n) 2012 - 17 Documents

Permanent URI for this communityhttps://dspace.psgrkcw.com/handle/123456789/3994

Browse

Now showing 1 - 17 of 17

AN EFFICIENT LEAF RECOGNITION ALGORITHM FOR PLANT CLASSIFICATION USING SUPPORT VECTOR MACHINE (Conference Paper)
(IEEE, 2012-05-31) Arun Priya, C; Balasaravanan, T; Antony Selvadoss, Thanamani
Recognition of plants has become an active area of research as most of the plant species are at the risk of extinction. This paper uses an efficient machine learning approach for the classification purpose. This proposed approach consists of three phases such as preprocessing, feature extraction and classification. The preprocessing phase involves a typical image processing steps such as transforming to gray scale and boundary enhancement. The feature extraction phase derives the common DMF from five fundamental features. The main contribution of this approach is the Support Vector Machine (SVM) classification for efficient leaf recognition. 12 leaf features which are extracted and orthogonalized into 5 principal variables are given as input vector to the SVM. Classifier tested with flavia dataset and a real dataset and compared with k-NN approach, the proposed approach produces very high accuracy and takes very less execution time.
EFFICIENT PREDICTION OF PHISHING WEBSITES USING SUPERVISED LEARNING ALGORITHMS (Conference Paper)
(Elsevier Ltd, 2012) Santhana Lakshmi, V; Vijaya, M S
Phishing is one of the luring techniques used by phishing artist in the intention of exploiting the personal details of unsuspected users. Phishing website is a mock website that looks similar in appearance but different in destination. The unsuspected users post their data thinking that these websites come from trusted financial institutions. Several antiphishing techniques emerge continuously but phishers come with new technique by breaking all the antiphishing mechanisms. Hence there is a need for efficient mechanism for the prediction of phishing website. This paper employs Machine-learning technique for modelling the prediction task and supervised learning algorithms namely Multi layer perceptron, Decision tree induction and Naïve bayes classification are used for exploring the results. It has been observed that the decision tree classifier predicts the phishing website more accurately when comparing to other learning algorithms.
ENHANCED PHOTOCATALYTIC ACTIVITY OF COBALT-DOPED CEO2 NANORODS (Article)
(Springer Link, 2012-09-28) Sabari Arul, N; Mangalaraj, D; Pao Chi, Chen; Ponpandian, N; Meena, P; Yoshitake, Masuda
In this paper, CeO2 and cobalt-doped CeO2 nanorods synthesized by surfactant free co-precipitation method. The microstructures of the synthesized products were characterized by XRD, FESEM and TEM. The structural properties of the grown nanorods have been investigated using electron diffraction and X-ray diffraction. High resolution transmission electron microscopy studies show the polycrystalline nature of the Co-doped cerium oxide nanorods with a length of about 300 nm and a diameter of about 10 nm were produced. The X-ray Photoelectron spectrum confirms the presence of cobalt in cerium oxide nanorods. From BET, the specific surface area of the CeO2 (Co-doped) nanostructures (131 m2 g−1) is found to be significantly higher than that of pure CeO2 (52 m2 g−1). The Co-doped cerium nanorods exhibit an excellent photocatalytic performance in rapidly degrading azodyes acid orange 7 (AO7) in aqueous solution under UV illumination.
IMPLICATIONS OF BACTERIAL ISOLATES IN HEAVY METAL TOLERANCE TO THE POLLUTED ENVIRONMENT (Article)
(International Journal of Pharmaceutical Sciences Review and Research, 2012-09) Siva Ananthi, T.A; Meerabai, R S
Two isolates namely, Bacillus sp. and Leclercia adecarboxylata were isolated from soil contaminated with wide range of heavy metals. Minimum inhibitory concentration (MIC) for both the isolates was at 2000 mg Pb L -1 and also exhibited high resistant to wide range of antibiotics.
IN VITRO ANTIBACTERIAL ACTIVITY OF HIBISCUS ROSA–SINENSIS FLOWER EXTRACT AGAINST HUMAN PATHOGENS (Article)
(Elsevier, 2012-05) Ruban, P; Gajalakshmi, K
To access the in vitro antibacterial activity of Hibiscus rosa–sinensis H. rosa-sinensis) flower extract against human pathogens.
