Time filter

Source Type

Nandakumar L.,Model Engineering College | Nandakumar P.,Cochin University of Science and Technology
2013 International Conference on Control Communication and Computing, ICCC 2013 | Year: 2013

Spirometry is the most commonly performed Pulmonary Function Test (PFT) which is used to distinguish obstructive from restrictive lung diseases. This paper presents the basic system requirements for an automatic pulmonary disease classification system based on spirometric signal using a novel algorithm. The software of the system extracted features from the digitized spirogram waveform values and classified the disorders with minimum uncertainty. Classification was done by generating more data from the available trials/ tests using an Evolutionary Approach called Genetic Algorithm (GA) and without using any prediction equations as done by the conventional spirometers. Thus GA ensures reduction in the number of trials to be performed by the patient there by reducing patient stress. The hardware requirements for implementation on an embedded system are also presented. On an average, the accuracy was found to be 95.74%. © 2013 IEEE.


Mini M.G.,Model Engineering College
Proceedings of the 2nd Kuwait Conference on e-Services and e-Systems, KCESS'11 | Year: 2011

In this paper, we present a novel approach to the classification of digital mammograms into normal and abnormal classes for breast cancer detection. First, the structures in mammograms produced by normal glandular tissue of varying density are eliminated using a Wavelet Transform (WT) based local average subtraction. Then the linear markings formed by the normal connective tissue are identified and removed. Any abnormality that may exist in the mammogram is therefore enhanced in the residual image, which makes the decision regarding the normality of the mammogram much easier. Features derived from the residual images are applied to a Probabilistic Neural Network (PNN) for classification. © 2011 ACM.


Devi P.S.A.,Model Engineering College | Mini M.G.,Model Engineering College
Proceedings - 2012 International Conference on Advances in Computing and Communications, ICACC 2012 | Year: 2012

Computed radiographic images are usually large in size. So for storage and transmission the image should be compressed. This paper proposes a method in which image compression is achieved by applying linear prediction on wavelet coefficients. The image is decomposed up to four levels using wavelet transform and on the detail coefficients prediction is performed. The compressed image comprises of predictor coefficients and retained coefficients. Performing linear prediction on them recovers the decompressed image. The scheme is evaluated using subjective and objective criteria and found to suit Computed Radiographic (CR) images. © 2012 IEEE.


Arya Devi P.S.,Model Engineering College | Mini M.G.,Model Engineering College
Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering | Year: 2012

Each year, terabytes of image data- both medical and non medical- are generated which substantiates the need of image compression. In this paper, the correlation properties of wavelets are utilised in linear predictive coding to compress images. The image is decomposed using a one dimensional wavelet transform. The highest level approximation and a few coefficients of details in every level are retained. Using linear prediction on these coefficients the image is reconstructed.With less predictors and samples from the original wavelet coefficients compression can be achieved. The results are appraised in objective and subjective manner. © 2012 ICST Institute for Computer Science, Social Informatics and Telecommunications Engineering.


Rajan R.,Model Engineering College | Deepa B.,Naval Physical and Oceanographic Laboratory | Bhai D.S.,Naval Physical and Oceanographic Laboratory
Procedia Computer Science | Year: 2016

This paper presents a reliable method for target vessel identification in passive sonar by exploiting the underlying periodicity of propeller noise signal, using the principles of cyclostationarity. In conventional signal processing methods, random signals are treated as statistically stationary and the parameters of the underlying physical mechanism that generates the signal would not vary in time. However, for most manmade signals, some parameters vary periodically with time and this requires that random signals be modeled as cyclostationary. In the field of sonar, the propeller noise signal generated by underwater vessels is cyclostationary. As a ship propagates in the sea, noise generated during the collapse of cavitation-induced bubbles are modulated by the rotating propeller shaft and this results in characteristic amplitude modulated random noise signal, which can be detected using passive sonar. Processing these signals, the number of blades and the shaft frequency of the propeller can be identified. In this work, cyclostationary processing technique is introduced for processing propeller noise signal and it is observed to provide better noise immunity. A detailed comparison with the conventional DEMON processing is also presented. © 2016 The Authors. Published by Elsevier B.V.


