Feature Extraction Methods Based on Linear Predictive Coding and Wavelet Packet Decomposition for Recognizing Spoken Words in Malayalam

Speech signals are one of the most important means of communication among the human beings. In this paper, a comparative study of two feature extraction techniques are carried out for recognizing speaker independent spoken isolated words. First one is a hybrid approach with Linear Predictive Coding (LPC) and Artificial Neural Networks (ANN) and the second method uses a combination of Wavelet Packet Decomposition (WPD) and Artificial Neural Networks. Voice signals are sampled directly from the microphone and then they are processed using these two techniques for extracting the features. Words from Malayalam, one of the four major Dravidian languages of southern India are chosen for recognition. Training, testing and pattern recognition are performed using Artificial Neural Networks. Back propagation method is used to train the ANN. The proposed method is implemented for 50 speakers uttering 20 isolated words each. Both the methods produce good recognition accuracy. But Wavelet Packet Decomposition is found to be more suitable for recognizing speech because of its multi-resolution characteristics and efficient time frequency localizations

COMBINED FEATURE EXTRACTION TECHNIQUES AND NAIVE BAYES CLASSIFIER FOR SPEECH RECOGNITION

Speech processing and consequent recognition are important areas of Digital Signal Processing since speech allows people to communicate more natu-rally and efficiently. In this work, a speech recognition system is developed for re-cognizing digits in Malayalam. For recognizing speech, features are to be ex-tracted from speech and hence feature extraction method plays an important role in speech recognition. Here, front end processing for extracting the features is per-formed using two wavelet based methods namely Discrete Wavelet Transforms (DWT) and Wavelet Packet Decomposition (WPD). Naive Bayes classifier is used for classification purpose. After classification using Naive Bayes classifier, DWT produced a recognition accuracy of 83.5% and WPD produced an accuracy of 80.7%. This paper is intended to devise a new feature extraction method which produces improvements in the recognition accuracy. So, a new method called Dis-crete Wavelet Packet Decomposition (DWPD) is introduced which utilizes the hy-brid features of both DWT and WPD. The performance of this new approach is evaluated and it produced an improved recognition accuracy of 86.2% along with Naive Bayes classifier.

A Comparative Study of Wavelet Based Feature Extraction Techniques in Recognizing Isolated Spoken Words

Speech is a natural mode of communication for people and speech recognition is an intensive area of research due to its versatile applications. This paper presents a comparative study of various feature extraction methods based on wavelets for recognizing isolated spoken words. Isolated words from Malayalam, one of the four major Dravidian languages of southern India are chosen for recognition. This work includes two speech recognition methods. First one is a hybrid approach with Discrete Wavelet Transforms and Artificial Neural Networks and the second method uses a combination of Wavelet Packet Decomposition and Artificial Neural Networks. Features are extracted by using Discrete Wavelet Transforms (DWT) and Wavelet Packet Decomposition (WPD). Training, testing and pattern recognition are performed using Artificial Neural Networks (ANN). The proposed method is implemented for 50 speakers uttering 20 isolated words each. The experimental results obtained show the efficiency of these techniques in recognizing speech

"Alkaline Lipase Production by Marine Bacillus smithii BTMS 11"

Considering the potential of marine environment present study was designed for the screening and isolation of a potential salt tolerant. alkaline and thennotolerant lipase producing bacteria from the costal belts of South India and consequent development of ideal bioprocess for industrial production, purification characterisation and evaluation of the potential of the lipase enzyme for various industrial applications 1. Screening and isolation of a potential lipase producing bacteria. 2. Optimization of various physicochemical factors in Submerged fennentation for the production of alkaline lipase 3. Purification ofthe lipase enzyme 4. Characterisation of the enzyme 5. Evaluation of the enzyme for various industrial applications

Development of Techniques for the Automatic Extraction and Grade Detection of Glioma Tumors from Conventional Brain Magnetic Resonant Images

