“ Dr. Varadarajan B mentored and guided me during my Bachelor Thesis as well as during our time together at Inselspital, Bern (2014-2015). He introduced me to several domains of Biomedical Instrumentation. We worked together to develop concepts for the automation of an In-vitro Lung Model and his guidance enabled me to successfully design, implement and validate a LabVIEW based automation system. His knowledge in the domain of cardio-pulmonary modelling and Breath analysis is vast, and so is his hands-on experience with practical clinical implementations and deployments. Given his passion to carrying out interdisciplinary research involving fields from Bio-analytical instrumentation to automated embedded systems, I look forward to collaborate again with Dr. Varadarajan on interesting biomedical projects in the near future. ”
Balamurugan Varadarajan
Founder Stealth mode Startup | Artificial Intelligence Researcher | Industrial Consultant | Start-up Mentor |Music Technologist| Epigraphy enthusiast
Coimbatore, Tamil Nadu, India
2K followers
500+ connections
About
Disrupting industrial problems and humanizing technology with AI, AI engineer with extensive experience in both research and product development. Specialize in cross-domain knowledge to contribute to AI technologies for scientific and industrial data as an essential member of an innovative firm. Having worked on the creation and testing of AI solutions for more than a 8 years. Possess an unbridled passion for Artificial Intelligence with comprehensive knowledge of machine learning concepts and other related technologies. Unmatched abilities to identify, understand, and translate program requirements into sustainable, advanced technical solutions through continuous improvement of Al technologies.
Visionary who has a passion for transforming research into products and establishing exceptional teams. Scientific advisor and R&D mentor in MNC’s and Start up’s mentoring methods Ideation, concept development, concept testing, Academia to Industry transfer with NDAs.
My passion on music and support people and finding solutions to problems has always been what has propelled me throughout my career as an artist, vocal coach, author, scientist, and entrepreneur.
Earlier as Research Consultant at Robert Bosch R&D Solutions, Pricol and Matrimony.com my team designed and implemented large-scale intelligent systems, Machine Learning, Conversational AI, Embedded systems, Sensors and Biosensors.
Draeger, Germany was where I began my professional career as a researcher. I spent over four years, during my tenure at Draeger Research, I was actively involved with breath biomarker identification and pattern classification. I was instrumental in coming up with new patentable ideas.
I have a total of Four Invention Disclosures (Patents) to my credit.
I'm always interested in discussing research problem encountered in industries.
Lest's Connect!
Services
Activity
-
Want to Become a GenAI Developer by February 2025? Here's Your Complete Success Blueprint! I've crafted this comprehensive roadmap to transform…
Want to Become a GenAI Developer by February 2025? Here's Your Complete Success Blueprint! I've crafted this comprehensive roadmap to transform…
Liked by Balamurugan Varadarajan
-
🚀 2025 AI/ML Internships – Hourly Updated Opportunities! 🎓 Looking for AI/ML internships for 2025? Now’s the perfect time to get ahead! With…
🚀 2025 AI/ML Internships – Hourly Updated Opportunities! 🎓 Looking for AI/ML internships for 2025? Now’s the perfect time to get ahead! With…
Liked by Balamurugan Varadarajan
Experience
Education
-
Universität zu Lübeck
Doctorate Computer Science Engineering
-
Thesis: Model predictive control and electrochemical breath sensor design for propofol Anesthesia.
-
Vellore Institute of Technology
Bachelors of Engineering Electronics and Instrumentation
-
Activities and Societies: Active member in personality development and leadership programs.
Thesis title: Virtual instrumentation assisted resonance identification system for aircraft structures.
Licenses & Certifications
Publications
-
Classification of Groundnut Oil Using Advanced ATR-MIR Spectroscopy and Chemometrics
SpringerLink
In this work, attenuated total reflectance (ATR) mid infrared (MIR) spectroscopy has been used for analysis of edible cold pressed (CP) and other different brands of refined/hot pressed (HP) groundnut oils (Brand 1–3) for the first time. Frequencies at the MIR region, mainly at wavelengths of 5–11 µm, are examined for classification of groundnut oils. The effect of temperature of cold pressed and hot pressed commercial oil brands are investigated by heating oil samples at different temperatures…
In this work, attenuated total reflectance (ATR) mid infrared (MIR) spectroscopy has been used for analysis of edible cold pressed (CP) and other different brands of refined/hot pressed (HP) groundnut oils (Brand 1–3) for the first time. Frequencies at the MIR region, mainly at wavelengths of 5–11 µm, are examined for classification of groundnut oils. The effect of temperature of cold pressed and hot pressed commercial oil brands are investigated by heating oil samples at different temperatures of 50, 75, 100, 125, 150, 175, and 200 °C. Partial least square regression (PLSR) and K-means derivative spectra revealed the best calibration models to differentiate cold pressed oils and different brands of hot pressed groundnut oil samples, with coefficient of determination (R2) of 0.999 and root mean standard error of cross validation (RMSECV) of 0.285 and 0.373, respectively. It is noted that pure cold pressed and commercial brand groundnut oils showed a different trend of oxidation at different temperatures. Heated cold-pressed groundnut oil revealed notable spectral variations, than heating other commercial brands of oil.
