Development & evaluation of different acoustic models for Malayalam continuous speech recognition

Performance of any continuous speech recognition system is dependent on the accuracy of its acoustic model. Hence, preparation of a robust and accurate acoustic model lead to satisfactory recognition performance for a speech recognizer. In acoustic modeling of phonetic unit, context information is of prime importance as the phonemes are found to vary according to the place of occurrence in a word. In this paper we compare and evaluate the effect of context dependent tied (CD tied) models, context dependent (CD) and context independent (CI) models in the perspective of continuous speech recognition of Malayalam language. The database for the speech recognition system has utterance from 21 speakers including 11 female and 10 males. Our evaluation results show that CD tied models outperforms CI models over 21%.

Spectral clustering independent component analysis for tissue classification from brain MRI

A spectral angle based feature extraction method, Spectral Clustering Independent Component Analysis (SC-ICA), is proposed in this work to improve the brain tissue classification from Magnetic Resonance Images (MRI). SC-ICA provides equal priority to global and local features; thereby it tries to resolve the inefficiency of conventional approaches in abnormal tissue extraction. First, input multispectral MRI is divided into different clusters by a spectral distance based clustering. Then, Independent Component Analysis (ICA) is applied on the clustered data, in conjunction with Support Vector Machines (SVM) for brain tissue analysis. Normal and abnormal datasets, consisting of real and synthetic T1-weighted, T2-weighted and proton density/fluid-attenuated inversion recovery images, were used to evaluate the performance of the new method. Comparative analysis with ICA based SVM and other conventional classifiers established the stability and efficiency of SC-ICA based classification, especially in reproduction of small abnormalities. Clinical abnormal case analysis demonstrated it through the highest Tanimoto Index/accuracy values, 0.75/98.8%, observed against ICA based SVM results, 0.17/96.1%, for reproduced lesions. Experimental results recommend the proposed method as a promising approach in clinical and pathological studies of brain diseases

Brain Tissue Classification from Multispectral MRI by Wavelet based Principal Component Analysis

In this paper, we propose a multispectral analysis system using wavelet based Principal Component Analysis (PCA), to improve the brain tissue classification from MRI images. Global transforms like PCA often neglects significant small abnormality details, while dealing with a massive amount of multispectral data. In order to resolve this issue, input dataset is expanded by detail coefficients from multisignal wavelet analysis. Then, PCA is applied on the new dataset to perform feature analysis. Finally, an unsupervised classification with Fuzzy C-Means clustering algorithm is used to measure the improvement in reproducibility and accuracy of the results. A detailed comparative analysis of classified tissues with those from conventional PCA is also carried out. Proposed method yielded good improvement in classification of small abnormalities with high sensitivity/accuracy values, 98.9/98.3, for clinical analysis. Experimental results from synthetic and clinical data recommend the new method as a promising approach in brain tissue analysis.

Wavelet based Independent Component Analysis for Multispectral Brain Tissue Classification

Multispectral analysis is a promising approach in tissue classification and abnormality detection from Magnetic Resonance (MR) images. But instability in accuracy and reproducibility of the classification results from conventional techniques keeps it far from clinical applications. Recent studies proposed Independent Component Analysis (ICA) as an effective method for source signals separation from multispectral MR data. However, it often fails to extract the local features like small abnormalities, especially from dependent real data. A multisignal wavelet analysis prior to ICA is proposed in this work to resolve these issues. Best de-correlated detail coefficients are combined with input images to give better classification results. Performance improvement of the proposed method over conventional ICA is effectively demonstrated by segmentation and classification using k-means clustering. Experimental results from synthetic and real data strongly confirm the positive effect of the new method with an improved Tanimoto index/Sensitivity values, 0.884/93.605, for reproduced small white matter lesions

Synthesis, Characterization and Applications of Hybrid Nanocomposites of TiO2 With Conducting Polymers

