Deep learning based ICU monitoring of patients using CCTV footage
ICU monitoring using CCTV footage
Posts by Collection
projects
OSIC Pulmonary Fibrosis Progression
Position 131/2907, Predict lung function decline, Kaggle
RANZCR CLiP - Catheter and Line Position Challenge
Classify the presence and correct placement of tubes on chest x-rays to save lives, Kaggle Competition
CommonLit Readability Prize
Position 305/3852, Kaggle
COVCT: GSOC proposal for android application (CovCT) for analyzing COVID and non-COVID data.
Project proposal for Google GSOC in association with Emory university school of medicine.
DermaAI - Deep learning based Skin lesions Classification
CNNs based classification of skin lesions
EyeAI - Android app
Prototype Deep leanring based android app for eye disease classification 
MLB Player Digital Engagement Forecasting
Position 65/852, Kaggle
Vitals: Android app to track patient vitals
Track what matters
Optiver Realized Volatility Prediction
Position 356/3852, Kaggle, Apply your data science skills to make financial markets better
Sartorius - Cell Instance Segmentation
Position 230/1305, Detect single neuronal cells in microscopy images, Kaggle
Multiagent agent efficient team coordination in Football using QMIX reinforcement learning algorithm
Project for CS-7642, MSCS Gatech, USA
Surgical Tracking in endoscopic videos
Tracking surgical views in endoscopic videos
AMEX Default Prediction
Project for CS-7641, MSCS Gatech, USA
Efficient blood pumping in Bionic heart via distributed control as Multi-agent system
Project for Multirobot systems (CS-7631), MSCS Gatech, USA
Path planning to control robotic arm for suturing
Project for CS-6739 Medical robotics course, MSCS Gatech, USA
Optimize Task Allocation via Redundancy in Multi-Agent Systems
Project for CS-7431 Multi-agent systems course, MSCS Gatech, USA
publications
In-Silico Repositioning of Drugs for Neurofibromatosis 2 Vestibular Schwannoma using Machine Learning
Published in Synapse, 2020
Deep learning based model to re-purpose drugs drugs to new diseases(Neurofibromatosis 2 Vestibular Schwannoma). Part of submission for Hack4Rare hacakathon by MIT.
Download pdf here here
Personalized Brain State Targeting via Reinforcement Learning
Published in Neuromatch academy, 2020
We propose a novel use of reinforcement learning as an active closed-loop assistive system that learns in real time to lead any brain state to a given goal state.
Download pdf here here
Validation of expert system enhanced deep learning algorithm for automated screening for COVID-Pneumonia on chest X-rays
Published in Nature - Scientific Reports, 2021
We describe CovBaseAI, an explainable tool using an ensemble of three DL models and an expert decision system (EDS) for COVID-Pneumonia diagnosis, trained entirely on pre-COVID-19 datasets.
Download pdf here here
Roadmap to Autonomous Surgery - A Framework to Surgical Autonomy
Published in arxiv, 2022
We break down the path of surgical automation into features required and current challenges and advances required to make this happen
Download pdf here here
Multi-Modality Deep Learning Methods to Learn Alzheimer’s Disease Classification
Published in Georgia Institute of Technology, 2023
Paper presentation at Suddath Symposium(Biomedical Informatics and AI for Biodiscovery and Healthcare) Georgia Institute of Technology. Mar 2023
Autonomous Soft Tissue Retraction Using Demonstration-Guided Reinforcement Learning
Published in MICCAI conference, 2023
Learning to control DaVinci surgical robot for soft tissue manipulation using expert demonstrations.
Download pdf here here
Multi-Modal Deep Feature Integration for Alzheimer’s Disease Staging
Published in IEEE BIBM conference, 2023
Learning Alzheimer’s disease stage classification using multimodal data: MRI, PET, EHR, and Genomics data. Published at IEEE BIBM conference 2023
Class-Incremental Continual Learning for General Purpose Healthcare Models
Published in NEURIPS, 2023
Building medical imaging AI that can learn new diseases without catastrophic forgetting on previous tasks, in different medical modalities, specialties, and hospitals.
GraphPrint: Combining Traditional Fingerprint with Graph Neural Networks For Drug Target Prediction
Published in NEURIPS, 2023
Combining traditional molecular and protein features with 3D features from graph neural network for drug target affinity prediction.