- Speech and Audio Processing
- Obstructive Sleep Apnea Research
- Voice and Speech Disorders
- Advanced Battery Technologies Research
- Renal and Vascular Pathologies
- Digital Filter Design and Implementation
- Advanced Adaptive Filtering Techniques
- Electric Vehicles and Infrastructure
- Microgrid Control and Optimization
- Pediatric Urology and Nephrology Studies
- Kidney Stones and Urolithiasis Treatments
- Advanced DC-DC Converters
- Quantum Mechanics and Applications
- Quantum Information and Cryptography
- Advanced X-ray and CT Imaging
- Neuroscience of respiration and sleep
- Hearing Loss and Rehabilitation
- Subtitles and Audiovisual Media
- Power Quality and Harmonics
- Radiation Effects in Electronics
- Quantum Computing Algorithms and Architecture
- Magnetic Properties and Applications
- Radiation Dose and Imaging
- Electromagnetic wave absorption materials
- Infant Health and Development
Government Medical College
2017-2023
Australian Hearing
2023
The University of Sydney
2019-2021
Banaras Hindu University
2020
Institute of Medical Sciences
2020
University of York
2018
University of Kerala
2014-2015
Northeast Agricultural University
2014
Rajiv Gandhi Centre for Biotechnology
2011
The Machine learning-based EMI shielding effect prediction on polymer composite materials is of supreme importance in modern electronic applications as this serves a robust protective barrier, safeguarding components from electromagnetic interference. But, capturing the multifactorial nature composites and handling multi-objective optimization still difficult to achieve with existing machine-learning approaches. Hence, research proposes novel “Bio-inspired Predictive Insight Optimization...
One of the increasingly common unexpected outcomes extensive usage electronic devices and systems is electromagnetic interference (EMI). The need for efficient fillers shielding materials to manage (EMI) associated issues rising. Adding more filler typically means greater production costs, poor dispersion, unintended agglomeration, which makes polymer composites harder work with mechanically weak. Therefore, it highly desired design a strong composite conductive content that nonetheless...
Abstract Study Objectives Acoustic analysis of isolated events and snoring by previous researchers suggests a correlation between individual acoustic features site collapse events. In this study, we hypothesized that multiparameter evaluation snore sounds during natural sleep would provide robust prediction the predominant airway collapse. Methods The audio signals 58 obstructive apnea patients were recorded simultaneously with full-night polysomnography. was determined manual shape airflow...
This paper presents a low complex design of non-uniformly spaced digital finite impulse response (FIR) filter bank for hearing aid application. Frequency masking (FRM) technique is used the implementation 10 subband filters. FRM ensure drastic reduction in number multipliers and adders linear phase FIR filter. It employs two half-band filters as prototype filters, which leads to significant savings terms arithmetic operations. Further can be achieved by using with minimum order. The...
Servo design includes the modelling of BLDC motor and to a proper compensator meet launch vehicle requirements. Compensator is based on step response open loop plant. A compensation scheme including PI controller notch filter thus included in plant Brush less torque motor, which used as actuator control engine. The system closed using compensator. From it inferred that along with ready for thrust vehicles.
A lot of effort has been devoted to the design uniform and non-uniform filter banks for hearing aid applications. But in most cases, it never deals with large variation losses at mid frequencies. This paper presents a low complex non-uniformly spaced digital finite impulse response (FIR) bank application. Frequency masking (FRM) technique is used implementation 8 subband filters, single half-band as prototype filter. With FRM filter, drastic reduction number multipliers adders linear phase...
This study provides a novel approach for an automated system using machine learning algorithm to predict the predominant site of upper airway collapse into four classes ('lateral wall', 'palate', 'tongue-base' related or 'multi-level' site-of-collapse) in obstructive sleep apnoea (OSA) patients from audio signal recorded during normal sleep.Snore sounds 58 were simultaneously with full-night polysomnography ceiling mounted microphone. The probable site-of-airway was determined by manual...
