DMI Engineering College

Aralvaimozhi, India

DMI Engineering College

Aralvaimozhi, India
Time filter
Source Type

Vijayan R.,University of Zagreb | Karthikeyan P.,University of Zagreb | Bharanichandar J.,University of Zagreb | Palanisamy R.,University of Zagreb | Thanka Geetha T.,DMI Engineering College
International Journal on Smart Sensing and Intelligent Systems | Year: 2017

This project is concerned to analyze and increase the efficiency of patrol inspection and thus reduces time consumption for inspection. Inspection is the process of checking whether the specification of the product meet the standard specification provided by the customer. Inspector takes more time for checking the parameter that meet the specification at all time than Checking the parameters that does not satisfy the customer specification which leads to rejection .Thus the inspector should inspect the parameter that increase the rejection or rework with more attention .on the whole this concept helps the inspector to improve the quality of the product by inspecting more components according to the frequency of the component.

Bommy B.,Csi Institute Of Technology | Raj A.A.,Dmi Engineering College
Journal of Circuits, Systems and Computers | Year: 2017

In the process of image acquisition and transmission, data can be corrupted by impulse noise. This paper presented the removal of impulse noise in medical image by using Very Large Scale Integrated circuit (VLSI) implementation. The Low Cost Reduced Simple Edge Preserved De-noising (LCRSEPD) technique is introduced using Low Area Carry Select Adder (CSLA) to remove the salt and pepper noise instead of normal adder. Thus, LCRSEPD technique preserves visual performance and edge features in terms of quality and quantitative evaluation. By optimizing the architecture, low cost RSEPD can achieve low computational complexity that will reflect in area, power and delay. Compared to the previous VLSI implementations, the LCRSEPD implementation with CSLA adder has achieved good medical image quality and less hardware cost due to the reduction of area, power and delay. © 2018 World Scientific Publishing Company

Raj A.A.,DMI Engineering College
Eurasip Journal on Wireless Communications and Networking | Year: 2016

Multicarrier complementary-coded code division Multiple Access (MC CC-CDMA) is becoming an attractive multiple access technique for high data rate transmission in future wireless communication systems. MC CC-CDMA systems transmitting over frequency-selective channels suffer from multiple access interference (MAI) owing to non-ideal correlation properties of complementary codes (CC). MC CC-CDMA with equalization has recently gained much attention for its ability to offer an excellent performance than traditional systems in frequency-selective fading channels. In this paper, the authors present an analytical study and investigation of MC CC-CDMA downlink system using different combining schemes. The use of parallel interference cancellation (PIC) under frequency-selective Nakagami-m fading channels is also analyzed. A comparison among different combining schemes is provided to show the impact of PIC with minimum mean square error combining (MMSEC) and maximal ratio combining (MRC) on the performance of MC CC-CDMA system. The analytical and simulation results show that the combination of general combining schemes with PIC provides an efficient solution to suppress MAI in downlink MC CC-CDMA system than conventional MC-CDMA systems using Walsh codes under frequency-selective channels. © 2016, Judson and Raj.

Drowsiness is considered as a significant risk factor that contributes to large number of accidents. This study, focuses on methodologies developed for counteracting its effects with very accurate classification techniques categorizing the different drowsy states and alerting the person at definite instants. An optimal Bootstrap technique is applied to features extracted by Daubechies Wavelet Transform (DWT) and the drowsy states are classified using Neural Network (NN) classifier. The Receiver Operating Characteristics (ROC) curve shows the classification accuracy and the computation time is also calculated. In order to improve the efficiency of the proposed method, Fractional Fourier Transform (FrFT) based feature extraction is implemented with ABC (Artificial Bee Colony) for optimization and classification done using NN and Sparse classifiers. The three methods exhibit high efficiency in improving the system's performance in terms of accuracy F1 score and computation time. A comparative study of the three methods is also done with the latter showing better results. © Medwell Journals, 2016.

Stony M.J.,DMI Engineering College
Journal of Chemical and Pharmaceutical Sciences | Year: 2015

In this paper, a zero-voltage transition PWM synchronous buck converter, which is designed to function at low output voltage and high efficiency typically necessary for portable systems. To make the DC-DC converter efficient at lower voltage, synchronous buck converter is an obvious choice because of lower conduction loss in the diode. The high-side IGBT is subjugated by the switching loses and it is eliminated by the soft switching technique. Additionally, the resonant auxiliary circuit deliberate is also devoid of the switching losses. The suggested procedure ensures an efficient converter. Theoretical analysis, computer simulations are presented to explain the proposed schemes.