INFLUENCE OF COPPER ON THE MAGNETIC PROPERTIES OF COBALT FERRITE NANO PARTICLES (Article)
(Elsevier, 2012-08) Balavijayalakshmi, J; Suriyanarayanan, N; Jayapraksah, R
Copper substituted cobalt ferrite nano particles Co(1 − x)CuxFe2O4 (where x = 0, 0.2, 0.4, 0.6, 0.8, 1) are successfully synthesized using co-precipitation method and samples are sintered at 900 °C. The average nano crystalline sizes are found to be in the range of 37–52 nm. As the copper concentration increases, the magnetization of the octahedral sites and hence the net magnetization decreases. It is also observed that the saturation magnetization (Ms), remanent magnetization (Mr) and coercivity (Hc) decrease with increase in copper substitution. The frequency of the absorption band around 600 cm− 1 is shifted to a lower value. Plates and sponge like surface morphology of copper mixed ferrites are studied.
THE INHIBITION EFFECT OF THIAZINE COMPOUNDS TOWARDS THE CORROSION OF MILD STEEL IN SULPHURIC ACID MEDIA (Article)
(Rasayan Journal of Chemistry, 2012) Hemapriya, V; Parameswari, K; Bharathy, G
The inhibition effect of thiazines (AT, CBT & NBT) on mild steel corrosion in 1M sulphuric acid (H2SO4) was investigated by weight loss, potentiodynamic polarization and electrochemical impedance spectroscopy (EIS) techniques. The result showed that corrosion rate was significantly decreased in presence of the inhibitors. The inhibiting action increases with the concentration of thiazine compounds to attain 99 % at 0.5mM of (AT). The increase in temperature leads to a decrease in the inhibition efficiency of the compounds in the temperature range 308-353K. Adsorption of thiazines on the mild steel surface in 1M H2SO4 obeyed the Langmuir adsorption isotherm. EIS measurements showed an increase in charge transfer resistance (Rct) with concentration. Potentiodynamic polarization study showed that the inhibitors act as mixed type, controlling both the anodic and cathodic reactions. Surface analysis by SEM confirmed the formation of adsorbed protective layer of the inhibitor on the steel surface
INVESTIGATION OF BENZOTHIAZOLE DERIVATIVES AS CORROSION INHIBITORS FOR MILD STEEL (Article)
(Portugaliae Electrochimica Acta, 2012) Parameswari, K; Chitra, S; Selvaraj, A; Brindha, S; Menaga, M
The influence of benzothiazole derivatives on corrosion inhibition of mild steel in 1 M H2SO4 was studied by weight loss, potentiodynamic polarization and AC-impedance techniques. The synergistic effect by the addition of halide ions had been studied. The experimental results showed that the inhibition efficiency increases with increasing inhibitor concentration, but decreases with increasing temperature; potentiodynamic polarization curves showed that benzothiazole derivatives acted as cathodic inhibitors in 1 M H2SO4. This was supported by the impedance measurements which showed a change in the charge transfer resistance and double layer capacitance, indicating adsorption of Benzothiazole derivatives on the mild steel surface. Atomic absorption spectroscopy studies showed that the inhibition efficiency increases with increasing inhibitor concentration.
ISOLATED TAMIL DIGIT SPEECH RECOGNITION USING TEMPLATE-BASED AND HMM-BASED APPROACHES (Conference Paper)
(Springer Link, 2012) Karpagavalli, S; Deepika, R; Kokila, P; Usha Rani, K; Chandra, E
For more than three decades, a great amount of research was carried out on various aspects of speech signal processing and its applications. Highly successful application of speech processing is Automatic Speech Recognition (ASR). Early attempts to ASR consisted of making deterministic models of whole words in a small vocabulary and recognizing a given speech utterance as the word whose model comes closest to it. The introduction of Hidden Markov Models (HMMs) in the early 1980 provided much more powerful tool for speech recognition. And the recognition can be done for continuous speech using large vocabulary, in a speaker independent manner. Two approaches like conventional template-based and Hidden Markov Model usually performs speaker independent isolated word recognition. In this work, speaker independent isolated Tamil digit speech recognizers are designed by employing template based and HMM based approaches. The results of the approaches are compared and observed that HMM based model performs well and the word error rate is greatly reduced.
