k) 2015 - 38 Documents

Permanent URI for this communityhttps://dspace.psgrkcw.com/handle/123456789/4003

Browse

Now showing 1 - 20 of 38

DETECTION OF A PERSON USING DESCRIPTIVE FEATURES OF TAMIL HANDWRITING AND PATTERN LEARNING
(International Journal of Applied Engineering Research, 2015) Thendral, T; Vijaya, M S
Pattern classification technique is used for writer identification task in Tamil handwriting document images. Tamil is a classical language in India especially to south Indian people. Compared to other languages, this language has more distinctive features like style, strokes, loops, crossings and junctions. Handwritings written in Tamil language are collected and used as input images. The input images are scanned, analyzed and their describing features are defined. They are classified using supervised learning algorithms like support vector machine (SVM), extreme machine learning (ELM) and back propagation algorithm (BPA). Comparative results of these algorithms are analyzed and shown that ELM outperforms with 100% accuracy.
STRUCTURAL AND INTERACTION PROPERTIES OF PORPHYRIN LAYERS — A QUANTUM CHEMICAL STUDY
(IOP Publishing Ltd, 2015) Praveena, G; Abiram, A
This paper is proposed to understand the interaction of porphyrin layers with diatomic molecules interacting at their interior regions by applying ab initio and density functional theory (DFT) methods. We have used NO, CO, and O2 diatomic molecules to interact with the porphyrin layers. The most common Fe-centered metalloporphyrin structure with tetra-pyrrlic rings having N4 core is chosen for the study. The optimization of Porphyrin-Porphyrin (PI-PII) and Porphyrin-Diatomic molecule-Porphyrin (PI-AB-PII) (AB = NO, CO, and O2) complexes are performed using HF method. In order to understand the planarity and appropriate stacking size of porphyrins and also to infer the separation of diatomic molecules between porphyrin layers the behavior of PI-AB-PII complexes (where AB = NO, CO, and O2) are analyzed using structural properties and molecular electrostatic potentials (MEP). The MEPs are calculated using hybrid exchange correlation functional B3PW91 of DFT along with 6-31+G* basis set for the PI-PII and PI-AB-PII complexes obtained from HF method.
SATIN LEAF (CHRYSOPHYLLUM OLIVIFORME) EXTRACT MEDIATED GREEN SYNTHESIS OF SILVER NANOPARTICLES: ANTIOXIDANT AND ANTICANCER ACTIVITIES
(Journal of Pharmaceutical Sciences and Research, 2015) Anju Varghese, R; Anandhi, P; Arunadevi, R; Boovisha, A; Sounthari, P; Saranya, J; Parameswari, K; Chitra, S
The recent development and implementation of new technologies have led to new era, the nano-revolution which unfolds role of plants in bio and green synthesis of nanoparticles which seem to have drawn quite an unequivocal attention with a view of synthesizing stable nanoparticles. The biosynthesis of nanoparticles has been proposed as a cost effective and environmental friendly alternative to chemical and physical methods. Plant mediated synthesis of nanoparticles is a green chemistry approach that interconnects nanotechnology and plant biotechnology. In the present study, synthesis of silver nanoparticles (AgNPs) has been demonstrated using extracts of Chrysophyllum oliviforme reducing aqueous silver nitrate. The synthesized nanosilver was characterized by IR, UV, XRD and SEMEDS. The synthesized nano silver have been screened for antioxidant and anticancer activities.
A NEW FRAMEWORK FOR TEA PLANT RECOGNITION USING EXTREME LEARNING MACHINE WITH VERY FEW FEATURES
(International Journal of Applied Engineering Research, 2015) Arunpriya, C; Arunpriya, C; Thanamani, A S; Thanamani, A S
Due to more and more tea varieties in the current tea market, rapid and accurate identification of tea varieties is crucial for tea quality control. Tea quality mainly depends on the variety of leaf, growing environment, manufacturing conditions, size of ground tea leaves and infusion preparation. In the past few years, tea cultivar has been assessed by morphological assessment coupled with pattern recognition. This paper uses an efficient machine learning approach called Extreme Learning Machine (ELM) for the classification purpose. The proposed approach consists of four phases which are as preprocessing, feature extraction, feature clustering and classification. Additionally, this work proposes an iterative algorithm for feature clustering and applies it to leaf recognition. Feature clustering is a powerful tool to reduce the dimensionality of the selected feature. For improving the accuracy and performance of tea leaf recognition, ELM is implemented. The classifier is tested with 20 leaves from each variety and compared with k-NN and RBF approach. The proposed ELM classification produces effective results.
