Vinayak Bairagi - Profile on Academia.edu (original) (raw)

Papers by Vinayak Bairagi

Symmetry, Jun 23, 2024

The automatic speaker verification system is susceptible to replay attacks. Recent literature has... more The automatic speaker verification system is susceptible to replay attacks. Recent literature has focused on score-level integration of multiple features, phase information-based features, high frequency-based features, and glottal excitation for the detection of replay attacks. This work presents glottal excitation-based all-pole group delay function (GAPGDF) features for replay attack detection. The essence of a group delay function based on the all-pole model is to exploit information from the speech signal phase spectrum in an effective manner. Further, the performance of integrated high-frequency-based CQCC features with cepstral features, subband spectral centroid-based features (SCFC and SCMC), APGDF, and LPC-based features is evaluated on the ASVspoof 2017 version 2.0 database. On the development set, an EER of 3.08% is achieved, and on the evaluation set, an EER of 9.86% is achieved. The proposed GAPGDF features provide an EER of 10.5% on the evaluation set. Finally, integrated GAPGDF and GCQCC features provide an EER of 8.80% on the evaluation set. The computation time required for the ASV systems based on various integrated features is compared to ensure symmetry between the integrated features and the classifier.

Analyzing electroencephalograph signals for early Alzheimer’s disease detection: deep learning vs. traditional machine learning approaches

International Journal of Power Electronics and Drive Systems/International Journal of Electrical and Computer Engineering, Jun 1, 2024

Alzheimer’s disease (AD) stands as a progressive neurodegenerative disorder with a significant gl... more Alzheimer’s disease (AD) stands as a progressive neurodegenerative disorder with a significant global public health impact. It is imperative to establish early and accurate diagnoses of AD to facilitate effective interventions and treatments. Recent years have witnessed the emergence of machine learning (ML) and deep learning (DL) techniques, displaying promise in various medical domains, including AD diagnosis. This study undertakes a comprehensive contrast between conventional machine learning methods and advanced deep learning strategies for early AD diagnosis. Conventional ML algorithms like support vector machines, decision trees, and K nearest neighbor have been extensively employed for AD diagnosis through relevant feature extraction from heterogeneous data sources. Conversely, deep learning techniques such as multilayer perceptron (MLP) and convolutional neural networks (CNNs) have demonstrated exceptional aptitude in autonomously uncovering intricate patterns and representations from unprocessed data like EEG data. The findings reveal that while traditional ML methods may perform adequately with limited data, deep learning techniques excel when ample data is available, showcasing their potential for early and precise AD diagnosis. In conclusion, this research paper contributes to the ongoing discourse surrounding the choice of appropriate methodologies for early Alzheimer’s disease diagnosis.

Indonesian journal of electrical engineering and computer science, Apr 1, 2024

An efficient deep-learning prediction model for identifying chronic kidney disease (CKD) from exh... more An efficient deep-learning prediction model for identifying chronic kidney disease (CKD) from exhaled breath is presented in this paper. The concentration of urea will be higher in CKD patients. Salivary urease breaks down the stored urea into ammonia, which is then excreted through breath. Thus, by monitoring the breath ammonia content, it is possible to identify the presence of high urea levels in the body. In this work, a novel sensing module is developed and applied to measure and assess the amount of ammonia in exhaled breath. Moreover, an effective deep learning prediction model that combines the CatBoost algorithm and convolutional neural network (CNN) is used to automate the prediction of disease. The proposed model, which combines the benefits of gradient-boosting and CNN, attained an exceptional accuracy of 98.37%. Experiments are conducted to evaluate the proposed model using real-time data and to assess how well it performs in comparison with existing deep learning methods. Our study's findings demonstrate that kidney disease can be accurately and noninvasively diagnosed using the proposed approach.