Cerebral glioma is the most prevalent primary brain tumor, which are classified broadly into low and high grades according to the degree of malignancy. High grade gliomas are highly malignant which possess a poor prognosis, and the patients survive less than eighteen months after diagnosis. Low grade gliomas are slow growing, least malignant and has better response to therapy. To date, histological grading is used as the standard technique for diagnosis, treatment planning and survival prediction. The main objective of this thesis is to propose novel methods for automatic extraction of low and high grade glioma and other brain tissues, grade detection techniques for glioma using conventional magnetic resonance imaging (MRI) modalities and 3D modelling of glioma from segmented tumor slices in order to assess the growth rate of tumors. Two new methods are developed for extracting tumor regions, of which the second method, named as Adaptive Gray level Algebraic set Segmentation Algorithm (AGASA) can also extract white matter and grey matter from T1 FLAIR an T2 weighted images. The methods were validated with manual Ground truth images, which showed promising results. The developed methods were compared with widely used Fuzzy c-means clustering technique and the robustness of the algorithm with respect to noise is also checked for different noise levels. Image texture can provide significant information on the (ab)normality of tissue, and this thesis expands this idea to tumour texture grading and detection. Based on the thresholds of discriminant first order and gray level cooccurrence matrix based second order statistical features three feature sets were formulated and a decision system was developed for grade detection of glioma from conventional T2 weighted MRI modality.The quantitative performance analysis using ROC curve showed 99.03% accuracy for distinguishing between advanced (aggressive) and early stage (non-aggressive) malignant glioma. The developed brain texture analysis techniques can improve the physician’s ability to detect and analyse pathologies leading to a more reliable diagnosis and treatment of disease. The segmented tumors were also used for volumetric modelling of tumors which can provide an idea of the growth rate of tumor; this can be used for assessing response to therapy and patient prognosis.

Alkaline protease from a non-toxigenic mangrove isolate of Vibrio sp. V26 with potential application in animal cell culture

Vibrio sp. V26 isolated from mangrove sediment showed 98 % similarity to 16S rRNA gene of Vibrio cholerae, V. mimicus, V. albensis and uncultured clones of Vibrio. Phenotypically also it resembled both V. cholerae and V. mimicus.Serogrouping, virulence associated gene profiling, hydrophobicity, and adherence pattern clearly pointed towards the non—toxigenic nature of Vibrio sp. V26. Purification and characterization of the enzyme revealed that it was moderately thermoactive, nonhemagglutinating alkaline metalloprotease with a molecular mass of 32 kDa. The application of alkaline protease from Vibrio sp. V26 (APV26) in sub culturing cell lines (HEp-2, HeLa and RTG-2) and dissociation of animal tissue (chick embryo) for primary cell culture were investigated. The time required for dissociation of cells as well as the viable cell yield obtained by while administeringAPV26 and trypsin were compared. Investigations revealed that the alkaline protease of Vibrio sp. V26 has the potential to be used in animal cell culture for subculturing cell lines and dissociation of animal tissue for the development of primary cell cultures, which has not been reported earlier among metalloproteases of Vibrios.

Potential application of β-1, 3 glucanase from an environmental isolate of Pseudomonas aeruginosa MCCB 123 in fungal DNA extraction

Pseudomonas aeruginosa MCCB 123 was grown in a synthetic medium for β-1,3 glucanase production. From the culture filtrate, β-1,3 glucanase was purified with a molecular mass of 45 kDa. The enzyme was a metallozyme as its β-1,3 glucanase activity got inhibited by the metal chelator EDTA. Optimum pH and temperature for β-1,3 glucanase activity on laminarin was found to be 7 and 50 °C respectively. The MCCB 123 β-1,3 glucanase was found to have good lytic action on a wide range of fungal isolates, and hence its application in fungal DNA extraction was evaluated. β-1,3 glucanase purified from the culture supernatant of P. aeruginosa MCCB 123 could be used for the extraction of fungal DNA without the addition of any other reagents generally used. Optimum pH and temperature of enzyme for fungal DNA extraction was found to be 7 and 65 °C respectively. This is the first report on β-1,3 glucanase employed in fungal DNA extraction

Ontology based Framework for News Extraction in Visual Media

Anticipating the increase in video information in future, archiving of news is an important activity in the visual media industry. When the volume of archives increases, it will be difficult for journalists to find the appropriate content using current search tools. This paper provides the details of the study we conducted about the news extraction systems used in different news channels in Kerala. Semantic web technologies can be used effectively since news archiving share many of the characteristics and problems of WWW. Since visual news archives of different media resources follow different metadata standards, interoperability between the resources is also an issue. World Wide Web Consortium has proposed a draft for an ontology framework for media resource which addresses the intercompatiblity issues. In this paper, the w3c proposed framework and its drawbacks is also discussed

