Subit Chakrabarti
Boston, Massachusetts, United States
1K followers
500+ connections
About
I develop novel spatio-temporal machine learning methods applicable for large-scale earth…
Activity
-
I have been very impressed by Coastal Carbon and the work they are doing to provide better data about nature-based ocean restoration projects. If you…
I have been very impressed by Coastal Carbon and the work they are doing to provide better data about nature-based ocean restoration projects. If you…
Shared by Subit Chakrabarti
Experience
Education
-
-
Activities and Societies: Audio Engineering Society (AES), Small Satellite Design Club (SSDC)
Specialization: Control, Signal Processing and Machine Learning.
-
-
Activities and Societies: IEEE Student Chapter
Graduated with Honors. Secretary of the IEEE Student Chapter and increased student participation by more than 50%. Started a collegiate intra-mural technical competition with a variety of events to encourage students to pursue STEM majors. Was Instructor at two regional IEEE workshops - on "Implementation of Algorithms on Embedded Devices" and "Starting C Programming".
Volunteer Experience
-
Chair for Young Professional Activities
IEEE Geoscience and Remote Sensing (GRSS)
- 4 years 2 months
Organize professional development, technical outreach, and social events for young professionals in the IEEE Geosciences and Remote Sensing society.
-
Voting member of the Administrative Committee
IEEE Geoscience and Remote Sensing (GRSS)
- Present 3 years 8 months
Elected by society members to serve on the society's board.
Publications
-
Disaggregation of Remotely Sensed Soil Moisture in Heterogeneous Landscapes using Holistic Structure based Models
IEEE Transactions on Geoscience and Remote Sensing
-
Downscaling Satellite based Soil Moisture using High Resolution Remote Sensing Products and Information Theory
IEEE Geoscience and Remote Sensing Society
(Under Review)
Other authors -
Downscaling Satellite-Based Soil Moisture in Heterogeneous Regions Using High-Resolution Remote Sensing Products and Information Theory: A Synthetic Study
IEEE Transactions on Geoscience and Remote Sensing
In this study, a novel methodology based upon the information-theoretic measures of entropy and mutual information was implemented to downscale satellite soil moisture observations from 10 km to 1 km.
Other authors -
Assimilation of SMOS Soil Moisture for Quantifying Drought Impacts on Crop Yield in Agricultural Regions
EEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
This study investigates the effects of agricultural drought on crop yields, through integration of crop growth models and remote sensing observations using a machine learning driven downscaling-assimilation framework.
Other authors -
Assimilation of Downscaled SMOS Soil Moisture for Quantifying Drought Impacts on Crop Yield in Agricultural Regions in Brazil
American Geophysics Union Fall Meeting Abstracts
Courses
-
Advanced Electromagnetics
EEL6535
-
Advanced Machine Learning
CAP6617
-
Advanced Projects in Data Sciences
CIS6930
-
Information Theoretic Machine Learning
EEL6935
-
Machine Learning
CAP6610
-
Noise in Linear Systems
EEL5544
-
Remote Sensing In Hydrology
ABE6037
Projects
-
Using Manifold based Dimensionality Reduction for Image Race Classification
Compared 13 of the most popular dimensionality reduction methods based on their performance by,
1) Comparing their performance on benchmark data-sets.
2) Evaluating loss in SVM classifier performance following dimensionality reduction, and,
3) Implementing the Dimensionality Reduction+Clustering scheme on the RaceSpace Data set (http://www.cise.ufl.edu/~anand/RaceSpace.tar.xz)
The Algorithms compared were :- ISOMAP, Locally Linear Embedding, Laplacian Eigenmaps, Hessian…Compared 13 of the most popular dimensionality reduction methods based on their performance by,
1) Comparing their performance on benchmark data-sets.
2) Evaluating loss in SVM classifier performance following dimensionality reduction, and,
3) Implementing the Dimensionality Reduction+Clustering scheme on the RaceSpace Data set (http://www.cise.ufl.edu/~anand/RaceSpace.tar.xz)
The Algorithms compared were :- ISOMAP, Locally Linear Embedding, Laplacian Eigenmaps, Hessian Eigenmaps, PCA, Kernel-PCA, Independant Component Analysis, Self-Organizing Maps, Local Tangent Space Alignment, Laussian Process Latent Variable analysis, Stochastic Proximity Embedding, Diffusion Maps and Deep Autoencoders.Other creators -
Parallelizing PRI
Implemented the PRI disaggregatin algorithm from one of my previous publications (https://dx.doi.org/10.1109/JSTARS.2014.2315999) on a 64-core subsection of the University of Florida High Performance Computer using the OpenMPI framework and new metrics. Reduced computation times by upto 75 % when tested over the Lower La Plata basin region of South America.