Gnana Jebadas D.,DMI Engineering College | Albert Raj A.,DMI Engineering College
Biomedical Research (India) | Year: 2017

White Matter (WM) atrophy is a good marker of cognitive decline and progression of Alzheimer’s disease (AD). Precise segmentation of WM from structural Magnetic Resonance (MR) images is pivotal in the accurate quantification of WM atrophy. An image processing framework for the accurate segmentation of WM is proposed in this article. The proposed framework comprises background removal, restoration of the image with Non-Local Means (NLM) Filter, enhancement with Contrast Limited Adaptive Histogram Equalization (CLAHE), skull stripping and k-Means segmentation with histogram guided initialization. The framework exhibited a mean Dice Similarity Index (DSI) of 87.27% with a standard deviation of ± 5.74, on axial plane MR images of T1 series, from 30 subjects, against manual segmentation as ground truth. © 2017, Scientific Publishers of India. All rights reserved.

Shiny Angel T.S.,SRM University | Rodrigues P.,DMI Engineering College
International Journal of Applied Engineering Research | Year: 2015

Software size estimation is a key factor to determine the amount of time and effort needed to develop software systems, and the e-learning systems are no exception. The success of any software project largely depends on effective estimation of project effort, time and cost. Estimation helps in setting realistic targets for completing the project. The basic element for estimating all is size. The software industry uses various sizing techniques they are Lines of code, Function points, feature points, use case points, object points, internet points, etc. are not effectively supported for determine the size of E-Learning system that affect all estimates. The wrong estimates lead incompleteness, loss and customer dissatisfaction. This paper presents the popular sizing techniques and their inabilities in sizing and also the necessities of new sizing approach for E-Learning system. © Research India Publications.

Amirthasaravanan A.,Tamil University | Rodrigues P.,DMI Engineering College | Sudhesh R.,Tamil University
Asian Journal of Information Technology | Year: 2016

In recent years, web realm has Service-Oriented Architectures (SOA) as the primary standard for IT infrastructures. Indeed with the commencement of service oriented architecture, web services have gained absurd progression. Web service discovery has become progressively more substantial. Discovering the most suitable web service from huge collection of web services is very crucial for the successful implementation of the web applications. In web service discovery automation, during matching, Quality of Service (QoS) attributes are continuously need to deem. Aiming at this, Bio-inspired algorithms for semantic web services were initiated. Bio-inspired algorithm is a meta heuristics method that imitates the nature in order to unravel optimization problem and evaluates the analysis of some popular bio-inspired optimization algorithm systematically. This paper proposes a new bio inspired algorithm which is inspired from Slime Mold. Slime mold is a fungus. Slime molds are habitually observed when they form large colonies on mulch around trees or shrubs. They may initially appear as a slimy mound or crowd. Slime mold has a unique intelligence to find the pray and it's often unsighted. The character of slime mold is inspired and it solves the problem of complex and composite web services and produces optimized web services. © Medwell Journals, 2016.

Reena Daphne R.,Cape Institute of Technology | Albert Raj A.,DMI Engineering College
Procedia Engineering | Year: 2012

Drowsiness is considered as a significant risk factor that contributes to large number of accidents. Therefore a method is developed for counteracting its effects and hence a very accurate classification of drowsiness is needed so as to categorize the different states of drowsiness and thus the person can be alerted at definite instants. The quality of extracted features is assessed on datasets collected from various subjects irrespective of age, sex and also the start and stop of the signal monitoring time of the subjects. An optimal Fuzzy Entropy Mutual Information(FEMI) methodology is implemented into Wavelet Packet Transform(WPT) decomposition so as to extract the features and the various instants of drowsiness of the subject is obtained. The Receiver Operating Characteristics (ROC) curve shows the classification accuracy of the SVM. © 2012 Published by Elsevier Ltd.

Sugitha G.,Cape Institute of Technology | Albert Raj A.,DMI Engineering College
International Journal of Applied Engineering Research | Year: 2014

In modern generation the applications of wireless adhoc networks are increasing in use. Due to the random mobility of nodes the adhoc network may be partitioned. A fault tolerant network can be achieved by avoiding the communication network disconnections. So identification of critical nodes in the network is an important problem in wireless adhoc network. This paper presents a novel critical node identification algorithm by constructing BFS tree. The metrics for evaluation has been considered are communication overhead, throughput and jitter. © Research India Publications.

Loading DMI Engineering College collaborators
Loading DMI Engineering College collaborators