This paper provides the results of an unsupervised learning algorithm that characterize upper airway collapse in obstructive sleep apnoea (OSA) patients using snore signal during hypopnoea events. Knowledge regarding site-of-collapse could improve ability choosing most appropriate treatment for OSA and thereby improving outcome. In this study, we implemented k-means clustering to label data Audio were recorded simultaneously with full-night polysomnography a ceiling microphone. Various time...
In this study we investigated if audio signals may carry information related to the site of obstruction upper airway. The regarding collapse could improve obstructive sleep apnoea (OSA) treatment by allowing more individualized or structure-specific therapy. preliminary study, developed an algorithm for automatically determining in 13 OSA patients through snoring analysis. Audio was recorded with a ceiling mounted microphone, simultaneously full-night polysomnography during sleep. surrogate...
This paper provides some considerations regarding using individualized head-related transfer functions for rendering binaural spatial audio over headphones. It briefly considers the degree of benefit that individualization may provide. then examines variation existing within ear morphology across listeners Sydney-York Morphological and Recording Ears (SYMARE) database kernel principal component analysis large deformation diffeomorphic metric mapping framework. The in directivity patterns...
Knowledge regarding the site of airway collapse could help in choosing an appropriate structure-specific or individualized treatment for obstructive sleep apnoea (OSA). We investigated if audio signal recorded during hypopnoea (partial obstruction) events can predict site-of-collapse upper airway. In this study, we designed automatic classifier that predicts predominant a patient as "lateral wall", "palate", "tongue-based" related "multi-level" by processing signal. The probable was...
The renal tract is mainly investigated for abnormal function and to identify causes of colic haematuria. Increasing use ultrasound computed tomography have limited the role plain radiographs. However, they are still used in initial assessment abdominal evaluate potential or bowel abnormalities. Intravenous urograms radiological examinations urinary performed following intravenous injection iodinated contrast. They classical means by which assess kidneys ureters. Ultrasound often first...
The autoimmune regulator gene Aire shows predominant expression in thymus and other immunologically relevant tissues, is assigned the major function of programming autoreactive T-cell deletion. However, this tissues outside immune system raises a question about its possible beyond deletion dogma. We detected mouse testis, AIRE protein was remarkably high postmeiotic germ cells. Sequencing results indicate that testis expressed variant 1a. could be spermatozoa, with heavy localization on...
Electromagnetic interference (EMI) has been identified as one of the ever-increasing unintended consequences widespread use electronic devices and systems. There is a growing demand for effective shielding materials fillers to control EMI related concerns. Increased filler content usually results in higher costs, poor dispersion, unwanted agglomeration, making polymer composites mechanically fragile difficult produce. As result, developing robust composite with conductive while maintaining...
This study explores the feasibility of employing machine learning to classify acoustic features speech for detecting hearing loss in preschool children. Acknowledging critical developmental impacts early identification and challenges associated with traditional testing methods this age group, we propose a novel, scalable approach leveraging automatic analysis. Using recordings from children without loss, used wav2vec 2.0 ComParE feature sets capture characteristics compared LSTM, DNN,...
In this study, the development of an automatic algorithm is presented to classify nocturnal audio recording obstructive sleep apnoea (OSA) patient as OSA related snore, simple snore and other sounds. Recent studies has been shown that knowledge regarding could assist in identifying site airway collapse. Audio signal was recorded simultaneously with full-night polysomnography during a ceiling microphone. Time frequency features were extracted into Two algorithms developed extract using linear...
Microgrid otherwise distributed electrical power plant, whichconsists of different energy inputs, integrated using renewable source (RES)based distribution generators (DG), which is on electronics basedprototypes, so quality issues in sector are seriously increasing. If it controlled properly, DG inverters used for mitigating problems like harmonics, compensation reactive and unbalancing the system. This type inverter called as multifunctional grid tied (MFGTI). With thelatest developments...
Knowledge regarding the site-of-collapse in upper airway obstructive sleep apnoea (OSA) has implications for treatment options and their outcomes. However, current methods to identify are not suitable clinical practice due invasive nature, time/cost of tests inconsistency obstruction site identified with natural drug-induced sleep. In this study, we adopted an unsupervised algorithm predominant during using nocturnal audio recordings. Nocturnal was recorded together full-night...