-
Near-real-time pulmonary shunt and dead space measurement with micropore membrane inlet mass spectrometry in pigs with induced pulmonary embolism or acute lung failure.
Journal of Clinical Monitoring and Computing
The multiple inert gas elimination technique (MIGET) using gas chromatography (GC) is an established but time-consuming method of determining ventilation/perfusion (VA/Q) distributions. MIGET—when performed using Micropore Membrane Inlet Mass Spectrometry (MMIMS)—has been proven to correlate well with GC-MIGET and reduces analysis time substantially. We aimed at comparing shunt fractions and dead space derived from MMIMS–MIGET with Riley shunt and Bohr dead space, respectively. Thirty…
The multiple inert gas elimination technique (MIGET) using gas chromatography (GC) is an established but time-consuming method of determining ventilation/perfusion (VA/Q) distributions. MIGET—when performed using Micropore Membrane Inlet Mass Spectrometry (MMIMS)—has been proven to correlate well with GC-MIGET and reduces analysis time substantially. We aimed at comparing shunt fractions and dead space derived from MMIMS–MIGET with Riley shunt and Bohr dead space, respectively. Thirty anesthetized pigs were randomly assigned to lavage or pulmonary embolism groups. Inert gas infusion (saline mixture of SF6, krypton, desflurane, enflurane, diethyl ether, acetone) was maintained, and after induction of lung damage, blood and breath samples were taken at 15-min intervals over 4 h. The samples were injected into the MMIMS, and resultant retention and excretion data were translated to VA/Q distributions. We compared MMIMS-derived shunt (MM-S) to Riley shunt, and MMIMS-derived dead space (MM-VD) to Bohr dead space in 349 data pairs. MM-S was on average lower than Riley shunt (− 0.05 ± 0.10), with lower and upper limits of agreement of − 0.15 and 0.04, respectively. MM-VD was on average lower than Bohr dead space (− 0.09 ± 0.14), with lower and upper limits of agreement of − 0.24 and 0.05. MM-S and MM-VD correlated and agreed well with Riley shunt and with Bohr dead space. MM-S increased significantly after lung injury only in the lavage group, whereas MM-VD increased significantly in both groups. This is the first work evaluating and demonstrating the feasibility of near real-time VA/Q distribution measurements with the MIGET and the MMIMS methods.
-
An in vitro lung model to assess true shunt fraction by multiple inert gas elimination
Public Library of Science
The Multiple Inert Gas Elimination Technique, based on Micropore Membrane Inlet Mass Spectrometry, (MMIMS-MIGET) has been designed as a rapid and direct method to assess the full range of ventilation-to-perfusion (V/Q) ratios. MMIMS-MIGET distributions have not been assessed in an experimental setup with predefined V/Q-distributions. We aimed (I) to construct a novel in vitro lung model (IVLM) for the simulation of predefined V/Q distributions with five gas exchange compartments and (II) to…
The Multiple Inert Gas Elimination Technique, based on Micropore Membrane Inlet Mass Spectrometry, (MMIMS-MIGET) has been designed as a rapid and direct method to assess the full range of ventilation-to-perfusion (V/Q) ratios. MMIMS-MIGET distributions have not been assessed in an experimental setup with predefined V/Q-distributions. We aimed (I) to construct a novel in vitro lung model (IVLM) for the simulation of predefined V/Q distributions with five gas exchange compartments and (II) to correlate shunt fractions derived from MMIMS-MIGET with preset reference shunt values of the IVLM. Five hollow-fiber membrane oxygenators switched in parallel within a closed extracorporeal oxygenation circuit were ventilated with sweep gas (V) and perfused with human red cell suspension or saline (Q). Inert gas solution was infused into the perfusion circuit of the gas exchange assembly. Sweep gas flow (V) was kept constant and reference shunt fractions (IVLM-S) were established by bypassing one or more oxygenators with perfusate flow (Q). The derived shunt fractions (MM-S) were determined using MIGET by MMIMS from the retention data. Shunt derived by MMIMS-MIGET correlated well with preset reference shunt fractions. The in vitro lung model is a convenient system for the setup of predefined true shunt fractions in validation of MMIMS-MIGET.
