Swanirbhar Majumder | North Eastern Regional Institute of Science and Technology (original) (raw)

Books by Swanirbhar Majumder

Like all human beings have different fingerprints, they have differently shaped hearts. The ECG, ... more Like all human beings have different fingerprints, they have differently shaped hearts. The ECG, or the electrocardiogram, is the signature of the movements by the human heart, and thus, all ECGs are different. ECG biometrics is an area of biometric identification by the usage of the ECG features in time or frequency/transform domain. Along with these, if the present-day cloud servers also come to play, one has an efficient and cost-effective ECG-based biometric system using cloud computing to provide real-time identification via a secure connection. This chapter focuses on ECG-based biometrics with an overview at the end about how cloud-based big databases of stored ECG signatures and cloud servers can play a part in it.

: Handbook of Research on Computational Intelligence for Engineering, Science, and Business

These days, for the copyright protection and security of multimedia data in this age of the tech-... more These days, for the copyright protection and security of multimedia data in this age of the tech-savvy world, watermarking is a very important technique. Moreover, with the inclusion of biometrics for the watermarking schemes, the concept of “something you are” is included in the watermark and/or cover image. This thereby increases the security intensity in the multimedia data. And to give a glimpse of the technique the concepts of Watermarking, biometric and watermarking using biometrics is discussed. Finally, a particular case of real time watermarking of data using biometric is discussed by specifying a practical example.

Delay in cardiac repolarization causes ventricular tachyarrhythmias as well as Torsade de pointes... more Delay in cardiac repolarization causes ventricular tachyarrhythmias as well as Torsade de pointes (TdP). A feature of TdP is pronounced prolongation of the QT interval in the supraventricular beat preceding the arrhythmia. TdP can degenerate into ventricular fibrillation, leading to sudden death. Thus QT interval measurement and regular verification of the interval is important for analyzing cardiac health. A novel and simple approach to determine the duration of ventricular repolarization, i.e. QT interval of a recorded ECG wave is proposed here. Here a fully automatic method for measurement of QT interval is proposed, i.e. by five-point differentiation of ECG data and noting the slope change of the resulting graph. Points with zero slopes were considered as the end of respective waves. The algorithm is tested with physionet database. So this thesis contains the basics of ECG DATA ANALYSIS in the TIME PLANE with MATLAB based Programs and results all based on the 2006 Challange of Computers in Cardiology now called Computing in Cardiology (http://www.cinc.org/. It is benifical for the firstimers working in ECG Signal Processing.

Presently the WWW phenomenon has brought the world in to the personal computer. Digital media is ... more Presently the WWW phenomenon has brought the world in to the personal computer. Digital media is thereby given high priority. But this has increased the frequency of security breach of intellectual properties. Therefore copyright protections and content integrity verification are highly recommended. What we need is newer data hiding techniques that must be imperceptible, robust, highly secured, etc. Digital image watermarking is one of the ways that is resilient to various attacks on the image based digital media where data authentication is done by embedding of a watermark in image characteristics. This work incorporates singular value decomposition (SVD) based image watermarking. Here unlike previous work done by researchers, error control coding (ECC) and artificial neural networks (ANN) for the authentication purposes have been used. ECC and ANN increase the robustness of the method against malicious attacks.

Compression of data in any form is a large and active field as well as a big business. Image comp... more Compression of data in any form is a large and active field as well as a big business. Image compression is a subset of this huge field of data compression, where the compression of image data is taken specifically. Wavelet transform is one of the popular transforms used in this field and its lifting based variant has become very popular for its easy hardware implementability. For images, the inter-pixel relationship is highly non-linear and unpredictive in the absence of a prior knowledge of the image itself. The back propagation based neural network (BPNN) takes into account the psycho visual features, dependent mostly on the information contained in images. Thereby preserving most of the characteristics of the data while working in a lossy manner and maximize the compression performance. So here image compression based on the lifting wavelet transform is taken in to account along with the BPNN based adaptive technique. Firstly by varying quantization levels for the lifting wavelet transform and number of hidden neurons for the BPNN an optimized compression percentage is reached for suitable adaptive hardware implementation of image compression with both the techniques.