LABEL SEQUENCE LEARNING BASED PROTEIN SECONDARY STRUCTURE PREDICTION USING HYDROPHOBICITY SCALES (Conference Paper)
(Springer Link, 2012) Vinodhini, R; Vijaya, M S
Proteins are complex molecules, each comprised of its own combination of twenty different amino acids. Protein secondary structure is a polypeptide that has formed an arrangement of amino acids that are located next to one another in a linear fashion. Protein secondary structure prediction refers to the prediction of the conformational state of each amino acid residue of a protein sequence as one of the three possible states, namely helices, strands, or coils, denoted as H, E, and C, respectively. Protein sequence is the only resource that provides the information to survive denaturing process, so it is essential to find the secondary structure of a protein sequence. The existing methodology uses only one hydrophobicity scale called Kyte-Doolittle whereas in this paper three scales such as, Kyte-Doolittle scale, Hopp-Woods scale and Rose scale are used for protein secondary structure prediction. This Paper formulates secondary structure prediction task as sequence labeling and a new coding scheme is introduced with multiple windows to predict secondary structure of proteins using hydrophobicity scales. Protein sequences with their physical and chemical properties are learned using SVMhmm that creates a learned model, which is then used to predict protein secondary structure of an unknown primary sequence. It is reported 77.11% accuracy based on Q3 measures, when SVMhmm is used.
LIPASE PRODUCTION BY ASPERGILLUS TERREUS USING COTTON SEED OIL AS CARBON SOURCE (Article)
(Plant Archives, 2012) Sumathi, R; Meerabai, R S
Fungi isolated from soil were screened for exogenous lipolytic activity. The highest lipase activity was found in an isolate of Aspergillus terreus. Optimal cultural conditions influencing the growth and production of extra cellular lipase from this fungus was investigated. The lipase yield was maximum on day 5 of incubation when the medium was supplemented with maltose and cotton seed oil as sole carbon source and potassium nitrate as nitrogen source at pH 7 and at temperature of 40°C.
PERFORMANCE EVALUATION OF SEMANTIC BASED AND ONTOLOGY BASED TEXT DOCUMENT CLUSTERING TECHNIQUES (Conference Paper)
(Elsevier Ltd, 2012) Punitha, S C; Punithavalli, M
The amount of digital information is created and used is steadily growing along with the development of sophisticated hardware and software. This has increased the need for powerful algorithms that can interpret and extract interesting knowledge from these data. Data mining is a technique that has been successfully exploited for this purpose. Text mining, a category of data mining, considers only digital documents or text. Text Clustering is the process of grouping text or documents such that the document in the same cluster are similar and are dissimilar from the one in other clusters. This paper studies the working of two sophisticated algorithms. The first work is a hybrid method that combines pattern recognition process with semantic driven methods for clustering documents, while the second uses an ontology-based approach to cluster documents. Through experiments, the performance of both the selected algorithms is analyzed in terms of clustering efficiency and speed of clustering.
PHARMACOGNOSTICAL, PHYTOCHEMICAL AND HEAVY METAL STUDIES ON AN ETHNO MEDICINAL PLANT-CORALLOCARPUS EPIGAEUS (ROTTL. &WILD.) CLARKE (Article)
(International Journal of Pharmacognosy and Phytochemical Research, 2012) Umadevi, U; Kamalam, M
Leaf, stem and tuber powder of Corallocarpus epigaeus were investigated for its pharmacognostical, phytochemical and heavy metal properties. Analytical value (loss on drying, total ash, acid insoluble ash, water soluble ash), solubility percentage, fluorescent analysis, extractive value using different solvents (petroleum ether, benzene, chloroform, acetone, ethanol, methanol and water), qualitative phytochemical analysis for detection of alkaloids, glycosides, flavonoids, tannins, phenols, proteins, amino acids, saponins and terpenoids. HPTLC studies of glycosides, flavonoids, phenolic compounds and heavy metal analysis for the accumulation of lead, copper and cadmium were studied. Analytical value, extractive value and solubility percentage exhibited marked difference between the leaf, stem and tuber powder of C. epigeaus. Fluorescent analysis does not differ among the selected plant parts under normal and UV light. Qualitative analysis of acetone and water extracts revealed the presence of secondary metabolites like alkaloids, glycosides, flavonoids, terpenoids, tannins, phenol, fats and fatty acids. HPTLC studies also confirmed the presence of glycosides, flavonoids and phenolic compounds. Heavy metals present in the plant parts are lower than the permissible level.
