Intro

As a computer scientist, I work in the intersection between machine learning, ubiquitous computing, and mental health. Prior to my PhD, I was Data & AI graduate scientist at AstraZeneca, where I pursued practical research problems in medical imaging, digital health, and bioinformatics.

Currently, my research focuses on the following areas:

  1. Investigating the relationship between para-linguistic features in speech and mental illness symptoms.
  2. Robust speech-based machine learning models that generalize across populations using unsupervised and semi-supervised methods.
  3. Moving toward real-time intervention systems for mental health emergencies like suicidal ideation.

Research

Publications

2023

[12] Investigating generalizability of speech-based suicidal ideation detection using mobile phones.
Arvind Pillai, Subigya Nepal, Weichen Wang, Matthew Nemesure, Michael Heinz, George Price, Damien Lekkas, Amanda Collins, Tess Griffin, Benjamin Buck, Sarah M. Preum, Trevor Cohen, Nicholas C Jacobson, Dror Ben-Zeev, Andrew Campbell.
Proceedings of the ACM on interactive, mobile, wearable and ubiquitous technologies. (UbiComp 2024)

[11] Rare life event detection via mobile sensing using multi-task learning.
Arvind Pillai, Subigya Nepal, Andrew Campbell.
In Conference on Health, Inference, and Learning. PMLR. (CHIL 2023)
Paper

2022

[10] First-gen lens: Assessing mental health of first-generation students across their first year at college using mobile sensing.
Weichen Wang, Subigya Nepal, Jeremy F. Huckins, Lessley Hernandez, Vlado Vojdanovski, Dante Mack, Jane Plomp, Arvind Pillai, Mikio Obuchi, Alex daSilva, Ellis Murphy, Elin Hedlund, Courtney Rogers, Meghan Meyer, Andrew Campbell.
Proceedings of the ACM on interactive, mobile, wearable and ubiquitous technologies. (UbiComp 2023)
Paper

[9] Accurate step count with generalized and personalized deep learning on accelerometer data.
Long Luu, Arvind Pillai, Halsey Lea, Ruben Buendia, Faisal M. Khan, Glynn Dennis
Sensors. vol. 22, no.11, p.3989
Paper

[8] Accurate step count with generalizable deep learning on accelerometer data.
Long Luu, Arvind Pillai, Halsey Lea, Ruben Buendia, Faisal M. Khan, Glynn Dennis
In International Conference on Pervasive Intelligence and Computing. IEEE.
Paper

[7] Machine learning enabled non-invasive diagnosis of nonalcoholic fatty liver disease and assessment of abdominal fat from mri data.
Arvind Pillai, Kamen Bliznashki, Emmette Hutchison, Chanchal Kumar, Mishal Patel.
medRxiv.
Paper

2021 & Prior

[6] Effective expression analysis using gene interaction matrices and convolutional neural network.
Arvind Pillai, Piotr Grabowski, Bino John.
bioRxiv. pp. 2021–09.
Paper

[5] Machine learning enabled non-invasive diagnosis of nonalcoholic fatty liver disease and assessment of abdominal fat from mri data.
Arvind Pillai, Kamen Bliznashki, Emmette Hutchison, Chanchal Kumar, Mishal Patel.
In Machine Learning for Health @ NeurIPS. (ML4H 2020)
Paper

[4] Personalized step counting using wearable sensors: A domain adapted lstm network approach.
Arvind Pillai, Halsey Lea, Faisal M. Khan, Glynn Dennis
In 2019 Applications of Machine Learning in Pharma and Healthcare (PharML) @ ECML-PKDD. (PharML 2019)
Paper

[3] Graph convolutional networks for predicting drug-protein interactions.
Hafez E. Manoochehri, Arvind Pillai, Mehrdad Nourani
In 2019 IEEE International Conference on Bioinformatics and Biomedicine. (IEEE BIBM 2019)
Paper

[2] Local diagonal extrema number pattern: A new feature descriptor for face recognition.
Arvind Pillai, Rajkumar Soundrapandiyan, Swapnil Satapathy, Suresh C. Satapathy, Ki-Hyun Jung, Rajakumar Krishnan.
Future Generation Computer Systems. vol. 81, pp. 297–306, 2018.
Paper