Muhammad P.,Model Engineering College | Devi S.A.,Model Engineering College
Procedia Computer Science | Year: 2016

This paper presents a MEMS accelerometer based handheld embedded device and its associated dynamic time warping (DTW) based algorithm for recognizing hand writing gestures. Device can be used to draw gestures for English lower case letters, Arabic numerals in their own style and speed. Furthermore the proposed device can detect different direction movement such as left, right, up, down, push and pull for employing video game and mobile game control. The accelerometer signals are processed within the device itself and result of recognition is transmitted via Bluetooth to smart device such as computer, smart phone, tablets etc. Furthermore we have introduced a novel method of fast and memory efficient implementation of DTW in embedded domain. Also we have developed an effective motion detection method based on adaptive mean value calculation of accelerometer signals also we introduced an effective template selection criterion. The effectiveness of proposed system and associated algorithm were validated through various experiments. © 2016 The Authors. Published by Elsevier B.V.


Varghese S.,Model Engineering College | Sinchu P.,Naval Physical Oceanographic Laboratory | Subhadra Bhai D.,Naval Physical Oceanographic Laboratory
Procedia Computer Science | Year: 2016

This paper presents an effective solution to the problems of multi-target tracking in passive sonar. Since bearing information alone is used, target crossing problems arises in passive sonar. Nearest Neighbor Joint Probabilistic Data Association (NNJPDA) is employed for the information processing. Further a prediction mechanism is used, where the track bearing depends only on the predicted value not on the measurements. This leads to the correct assignment of measurements with the track in the clutter and thereby avoids the track loss. The state estimation is then refined by Kalman filtering based on the corrected measurements from the NNJPDA technique. Thus accurate and continuous track is maintained. © 2016 The Authors. Published by Elsevier B.V.


Anoop T.R.,Model Engineering College | Mini M.G.,Model Engineering College
International Journal of Biometrics | Year: 2015

Fingerprint alteration is a major threat to automatic fingerprint identification systems, especially in boarder security control system. A Hough transform-based method for detection and classification of altered fingerprint is presented here. Altered fingerprints consists of huge amount of broken ridges due to different process used for making alteration and this in turn causes large number of ridge ending. The amount of ridge endings is different in different types of altered fingerprints. Hough transform-based method proposed in this paper utilises the variation in ridge ending density as a feature for detection and classification of altered fingerprints. The ridge end points in normal and altered fingerprints are collinear even though they are distributed randomly in the image space. Due to the variation of ridge ending density, the number of collinear ridge end points varies with respect to normal and different types of alteration. Making use of this, a threshold is selected in the Hough accumulator to perform detection and classification of fingerprint alteration. A method for the classification of scar present in altered and normal fingerprints is also proposed here. © 2015 Inderscience Enterprises Ltd.


Mathew J.,College of Engineering, Trivandrum | Philip P.,Model Engineering College
2015 International Conference on Advances in Computing, Communications and Informatics, ICACCI 2015 | Year: 2015

India is a populous, multi-lingual, multi-cultural developing country marred by inherent deficiencies in its Pharmaceutical & Healthcare sector. On one hand the problem of counterfeit pharmaceutical drugs is on the rise, whereas on the other hand the average common man is being financially & medically exploited by authorized / un-authorized doctors with their overdose of medical prescriptions, with an added risk of the patient, skipping part of this complex medication regimen. To mitigate these issues currently prevailing in India, we propose a Cloud-based Integrated Medication Management System. As a precursor to it, a Web-based Inpatient Medication Management System for hospitals is being developed and the preliminary results of the same is outlined in this short paper. This is just a concept which takes advantage of the rapidly growing cloud based networking infrastructure along with the increased penetration of internet in India. The paper also sheds light on the functional details of the proposed concept and its potential impact on the society. © 2015 IEEE.


Prameela B.,AdiShankara Institute of Engineering and Technology | Jagadeesh Kumar P.,Model Engineering College
Proceedings - 2013 3rd International Conference on Advances in Computing and Communications, ICACC 2013 | Year: 2013

A Low Noise Amplifier (LNA) based on NEC 0.3μm GaAs MESFET technology has been designed with a modified cascode configuration which makes use of two common source transistors. In the 2-3GHz range, the designed LNA has a noise figure less than 0.65dB, maximum intrinsic gain of 18.4dB, P1dB of 2d Bm, IIP3 of - 1.6dBm and 20mW power consumption at a supply voltage of 3V. The dynamic range of the designed LNA is 60.6dB. The characteristic impedance is chosen as 50Ω. The custom layout of the proposed LNA has been designed. © 2013 IEEE.

Loading Model Engineering College collaborators
Loading Model Engineering College collaborators