Detergent compatible alkaline lipase produced by marine Bacillus smithii BTMS 11

Bacillus smithii BTMS 11, isolated from marine sediment, produced alkaline and thermostable lipase. The enzyme was purified to homogeneity by ammonium sulfate precipitation and ion exchange chromatography which resulted in 0.51 % final yield and a 4.33 fold of purification. The purified enzyme was found to have a specific activity of 360 IU/mg protein. SDS-PAGE analyses, under non-reducing and reducing conditions, yielded a single band of 45 kDa indicating the single polypeptide nature of the enzyme and zymogram analysis using methylumbelliferyl butyrate as substrate confirmed the lipolytic activity of the protein band. The enzyme was found to have 50 C and pH 8.0 as optimum conditions for maximal activity. However, the enzyme was active over wide range of temperatures (30–80 C) and pH (7.0–10.0). Effect of a number of metal salts, solvents, surfactants, and other typical enzyme inhibitors on lipase activity was studied to determine the novel characteristics of the enzyme. More than 90 % of the enzyme activity was observed even after 3 h of incubation in the presence of commercial detergents Surf, Sunlight, Ariel, Henko, Tide and Ujala indicating the detergent compatibility of B. smithii lipase. The enzyme was also found to be efficient in stain removal from cotton cloths. Further it was observed that the enzyme could catalyse ester synthesis between fatty acids of varying carbon chain lengths and methanol with high preference for medium to long chain fatty acids showing 70 % of esterification. Results of the study indicated scope for application of this marine bacterial lipase in various industries

Characterization of an extracellular alkaline serine protease from marine Engyodontium album BTMFS10

An alkaline protease from marine Engyodontium album was characterized for its physicochemical properties towards evaluation of its suitability for potential industrial applications. Molecular mass of the enzyme by matrix-assisted laser desorption ionization-mass spectrometry (MALDI-MS) analysis was calculated as 28.6 kDa. Isoelectric focusing yielded pI of 3–4. Enzyme inhibition by phenylmethylsulfonyl fluoride (PMSF) and aprotinin confirmed the serine protease nature of the enzyme.Km, Vmax, and Kcat of the enzyme were 4.727 9 10-2 mg/ml, 394.68 U, and 4.2175 9 10-2 s-1, respectively. Enzyme was noted to be active over a broad range of pH (6–12) and temperature (15–65 C), withmaximumactivity at pH 11 and 60 C. CaCl2 (1 mM), starch (1%), and sucrose (1%) imparted thermal stability at 65 C. Hg2?, Cu2?, Fe3?, Zn2?, Cd?, and Al3? inhibited enzyme activity, while 1 mMCo2? enhanced enzyme activity. Reducing agents enhanced enzyme activity at lower concentrations. The enzyme showed considerable storage stability, and retained its activity in the presence of hydrocarbons, natural oils, surfactants, and most of the organic solvents tested. Results indicate that the marine protease holds potential for use in the detergent industry and for varied applications.

Automatic Optic Disc Boundary Extraction from Color Fundus Images

Efficient optic disc segmentation is an important task in automated retinal screening. For the same reason optic disc detection is fundamental for medical references and is important for the retinal image analysis application. The most difficult problem of optic disc extraction is to locate the region of interest. Moreover it is a time consuming task. This paper tries to overcome this barrier by presenting an automated method for optic disc boundary extraction using Fuzzy C Means combined with thresholding. The discs determined by the new method agree relatively well with those determined by the experts. The present method has been validated on a data set of 110 colour fundus images from DRION database, and has obtained promising results. The performance of the system is evaluated using the difference in horizontal and vertical diameters of the obtained disc boundary and that of the ground truth obtained from two expert ophthalmologists. For the 25 test images selected from the 110 colour fundus images, the Pearson correlation of the ground truth diameters with the detected diameters by the new method are 0.946 and 0.958 and, 0.94 and 0.974 respectively. From the scatter plot, it is shown that the ground truth and detected diameters have a high positive correlation. This computerized analysis of optic disc is very useful for the diagnosis of retinal diseases

Microbial use of organic substrates and maize growth, especially in saline and alkaline soils of Pakistani Punjab