[1] Adaptive new top-hat transform and multi-scale sequential toggle operator based infrared image enhancement.
Arvind Pillai, Rajkumar Soundrapandiyan, K. Marimuthu, G. Rakasekaran
In 2017 Innovations in Power and Advanced Computing Technologies (i-PACT). IEEE, 2017, pp. 1–5.
Paper

Experience

Work

click here
Data Science & AI Graduate Scientist
AstraZeneca
September 2019 - July 2021

  • Rotation 3 - Analysed gene expression data by developing a novel transformation. Ultimately, we predicted compound-dose toxicity from the Toxicogenomics-Gates dataset and classfied cancer subtypes from The Cancer Genome Atlas (TCGA) dataset.
  • Rotation 2 - Developed a pre-diagnostic tool to stratify patients with Nonalcoholic Fatty Liver Disease using abdominal MRI data from the UK biobank.
  • Rotation 1 - Built a step count algorithm to classify steps across two wearable different devices.

Teaching

click here
Teaching Assistant
Dartmouth College
Spring 2023 - CS1 Introduction to Programming (Prof. Andrew Campbell)
Spring 2022 - CS1 Introduction to Programming (Prof. Andrew Campbell)
Fall 2021 - CS1 Introduction to Programming (Prof. Vasanta Kommineni)

Professional

Reviewer

2023 - ACM IMWUT/UbiComp, ML4H
2021 - Machine Learning for Healthcare (ML4H) @ NeurIPS

Talks

November 2023 - Alan Turing Institute - Data Science for Mental Health
"Generalizability in Mental Health: A Spotlight On Speech-Based Suicidal Ideation Detection"
Slide Deck

May 2023 - Dartmouth College (Research Presentation Exam)
"ArcFace: Additive Angular Margin Loss for Deep Face Recognition by Deng, J., Guo, J., et al."
Slide Deck

October 2022 - VIT University
"Towards detecting suicidal ideation in individuals experiencing mental health symptoms using audio diaries from mobile mobiles"

Contact

Elements

Text

This is bold and this is strong. This is italic and this is emphasized. This is superscript text and this is subscript text. This is underlined and this is code: for (;;) { ... }. Finally, this is a link.

Heading Level 2

Heading Level 3

Heading Level 4

Heading Level 5
Heading Level 6

Blockquote

Fringilla nisl. Donec accumsan interdum nisi, quis tincidunt felis sagittis eget tempus euismod. Vestibulum ante ipsum primis in faucibus vestibulum. Blandit adipiscing eu felis iaculis volutpat ac adipiscing accumsan faucibus. Vestibulum ante ipsum primis in faucibus lorem ipsum dolor sit amet nullam adipiscing eu felis.

Preformatted

i = 0;

while (!deck.isInOrder()) {
    print 'Iteration ' + i;
    deck.shuffle();
    i++;
}

print 'It took ' + i + ' iterations to sort the deck.';

Lists

Unordered

  • Dolor pulvinar etiam.
  • Sagittis adipiscing.
  • Felis enim feugiat.

Alternate

  • Dolor pulvinar etiam.
  • Sagittis adipiscing.
  • Felis enim feugiat.

Ordered

  1. Dolor pulvinar etiam.
  2. Etiam vel felis viverra.
  3. Felis enim feugiat.
  4. Dolor pulvinar etiam.
  5. Etiam vel felis lorem.
  6. Felis enim et feugiat.

Icons

Actions

Table

Default

Name Description Price
Item One Ante turpis integer aliquet porttitor. 29.99
Item Two Vis ac commodo adipiscing arcu aliquet. 19.99
Item Three Morbi faucibus arcu accumsan lorem. 29.99
Item Four Vitae integer tempus condimentum. 19.99
Item Five Ante turpis integer aliquet porttitor. 29.99
100.00

Alternate

Name Description Price
Item One Ante turpis integer aliquet porttitor. 29.99
Item Two Vis ac commodo adipiscing arcu aliquet. 19.99
Item Three Morbi faucibus arcu accumsan lorem. 29.99
Item Four Vitae integer tempus condimentum. 19.99
Item Five Ante turpis integer aliquet porttitor. 29.99
100.00

Buttons

  • Disabled
  • Disabled

Form