Anirudh Som

Email  |  Resume  |  GitHub  |  LinkedIn  |  Twitter

I am a PhD candidate in the ECEE department at Arizona State University (ASU). Here, I am part of the Geometric Media Lab and I am advised by Pavan Turaga.

I received my MS degree from ASU, during which I worked as a computer vision algorithm developer under Pavan Turaga. I've spent time as an intern at Mayo Clinic, Lawrence Livermore National Laboratory and Roche.

My research interests lie in computer vision, computational topology, differential geometry, dynamical system analysis, machine learning and deep learning. My research centers around analyzing and modeling time-series data collected from different sensing devices, for the following applications - human activity recognition, movement quality assessment, Parkinson's disease severity assessment, electrocardiogram (ECG) signal analysis.

News

Under Review Preprints
11) Modeling Wearable Sensor Data: Alternatives to Supervised Learning for Human Activity Recognition
Anirudh Som, Jayaraman J. Thiagarajan, Rushil Anirudh, Matthew P. Buman, Pavan Turaga
Paper


Publications
10) AMC-Loss: Angular Margin Contrastive Loss for Improved Explainability in Image Classification
Hongjun Choi, Anirudh Som, Pavan Turaga
Computer Vision and Pattern Recognition (CVPR) Workshops, 2020
Paper


9) PI-Net: A Deep Learning Approach to Extract Topological Persistence Images
Anirudh Som, Hongjun Choi, Karthikeyan N. Ramamurthy, Matthew P. Buman, Pavan Turaga
Computer Vision and Pattern Recognition (CVPR) Workshops, 2020
Paper | Code | Slides | Video


8) Unsupervised Pre-trained Models from Healthy ADLs Improve Parkinson’s Disease Classification of Gait Patterns
Anirudh Som, Narayanan Krishnamurthi, Matthew P. Buman, Pavan Turaga
IEEE Engineering in Medicine and Biology Society (EMBC), 2020
Paper | Slides


7) Topological Descriptors for Parkinson’s Disease Classification and Regression Analysis
Afra Nawar, Farhan Rahman, Narayanan Krishnamurthi, Anirudh Som, Pavan Turaga
IEEE Engineering in Medicine and Biology Society (EMBC), 2020
Paper | Code | Slides | Video


6) Geometric Metrics for Topological Representations
Anirudh Som, Karthikeyan N. Ramamurthy, Pavan Turaga
Book-chapter in the Springer Handbook of Variational Methods for Nonlinear Geometric Data, 2020
Handbook | Chapter


5) Perturbation Robust Representations of Topological Persistence Diagrams
Anirudh Som, Kowshik Thopalli, Karthikeyan N. Ramamurthy, Vinay Venkataraman, Ankita Shukla, Pavan Turaga
European Conference on Computer Vision (ECCV), 2018
Paper | Supplementary | Poster | Code


4) Multiscale Evolution of Attractor-shape Descriptors for Assessing Parkinson's Disease Severity
Anirudh Som, Narayanan Krishnamurthi, Vinay Venkataraman, Karthikeyan N. Ramamurthy, Pavan Turaga
Global Conference on Signal and Information Processing (GlobalSIP), 2017
Paper | Slides


3) Riemannian Geometric Approaches for Measuring Movement Quality
Anirudh Som, Rushil Anirudh, Qiao Wang, Pavan Turaga
Computer Vision and Pattern Recognition (CVPR) Workshops, 2016
Paper | Poster


2) Attractor-shape Descriptors for Balance Impairment Assessment in Parkinson's Disease
Anirudh Som, Narayanan Krishnamurthi, Vinay Venkataraman, Pavan Turaga
IEEE Engineering in Medicine and Biology Society (EMBC), 2016
Paper | Slides


1) Geometric Approaches for Modeling Movement Quality: Applications in Motor Control and Therapy
Anirudh Som | Master of Science (MS) Thesis
ProQuest LLC, 2016
Paper | Slides
Teaching
EEE 334 - Circuits 2 | Spring 2017 to Spring 2019