International journal of innovative technology and exploring engineering, Aug 30, 2019

In the recent years, costliest Alzheimer disease (AD) is now primary reason for the cause of deat... more In the recent years, costliest Alzheimer disease (AD) is now primary reason for the cause of death. An early finding is essential as there is no cure for severe AD. Despite recent advances, early finding of Alzheimer disease from electroencephalography (EEG) remains a difficult job. In this paper, we focus a spectral and signal complexity measures through which such early findings can possibly be improved.

International Journal of Informatics and Communication Technology, Jun 22, 2017

The term Arrhythmia refers to any change from the normal sequence in the electrical impulses. It ... more The term Arrhythmia refers to any change from the normal sequence in the electrical impulses. It is also treated as abnormal heart rhythms or irregular heartbeats. The rate of growth of Cardiac Arrhythmia disease is very high & its effects can be observed in any age group in society. Arrhythmia detection can be done in many ways but effective & simple method for detection & diagnosis of Cardiac Arrhythmia is by doing analysis of Electrocardiogram signals from ECG sensors. ECG signal can give us the detail information of heart activities, so we can use ECG signals to detect the rhythm & behaviour of heart beats resulting into detection & diagnosis of Cardiac Arrhythmia. In this paper new & improved methodology for early Detection & Classification of Cardiac Arrhythmia has been proposed. In this paper ECG signals are captured using ECG sensors & this ECG signals are used & processed to get the required data regarding heart beats of the human being & then proposed methodology applies for Detection & Classification of Cardiac Arrhythmia. Detection of Cardiac Arrhythmia using ECG signals allows us for easy & reliable way with low cost solution to diagnose Arrhythmia in its prior early stage.

Implementing Concatenative Text-To-Speech Synthesis System for Marathi Language using Python

SSRG international journal of electrical and electronics engineering, Sep 30, 2022

Future scope and application

Elsevier eBooks, 2022

Novel slope-based onset detection algorithm for electromyographical signals

International Journal of Biomedical Engineering and Technology, 2021

Electromyography (EMG) is a technique of acquiring neuromuscular activity of muscle. Onset and of... more Electromyography (EMG) is a technique of acquiring neuromuscular activity of muscle. Onset and offset gives information about activation and deactivation timings of motor units. This paper proposes a novel slope-based algorithm for onset and offset detection. EMG data are collected from different muscle of different subjects using surface EMG electrodes. Data is divided into smaller windows and average instantaneous amplitude (AIA) and slope is calculated for each window. A threshold is decided to avoid baseline noise. Below threshold, maximum and minimum slope is detected as the onset and offset respectively. The results are accurate compared to single threshold and double threshold method. Accuracy increases with computation complexity (arithmetic calculations); if compared with root mean square (RMS)-based algorithm. The only limitation is decrease in accuracy if signal is acquired between two muscle contractions. The proposed slope-based onset detection algorithm can be way out between accuracy and computational complexity.

Mobile Phone Sniffer: Radiation Analysis in India

Wireless Communication, 2011

Phone Radiation and Health concerns have been raised, particularly following the huge boost-up in... more Phone Radiation and Health concerns have been raised, particularly following the huge boost-up in the use of wireless mobile telephony all through the world. Mobile phones uses electromagnetic radiation in the microwave range and some people consider this might be damaging to human health. These concerns have induced a hefty body of research. In this paper, we have developed hardware to measure the radiation of mobile phones. We have done comparative study of all models of handsets from various companies in India. The analysis is done in metro city-Pune.