A HIERARCHICAL APPROACH IN TAMIL PHONEME CLASSIFICATION USING SUPPORT VECTOR MACHINE
(Indian Journal of Science and Technology, 2015) Karpagavalli, S; Chandra, E
Most of the speech recognition systems are designed based on the sub-word unit phoneme which is the basic sound unit of a language. In the proposed work, a novel hierarchical approach based phoneme classification task has been carried out to reduce time complexity and search space. Hierarchical classification of set of Tamil phonemes has been done in three levels. Phoneme boundaries of the given speech utterance are identified using Spectral Transition Measure (STM) and phonemes are separated. Mel-Frequency Cepstral Coefficients (MFCC) are extracted for each phoneme represented by 9 frames including the contextual frames of corresponding phoneme. In each hierarchical level, different number of models is built using Support Vector Machine (SVM) for classifying each phoneme group/phoneme. It is observed from the results that in hierarchical approach phoneme group recognition rate at level 1 and 2 has greatly improved compared to flat classification model. Complexity of search space is significantly reduced at level 2 and level 3 contrasts to flat phoneme classification model. Hierarchical phoneme classifier can be very well employed in phoneme recognition task which is useful in applications such as spoken term detection, out-ofvocabulary detection, named entity recognition, spoken document retrieval.
THE INHIBITING EFFECT OF SOME QUINOXALINE DERIVATIVE TOWARDS MILD STEEL CORROSION IN ACID MEDIA: CHEMICAL, ELECTROCHEMICAL AND THEORETICAL STUDIES
(Journal of Materials and Environmental Science, 2015) Saranya, J; Sounthari, P; Kiruthuka, A; Parameswari, K; Chitra, S
Corrosion inhibition of mild steel in 1 M H2SO4 was investigated in the absence and presence of different concentrations of quinoxaline derivatives namely (3E)-3-(phenylimino)-3,4-dihydroquinoxalin-2(1H)-one (PDQO), (3E)-3-[(2-methylphenyl) imino]-3,4-dihydroquinoxalin-2(1H)-one (MPDQO) and (3E)-3-[(2-methoxy-phenyl)imino]-3,4-dihydroquinoxalin-2(1H)- one (MOPDQO). Weight loss, potentiodynamic polarization and electrochemical impedance spectroscopy (EIS) measurements were employed. Impedance measurements showed that the charge transfer resistance increased and double layer capacitance decreased with increase in the inhibitor concentration. Potentiodynamic polarization study showed that the inhibitors acted as mixed-type inhibitors. The adsorption of these compounds on the mild steel surface obeys a Langmuir adsorption isotherm. Results obtained reveal that compound MOPDQO is the best inhibitor and the inhibition efficiency follows the sequence: MOPDQO > MPDQO > PDQO. Electronic properties such as highest occupied molecular orbital (EHOMO) and lowest unoccupied molecular orbital (ELUMO), the energy difference (ΔE) between EHOMO and ELUMO, dipole moment (μ), electronegativity (χ), electron affinity (A), hardness (η), softness (σ), ionization potential (I), the fraction of electrons transferred (ΔN), total energy (TE) were calculated and discussed. The results showed that the corrosion inhibition efficiency increased with an increase in the EHOMO values but decrease in the ELUMO values. Mulliken atomic charges, Fukui functions and softness indices were discussed in order to characterize the inhibition property of the inhibitors
CLASSIFICATION OF HEART RATE USING BACK PROPAGATION NEUTRAL NETWORKS
(International Journal of Bio-Science and Bio-Technology, 2015) Kavitha, R; Christopher, T
A condition of abnormal electrical activity in the heart which is a threat to humans is shown by this electrocardiogram. It is a representative signal containing information about the condition of the heart. The of the P-QRS-T wave shape and size and their time intervals between its various peaks these are all contain useful information about the nature of disease affecting the heart. This paper presents a technique to examine electrocardiogram (ECG) signal, take out the features for the heart beats classification. Collect data from MIT-BIH database. The heart rate is used as the base signal from which certain parameters are extracted and presented to the BPN for classification
AUTOMATIC TAG RECOMMENDATION FOR JOURNAL ABSTRACTS USING STATISTICAL TOPIC MODELING
(Springer Link, 2015) Anupriya, P; Karpagavalli, S
Topic modeling is a powerful technique for unsupervised analysis of large document collections. Topic models conceive latent topics in text using hidden random variables, and discover that structure with posterior inference. Topic models have a wide range of applications like tag recommendation, text categorization, keyword extraction and similarity search in the broad fields of text mining, information retrieval, statistical language modeling.In this work, a dataset with 200 abstracts fall under four topics are collected from two different domain journals for tagging journal abstracts. The document model is built using LDA (Latent Dirichlet Allocation) with Collapsed Variational Bayes (CVB0) and Gibbs sampling. Then the built model is used to find appropriate tag for a given abstract. An interface is designed to extract and recommend the tag for a given abstract.