-
Investigation of Stiff Deployment Mechanisms for Small Satellite Platforms
Mentored a team of around 10 undergraduate students from University of Florida in building a 3-u nano-satellite to study the properties of a novel deployment mechanism in situations where the satellite has to undergo rapid retargeting maneuvers. The team was selected to fly in NASA's Reduced Gravity Experiment program in June 2014 to test the hypotheses we put forward. We successfully recorded the stress on the mechanism that deployment caused.
Other creators -
A Comparative Review of Supervised Learning Algorithms.
Compares the most performance of 11 of the most popular supervised learning algorithms of varying complexity on standard data-sets and subsequently, implements them on them on the very high volume HIGGS Boson Data set to understand their scalability.
Algorithms used : Kernel SVM, k-Nearest Neighbours, Naive Bayes, Random Forests, Recursive Neural Networks, Rate Distortion Auto-Encoders, Ada-Boost and a deep belief network.
Other creators -
Image Segmentation using the Principle of Relevant Information
Applied the Principle of Relevant Information (previously developed at CNEL) to Image Segmentation which performs better than state-of-the-art benchmarks.
-
Investigating the Limits of Traditional FIR filters
Implemented hierarchial FIR filter banks to separate a noisy Electroencephalogram (EEG) signal to show that the most complex FIR system can be beaten by a simple adaptive Weiner filter.
-
CORDIC Rotation on an 8-Bit Processor for Scientific Computation
Designed an area efficient implementation of the CORDIC (COordinate Rotation Digital Computer) algorithm which is an iterative algorithm for the calculation of the rotation of a two dimensional vector in linear, circular or hyperbolic coordinates using only adders and shifters.
-
Design and Implementation of a PC based Multi Motor System for Actuation of a Four Fingered Dexterous Robotic Hand
Developed a machine learning algorithm for a virtual sensing interface between a tele-operated robotic hand and sensing glove. Performed integration of sensor data to characterize robotic hand movements based on real life glove gestures.
-
Design and implementation of a high frequency resonant transformer for wireless transmission of Electricity.
Modified Tesla's original designs for the Spark-Gap Coil by adding modern power electronics to light up a fluorescent bulb in a ~3 m radius without using exorbitant levels of power in the source coil.
-
Autonomous Navigation through Obstacle Source constrained to using an 8-Bit Processor
Developed an optimized version the flood-fill algorithm with dynamic constraints for an autonomous vehicle capable of navigating through a maze in the shortest possible time, where the starting and end points are not predefined.
-
Real-time non-coherent acquisition of packets in an 802.11b channel
-
Built a real-time scheme to acquire the 56-bit SYNC code for 802.11g communications, in the presence of AWGN when neither timing or phase knowledge is available using intelligent energy change detection in the channel.
Honors & Awards
-
IEEE IGARSS 2015 Student Paper Contest - 2nd Prize
IEEE
One of the 3 prize winning presentations out of 10 finalists at the IEEE IGARSS 2015 in Milan, Italy. The 10 finalists were chosen by the IEEE awards committee out of 100 chosen submissions to the IGARSS conference. More details at www.igarss2015.org/StudentContest.asp
https://www.youtube.com/watch?v=WOTNDEzIrFM -
IEEE Geoscience and Remote Sensing Travel Grant
IEEE
Travel grant issued to attend IEEE IGARSS 2015 in Italy.
-
SSDC Team Lead of the Year
Small Satellite Design Club, University of Florida
For leading the UF Microgravity team into the top stage of the NASA reduced gravity program.
-
Superior Academic Achievement Award
School of Engineering, University of Florida
-
Indian Academy of Sciences Undergraduate Research Fellowship
Indian Academy of Sciences (http://www.ias.ac.in/)
About 100 fellowships awarded every year from >4500 applications throughout India.
Test Scores
-
Test of English as a Foreign Language (TOEFL)
Score: 117/120
-
Graduate Record Examination (GRE)
Score: 327/340
Languages
-
English
Full professional proficiency
-
Hindi
Native or bilingual proficiency
-
Bengali
Native or bilingual proficiency
-
French
Elementary proficiency
Organizations
-
American Geophysics Union
Graduate Student Member
- Present -
IEEE
Student Member
- PresentWas Secretary of Local Student Chapter for Year 2011-2012
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 More