A nanocomposite is a multiphase solid material where one of the phases has one, two or three dimensions of less than 100 nanometers (nm), or structures having nano-scale repeat distances between the different phases that make up the material. In the broadest sense this definition can include porous media, colloids, gels and copolymers, but is more usually taken to mean the solid combination of a bulk matrix and nano-dimensional phase(s) differing in properties due to dissimilarities in structure and chemistry. The mechanical, electrical, thermal, optical, electrochemical, catalytic properties of the nanocomposite will differ markedly from that of the component materials. Size limits for these effects have been proposed, <5 nm for catalytic activity, <20 nm for making a hard magnetic material soft, <50 nm for refractive index changes, and <100 nm for achieving superparamagnetism, mechanical strengthening or restricting matrix dislocation movement. Conducting polymers have attracted much attention due to high electrical conductivity, ease of preparation, good environmental stability and wide variety of applications in light-emitting, biosensor chemical sensor, separation membrane and electronic devices. The most widely studied conducting polymers are polypyrrole, polyaniline, polythiophene etc. Conducting polymers provide tremendous scope for tuning of their electrical conductivity from semiconducting to metallic region by way of doping and are organic electro chromic materials with chemically active surface. But they are chemically very sensitive and have poor mechanical properties and thus possessing a processibility problem. Nanomaterial shows the presence of more sites for surface reactivity, they possess good mechanical properties and good dispersant too. Thus nanocomposites formed by combining conducting polymers and inorganic oxide nanoparticles possess the good properties of both the constituents and thus enhanced their utility. The properties of such type of nanocomposite are strongly depending on concentration of nanomaterials to be added. Conducting polymer composites is some suitable composition of a conducting polymer with one or more inorganic nanoparticles so that their desirable properties are combined successfully. The composites of core shell metal oxide particles-conducting polymer combine the electrical properties of the polymer shell and the magnetic, optical, electrical or catalytic characteristics of the metal oxide core, which could greatly widen their applicability in the fields of catalysis, electronics and optics. Moreover nanocomposite material composed of conducting polymers & oxides have open more field of application such as drug delivery, conductive paints, rechargeable batteries, toners in photocopying, smart windows, etc.The present work is mainly focussed on the synthesis, characterization and various application studies of conducting polymer modified TiO2 nanocomposites. The conclusions of the present work are outlined below, Mesoporous TiO2 was prepared by the cationic surfactant P123 assisted hydrothermal synthesis route and conducting polymer modified TiO2 nanocomposites were also prepared via the same technique. All the prepared systems show XRD pattern corresponding to anatase phase of TiO2, which means that there is no phase change occurring even after conducting polymer modification. Raman spectroscopy gives supporting evidence for the XRD results. It also confirms the incorporation of the polymer. The mesoporous nature and surface area of the prepared samples were analysed by N2 adsorption desorption studies and the mesoporous ordering can be confirmed by low angle XRD measurementThe morphology of the prepared samples was obtained from both SEM & TEM. The elemental analysis of the samples was performed by EDX analysisThe hybrid composite formation is confirmed by FT-IR spectroscopy and X-ray photoelectron spectroscopyAll the prepared samples have been used for the photocatalytic degradation of dyes, antibiotic, endocrine disruptors and some other organic pollutants. Photocatalytic antibacterial activity studies were also performed using the prepared systemsAll the prepared samples have been used for the photocatalytic degradation of dyes, antibiotic, endocrine disruptors and some other organic pollutants. Photocatalytic antibacterial activity studies were also performed using the prepared systems Polyaniline modified TiO2 nanocomposite systems were found to have good antibacterial activity. Thermal diffusivity studies of the polyaniline modified systems were carried out using thermal lens technique. It is observed that as the amount of polyaniline in the composite increases the thermal diffusivity also increases. The prepared systems can be used as an excellent coolant in various industrial purposes. Nonlinear optical properties (3rd order nonlinearity) of the polyaniline modified systems were studied using Z scan technique. The prepared materials can be used for optical limiting Applications. Lasing studies of polyaniline modified TiO2 systems were carried out and the studies reveal that TiO2 - Polyaniline composite is a potential dye laser gain medium.