STOCK PRICE PREDICTION USING SUPPORT VECTOR REGRESSION (Conference Paper)
(Springer Link, 2012) Abirami, R; Vijaya, M S
Forecasting stock price is an important task as well as difficult problem. Stock price prediction depends on various factors and their complex relationships. Prediction of stock price is an important issue in finance. Stock price prediction is the act of trying to determine the future value of a company stock. The successful prediction of a stock future price could yield significant profit. Hence an efficient automated prediction system is highly essential for stock forecasting. This paper demonstrates the applicability of support vector regression, a machine learning technique, for predicting the stock price by learning the historic data. The stock data for the period of four years is collected and trained with various parameter settings. The performance of the trained model is evaluated by 10-fold cross validation for its predictive accuracy. It has been observed that the support vector regression model with RBF kernel shows better performance when compared with other models.
SYNTHESIS AND CHARACTERIZATION OF EPOXY–SILICONE–POLYTHIOPHENE INTERPENETRATING POLYMER NETWORK FOR CORROSION PROTECTION OF STEEL (Article)
(Elsevier, 2012-12) Palraj, S; Selvaraj, M; Vidhya, M; Rajagopal, G
Polymer alloys, particularly interpenetrating polymer networks (IPNs) exhibit excellent coating properties. Often combination of polymers result in IPNs with controlled morphologies and synergistic behavior. In this study, corrosion-resistant IPNs were prepared from immiscible resins (epoxy, silicone and thiophene) using a cross-linking agent and a catalyst. GPC, FTIR, NMR, TG, DTA and SEM studies used to fix the best performing IPN. Surface morphology studies using SEM confirm the incorporation of silicone and polythiophene in to the epoxy polymer to form homogeneously micro structured IPN. The heat-resistance of the IPN was determined as per ASTM 2485. The improved corrosion resistance of the IPN was evaluated by AC impedance measurements.
SYNTHESIS AND CHARACTERIZATION OF POLYANILINE/MNWO4 NANOCOMPOSITES AS ELECTRODES FOR PSEUDOCAPACITORS (Article)
(Elsevier, 2012-03-15) Saranya, S; Kalai Selvan, R; Priyadharsini, N
Polyaniline (PAni)/MnWO4 nanocomposite was successfully synthesized by in situ polymerization method under ultrasonication and the MnWO4 was prepared by surfactant assisted ultrasonication method. The thermal stability of PAni was determined by TG/DTA (Thermo Gravimetric/ Differential thermal analysis). The structural and morphological features of PAni, MnWO4 and PAni/MnWO4 composite was analyzed using Fourier transform infrared spectrometry, X-ray diffraction (XRD), scanning electron microscope (SEM) and Transmission electron microscope (TEM) images. The electro-chemical properties of PAni, MnWO4 and its composites with different weight percentage of MnWO4 loading were studied through cyclic voltammetry (CV) for the application of supercapacitors as active electrode materials. From the cyclic voltammogram, 50% of MnWO4 impregnated PAni showed a high specific capacitance (SC) of 481 F/g than their individual counterparts of PAni (396 F/g) and MnWO4 (18 F/g). The galvanostatic charge–discharge studies indicate the in situ polymerized composite shows greater specific capacitance (475 F/g) than the physical mixture (346 F/g) at a constant discharge current of 1 mA/cm2 with reasonable cycling stability. The charge transfer resistance (Rct) of PAni/MnWO4 composite (22 ohm) was calculated using electrochemical impedance spectroscopy (EIS) and compared with its physical mixture (58 ohm).
SYNTHESIS OF INDIUM OXIDE CUBIC CRYSTALS BY MODIFIED HYDROTHERMAL ROUTE FOR APPLICATION IN ROOM TEMPERATURE FLEXIBLE ETHANOL SENSORS (Article)
(Elsevier, 2012-03-15) Seetha, M; Meena, P; Mangalaraj, D; Yoshitake, Masuda; Senthil, K
Indium oxide cubic crystals were prepared by using hexamethylenetetramine and indium chloride without the addition of any structure directing agents. The chemical route followed in the present work was a modified hydrothermal synthesis. The average crystallite size of the prepared cubes was found to be 40 nm. A blue emission at 418 nm was observed at room temperature when the sample was excited with a 380 nm Xenon lamp. This emission due to oxygen vacancies made the material suitable for gas sensing applications. The synthesized material was made as a composite film with polyvinyl alcohol which was more flexible than the films prepared on glass substrates. This flexible film was used as a sensing element and tested with ethanol vapours at room temperature. The film showed fast response as well as recovery to ethanol vapours with a sensor response of about 1.4 for 100 ppm of the gas.