EFFECT OF DIELECTRIC INTERFACE ON THE TIGHT FOCUSING PROPERTIES OF RADIALLY POLARIZED ANNULAR MULTI GAUSSIAN BEAMS
(Springer Link, 2015) Lavanya, M; Prabakaran, K; Rajesh, K B; Udhayakumar, M
A super-length optical needle (44 of strong transversally polarized field with homogeneous intensity along the optical axis and sub-diffraction beam size (0.48 can be generated by focusing a radially polarized beam through a dielectric interface with an annular high numerical aperture (NA) lens. Moreover, the focal shifts induced by the mismatch of the refractive indices across the interface has been found. The dependence of focal shifts and spot size of the focused field on the probe depth and NA of the objective is also analyzed in detail by numerical calculations using vector diffraction theory. Such kind of non-diffracting optical needle may have applications in atom-optical experiments, such as with atom trap and atom switches.
GENETIC DIVERGENCE OF BREAD WHEAT GENOTYPES BASED ON CLUSTER AND PRINCIPAL COMPONENT ANALYSIS FOR BREEDING STRATEGIES
(Biochemical and Cellular Archives, 2015) Shajitha, P; Sivasamy, M; Gajalakshmi, K; Baghyalakshmi, K; Vikas, V K
The genetic divergence study was conducted to estimate the nature and magnitude of diversity in Lr19+ and Lr19-lines of bread wheat. The divergence analysis including Tocher's, canonical (vector) and Principal component analysis(PCA) for yield and its nine contributing characters were studied. The twenty two wheat genotypes were grouped into four clusters by both Tocher's method of divergence study. The result of PCA revealed that all the 4 principal components (PC1, PC2, PC3 and PC 4) contributed 93.35% of the total variability. The first PC assigned 60% and the second PC assigned 16% and of total variation between traits. The first PC was more related to days to heading, plant height, tillers per lant, spikelets per spike, grain yield per spike and peduncle length. Therefore, selection based on first component is helpful for a good hybridization breeding program. The information obtained from this study can be used to plan crosses and maximized the use of genetic diversity and expression of heterosis from alien translocation.
ADSORPTION AND DENSITY FUNCTIONAL THEORY ON CORROSION OF MILD STEEL BY A QUINOXALINE DERIVATIVE
(Scholars Research Library, 2015) Saranya, J; Sounthari, P; Parameswari, K; Chitra, S
(3E)-3-{[4-(phenylsulfonyl)]imino}-3,4-dihydroquinoxalin-2(1H)-one (PSDQO) has been synthesized and its inhibiting action on the corrosion of mild steel in 1 M H2SO4 has been assessed by weight loss method at 303 K – 333 K. The results of the investigation show that this compound has excellent inhibiting properties for mild steel corrosion in sulphuric acid. Inhibition efficiency increases with increase in the concentration of the inhibitor. The adsorption of the inhibitor was tested for Langmuir, Temkin, Flory-Huggin’s and El-Awady isotherm and proved physical adsorption. Quantum chemical calculations were employed to give further insight into the mechanism of inhibitive action of the inhibitor
STRUCTURAL AND OPTICAL CHARACTERIZATION OF PURE AND STARCH-CAPPED ZNO QUANTUM DOTS AND THEIR PHOTOCATALYTIC ACTIVITY
(SpringerLink, 2015) Vidhya, K; Saravanan, M; Bhoopathi, G; Devarajan, V P; Subanya, S
Among the different types of metal oxides, zinc oxide (ZnO) is a most commonly used metal oxide in a broad variety of applications. In the present investigation, a modified green synthesis route was used to synthesize pure and starch-capped ZnO (ZnO/starch) quantum dots (QDs) and studied their structural and optical characteristics. In this study, hexagonal crystal structure was observed in both pure and ZnO/starch QDs using X-ray diffraction technique. A spherical-shaped surface morphology was found with the size of 5–10 nm using transmission electron microscope technique. The interaction between ZnO QDs and starch molecules was proved via Fourier infra-red spectrometer technique. On the other hand, their fluorescence behaviors were investigated using photoluminescence technique, in that the ZnO/starch QDs showed an enhanced emission behavior when compared to the pure ZnO QDs. Further, the solar photocatalytic activity of both the ZnO QDs was examined with the dye Rhodamine B (RhB) at the end of 30, 60, 90, and 120 min. In this, ZnO/ starch QDs show a good and more decomposition of RhB than pure ZnO QDs. Collectively, in the present study, green synthesis route produced an efficient QDs (pure and ZnO/starch) and it will be very useful for many other QDs. The ZnO/starch QDs are suitable for decomposing the RhB and other toxic organic dyes.