-
Validation of MMIMS‐MIGET (multiple inert gas elimination technique by micropore membrane inlet mass spectrometry) in an in vitro lung model of lung compartments with low‐to‐normal ventilation‐perfusion ratios
European Journal of Anaesthesiology (EJA)
Background and Goal of Study: MMIMS‐MIGET has been designed as rapid and direct method to assess the full range of VA/Q distributions.1,2 In an in‐vitro lung model (IVLM), MMIMS‐MIGET shunt has been shown to correlate well with preset model shunt.3 In this study we aimed to compare low (0.005< VA/Q< 0.1) to normal (0.1< VA/Q< 10)4 VA/Q compartments determined by MMIMS‐MIGET (MM‐VQ) with reference low‐to‐normal VA/Q compartments as preset in the IVLM (IVLM‐VQ).
-
In vitro lung model to assess gas exchange by multiple inert gas elimination technique (MIGET) using micropore membrane inlet mass spectrometry (MMIMS)
European Journal of Anaesthesiology
Background: Currently, gas exchange analysis by MIGET based on MMIMS is under evaluation by several groups 1,2. MMIMS‐MIGET shunt has been shown to correlate well with Riley shunt in a porcine lavage lung model1. Membrane oxygenators have been used as model to describe nitric oxide and carbon monoxide transfer2. So far, MIGET has not been tested in such a setup to assess predefined ventilation perfusion (VA/Q) distributions. In this study we aimed (I) to design an in vitro lung model (IVLM)…
Background: Currently, gas exchange analysis by MIGET based on MMIMS is under evaluation by several groups 1,2. MMIMS‐MIGET shunt has been shown to correlate well with Riley shunt in a porcine lavage lung model1. Membrane oxygenators have been used as model to describe nitric oxide and carbon monoxide transfer2. So far, MIGET has not been tested in such a setup to assess predefined ventilation perfusion (VA/Q) distributions. In this study we aimed (I) to design an in vitro lung model (IVLM) which comprises 5 separate gas exchange compartments and (II), to compare shunt fractions derived from MMIMS‐MIGET with preset reference shunt values of the IVLM.
-
Time course of ethanol and propofol exhalation after bolus injection using ion molecule reaction-mass spectrometry
SpringerLink
The transit of ethanol from blood to breath gas is well characterised. It is used for intraoperative monitoring and in forensic investigations. A further substance, which can be measured in breath gas, is the phenol propofol. After a simultaneous bolus injection, the signals (time course and amplitude) of ethanol and propofol in breath gas were detected by ion molecule reaction-mass spectrometry (IMR-MS) and compared. After approval by the regional authorities, eight pigs were endotracheally…
The transit of ethanol from blood to breath gas is well characterised. It is used for intraoperative monitoring and in forensic investigations. A further substance, which can be measured in breath gas, is the phenol propofol. After a simultaneous bolus injection, the signals (time course and amplitude) of ethanol and propofol in breath gas were detected by ion molecule reaction-mass spectrometry (IMR-MS) and compared. After approval by the regional authorities, eight pigs were endotracheally intubated after a propofol-free induction with etomidate. Boluses of ethanol (16 μg/kg) and propofol (4 or 2 mg/kg) were infused alone and in combination. For both substances, breath gas concentrations were continuously measured by IMR-MS; the delay time, time to peak and amplitude were determined and compared using non-parametric statistic tests. IMR-MS allows a simultaneous continuous measurement of both substances in breath gas. Ethanol appeared (median delay time, 12 vs 29.5 s) and reached its peak concentration (median time to peak, 45.5 vs 112 s) significantly earlier than propofol. Time courses of ethanol and propofol in breath gas can be simultaneously described with IMR-MS. Differing pharmacological and physicochemical properties of the two substances can explain the earlier appearance and time to peak of ethanol in breath gas compared with propofol.
-
The relative influence of phosphorylation and methylation on responsiveness of peptides to MALDI and ESI mass spectrometry.
Journal of Mass spectrometry
Honors & Awards
-
Postdoctoral Fellowship, University of Bern, Switzerland
Swiss National Science Foundation
The fellowship was awarded to work as a Research associate from April 2011 to May 2015 .
-
Dräger PhD fellowship, Dräger, Luebeck, Germany
Dräger, Luebeck, Germany
A priviliged Industrial Doctoral fellowship in collaboration with the University of Luebeck, Germany for working in the R&D development.
-
CSIR Research Intern Fellowship
CSIR - India
The CSIR Research Intern Fellowship was awarded for 2 years from April 2004 - April 2006.
-
Project Top 10 in Country
National Instruments, India
“Virtual Instrumentation assisted Resonance Identification System for Aircraft Structures” – bachelors project, selected one among the top 10 in the country in the 2nd National Level Virtual Instrumentation Conference (January 2004, VI Mantra, Bangalore, India) conducted by National Instruments, India.
