4.Conference Paper (13)
Permanent URI for this collectionhttps://dspace.psgrkcw.com/handle/123456789/3921
Browse
13 results
Search Results
Item DEEP LEARNING PREDICTIVE MODEL FOR DETECTING HUMAN INFLUENZA VIRUS THROUGH BIOLOGICAL SEQUENCES(Springer Link, 2020-09-08) Nandhini, M; Vijaya, M SSwine influenza is a contagious disease which is generated by one of the swine influenza viruses. Any modification in protein will alter the biological activity and lead to illness. Obtaining appropriate information from virus protein sequence is an interesting research problem in bioinformatics. The aim of this research work is to develop deep neural network (DNN)-based virus identification model for detecting the virus accurately with the protein sequences using deep learning. Deep learning is gaining more importance because of its governance in terms of accuracy when the network trained with large amount of data. A corpus of 404 protein sequences associated with nine types of human influenza virus is collected for training the deep neural network and building the model. Various parameters of the DNN such as input layer, hidden layer and output layer are fine-tuned to improve the efficiency of the model. Sequential model is created for developing DNN classification model using Adam optimizer with Softmax and ReLu activation functions. It is observed that experiments of proposed human influenza virus identification model with DNN classifier give 80% of accuracy and outperform with other ensemble learning algorithms.Item DEEP NEURAL NETWORK FOR EVALUATING WEB CONTENT CREDIBILITY USING KERAS SEQUENTIAL MODEL(Springer Link, 2020-08-08) Manjula, R; Vijaya, M SWeb content credibility determines the measure of acceptable and reliable of the web content that is observed. Content will prove to be unreliable if it is not updated, and it is not controlled for remarkable, and therefore, web content credibility is considerably essential for the people to assess the content. The analysis of content credibility is a vital and challenging task as the content credibility is outlined on crucial factors. This paper focuses on building deep neural network (DNN)-based predictive model using sequential model API to evaluate credibility of a webpage content. Deep neural network (DNN) is considered as an extremely promising decision-making architecture, and it performs feature extraction and transformation with the use of refined statistical modeling. A corpus of 400 webpage contents has been developed, and the factors like readability, freshness, and duplicate content are defined and captured from the webpage content. These features are redefined, and a new set of features is self-learned through the deep layers of neural network. Numeric labeling is used for defining credibility, wherein five-point Likert scale rating is used to denote the content credibility. By using sequential model, KerasRegressor with ADAM optimizer and a multilayer network is generated for building DNN-based predictive model and discovered that deep neural network outperforms other general regression algorithms in prediction scores.Item MALWARE FAMILY CLASSIFICATION MODEL USING USER DEFINED FEATURES AND REPRESENTATION LEARNING(Springer Link, 2020-11-20) Gayathri, T; Vijaya, M SMalware is very dangerous for system and network user. Malware identification is essential tasks in effective detecting and preventing the computer system from being infected, protecting it from potential information loss and system compromise. Commonly, there are 25 malware families exists. Traditional malware detection and anti-virus systems fail to classify the new variants of unknown malware into their corresponding families. With development of malicious code engineering, it is possible to understand the malware variants and their features for new malware samples which carry variability and polymorphism. The detection methods can hardly detect such variants but it is significant in the cyber security field to analyze and detect large-scale malware samples more efficiently. Hence it is proposed to develop an accurate malware family classification model contemporary deep learning technique. In this paper, malware family recognition is formulated as multi classification task and appropriate solution is obtained using representation learning based on binary array of malware executable files. Six families of malware have been considered here for building the models. The feature dataset with 690 instances is applied to deep neural network to build the classifier. The experimental results, based on a dataset of 6 classes of malware families and 690 malware files trained model provides an accuracy of over 86.8% in discriminating from malware families. The techniques