SPEECH EMOTION RECOGNITION USING CLASSIFICATION ALGORITHMS
(International Journal of Applied Engineering Research, 2015) Meenakshi, S; Karpagavalli, S
Emotion Recognition from one’s speech is natural activity in human beings. Emotion recognition aims at identifying the emotional state of a speaker from his/her speech signal. The emotion recognition is useful in applications that are lie detection, in car board system, authentication systems and automatic emotional detection in call centers. There are different categories of emotions such as joy, fear, disgust, surprise, anger, sadness, boredom and neutral. In this proposed work, emotional speech files are collected from Berlin Emotional Speech Database (EMO-DB) covering exclusively 3 emotions Neutral, Anger and Sad. Information on emotion is encoded mainly phonetic and acoustic properties of spoken language. Prosodic features and voice quality also infers emotion characteristics. The emotion speech files are processed to extract features like energy, pitch, intensity and Mel-Frequency Cepstral Coefficient (MFCC). Emotion recognizer is designed with classifiers like Multilayer Perceptron (MLP) and Support Vector Machine (SVM). The experiment carried out for male and female speech files with acoustic features separately and acoustic features along with short term spectral features. The performances of the classifiers are evaluated with predictive accuracy.
SYNTHESIS, CHARACTERISATION AND BIOLOGICAL STUDIES ON FE(II) AND ZN(II) QUINOLINE SCHIFF BASE COMPLEXES
(International Journal of ChemTech Research, 2015) Sudha, N; Selvi, G
The synthesis and characterization of transition metal complexes containing Schiff bases as ligands due to their application as catalyst in many reactions and related to synthetic organic and natural oxygen carriers. Molecules containing donor-acceptors such as Schiff bases have ability to serve as polymeric ultraviolet stabilizers, laser dyes. The present work is focused on the study of co-ordination behaviour of thiosemicarbazone Schiffbase with hydrated Fe(II) and Zn(II) chlorides. Analytical and spectral data confirmed the structure of the complexes. Also absorption at 305nm might be due to the extended conjugation of the ring or may be due to the ring residue. Antibacterial and Antifungal activities were carried out using Disc diffusion method and the compounds were found to be active.
DIABETIC RETINAL EXUDATES DETECTION USING EXTREME LEARNING MACHINE
(Springer Link, 2015) Asha, P R; Karpagavalli, S
Diabetic Retinopathy is a disorder of the retina as a result of the impact of diabetes on the retinal blood vessels. It is the major cause of blindness in people like age groups between 20 & 60. Since polygenic disorder proceed, the eyesight of a patient may commence to deteriorate and causes blindness. In this proposed work, the existence or lack of retinal exudates are identified using Extreme Learning Machine(ELM). To discover the occurrence of exudates features like Mean, Standard deviation, Centroid and Edge Strength are taken out from Luv color space after segmenting the Retinal image. A total of 100 images were used, out of which 80 images were used for training and 20 images were used for testing. The classification task carried out with classifier extreme learning machine (ELM). An experimental result shows that the model built using Extreme Learning Machine outperforms other two models and effectively detects the presence of exudates in retina.
COMPARATIVE MICROBIOLOGICAL ANALYSIS OF WATER STORED IN DIFFERENT STORAGE VESSELS
(International Journal of Pharma and Bio Sciences, 2015) Radha, R; Susheela, P
Water is most essential for existence of life on earth. Water is the basic necessity of all living creatures and its important use are for drinking purpose. Water intended for human consumption must be safe and free from microbes. Therefore this investigation was taken with the objective to study the effect of storage of lake water in different vessels like plastic, clay, copper and stainless steel by comparing the number of coliforms present in the water before and after storage. The findings may have significant implications in the use of vessels made of copper and its alloys for household storage of drinking water.
