Time filter

Source Type

Rajaganapathy C.D.,PERI Institute of Technology
Research Journal of Applied Sciences, Engineering and Technology | Year: 2015

The main aim of this study is to survey about various techniques of fault prediction, clustering and classification to identify the defects in software modules. A software system consists of various modules and any of these modules can contain the fault that harmfully affects the reliability of the system. But early predictions of faulty modules can help in producing fault free software. So, it is better to classify modules as faulty or non-faulty after completing the coding. Then, more efforts can be put on the faulty modules to produce a reliable software. A fault is a defect or error in a source code that causes failures when executed. A faulty software module is the one containing number of faults, which causes software failure in an executable product. A software module is a set of functionally related source code files based on the system's architecture. Fault data can be collected from problem reporting system based on the module level. Defect prediction is particularly important in the field of software quality and reliability. Accurate prediction of faulty modules enables the verification and validation activities focused on the critical software components. A software quality classification model predicts the risk factor for software modules, which is an effective tool for targeting timely quality improvement actions. A desired classification technique provides better classification accuracy and robustness. This study surveys various fault prediction, clustering and classification techniques in order to identify the defects in software modules. © Maxwell Scientific Organization, 2015.


Amutha Devi C.,PERI Institute of Technology
Journal of Theoretical and Applied Information Technology | Year: 2013

Stroke is a cardiovascular disease that occurs whenever blood supply to the brain is stopped. For the diagnosis of the brain strokes, characterization of the progress of the disease and monitoring the treatment therapies, neuro-imaging techniques in the form of Magnetic Resonance Images (MRI) are widely used. Accurate segmentation and classification of stroke affected regions are essential for correct detection and diagnosis. Image classification is a critical step for high-level processing of automatic brain stroke classification. In this paper, a method is proposed for classifying the MRI images into stroke and non-stroke images. Features are extracted using Watershed segmentation and Gabor filter. The extracted features are classified using Multilayer Perceptron (MLP). Experiments have been conducted to evaluate the efficiency of the proposed method with varying number of features. © 2005 - 2013 JATIT & LLS. All rights reserved.


Balakrishnan G.,National Institute of Technology Tiruchirappalli | Balakrishnan G.,PERI Institute of Technology | Sundari S.T.,Indira Gandhi Center for Atomic Research | Kuppusami P.,Indira Gandhi Center for Atomic Research | And 5 more authors.
Thin Solid Films | Year: 2011

Thin films of cerium oxide (CeO2) have been deposited on (100) Si substrates using pulsed laser deposition technique at various substrate temperatures from room temperature (RT) to 973 K at an optimized oxygen partial pressure of 3 Pa. Structural, morphological and optical properties have been carried out using X-ray diffraction (XRD), Raman, ellipsometry and atomic force microscopy techniques. XRD results showed that the deposited films are polycrystalline with cubic structure. At room temperature, the film showed preferred orientation along (111) plane, while at higher temperatures, it exhibited preferred orientation along (200). The crystallite sizes were calculated and were found to be in the range 17-52 nm. The texture coefficient for (200) reflection increased until 573 K, and then decreased in the temperature range 673-973 K. The Raman peak appeared at 463 cm- 1 due to the F2g active mode also confirmed the formation of CeO 2 with a cubic structure. There was a systematic variation in the Raman peak intensity, frequency shift and line broadening with the increase of temperature. The ellipsometry studies showed that the refractive index and band gap increased from 2.2 to 2.6 and 3.4 to 3.6 eV, respectively with increasing substrate temperature from RT to 973 K. © 2010 Elsevier B.V.All rights reserved.


Pauline S.A.,Anna University | Sahila S.,Anna University | Gopalakrishnan C.,SRM University | Nanjundan S.,PERI Institute of Technology | Rajendran N.,Anna University
Progress in Organic Coatings | Year: 2011

