Thovalai, India
Thovalai, India

Time filter

Source Type

Linda C.H.,CSI Institute of Technology
Applied Soft Computing Journal | Year: 2011

Crack of the bone is a very serious medical condition. In medical applications, sensitivity in detecting medical problems and accuracy of detection are often in conflict. Computer detection of cracks can assist the doctors by flagging suspicious cases for closer examinations and thus improve the timeliness and accuracy. This paper presents the detailed image processing procedure including the grid formation, local thresholding, threshold value interpolation, segmentation using fuzzy index measure, background removal, and morphological filtering for the determination of infestation sites of a crack in X-ray image. The image processing procedure was tested with X-ray images of several types of crack bones. Additional tests and analyses were also performed using the developed algorithm on the X-ray images obtained with different image acquisition parameter. Compared to existing methods, this approach enhances the accuracy and reliability of proposed work. © 2011 Elsevier B.V.

Brabin T.A.,Csi Institute Of Technology | Nageswara Rao B.,Vikram Sarabhai Space Center
International Journal of Pressure Vessels and Piping | Year: 2011

An accurate prediction of the burst pressure of cylindrical vessels is very important in the engineering design for the oil and gas industry. Some of the existing predictive equations are examined utilizing test data on different steel vessels. Faupel's bursting pressure formula is found to be simple and reliable in predicting the burst strength of thick and thin-walled steel cylindrical vessels. © 2011 Elsevier Ltd.

Kesavan Nair N.,Csi Institute Of Technology
International Journal of Electrical Power and Energy Systems | Year: 2013

This paper presents the design and implementation of Power System Stabilizers in a multimachine power system based on innovative evolutionary algorithm overtly as Breeder Genetic Algorithm with Adaptive Mutation. For the analysis purpose a Conventional Power System Stabilizer was also designed and implemented in the same system. Simulation results on multimachine systems subjected to small perturbation and three phase fault radiates the effectiveness and robustness of the proposed Power System Stabilizers over a wide range of operating conditions and system configurations. The results have shown that Adaptive Mutation Breeder Genetic Algorithms are well suited for optimal tuning of Power System Stabilizers and they work better than conventional Genetic Algorithm, since they have been designed to work on continuous domain. This proposed Power System Stabilizer is demonstrated through a weakly connected three multi-machine test systems. © 2012 Elsevier Ltd. All rights reserved.

Ansalam Raj T.G.,Csi Institute Of Technology | Narayanan Namboothiri V.N.,Cochin University of Science and Technology
International Journal of Advanced Manufacturing Technology | Year: 2010

Determination of optimal cutting parameters is one of the most important elements in any process planning of metal parts. This paper presents a development of an improved genetic algorithm (IGA) and its application to optimize the cutting parameters for predicting the surface roughness is proposed. Optimization of cutting parameters and prediction of surface roughness is concerned with a highly constrained nonlinear dynamic optimization problem that can only be fully solved by complete enumeration. The IGA incorporating a stochastic crossover technique and an artificial initial population scheme is developed to provide a faster search mechanism. The main advantage of the IGA approach is that the "curse of dimensionality" and a local optimal trap inherent in mathematical programming methods can be simultaneously overcome. The IGA equipped with an improved evolutionary direction operator and a migration operation can efficiently search and actively explore solutions. The IGA approach is applied to predict the influence of tool geometry (nose radius) and cutting parameters (feed, speed, and depth of cut) on surface roughness in dry turning of SS 420 materials conditions based on Taguchi's orthogonal array method. Additionally, the proposed algorithm was compared with the conventional genetic algorithm (CGA), and we found that the proposed IGA is more effective than previous approaches and applies the realistic machining problem more efficiently than does the conventional genetic algorithm (CGA). © 2009 Springer-Verlag London Limited.

Franklin S.W.,CSI Institute of Technology | Rajan S.E.,Mepco Schlenk Engineering College, Sivakasi
Applied Soft Computing Journal | Year: 2014

Diabetic retinopathy (DR) is the major ophthalmic pathological cause for loss of eye sight due to changes in blood vessel structure. The retinal blood vessel morphology helps to identify the successive stages of a number of sight threatening diseases and thereby paves a way to classify its severity. This paper presents an automated retinal vessel segmentation technique using neural network, which can be used in computer analysis of retinal images, e.g., in automated screening for diabetic retinopathy. Furthermore, the algorithm proposed in this paper can be used for the analysis of vascular structures of the human retina. Changes in retinal vasculature are one of the main symptoms of diseases like hypertension and diabetes mellitus. Since the size of typical retinal vessel is only a few pixels wide, it is critical to obtain precise measurements of vascular width using automated retinal image analysis. This method segments each image pixel as vessel or nonvessel, which in turn, used for automatic recognition of the vasculature in retinal images. Retinal blood vessels are identified by means of a multilayer perceptron neural network, for which the inputs are derived from the Gabor and moment invariants-based features. Back propagation algorithm, which provides an efficient technique to change the weights in a feed forward network is utilized in our method. The performance of our technique is evaluated and tested on publicly available DRIVE database and we have obtained illustrative vessel segmentation results for those images. © 2014 Published by Elsevier B.V.