We present a comparative study for correlation coefficients of three different, but popular trans... more We present a comparative study for correlation coefficients of three different, but popular transforms of audio signals i.e. Fast Fourier Transform (FFT), Cepstrum and Discrete Cosine Transform (DCT). But this study is done keeping into mind an important application, the heart sound analysis or heart auscultation analysis which manually is done by doctors for disease identification. We present a very simple automated software based approach for first detecting whether the heart is normal or abnormal and then identifying the disease if within the range of diseases for which it has been trained. Here our application has been trained for only three heart diseases, Mitral Regurgitation, Mitral Stenosis, and Splits. Further training might enable our application for identifying other diseases as well. We get better the detection accuracy with the increase of training data. We have taken the help of FBS (Frontiers in Bioscience) online data base for heart sounds for this purpose, and have used their .wav format of heart sound files for our analysis. But along with these we also found out that though Cepstrum is a very important transform for speaker recognition and other audio based application, but here in case of heart sound analysis it is not very user friendly for analysis.

Papers by Swanirbhar Majumder

This paper presents the prediction of ECG features using artificial neural networks from respirat... more This paper presents the prediction of ECG features using artificial neural networks from respiratory, plethysmographic and arterial blood pressure(ABP) signals. One cardiac cycle of ECG signal consists of P-QRS-T wave. This process of feature prediction determines the amplitudes and intervals in the ECG signal for subsequent analysis. The amplitude and interval values of ECG signal determine the functioning of heart for every human. This process is based on artificial neural network (ANN) and other signal analysis technique. In this process a feed forward multilayer perceptron network has been designed using back propagation algorithm. ECG signal is predicted from this network from the application of the respiratory, plethysmographic and ABP data to its input layer. For analyzing the data, a five point differentiation is done on the signal, so as to note the slope change of the resulting graph. Points with zero slopes were considered as the end of respective waves. The algorithm is tested with physionet database. The training and simulation results of the network have been obtained from Matlab7® software.

In this age of cloud computing, androids and smart phones the popularity of digital media has rea... more In this age of cloud computing, androids and smart phones the popularity of digital media has reached heights that have never been imagined. This is due to the efficient and omnipresent internet connectivity. So the copyright protection of intellectual properties and multimedia data has become a necessity for prevention of illegal copying and content integrity verification. Thus latest digital watermarking techniques that satisfy the requirements of imperceptibility, robustness, capacity, and security are being developed time to time. That’s why everyday newer techniques are being employed for the same. Here we present a novel method of digital image watermarking using singular value decomposition (SVD) and Gene Expression Programming (GEP). The popular wavelet based watermarking techniques have been coupled with the GEP which helps in providing a robust watermarking scheme.

The core target of this paper is to estimate human age automatically through facial image analysi... more The core target of this paper is to estimate human age automatically through facial image analysis. In this research study we put forward a system constructed on the basis of Gene Expression Programming (GEP) to estimate human ages using face features. Gene expression programming (GEP) is a handy tool to find out functions. Due to prompt developments in machine vision and computer graphics, age estimation through faces have turn out to be most dominant issues now a days due to their widespread applications in real world, such as safety control, investigation monitoring, biometrics, scientific art, automated client relationship management and cosmetology. As it is difficult to estimate the actual age, our system is going to estimate the ages within certain ranges. Total age range is classified into four classifications which differentiate the individual's oldness in relation with age. Our proposed approach has been initialized with GEP and then developed and tested using MATLAB. A public data set, FG-NET was used to develop the system. The quality of the proposed system for image-based age estimation is shown by broad experiments on the available database of FG-NET. To assess the performance of our system, we have done a relative study based on various parameters of GEP and found significant results.

