- Paris, France
My primary research interest is in Machine Learning, Data Science, Statistics, Systems Biology, and Bio Inspired Systems. The scope of my projects also include Pervasive Computing, Reality Mining, and Computer Vision.
A new tool for Collective Learning
Hydrodynamics of Super-Paramagnetic Micro-Beads
The primary interest in this study is the behaviour of magnetic micro-objects under magnetic field in water. We expect to quantify the hydrodynamic drag between dissimilar objects. My work here was to capture the motion of the beads (
r=2.4µm) under externally applied magnetic field as they attract towards each other. Strict requirements of the protocol included controlled medium viscosity, frame rate
>= 300 fps, and
We reached average frame rate of
~800 fps. Using open source tools
scikit-image, I developed a processing pipeline to isolate, track, and calculate motion dynamics from the frames.
The Mechanical Sense of Paramecium
At a crossroad between physics, biology, and neuroscience, coupled with experimental and theoretical biophysics, this project aims to decipher the mechanism simple organisms such as Paramecium use to detect and avoid obstacles in their trajectories. Using micromilled pools of defined geometry and automatic tracking of paramecia, we expect to find correlations between external stimuli and internal responses that give it a directional sense.
As a research intern, I developed high-frequency image analysis and hardware control pipeline to track long trajectories in real time. I wrote a driver for the Microscope Objective utilising 3D Vector Space, and a high-speed image aquisition and processing (~50fps) tool. Using these software we were able to follow the trajectory of moving Paramecium.
Study of Diversity in Phyllotactic Patterns
Phyllotaxis is the arrangement of lateral organs in plants. In this project we attempt to explain the origin of emergent patterns, transitions, and irregularities in such arrangements. Using cylindrical projection unrolling and unwarping, the aim was to develop a pipeline allowing better study of complicated plant organs.
Personalised Medical Events, Conferences, and Courses Recommendation for Doctors at NHS, UK
At Agora, I was responsible for designing and implementing web services for aggregation, classification, and personalised recommendation of events at National Health Services (NHS) in the UK.
Computer Vision and Information Extraction
Developed and shipped a utility for digitizing waveforms and extracting metadata from
ECGreports, written in pure Python. It is being used at Brigham and Women’s Hospital, Boston for processing more than a million patient records.
Also worked on extracting normalized tabular data from scanned medical records. Key challenges here involved handling skewed, desaturated and otherwise low quality images.
Survaider Web App and Survey Builder
Development of web app backend and
REST APIin Python using
Design and development of the frontend. Technology stack consisted
Socket.IOfor realtime content.
Human Activity Recognition from Acceleration data Under Naturalistic Conditions
The goal of this project was to develop a system for recognition of low level human activities, such as Walking, Running, Sitting, etc., using a single tri-axial accelerometer time series. The undertaken challenge of this system was to effectively solve the recognition task irrespective of the location of sensor on human body.
Using supervised learning method, we trained a Random Forest Classifier using feature vectors obtained via our model. We were able to produce an accuracy of
95%through our model.
Aspiring Researcher Challenge
As a research associate, I was part of the team which was responsible for developing a large, online experiment to study the wisdom of the crowd where I formulated the algorithm for scraping and formatting raw data off multiple crowdfunding platforms.
Publication: “Investigating the ‘Wisdom of Crowds’ at Scale”, ACM UIST 2015, Charlotte, NC.
Modelling and Network Analysis of Intronic miRNA Mediated Gene Expression Regulation
In this project, we developed a mathematical model for gene expression regulation via intronic micro
RNAs, based on emperical data and experimental observations at IGIB.
As a part of study, we’ve also generated a
miRNA <=> mRNAtarget network using various available databases.
Responsibilities include maintainance and development of the web portal, website and online presence of the organization.
Developed an open-source and modular
Worked to build a classification system for geospacial features between texts originated in different continents. Other responsibilities included design and development of several web portals, graphic designing, media and publishing tasks.
Talks and Workshops
Alohomora: Unlocking Magical Bits in Python
In this talk at FOSSASIA Summit, I gave a presentation covering several advance patterns in the Python programming language. In the presentation I introduced the audience with Metaclasses, Decorators and Patching.
Game Development Workshop under UK-India Education and Research Initiative
Delivered sessions on Arduino programming, DAC, ADC and PWM.
Approches Interdisciplinaires du Vivant
B.Tech. (IT and Mathematical Innovations)
- Information Technology
- Systems Biology
AISSCE (XII Std.)
AISSE (X Std.)
Hues: Colored terminal text made easy for Python
Hues is a Python package which facilitates printing ANSI encoded text to terminal in unix-like systems.
metaRNA: Find target sites for the miRNAs in genomic sequences
metaRNA finds potential target sites for the microRNAs in genomic sequences. It is built on miRanda, an algorithm for detection and ranking of the targets of microRNA.
PyBloomFilter: Fast, Memory Mapped Bloom Filter
The goal of
PyBloomFilteris to provide a fast, simple, scalable and correct library for Bloom Filters in Python.
MongoCapsule: Encapsulated MongoEngine
MongoCapsule is a very thin wrapper around MongoEngine. It encapsulates MongoEngine attributes under a single namespace and hence allows explicit declaration without context switches.
Elasticsearch-Synonyms: Utilities for working with Synonym Filter in Elasticsearch
This repository contains a curated dataset of synonyms in
SolrFormat. These synonyms can be used for Elasticsearch Synonym Token Filter configuration. It provides a tool to lint and validate the synonym files.
- Python ●●●●●
- Stylus/CSS ●●●●
- CoffeeScript ●●●●
- Print Media ●●●
- CAD/CAM ●●●
- Illustration ●●
- User Interface ●●●
- Scientific Computing ●●●●
- DevOps ●●●