Aditya Singh

Hi! I’m Aditya.

I’m a Machine Learning Data Scientist at Thermo Fisher Scientific where I focus on B2B recommender systems. Previously, I graduated with highest distinction in Information Systems from Carnegie Mellon University. I have a broad range of interests ranging from evaluation of ML in production, scaleable use cases of intelligent system and natural language processing with a focus on domain specific capabilities. I also assist various startups in these areas.

My work has been published in IEEE Radar and AMIA, won national competitions and led to patent applications.

~ past life

At CMU, besides academia I spent my time doing research, teaching and playing football. I collaborated on research with Prof. Bhiksha Raj, Prof. Rema Padman and Prof. Seth Goldstein. I also led my team to win the CMU Summer Football Championship. Prior to CMU, I graduated magna cum laude in Computer Science from Ashoka University, where I was advised by Prof. Debayan Gupta.

I love meeting cool people on the internet - you can reach me at adiisingh1099@gmail.com

news

May 05, 2023	Won 1st place and a prize of $35k in the finals of 3C-AI4H Bowl hosted by Institute of Augmented Intelligence, Northwestern University for AIquitas, the AI system matching clinical trials to patients.
Jan 30, 2023	Joined the Intelligence Generation team in the Data Science Center of Excellence, Corporate at Thermo Fisher Scientific as a Senior Data Scientist.
Jan 15, 2023	Our work “A Machine Learning Approach to Evaluate Clinical Trial Criteria” was accepted in the AMIA Clinical Informatics Conference 2023.
Dec 15, 2022	Graduated with highest distinction from Carnegie Mellon University with a Msc. in Information Systems.
Jun 01, 2022	Joined the NLP team as a Data Scientist intern at Verusen.AI.

selected publications

AMIA

Designing Clinical Trials to Improve Diversity, Equity and Inclusion (DEI): A Machine Learning Approach to Evaluate Clinical Trial Criteria

In AMIA 2023 Clinical Informatics Conference , May 2023

Abs PDF Poster

Presentation Outline 1. Problem and Consequences: Lack of DEI in clinical trials 2. Status Quo and Challenges: Discussion of existing processes and bottlenecks 3. Proposed Solution: Discussion of system and technical components 4. Results: Performance of ML models, use case demonstration, user feedback from prototyping 5. Future Scope: Opportunities for extensions, scalability and generalizability
IEEE Radar

WALDO Finds You using Machine Learning: Wireless Adaptive Location and Detection of Objects

Aditya Singh, Pratyush Kumar, Vedansh Priyadarshi, and 3 more authors

In 2021 IEEE Radar Conference (RadarConf21) , May 2021

Abs PDF

We present a novel radar-based system for real-time indoor positioning and detection of objects and human-bodies with low-quality, inexpensive sensors. Using modern deep learning methods, we avoid the use of expensive hardware and computationally-expensive signal processing methods for object detection.We train our model on mini-Doppler maps, collected via software defined radios. Crucially, our system is different from existing RF-based detection systems as it operates in a less crowded frequency range of 433 MHz, allowing us to use inexpensive off-the shelf hardware. Our system, based on the VGG-16 model, reports high-accuracy results on: (1) classification of different objects/materials (plastic, glass, metal); (2) detection and classification of multiple visually and materially similar objects and the human-body; and (3) Simple object detection at different distances between the transmitter T x and the receiver R x .WALDO, using low frequency radio waves, is able to handle occlusions and bad lighting environments. Our results demonstrate that Deep Learning methods can be combined with inexpensive, low-frequency radars to achieve high accuracy in real-time on various useful tasks.