Franklin S.W.,CSI Institute of Technology | Rajan Dr. S.E.,Mepco Schlenk Engineering College, Sivakasi
International Journal of Bio-Science and Bio-Technology | Year: 2010

Personal Area Network for Intra-body communication using human body as the transmission medium enables wireless communication without transmitting radio wa es through the air. With the vision of transmitting data through the human body, several trials have been made to model the human body as communication channel through which cablefre transmission is achieved. Making use of human body as a transmission medium signal transmission offers new data communication scheme in biomedical monitoring systems. Such a new wireless data communication technology will offer substantially increased freedom for long-term risk patients. On body sensors in the form of intelligent band-aids monitor the human vital functions. Enabled by the intra-body communication capability of every on-body sensors, the recorded data will be transferred wireless through the body within the Body Area Network sensor nodes. Eventually, one single node will act as a central monitoring node and is connected by a traditional wireless link, e.g. blue tooth, to the remote hospital monitoring infrastructure. There, the data will be displayed or stored in the patient's record. Electronic data transfer over and through the human body has been proposed by research and industry as a promising technology for ultra low power wireless Body Area Networks.

Annlin Jeba S.V.,CSI Institute of Technology | Paramasivan B.,National Engineering College
European Journal of Scientific Research | Year: 2012

Wireless sensor networks are vulnerable to security attacks due to their unattended nature and deployment in hostile environment. Security attacks include false data injection, data forgery and eavesdropping. Adversaries can inject false data reports into the WSN through compromised nodes. The compromised nodes distort data integrity by injecting false data during data forwarding. The injected false data reports lead the en-route nodes and the base station to make false decision. Moreover, false decision depletes the energy of en-route nodes and the base station and creates threat to the lifetime of the sensor nodes. To detect and drop false data number of en-route filtering schemes have been developed. This paper review some of the existing en-route filtering schemes and analyses the performance of those en-route filtering schemes based on their filtering efficiency. Finally a case study about some of the en-route filtering scheme is provided and this provided the aspects for the designers to implement suitable scheme to defend against false data injection attack. © EuroJournals Publishing, Inc. 2012.

Annlin Jeba S.V.,Csi Institute Of Technology | Paramasivan B.,National Engineering College
Computers and Electrical Engineering | Year: 2013

Wireless sensor networks are networked systems that are deployed in an application specific region to sense the events of interest. The sensed event information has to be reported to the base station. When the event report is transmitted, adversaries can inject false event messages through compromised nodes on the path of data transfer. Falsified event messages when forwarded through en-route nodes lead to wastage of their limited energy. This study proposes a energy efficient multipath data transfer scheme to address the troubles caused by false data injection attack. This can be done by early detection and filtering of injected false data. Moreover, the multipath data transfer technique prevents the direct access of event information by a compromised en-route node. Simulations show that the proposed scheme could significantly improve the performance of false data filtering process without losing resiliency against node compromisation and data compromisation. © 2013 Elsevier Ltd. All rights reserved.

Aseer Brabin T.,Csi Institute Of Technology | Christopher T.,Vellore Institute of Technology | Nageswara Rao B.,Vikram Sarabhai Space Center
International Journal of Pressure Vessels and Piping | Year: 2010

Finite element analysis (FEA) has been carried out to obtain the elastic stress distribution at cylinder-to-cylinder junction in pressurized shell structures that have applications in space - vehicle design. To validate the finite element modeling and analysis results, three joint configurations, (viz., unfilleted butt joint with equal thickness, unfilleted butt joint with unequal thickness and filleted butt joint with equal thickness) having test results in open literature were considered. The peak stress values for these configurations obtained from FEA are close to that of test results. The peak stress value is found to reduce due to filleted butt joint as expected and also confirmed through test results. © 2010 Elsevier Ltd.

Umarani C.,Anna University | Basil Gnanappa S.,CSI Institute of Technology
International Journal of Earth Sciences and Engineering | Year: 2010

Results of quasi-static tests on quarter scale two-bay five-storey reinforced concrete frames, (i) a bare R.C.frame, (ii) R.C.frame infilled with clay brick masonry, (iii) R.C.frame infilled with confined clay brick masonry and (iv) R.C.frame infilled with confined thermocole are reported. The effectiveness of the infill-frame action is investigated in terms of stiffness, strength and hysteretic characteristics and compared with bare frame model. The strength, stiffness and energy absorption capacity of the infilled test units are much higher than those of the bare R.C.frame. The effect of using confined infill is discussed in resisting the lateral loads. A finite element software ANSYS has been used for the analysis. The experimental and analytical results compare well in the cases of R.C.frames with confined infill than those with unconfined infill. © 2010 CAFET-INNOVA TECHNICAL SOCIETY. All rights reserved.

Loading Csi Institute Of Technology collaborators
Loading Csi Institute Of Technology collaborators