Watermarking with biometrics has been proposed as a line of defense in the protection of IPR and ... more Watermarking with biometrics has been proposed as a line of defense in the protection of IPR and DRM. Robust watermarking of biometric information of the user in the host data may be used for this purpose. Fingerprints are the most popular and non- invasive biometric data used most widely. Here a process of embedding fingerprints data using a novel method of empirical mode decomposition (EMD) and gene expression programming (GEP) together is provided. The watermarking algorithm provided uses singular value decomposition (SVD) and lifting based discrete wavelet transform (DWT). The method provided is secure, robust and imperceptible form of watermarking. This watermarking technique has the advantage of using SVD and lifting based DWT which do not involve convolution thereby being easily implementable on hardware.

These days, with technological advancement, it is very easy for miscreants to produce illegal mul... more These days, with technological advancement, it is very easy for miscreants to produce illegal multimedia data copies. Various techniques of copyright protection of free data are being developed daily. Digital watermarking is one such technique, where digital embedding of the copyright information/watermark into the data to be protected. The two major ways of doing so are spatial domain and the robust transform domain. In this study, method for watermarking of digital images, with biometric data is presented. The usage of biometric instead of the traditional watermark increases the security of the image data. The biometric used here is iris. After the retinal scan, it is the most unique biometric. In terms of user friendliness in extracting the biometric, it comes after fingerprint and facial scan. The iris biometric template is generated from subject's eye images. The discrete cosine values of templates are extracted through discrete cosine transform and converted to binary code. This binary code is embedded in the singular values of the host image's coefficients generated through wavelet transform. The original image is thus firstly applied with the discrete wavelet transform followed up by the singular value decomposition of the subband coefficients. The algorithm has been tested with popular attacks for analysis of false recognition and rejection of subjects.

Word level Speech recognition is the process of automatic extracting and determining linguistic i... more Word level Speech recognition is the process of automatic extracting and determining linguistic information Conveyed by a
speech wave using computers.A successful speech detection system can helpful in many applications. Study of acoustical cues of Galo and
Adi language is main theme. The Galo and Adi tribe belongs to the Sino-Tibetan family of languages. The state of Arunachal Pradesh
has evolved a conspicuous dialect that distinguishes them from the rest of the tribes. A further classification can be based on the
"dialect" of the language. The variations of Galo and Adi spoken in these tribe differ from each other in intonation, sentence formation
and word usage.

With the daily advancement of technology, copyright protection of al types of digital media has b... more With the daily advancement of technology, copyright protection of al types of digital media has become an
important isue. Thus to aid the copyright protection digital watermarking has emerged as solution to this problem. In
this paper a new digital image watermarking scheme is proposed which combines Singular Value Decomposition (SVD)
and its multiresolution variant. Tests have ben undergone to check the proposed scheme for robustnes and
imperceptibilty. The scheme has ben compared with 3 previously standard schemes with respect to normalized
corelation coeficient value of detected watermark.

With the daily advancement of technology, copyright protection of all types of digital media has ... more With the daily advancement of technology, copyright protection of all types of digital media has become an important issue. Thus to aid the copyright protection digital watermarking has emerged as solution to this problem. In this paper a new digital image watermarking scheme is proposed which combines Singular Value Decomposition (SVD) and its multiresolution variant. Tests have been undergone to check the proposed scheme for robustness and imperceptibility.

This paper presents speaker recognition system with two popular multivariate tools that is Princi... more This paper presents speaker recognition system with two popular multivariate tools that is Principal Component Analysis (PCA) and Independent Component Analysis (ICA). The proposed approach evaluates the performance of such a speaker recognition system when trained and used in noisy environments. The two algorithms for PCA and ICA have been implemented in software keeping track of speech signal processing and recognition traits. The respective algorithms investigate the robust ability of PCA and ICA in regard of speaker recognition. The implementation, testing and comparison of the two algorithms have been carried out on real-time speaker database collected from fellow students of the department, via low cost lowquality PC microphones. It was found that application of ICA improved the performance of the speaker recognition model when compared to PCA, but with higher computation time. Experimental results show that use of ICA enabled extraction of higher order statistics thereby capturing speaker dependent statistical cues in a recognition system based on low resolution voice data collected via low cost microphones in noisy environments.