International journal of engineering research and technology, Apr 28, 2014

Alzheimer Disease is the Neuro-degenerative disease, which consists of the common form of dementi... more Alzheimer Disease is the Neuro-degenerative disease, which consists of the common form of dementia. It is the most expensive disease in the modern society & characterized by cognitive, intellectual as well as behavioral disturbance. Due to this, the early diagnosis of the disease is essential as it helps the patients & also his family to take preventive measures. EEG can be used the standardized tool for diagnosis of Alzheimer disease. Various abnormalities are found in the EEG signals of the patients suffering from Alzheimer disease. Hence, the need is to develop the detection of the disease in early stage called as Dementia, the first stage called Mild cognitive impairment (MCI). Role of EEG in diagnostic & clinical research of Alzheimer disease has become more useful in present decades. In present, the most critical task includes the diagnosis of the AD & its early detection in the preclinical stage. The need is to improve the diagnosis accuracy of the EEG signal. The paper presents the ideas of increasing the accuracy of the signal by using various methods. Basically, abnormalities in the EEG signals are characterized by slowing of signals, shift of power spectrum to low frequencies etc. In this way, EEG can be as the tool for the early diagnosis of Alzheimer disease.

Journal of King Saud University - Computer and Information Sciences, Oct 1, 2019

Airway obstruction is a common component in Chronic Obstructive Pulmonary Disease (COPD). Detecti... more Airway obstruction is a common component in Chronic Obstructive Pulmonary Disease (COPD). Detection of obstruction and its grading is very essential. Obstruction in the airways, forces the accessory muscles like sternomastoid muscle (SMM) of respiration to work. Normally, only essential muscles of respiration work. In the said paper electromyographic (EMG) analysis of SMM is done for COPD and Normal subjects. We have developed improved slope based onset detection algorithm to detect the onset and offset timing of EMG. Time domain features are extracted for COPD and normal subject. The onset detection algorithm reduces the number of computations by 32.96% and increases accuracy of feature calculation by 40.19%. Dominant time domain features are selected and applied to Support Vector Machine Classifier. The SVM classification algorithm is compared with Threshold and Naïve Bayes classification algorithm. SVM gives the highest accuracy of 87.80%, sensitivity of 89.65% and specificity of 83.33%. Results are also compared with previously used FEV1/FEV6 and Forced Oscillation Technique. The activity of SMM has a significant role in the classification of Normal and COPD subject. Further analysis of SMM can be done to find different grades of COPD.

Detection of Lung Cancer Pulmonary Nodules Using Computer Aided Detection System

2022 6th International Conference On Computing, Communication, Control And Automation (ICCUBEA, Aug 26, 2022

Lossless Compression of 3D Medical Images Using its Symmetry

Digital Image Processing, 2012

Now days 3D medical images like MRI, CT are integral part of standard health care. These images a... more Now days 3D medical images like MRI, CT are integral part of standard health care. These images are rich in volume and provide important diagnostic information, so there should be some proper method to compress these images. The method proposed in this paper is symmetry based technique for lossless compression of 3D medical image data. The proposed method uses 2D integer wavelet transform to decorrelate the data and block based intra-band prediction which uses anatomic symmetries present in structures of medical images to reduce energy of sub-bands. This method exploits the global and local symmetries of the wavelet transform sub-bands based on the main axis of symmetry. It uses Embedded Block Coder with Optimized Truncation (EBCOT), which encodes the residual data generated after prediction to provide resolution and quality scalability. The technique can be compared with other compression techniques like 3D JPEG2000, JPEG2000, and H.264/AVC and it gives an average improvement in compression ratios.

Sadhana-academy Proceedings in Engineering Sciences, May 19, 2020

Chronic lung disease, in which the airway gets obstructed, is known as Chronic Obstructive Pulmon... more Chronic lung disease, in which the airway gets obstructed, is known as Chronic Obstructive Pulmonary Disease (COPD). According to WHO, COPD kills more than 3 million people every year. Spirometry is used to diagnose COPD; has many limitations. There is a need for physiologically accurate and easy to perform diagnosis technology. Researchers confirmed the activity of sternomastoid muscle in COPD with research limitations of; sample size, few time-domain features, lack of onset detection and the non-stationary nature of Electromyographical signals (EMG). In this, paper COPD diagnosis is made by analyzing Sternomastoid muscle of respiration in time, frequency and time-frequency domain. The slope-based onset detection algorithm and conduction velocity lead to an improvement in COPD detection accuracy to 98.61%. The feature selection algorithm is developed for the selection of the most significant features. A single frequency Continuous Wavelet Transform (CWT) analysis at 7, 8 and 10 Hz of frequency is used to extract features and to classify COPD in its grades, leading to the classification accuracy of 85.89%. Non-invasive, easy to use COPD diagnosis and classification technique is developed.