This thesis consists of 4 main parts: (1) impact of growing maize on the decomposition of incorporated fresh alfalfa residues, (2) relationships between soil biological and other soil properties in saline and alkaline arable soils from the Pakistani Punjab, (3) decomposition of compost and plant residues in Pakistani soils along a gradient in salinity, and (4) interactions of compost and triple superphosphate on the growth of maize in a saline Pakistani soil. These 4 chapters are framed by a General Introduction and a Conclusions section. (1) In the first study, the effects of growing maize plants on the microbial decomposition of freshly chopped alfalfa residues was investigated in a 90-day pot experiment using a sandy arable soil. Assuming that the addition of alfalfa residues did not affect the decomposition of native soil organic matter, only 27% of the alfalfa residues were found as CO2. This suggests that a considerable part of alfalfa-C remained undecomposed in the soil. However, only 6% of the alfalfa residues could be recovered as plant remains in treatment with solely alfalfa residues. Based on d13C values, it was calculated that plant remains in treatment maize + alfalfa residues contained 14.7% alfalfa residues and 85.3% maize root remains. This means 60% more alfalfa-C was recovered in this treatment. (2) In the second study, the interactions between soil physical, soil chemical and soil biological properties were analysed in 30 Pakistani soils from alkaline and saline arable sites differing strongly in salinisation and in soil pH. The soil biological properties were differentiated into indices for microbial activity, microbial biomass, and community structure with the aim of assessing their potential as soil fertility indices. (3) In the third study, 3 organic amendments (compost, maize straw and pea straw) were added to 5 Pakistani soils from a gradient in salinity. Although salinity has depressive effects on microbial biomass C, biomass N, biomass P, and ergosterol, the clear gradient according to the soil salt concentration was not reflected by the soil microbial properties. The addition of the 3 organic amendments always increased the contents of the microbial indices analysed. The amendment-induced increase was especially strong for microbial biomass P and reflected the total P content of the added substrates. (4) The fourth study was greenhouse pot experiment with different combinations of compost and triple superphosphate amendments to investigate the interactions between plant growth, microbial biomass formation and compost decomposition in a strongly saline Pakistani arable soil in comparison to a non-saline German arable soil. The Pakistani soil had a 2 times lower content of ergosterol, a 4 times lower contents of microbial biomass C, biomass N and biomass P, but nearly a 20 times lower content of NaHCO3 extractable P. The addition of 1% compost always had positive effects on the microbial properties and also on the content of NaHCO3 extractable P. The addition of superphosphate induced a strong and similar absolute increase in microbial biomass P in both soils.

The electronic structure of anionic halide complexes of element 105 in aqueous solutions and their extraction by aliphatic amines

To study the complex formation of group 5 elements (Nb, Ta, Ha, and pseudoanalog Pa) in aqueous HCI solutions of medium and high concentrations the electronic structures of anionic complexes of these elements [MCl_6]^-, [MOCl_4]^-, [M(OH)-2 Cl_4]^-, and [MOCl_5]^2- have been calculated using the relativistic Dirac-Slater Discrete-Variational Method. The charge density distribution analysis has shown that tantalum occupies a specific position in the group and has the highest tendency to form the pure halide complex, [TaCl_6-. This fact along with a high covalency of this complex explains its good extractability into aliphatic amines. Niobium has equal trends to form pure halide [NbCl_6]^- and oxyhalide [NbOCl_5]^2- species at medium and high acid concentrations. Protactinium has a slight preference for the [PaOCl_5]^2- form or for the pure halide complexes with coordination number higher than 6 under these conditions. Element 105 at high HCl concentrations will have a preference to form oxyhalide anionic complex [HaOCl_5]^2- rather than [HaCl_6]^-. For the same sort of anionic oxychloride complexes an estimate has been done of their partition between the organic and aqueous phases in the extraction by aliphatic amines, which shows the following succession of the partition coefficients: P_Nb < P_Ha < P_Pa.

Catalase in fluvial biofilms: a comparison between different extraction methods and example of application in a metal-polluted river

Antioxidant enzymes are involved in important processes of cell detoxification during oxidative stress and have, therefore, been used as biomarkers in algae. Nevertheless, their limited use in fluvial biofilms may be due to the complexity of such communities. Here, a comparison between different extraction methods was performed to obtain a reliable method for catalase extraction from fluvial biofilms. Homogenization followed by glass bead disruption appeared to be the best compromise for catalase extraction. This method was then applied to a field study in a metal-polluted stream (Riou Mort, France). The most polluted sites were characterized by a catalase activity 4–6 times lower than in the low-polluted site. Results of the comparison process and its application are promising for the use of catalase activity as an early warning biomarker of toxicity using biofilms in the laboratory and in the field