: Handbook of Research on Computational Intelligence for Engineering, Science, and Business

In this paper a new watermarking scheme is proposed which combines Singular Value Decomposition (... more In this paper a new watermarking scheme is proposed which combines Singular Value Decomposition (SVD) and its multiresolution form (MR-SVD).The experimental results obtained through the proposed scheme establish the fact that the scheme yields better PSNR value thereby providing good imperceptible and robustness against various attacks. Both MRSVD and SVD are based on matrix operation, so their combination avoids the convolution function (as in the case of DWT) which involves a lot of resources.

Journal of Biomedical Science and Engineering, 2009

Here we present a method of QT interval measurement for Physionet's online QT Challenge ECG datab... more Here we present a method of QT interval measurement for Physionet's online QT Challenge ECG database using the combination of wavelet and time plane feature extraction mechanisms. For this we mainly combined two previous works one done using the Daubechies 6 wavelet and one time plane based with modifications in their algorithms and inclusion of two more wavelets (Daubechies 8 and Symlet 6). But found that out of these three wavelets Daubechies 6 and 8 gives the best output and when averaged with the interval of time plane feature extraction method it gives least percentage of error with respect to the median reference QT interval as specified by Physionet. Our modified time plane feature extraction scheme along with the wavelet method together produces best results for automated QT wave measurement as its regular verification is important for analyzing cardiac health. For the V2 chest lead particularly whose QT wave is of tremendous significance we have tested on 530 recordings of Physionet. This is because delay in cardiac repolarization causes ventricular tachyarrhythmias as well as Torsade de pointes (TdP). A feature of TdP is pronounced prolongation of the QT interval in the supraventricular beat preceding the arrhythmia. TdP can degenerate into ventricular fibrillation, leading to sudden death.

Digital media is a craze these days. With the present day Internet connectivity the world has bec... more Digital media is a craze these days. With the present day Internet connectivity the world has become smaller. The copyright protections of intellectual properties have become a necessity for prevention of illegal copying and content integrity verification. Newer data hiding techniques that satisfy the requirements of imperceptibility, robustness, capacity, or data hiding rate and security of the hidden data etc. are being developed. Therefore the preference to go for digital image watermarking, to show resiliency against various unintentional or deliberate attacks has increased. Watermarking is a method of data authentication by embedding a watermark in image characteristics with expectation. Here in this work, this is done using a mathematical tool called the singular value decomposition (SVD). Earlier SVD had been used individually, as a tool for watermarking of digital media, but this work incorporates error control coding to it, by a novel zig-zag scan operation on pixels done before coding, thereby increasing the robustness. This work here by focuses on using both of them together to provide a robust technique developed for protection of the intellectual property against the popular malicious attacks. The algorithm is later applied and tested on the standard checkmark techniques practically by attacking the watermarked image against standard simulated attacks and recovering the watermarked logo from it.

The alteration, repackaging, and redistribution of multimedia content like image, video, audio, e... more The alteration, repackaging, and redistribution of multimedia content like image, video, audio, etc. poses a serious threat to both national security and commercial markets. Presently with the growing popularity of digital media the world is becoming smaller and smaller. That is mainly due to the internet connectivity and WWW phenomena. But the copyright protection of intellectual properties has become a necessity for prevention of illegal copying and verification of content integrity. Here wavelet transform plays the role of an efficient and robust tool due to its multi-resolution capability along with singular value decomposition (SVD) for watermarking. Both of these when implemented with coded fingerprinting not only resist collusion attacks but can also help tracing colluders. This work here by focuses implementation of a hybrid watermarking scheme using SVD and wavelet transform along with coded fingerprinting developed for protection of the intellectual property.