IEEE Access

In this paper, we have proposed an automated medical system for detecting type 2 diabetes from ex... more In this paper, we have proposed an automated medical system for detecting type 2 diabetes from exhaled breath. Human breath can be used as a diagnostic sample for detecting many diseases as it contains many gases that are dissolved in the blood. Breath-based analysis stands out among the different non-invasive ways of detection as it provides more accurate predictions and offers many advantages. In this work, the concentration of acetone in the exhaled breath is analysed to detect type 2 diabetes. A new sensing module consisting of an array of sensors is implemented for monitoring the acetone concentration to detect the disease. Deep learning algorithms like Convolutional Neural Networks (CNN) are normally used to automatically analyse medical data to make predictions. Even though the CNN performs well, a few modifications to the network layout can further improve the classification accuracy of the learning model. To analyse the sensor signals to generate predictions, a new deep hybrid Correlational Neural Network (CORNN) is designed and implemented in this research. The proposed detection approach and deep learning algorithm offer improved accuracy when compared to other non-invasive techniques.

Automatic brain tumor detection using CNN transfer learning approach

Medical & Biological Engineering & Computing

Metallographic Image Analysis for Quality Assurance of Metals: A Review

Lecture notes in electrical engineering, 2022

International Journal of Advanced Computer Science and Applications

Fingerprint biometric as an identification tool for children recognition was started in the late ... more Fingerprint biometric as an identification tool for children recognition was started in the late 19 th century by Sir Galton. However, it is still not matured for children as adult fingerprint identification even after the span of two centuries. There is an increasing need for biometric identification of children because more than one million children are missing every year as per the report of International Centre of missing and exploited children. This paper presents a robust method of children identification by combining Discrete Cosine Transform (DCT) features and machine learning classifiers with Deep learning algorithms. The handcrafted features of fingerprint are extracted using DCT coefficient's mid and high frequency bands. Gaussian Naïve Base (GNB) classifier is best fitted among machine learning classifiers to find the match score between training and testing images. Further, the Transfer learning model is used to extract the deep features and to get the identification score. To make the model robust and accurate score level fusion of both the models is performed. The proposed model is validated on two publicly available fingerprint databases of children named as CMBD and NITG databases and it is compared with state-of-the-art methods. The rank-1 identification accuracy obtained with the proposed method is 99 %, which is remarkable compared to the literature.

Real Time SoC architectures for Analysis of EEG

2017 International Conference on Computing, Communication, Control and Automation (ICCUBEA), 2017

Electroencephalography (EEG) is a multichannel non-stationary brain signal composed of multi-freq... more Electroencephalography (EEG) is a multichannel non-stationary brain signal composed of multi-frequency. EEG signals are recorded with multiple electrodes either by scalp or intracranial method. It is well proven tool for brain disease detection or prediction. These brain signals are recorded with multiple electrodes with sampling rate. Thus the very huge data need to process and hence computationally intensive. Different architectures have been proposed and implemented to get high performance with accuracy from the device. This proposed work covers comparative study of different efficient architectures of the EEG signal analyzer and designs biosignal processor using FPGA by establishing link between FPGA and PC with URART serial link. More or less of the architectures of EEG signal processing are mainly used for seizure detection. The basic objective of this paper is to understand the implementation of real tiem EEG analyser using FPGA and SoC, to design simple bisignal processor for EEG analysis and analyze architectures based on different performance parameters like frequency of operation, peak power consumption, technology, memory size (bits), accuracy, ADC Resolution, chip area, gates/SRAM.

Applied Statistics

Research Methodology, 2019