provide better results for classifying malware into families.Item LUMINESCENCE COBALT (II) COMPLEXES: SYNTHESIS, CHARACTERIZATION, PHOTOPHYSICAL AND DFT STUDY(Elsevier, 2020) Sathya Priyadarshini, G; Selvi, GFour mononuclear cobalt (II) complexes of substituted hydrazino quinoline Schiff bases 1(a–d) were synthesised and characterized by UV, IR, NMR and TGA studies. The geometry of cobalt complexes 1(a–d) unambiguously attested as distorted octahedral’ and the ligand was coordinated through NNO donor fashion of tridentate nature. Structure of the proposed complexes were optimized using Density Functional theory (DFT) with Gaussian 09/ Gauss view software. Mulliken charges, global softness and electrophilicity index were derived for the optimized structure and the energy of highest occupied orbital (HOMO) and lowest unoccupied orbital (LUMO) and energy gap were calculated. The photophysical properties of the synthesised complexes were analyzed by UV–Visible and photoluminescence spectral studies, the results revealed that the emission bands centered in the range of 445–455 nm with higher luminescence intensity and relatively large Stoke’s shift observed (198 nm–215 nm) in the absorption and emission shoed a promising novel material towards OLED’S.Item A STUDY ON IMPROVED SYNTHETIC STRATEGY FOR NOVEL TRIAZINO QUINOLINE AND ITS NONLINEAR OPTICAL PROPERTIES(Elsevier, 2020) Namitha, R; Elakkiya, S; Selvi, GOrganic Light emitting diodes (OLED) are the emerging technology in the present era. Any molecule to acts as an OLED material, it should possess non-linear optical property. In this context, the synthesised novel 4′,7′-dimethyl-3-thioxo-1,2,4-triazinoquinolin-5-one and its derivatives IV(a-g) were studied for their nonlinear optical property theoretically using Gaussian 09. Synthesis of the targeted compounds were obtained from the potential precursors 2-chloro-4, 7-dimethylquinoline I(a-g). The synthesized compounds were characterized by FTIR, 1HNMR and 13CNMR spectral techniques. In prior to the synthesis molecular geometry and the probable active site for substitution/cyclisation were predicted by the theoretical investigation on the intermediate IIIa using B3LYP functional with 6-31G (d, p) basic set from the physical and chemical properties such as NBO analysis, Mulliken charges. The compounds III(a-g) and IV(a-g) are found to possess an appreciable Non Linear Optical property.Item SYNTHESIS OF CU DOPED COBALT OXIDE NANOPARTICLES AS AMMONIA GAS SENSOR OPERATING AT ROOM TEMPERATURE(Elsevier, 2020) Jincy, C S; Meena, PIn this work, hydrothermally synthesized copper doped cobalt oxide nanoparticles were utilized for the detection of ammonia gas. The powder samples were described by different characterization techniques. XRD spectrum revealed the crystalline structure of the sample. The morphology and component analysis of nanoparticles was done by SEM and EDAX respectively. The FTIR investigation affirmed the presence of functional group in the sample. Optical properties were assessed by UV–Vis spectroscopy. The optical properties were evaluated by UV–Vis spectroscopy. Doping is an effective way to increase gas sensitivity. The sensing properties of cobalt oxide nanoparticles has been enhanced due to the utilization of Cu as a dopant. In the present work, we put emphasis on a cost effective method to achieve supreme sensitivity towards NH3 gas at room temperature even at a lower concentration of 5 ppm. The presence of Cu ions on the surface of Co3O4 nanoparticles was found to enhance the sensor performance.Item INHIBITORY ACTION OF MACARANGA PELTATA LEAVES EXTRACT ON THE CORROSION OF MILD STEEL IN 0.5 M SULPHURIC ACID- QUANTUM CHEMICAL APPROACH(Elsevier, 2020) Athul, K K; Thilagavathy, P; Nalini, DWeight loss and electrochemical impedance spectroscopy (EIS) method were used for testing the corrosion inhibition effect of Macaranga peltata leaves (MPL) extract on corrosion of mild steel in 0.5 M sulphuric acid solution. The inhibitory effect of MPL was studied at various concentrations of the extract and different time of immersion. In all cases an optimal efficiency was found out. Maximum inhibition efficiency was 92.6% for 5%v/v at 5 h. Nyquist and Tafel plots gave a confirmation about the inhibitory action of the plant extract, agreeing with the weight loss method. The surface content of mild steel after immersion was investigated using IR and the inhibition mechanism is suggested as adsorption of the phytochemical constituents from the results. The Quantum chemical energy calculations become an additional support of the suggested mechanism.Item SYNTHESIS, CHARACTERIZATION, DFT, IN-VITRO ANTI-MICROBIAL, CYTOTOXICITY EVALUATION, AND DNA BINDING INTERACTIONS OF TRANSITION