Time filter

Source Type

Ramanathapuram, India

Dhanasekaran R.,Syed Ammal Engineering College
Journal of Imaging Science and Technology | Year: 2013

Segmentation of tumors in medical images is not only of high interest in serial treatment monitoring of 'disease burden' in oncologic imaging, but is also gaining popularity with the advance of image guided surgical approaches. Magnetic resonance images are widely used in the diagnosis of brain tumors. In this article, an automatic tumor detection and classification system is presented, which focuses on the structural study on both tumorous and normal tissue. The proposed system consists of the following steps: (i) pre-processing, (ii) feature extraction using an enhanced texton co-occurrence matrix and (iii) classification. In classification, a fuzzy logic based support vector machine is used to classify the experimental images into normal and abnormal. The obtained experimental results show that the proposed brain tumor detection approach is more robust than other neural network based classifiers, feed forward neural network and radial basis function, in terms of sensitivity, specificity and accuracy. © 2013 Society for Imaging Science and Technology. Source

Karthikeyan J.,Velammal College of Engineering and Technology | Dhana Sekaran R.,Syed Ammal Engineering College
International Journal of Electrical Power and Energy Systems | Year: 2011

The objective of the paper is to build a simple current controlled modulation technique for brushless dc motors. In electric traction and most other applications, a wide range of speed and torque control of the electric motor is required. The dc machine fulfills these requirements, but it requires constant maintenance. In the brushless permanent magnet motors, they do not have brushes and so there will be lesser maintenance. Brushless dc motors are widely used in applications which require wide range of speed and torque control because of its low inertia, fast response, high reliability and less maintenance. This current controlled technique is based on the generation of quasi-square wave currents using only one controller for the three phases. The current control strategy uses a triangular carrier for the power transistors which is simpler and more accurate than any other options. The advantages of this technique are: (a) The stator currents are completely characterized by their maximum amplitude. (b) The three phases are controlled with the same dc component, and then the phase currents are kept at exactly the same magnitude Imax. (c) The dc link current measurement is not required. (d) Phase currents are kept balanced and phase over currents are eliminated. © 2011 Elsevier Ltd. All rights reserved. Source

Dhanasekaran R.,Syed Ammal Engineering College
International Journal of Imaging Systems and Technology | Year: 2013

Segmentation is the process of labeling objects in image data. It is a decisive phase in several medical imaging processing tasks for operation planning, radio therapy or diagnostics, and widely useful for studying the differences of healthy persons and persons with tumor. Magnetic Resonance Imaging brain tumor segmentation is a complicated task due to the variance and intricacy of tumors. In this article, a tumor segmentation scheme is presented, which focuses on the structural analysis on both tumorous and normal tissues. Our proposed method hits the target with the aid of the following major steps: (i) Tumor Region Location, (ii) Feature Extraction using Multi-texton Technique, and (iii) Final Classification using support vector machine (SVM). The results for the tumor detection are validated through evaluation metrics such as, sensitivity, specificity, and accuracy. The comparative analysis is carried out by Radial Basis Function neural network and Feed Forward Neural Network. The obtained results depict that the proposed Multi-texton histogram and support vector machine based brain tumor detection approach is more robust than the other classifiers in terms of sensitivity, specificity, and accuracy. Copyright © 2013 Wiley Periodicals, Inc. Source

Marimuthu P.,Syed Ammal Engineering College | Chandrasekaran K.,Alagappa Chettiar College of Engineering And Technology
International Journal of Materials and Product Technology | Year: 2012

Goal of the metal cutting industries is to manufacture high quality products in short time. Surface quality is one of the most specified customer requirements in machining products. Surface quality of roughness is critical to the functional ability of machined components. Austenitic stainless steels (AISI 316) are generally regarded as more difficult to machine material due to their high strength, ductility and high work hardening tendency. Surface roughness (SR) is a vital role requirement in determining the surface quality of the product. The minimisation of SR is essential for the achievement of high quality. In this paper is to analyse the SR produced by CNC turning process on AISI 316 by different cases of coated cutting tool used at dry conditions. Multi-layered coated with TiCN+Al 2O 3 for first case and single-layered coated with (Ti, Al)N for second case. Experiments were carried out by using Taguchi's L27 orthogonal array. The effect of cutting parameters on SR was evaluated and optimum cutting conditions for minimising the SR was determined. Analysis of variance (ANOVA) was used for identifying the significant parameters affecting the responses. Copyright © 2012 Inderscience Enterprises Ltd. Source

Senthil Rajan A.,Mohamed Sathak Polytechnic Kilakarai | Raja K.,Anna University | Marimuthu P.,Syed Ammal Engineering College
Energy Conversion and Management | Year: 2014

In this field a multi basin solar still is, used to heighten the productivity. The concept of integrating the multi basin still with biomass heat source is introduced in this research area. In the multi basin still heat exchanger is placed at the bottom end of the watershed region. The heat exchanger is connected to the biomass boiler heat source to create heat energy. This system increases the water temperature in the sword and also increases the productivity in the blade. The upper watershed is separated into small stepped basins. So the flat plate collector and stepped basin are used to increase the turnout in this work. The heat from lower basin is used by the upper basin for desalination. Experiments are conducted with various water depths. In this work the solar still behaves like a capacitor. A conventional still is fabricated and run parallel with the experimental setup for comparison. Sensible heat storage materials such as cement blocks, sand, glass eggs are added to the tail end and top basins to increase water temperature. Latent heat storage materials such as water, wax are introduced in the material body of small pellets to increase productivity. Biomass such as wood, wood wastes, palm wastes is tried in this workplace. A higher productivity is obtained for sensible storage materials when compared to latent heat storage. Theoretical analysis is performed by using RSM (response surface methodology) well agrees with experimental values. The efficiency of the system is compared with conventional still. Experiments are conducted in once flow mode, continuous stream mode and solar modes. Output from RSM are compared with experimental values for error analysis. © 2014 Elsevier Ltd. All rights reserved. Source

Discover hidden collaborations