In this study the potential of the terpolymer synthesized from poly(maleic anhydride-co-methyl methacrylate) and hydroxymethylbenzimidazole as corrosion protective coating for 60-40 brass was evaluated using dip coating technique. The copolymer, poly(maleic anhydride-co-methyl methacrylate) synthesized using free radical solution polymerization was reacted with different feed ratios of hydroxymethylbenzimidazole (HMBD) to obtain terpolymers containing maleic anhydride, MMA and mono benzimidazolylmethyl ester of maleic acid (MBMEMA) units. Both the copolymer and the terpolymers were characterized using FT-IR, 1H NMR and 13C NMR spectroscopy. The thermal stability of the polymers was studied using thermogravimetric analysis (TGA) and the molecular weight of the polymer was analyzed using gel permeation chromatography (GPC). The effect of different concentrations of MBMEMA in the polymer for corrosion protection of brass in 3.5% NaCl solution was investigated using potentiodynamic polarization and electrochemical impedance spectroscopy. Effective corrosion protection was obtained when the mole fraction of MBMEMA was 0.24 in the terpolymer. The surface morphology of the polymer coated specimens was studied by scanning electron microscopy (SEM). Solution analysis was used to calculate the dezincification factor. © 2011 Elsevier B.V.


Balakrishnan G.,Changwon National University | Balakrishnan G.,PERI Institute of Technology | Kuppusami P.,Sathyabama University | Sastikumar D.,National Institute of Technology Tiruchirappalli | Song II J.,Changwon National University
Nanoscale Research Letters | Year: 2013

Alumina/zirconia (Al2O3/ZrO2) multilayer thin films were deposited on Si (100) substrates at an optimized oxygen partial pressure of 3 Pa at room temperature by pulsed laser deposition. The Al2O3/ZrO2multilayers of 10:10, 5:10, 5:5, and 4:4 nm with 40 bilayers were deposited alternately in order to stabilize a high-temperature phase of zirconia at room temperature. All these films were characterized by X-ray diffraction (XRD), cross-sectional transmission electron microscopy (XTEM), and atomic force microscopy. The XRD studies of all the multilayer films showed only a tetragonal structure of zirconia and amorphous alumina. The high-temperature XRD studies of a typical 5:5-nm film indicated the formation of tetragonal zirconia at room temperature and high thermal stability. It was found that the critical layer thickness of zirconia is ≤10 nm, below which tetragonal zirconia is formed at room temperature. The XTEM studies on the as-deposited (Al2O3/ZrO2) 5:10-nm multilayer film showed distinct formation of multilayers with sharp interface and consists of mainly tetragonal phase and amorphous alumina, whereas the annealed film (5:10 nm) showed the inter-diffusion of layers at the interface. © 2013 Balakrishnan et al.; licensee Springer.


Balakrishnan G.,PERI Institute of Technology | Sairam T.N.,Indira Gandhi Center for Atomic Research | Kuppusami P.,Indira Gandhi Center for Atomic Research | Thiumurugesan R.,Indira Gandhi Center for Atomic Research | And 3 more authors.
Applied Surface Science | Year: 2011

ZrO2 thin films were deposited at various oxygen partial pressures (2.0 × 10-5-3.5 × 10-1 mbar) at 973 K on (1 0 0) silicon and quartz substrates by pulsed laser deposition. The influence of oxygen partial pressure on structure, surface morphology and optical properties of the films were investigated. X-ray diffraction results indicated that the films are polycrystalline containing both monoclinic and tetragonal phases. The films prepared in the oxygen partial pressures range 2.0 × 10-5-3.5 × 10-1 mbar contain nanocrystals of sizes in the range 54-31 nm for tetragonal phase. The peak intensity of the tetragonal phase decreases with the increase of oxygen partial pressures. Surface morphology of the films examined by AFM shows the formation of nanostructures. The RMS surface roughness of the film prepared at 2.0 × 10-5 mbar is 1.3 nm while it is 3.2 nm at 3.5 × 10-1 mbar. The optical properties of the films were investigated using UV-visible spectroscopy technique in the wavelength range of 200-800 nm. The refractive index is found to decrease from 2.26 to 1.87 as the oxygen partial pressure increases from 2.0 × 10-5 to 3.5 × 10-1 mbar. The optical studies show two different absorption edges corresponding to monoclinic and tetragonal phases. © 2011 Elsevier B.V. All rights reserved.