METAL COMPLEXES OF QUINOXALINE SCHIFF BASE LIGAND(Elsevier, 2020) Jone Kirubavathy, S; Chitra, SA series of Cr(III), Mn(II), Fe(III), Co(II), Cu(II) and Ni(II) transition metal complexes of the quinoxaline based Schiff base ligand were synthesized and characterized on the basis of analytical, conductance, magnetic moment, FT-IR, NMR, ESR, EDAX and electronic spectral data. The ligand behaves as bidentate OO donors through phenolic oxygen and carbonyl oxygen in the quinoxaline ring. The molecular structure of the quinoxaline Schiff base ligand and Cu(II) complex was investigated theoretically. The optimized molecular structure was obtained from Gaussian 09 program. The antimicrobial activity of the ligand and the complexes were screened for various bacterial and fungal strains and found to be good for Co(II) and Mn(II) complexes and moderate for the other synthesized complexes. The minimum inhibitory concentration of the Co(II) and Mn(II)complexes against S. aureus, S. paratyphi and A. niger were found to be 250 μg/ml, 125 μg/ml, 500 μg/ml and 250 μg/ml, 250 μg/ml , 500 μg/ml respectively. The anti-cancer activity of the ligand and the complexes were studied against the human breast cancer cell lines MCF-7 and found to be good for Cu(II), Co(II) and Mn(II) complexes. The in-vitro anti-oxidant activities of the complexes and found to be moderate for all complexes. The DNA binding ability of the complexes were checked and their binding constants were reported using absorption and emission spectral studies.Item IMPACT OF MOLYBDENUM ON STRUCTURAL AND MORPHOLOGICAL PROPERTIES OF MANGANESE FERRITE NANOPARTICLES BY HYDROTHERMAL METHOD(Elsevier, 2020) Kaveri, N; Balavijayalakshmi, JThe study of transition metal ferrites have vast applications from microwave to radio-wave frequencies and are of great importance from both fundamental as well as in research aspect. Based on their magnetic properties, transition metal ferrites are found to have low magnetic anisotropies and are magnetically categorized as soft. Manganese ferrites are a group of soft spinel ferrite materials with high magnetic permeability, high electrical resistance and low loss. The doping of molybdenum improves its resistivity, strength and toughness. Due to their excellent electrical and magnetic properties, spinel ferrites are technologically important ceramic materials. As transition takes place from micron to nano regime, these materials are found to be with excellent chemical stability, moderate saturation magnetization and low eddy currents especially in spinel ferrites. In this present work, nanocrystalline ferrites of x varies as 0.4, 0.6 and 0.8 are synthesized by hydrothermal method. The prepared nanocrystalline ferrites are characterized by X-Ray Diffraction (XRD), Fourier Transform Infrared Spectroscopy (FT-IR), Energy Dispersive X-Ray Analysis (EDX) and Scanning Electron Microscopy (SEM) for analyzing its structural, functional groups and morphological structures. XRD analysis reveals that the resultant ferrite nanoparticles are found to have cubic structure. FT-IR spectral analysis shows two main broad metal–oxygen bands and confirms the presence of spinel ferrites. EDX analysis confirms the quantitative presence of elements without impurities. This study aims to fabricate the ferrites with better physical and magnetic properties that are useful in a variety of applications such as magnetic sensors, heavy metal removal and transducers.Item SYNTHESIS OF CO3O4 NANOPARTICLES FOR SENSING TOXIC GAS AT ROOM TEMPERATURE(Elsevier, 2020) Jincy, C S; Meena, POver the past few decades, there has been an increasing demand for inexpensive, accurate, portable and reliable gas sensors which can be used to detect combustible, flammable and toxic gases, and oxygen depletion. Typically, gases of interest include CO, NO, NO2, NH3, SO2, CO2, CH4 and other hydrocarbons. These gases can be harmful to human health if present beyond a certain concentration. Among various metal oxide semiconductors, p-type Cobalt oxide semiconductors are excellent materials for fabricating highly sensitive and selective gas sensors of high-performance. In this study, a novel and low cost chemical route has been developed to synthesize Co3O4 nanostructures. The efficiency of Co3O4 nanomaterials is improved by means of introducing n-type dopants. The synthesized nanomaterials were characterized by different characterization techniques like UV double beam spectrophotometry, X-ray diffraction (XRD), Fourier Transform Infrared Spectroscopy (FTIR), Scanning Electron Microscopy (SEM) and Energy Dispersive X-ray analysis (EDAX). The Cobalt oxide nanoparticles are observed to have a good response and sensitivity to ammonia gas at room temperature.