Languages
-
German
Limited working proficiency
-
English
Native or bilingual proficiency
-
Tamil
Native or bilingual proficiency
Recommendations received
1 person has recommended Balamurugan
Join now to viewMore activity by Balamurugan
-
Calling All Innovators! Are you building the next big thing in HealthCare, Smart Infra, Cleantech, or other future-ready sectors? TIDE 2.0 is here…
Calling All Innovators! Are you building the next big thing in HealthCare, Smart Infra, Cleantech, or other future-ready sectors? TIDE 2.0 is here…
Liked by Balamurugan Varadarajan
-
🚀 Calling Innovators & Researchers! 🚀 Are you ready to showcase your Research Work/ Technology to potential industry partners? DST-TEC, Anna…
🚀 Calling Innovators & Researchers! 🚀 Are you ready to showcase your Research Work/ Technology to potential industry partners? DST-TEC, Anna…
Liked by Balamurugan Varadarajan
-
7 Remote Jobs without Interviews ⤵️ [ Save Now ] 1. Monster Monster, a pioneer in online job aggregation, offers a wide range of remote roles…
7 Remote Jobs without Interviews ⤵️ [ Save Now ] 1. Monster Monster, a pioneer in online job aggregation, offers a wide range of remote roles…
Liked by Balamurugan Varadarajan
-
We are proud to share two amazing events organized by the 🦊Mozilla Firefox Club - VIT! 👨💻 Symphony.AI: An engaging offline alumni speaker…
We are proud to share two amazing events organized by the 🦊Mozilla Firefox Club - VIT! 👨💻 Symphony.AI: An engaging offline alumni speaker…
Liked by Balamurugan Varadarajan
-
Speaking today on the impact of AI on the publishing and media industries. among the journalists forum. Thanks Kombai S Anwar and Tamil Media Club…
Speaking today on the impact of AI on the publishing and media industries. among the journalists forum. Thanks Kombai S Anwar and Tamil Media Club…
Liked by Balamurugan Varadarajan
-
🌟 Exciting Opportunity: PhD Internships at the Audio, Music, and AI Lab (AMAAI) 🌟 I am happy to share that we have 𝗣𝗵𝗗 𝗶𝗻𝘁𝗲𝗿𝗻𝘀𝗵𝗶𝗽…
🌟 Exciting Opportunity: PhD Internships at the Audio, Music, and AI Lab (AMAAI) 🌟 I am happy to share that we have 𝗣𝗵𝗗 𝗶𝗻𝘁𝗲𝗿𝗻𝘀𝗵𝗶𝗽…
Liked by Balamurugan Varadarajan
-
What a year it's been... Here are my top 10 takeaways on genAI music software in 2024👇 1. Suno and Udio were sued by the Recording Industry…
What a year it's been... Here are my top 10 takeaways on genAI music software in 2024👇 1. Suno and Udio were sued by the Recording Industry…
Liked by Balamurugan Varadarajan
-
Happy to have handled an online hands-on session today, on "Tamil Computing using Large Language Models" for the Tamil Computing Research group,…
Happy to have handled an online hands-on session today, on "Tamil Computing using Large Language Models" for the Tamil Computing Research group,…
Liked by Balamurugan Varadarajan
-
As you all know, I write a ton about the audio industry, out of my love for sounds & products. While I try to promote every new initiative, talent &…
As you all know, I write a ton about the audio industry, out of my love for sounds & products. While I try to promote every new initiative, talent &…
Liked by Balamurugan Varadarajan
-
🎵 Happy to share that we presented our work at #ISMIR 2024 held in San Francisco, California! 🎵 Our research focuses on the automatic estimation…
🎵 Happy to share that we presented our work at #ISMIR 2024 held in San Francisco, California! 🎵 Our research focuses on the automatic estimation…
Liked by Balamurugan Varadarajan
-
🎶💻 How Does AI Beat Tracking Work? ◾ What is Beat Tracking? Beat tracking aims to detect all musical beats in a given song. For example, if a song…
🎶💻 How Does AI Beat Tracking Work? ◾ What is Beat Tracking? Beat tracking aims to detect all musical beats in a given song. For example, if a song…
Liked by Balamurugan Varadarajan
-
This is one of the MOST popular ML interview questions I have come across. If you want to bookmark a post, this would be the one. What is Batch…
This is one of the MOST popular ML interview questions I have come across. If you want to bookmark a post, this would be the one. What is Batch…
Liked by Balamurugan Varadarajan
Other similar profiles
Explore collaborative articles
We’re unlocking community knowledge in a new way. Experts add insights directly into each article, started with the help of AI.
Explore MoreOthers named Balamurugan Varadarajan
-
Balamurugan Varadarajan
Project Architect | Responsive Designer | Researcher
-
balamurugan varadarajan
Senior Medical Representative at Novartis
-
Balamurugan Varadarajan
Senior Medical Representative at Novartis India
3 others named Balamurugan Varadarajan are on LinkedIn
See others named Balamurugan Varadarajan