose a fast learning fully complex-valued neural classifier to solve the action recognition task. The classifier, termed as, ``fast learning fully complex-valued neural (FLFCN) classifier'' is a single hidden layer fully complex-valued neural network. The neurons in the hidden layer employ the fully complex-valued activation function of the type of a hyperbolic secant function. The parameters of the hidden layer are chosen randomly and the output weights are estimated as the minimum norm least square solution to a set of linear equations. The results indicate the superior performance of FLFCN classifier in recognizing the actions compared to real-valued support vector machines and other existing results in the literature. Complex valued representation of 2D motion and orthogonal decision boundaries boost the classification performance of FLFCN classifier. (c) 2012 Elsevier B.V. All rights reserved.

Microstructure and texture evolution during accumulative roll bonding of aluminium alloys AA2219/AA5086 composite laminates

Accumulative roll bonding of two aluminium alloys, AA2219 and AA5086 was carried out up to 8 passes. During the course of ARB, the deformation inhomogeneity between the two alloy layers results in interfacial instability after the 4th pass, necking of the AA5086 layers after the 6th pass and fracture along the necked regions after the 7th and 8th pass. The EBSD analysis shows deformation bands along the interfaces after 8 passes of ARB. The ARB-processed materials predominantly show characteristic deformation texture components. The weak texture after the 2nd pass results from the combination of a weakly-textured starting AA2219 layer and a strongly-textured starting AA5086 layer. A strong deformation texture forms due to the high imposed strain after a higher number of ARB passes. Subgrain formation and related shear banding induces copper/S components in the case of the small elongated grains, while planar slip leads to the formation of brass component in the large elongated grains.

Asymmetric and symmetric rolling of magnesium: Evolution of microstructure, texture and mechanical properties

In the present study, asymmetric rolling was carried out for incorporating a shear component during the rolling at different temperatures, and was compared with conventional (symmetric) rolling. The microstructures were investigated using electron back-scatter diffraction (EBSD). The strain incorporated was compared with the help of grain orientation spread (GOS). GOS was eventually used as a criterion to partition the microstructure for separating the deformed and the dynamically recrystallized (DRX) grains. The texture of the partitioned DRX grains was shifted by similar to 30 degrees along the c-axis from the deformed grains. The mechanism of dynamic recrystallization (DRX) has been identified as continuous dynamic recovery and recrystallization (CDRR). The partitioned deformed grains for the higher temperature rolled specimens exhibited a texture similar to the room temperature rolled specimen. The asymmetric rolling introduces a shear component which shifts the texture fibre by similar to 5-10 degrees from the conventional rolling texture. This led to an increase in ductility with little compromise on strength. (c) 2012 Elsevier B.V. All rights reserved.

Development of microstructure and texture in Copper during warm accumulative roll bonding

The evolution of microstructure and texture gradient in warm Accumulative Roll Bonded Cu-Cu multilayer has been studied. Grain size distribution is multimodal and exhibits variation from middle to surface layer. Evolution of texture is largely influenced by shear, in addition to rolling deformation. This leads to the formation of a texture comprising of high fraction of Brass and rolling direction-rotated cube components. Partial recrystallization was observed. Deformed and recrystallized grains were separated using a partition scheme based on grain orientation spread and textures were analyzed for both the partition. Retention of deformation texture components in recrystallized grains suggests the mechanism of recrystallization as continuous recrystallization. Shear deformation plays an important role in grain refinement through continuous recrystallization. (C) 2012 Elsevier Inc. All rights reserved.

Texture and formability studies on AA7020 Al alloy sheets

This paper deals with the influence of crystallographic texture on room temperature mechanical behavior of the sheets of the aluminum alloy AA7020 processed to different thicknesses. Three different thicknesses of the alloy sheet, namely 1, 1.85, and 3.6 mm, corresponding to different textures were investigated. Tensile tests were carried out at 0°, 45° and 90° with respect to sheet rolling direction and the resulting in-plane anisotropy in 0.2 proof stress, work hardening and plastic strain ratio (r-value) were determined. Texture derived r-values are also calculated and discussed vis-à -vis the experimentally obtained r-values. Finally the formability of the optimal alloy was studied using forming limit diagrams. Effect of natural aging, with a simulated heat treatment of 70 °C for 2 h on FLD was studied and compared with the as solutionized samples. It was observed that, the strain levels in the bi-axial region of the FLD were not much affected by the heat treatment. © 2012 Elsevier B.V. All rights reserved.