Balakrishnan G.,Changwon National University | Balakrishnan G.,PERI Institute of Technology | Thanigaiarul K.,Anna University | Sudhakara P.,Changwon National University | Song J.I.,Changwon National University
Applied Physics A: Materials Science and Processing | Year: 2013

The zirconium oxide (ZrO2) thin films are deposited on Si (100) and quartz substrates at various substrate temperatures (room temperature-973 K) at an optimized oxygen partial pressure of 3×10-2 mbar using pulsed laser deposition technique. The effect of substrate temperature on microstructural, optical and mechanical properties of the films is investigated. The X-ray diffraction studies show that the films deposited at temperatures ≤773 K are monoclinic, while the films deposited at temperatures ≤873 K show both monoclinic and tetragonal phases. Tetragonal phase content increases with the increase of substrate temperatures. The surface morphology and roughness are investigated using atomic force microscope in contact mode. The optical properties of the films show that the refractive indices (at 550 nm) are found to increase from 1.84 to 2.35 as the temperature raises from room temperature (RT) to 973 K. Nanoindentation measurements show that the hardness of the films is 11.8 and 13.7 GPa for the films deposited at 300 and 973 K, respectively. © 2012 Springer-Verlag Berlin Heidelberg.


Chinna Gounder Dhanajayan R.,PERI Institute of Technology | Appavu Pillai S.,Government of Tamilnadu
Soft Computing | Year: 2016

Software fault prediction and classification plays a vital role in the software development process for assuring high quality and reliability of the software product. Earlier prediction of the fault-prone software modules enables timely correction of the faults and delivery of reliable product. Generally, the fuzzy logic, decision tree and neural networks are deployed for fault prediction. But these techniques suffer due to low accuracy and inconsistency. To overcome these issues, this paper proposes a spiral life cycle model-based Bayesian classification technique for efficient software fault prediction and classification. In this process, initially the dependent and independent software modules are identified. The spiral life cycle model is used for testing the software modules in each life cycle of the software development process. Bayesian classification is applied to classify the software modules as faulty module and non-faulty module, by using the probability distribution models. Robust similarity-aware clustering algorithm performs clustering of the faulty and non-faulty software modules based on the similarity measure of the features in the dataset. From the experimental results, it is observed that the proposed method enables accurate prediction and classification of the faulty modules. The proposed technique achieves higher accuracy, precision, recall, probability of detection, F-measure and lower error rate than the existing techniques. The misclassification rate of the proposed technique is found to be lower than the existing techniques. Hence, the reliability of the software development process can be improved. © 2016 Springer-Verlag Berlin Heidelberg


Backiam A.N.,PERI Institute of Technology | Kousalyadevi R.,PERI Institute of Technology
2014 International Conference on Electronics and Communication Systems, ICECS 2014 | Year: 2014

Image compression and retrieval techniques are essential for visual database management in an efficient manner. These techniques may vary for each application. Fractal Image Compression is one of the best techniques for natural and still images. In this method an image is divided into non overlapping range blocks and overlapping domain blocks. The domain blocks are larger than the range blocks in size and number. All the domain blocks are collectively called as domain pool. Size of the domain pool determines the complexity of encoding phase. Each range block is encoded based on affine similarity between the domain blocks. The best matched domain block for each range block is given by Absolute Value of Pearson's Correlation Coefficient. Regardless of various advantages offered by fractal compression, such as high speed, high bit rate, high decompression and resolution independence, the major disadvantage is the high computational cost of the coding phase. This paper proposes two methods to reduce the complexity of the image coding phase. The first method classifies the domain pool into three classes with Fisher's classification technique and in the second method, a specific number of blocks of one class are considered for Fast Fractal Image Compression. © 2014 IEEE.


Subramaniam L.,Dr. M.G.R. Educational and Research Institute | Sendilvelan S.,PERI Institute of Technology
European Journal of Scientific Research | Year: 2012

Centrifugal pump impellers are high speed rotating components vulnerable to vibrations resulting in the failure of the system pump eventually. A modal analysis of the impeller is, therefore, very important in the design and development of impellers, to prevent premature failure. In this paper, the dynamic characteristics of a radial impeller with different blade thicknesses ranging from 3mm to 5mm with increments of 0.5mm are analysed by the numerical method, FEA. The experimental modal testing of the impellers is then done to validate the FEA results. The results are discussed and conclusions drawn. © EuroJournals Publishing, Inc. 2012.

Loading PERI Institute of Technology collaborators
Loading PERI Institute of Technology collaborators