HERITABILITY, CORRELATION AND PATH COEFFICIENT ANALYSIS FOR MORPHO-PHYSIOLOGICAL TRAITS IN WHEAT
(2015-01) Shajitha, P; Gajalakshmi, Kandasamy; Sivasamy, M; Nisha, P
Heritability, inter-relationship and path coefficient studies were performed in ten bread wheat genotypes in the background of (Lok-1, MACS2496, NI5439, NIAW 34, PBW 226, PBW 343, PBN 51, PBW 502, WH542 and WH147) carrying yield potential gene Lr19/Sr25 along with rust resistance. Very high broad sense heritability was estimated for all the morphological characters studied. Grains per spike exhibited highest heritability value of 99.4% while tillers per plant showed minimum value of 90%. Genotypically plant height, spike length, spikelets per spike, grains per spike and 1000-grain weight were positively and significantly correlated with tillers per plant while highly significantly associated phenotypically. Flag leaf area was positively but non-significantly associated with grain yield; whereas, fertile tillers per plant was negatively and nonsignificantly correlated with grain yield. Plant height, flag leaf area, spike length and grains per spike had positive direct effects on grain yield. While fertile tillers per plant, spikelets per spike and 1000-grain weight exhibited negative direct effects on grain yield. The traits having positive direct effects on grain yield are considered to be suitable selection criteria for evolving high yielding genotypes.
CROSS-INCOMPATIBILITY : PREVENTING FERTILIZATION IN EINKORN WHEAT (TRITICUM MONOCOCCUM)
(Connect Journals, 2015-01-11) Baghyalakshmi, K; Kumar, M; Subashini, G; Shajitha, P; Prabakaran, A J
Genetic variation in crop species and their wild relatives holds the key for successful breeding of improved cultivars. Gene pool of wild species is usually more difficult to manipulate than the one found within the cultivated species. However, the ease of manipulation and success in using genes from wild species will vary with the crosses attempted, species used and can be affected by both genotypes and ploidy level of the species used. T. monococcum, ‘A’ genome contributor to the present day bread wheat with basic number x =7 was crossed with cultivated species of T. dicoccum (NP200, 2n=28), T. durum (MACS2846, 2n=28) and T .aestivum (Agra Local, 2n=42) to develop progenies with the characters of both the parents. The wild species was used as female parents and cultivated plants as male parents. Crossing T. monococcum as female with T. dicoccum, T. durum and T. aestivum did not result in seed set. The analysis done on these crosses to investigate the cause for failure revealed that it could be due to post-fertilization problems.
ANALYSIS OF TAMIL CHARACTER WRITINGS AND IDENTIFICATION OF WRITER USING SUPPORT VECTOR MACHINE
(IEEE, 2015-01-26) Thendral, T; Vijaya, M S; Karpagavalli, S
Distinctive Handwriting is a thought provoking task in writer identification. The style and shape of the letters written by the same writer may vary and entirely different for different writers. Alphabets in the handwritten text may have loops, crossings, junctions, different directions and so on. Therefore exact prediction of individual based on his/her handwriting is highly complex and challenging task. This paper proposes a new model for learning the writer's identity constructed on Tamil handwriting. Handwritten documents written by the writers are scanned and segmented into words. Words are further segmented into characters for character level writer identification. The character writings in Tamil are analyzed and their describing features are defined. The Writer identification problem is formulated as classification task and a pattern classification technique namely Support Vector Machine has been employed to construct the model. It has been reported about 90. 6% of prediction accuracy by RBF kernel based classification model in character level writer identification.
IMPROVED MICROBIAL GROWTH INHIBITION ACTIVITY OF BIO-SURFACTANT INDUCED AG–TIO2 CORE SHELL NANOPARTICLES
(Elsevier, 2015-02) Nithyadevi, D; Suresh Kumar, P; Mangalaraj, D; Ponpandian, N; Viswanathan, C; Meena, P
Surfactant induced silver–titanium dioxide core shell nanoparticles within the size range of 10–50 nm were applied in the antibacterial agent to inhibit the growth of bacterial cells. The single crystalline silver was located in the core part of the composite powder and the titanium dioxide components were uniformly distributed in the shell part. HRTEM and XRD results indicated that silver was completely covered by titanium dioxide and its crystal structure was not affected after being coated by titanium dioxide. The effect of silver–titanium dioxide nanoparticles in the inhibition of bacterial cell growth was studied by means of disk diffusion method. The inhibition zone results reveal that sodium alginate induced silver–titanium dioxide nanoparticles exhibit 100% more antibacterial activity than that with cetyltrimethylbromide or without surfactant. UV–vis spectroscopic analysis showed a large concentration of silver was rapidly released into phosphate buffer solution (PBS) within a period of 1 day, with a much smaller concentration being released after this 1-day period. It was concluded that sodium alginate induced silver–titanium dioxide core shell nanoparticles could enhance long term cell growth inhibition in comparison with cetyltrimethylbromide or without surfactant. The surfactant mediated core shell nanoparticles have comparatively rapid, less expensive and wider applications in modern antibacterial therapy.