Hi, I'm Kunwar Saaim

"Deep in the ocean of computer science lies your imagination, technical skills, and the viability of your ideas."

~ K. M. Saaim

About Me

I'm Saaim, Computer Vision and Deep Learning research fellow at Indian Institute of Technology Delhi, India .

I enjoy reading research papers and see how disparate topics relate to developing new ideas. My research interests are in Computer Vision and Applied Artificial Intelligence, including biomedical image/signal processing, bioinformatics, and deep learning application in natural sciences.

Currently, I am a Junior Research Fellow (JRF) in Assistech lab, IIT Delhi and am seeking a thesis-based master's program.

  • Degree: Bachelor of Computer Engineering
  • University Aligarh Muslim University, India

Here are a few technologies I've been working with recently:
  • Python
  • PyTorch
  • TensorFlow
  • Keras
  • OpenCV
  • OpenVINO
  • JAX
  • C/C++
  • JavaScript
  • Flask
  • PyQt5
  • HTML/CSS

Projects

  • All
  • Classification
  • Segmentation
  • Image Generation
  • Key Point Detection
Nowcasting
Nowcasting Satellite Images

Nowcasting (forecasting for short duration) of Multi-spectral Satellite Imagery using Neural Networks (Bachelor's Thesis - COC4980)

Read More GitLab
Nanoparticle Segmentation
Nanoparticle Segmentation

Explaining different black box Segmentation Networks for Nanoparticle TEM Images

Read More
File Fragment Classification
File Fragment Classification

Efficient File Fragment Classification using inception style depthwise Separable Convolutional network, trained on FFT-75 dataset. The model achieves state-of-the-art performance on accuracy and inference time.

Read More
Seizure Detection
Seizure Detection

Explainable Residual Depthwise Separable convolution-based architecture for Seizure Detection, trained on CHB-MIT EEG dataset.

Read More
Animal Pose
Aquatic Animal Pose Estimation

Markerless Pose Estimation of Aquatic Animals in Visual feed

Extended Abstract Poster
Disorder Protein
Classification of Disordered Residues in Intrinsically Disordered Proteins

It is a many-to-many problem for which we designed a neural network composed of Bidirectional ConvLSTM & effective skip connections to predict the chances of disorderness of each amino acid in a protein sequence.

Read More
Object Detection
TensorFlow Object Detection App

PyQt5 GUI application for object detection using TensorFlow Object Detection API.

GitHub
Retinal Image
Retinal Image Generation and Segmentation

Fully unsupervised two-step pipeline for synthesizing high-quality retinal images, along with the corresponding segmented vessel structure.

Read More
Smart Diagnose
Smart Diagnose

Smart Diagnose is a web app that predicts whether a chest x-ray consists of Pneumonia, in case of Pneumonia an image with localization on x-ray is also displayed.

GitHub

Resume

Education

Bachelor of Technology: Computer Engineering

2017 - 2021

Aligarh Muslim University, Aligarh, India

Bachelor's Thesis Title: Nowcasting of Multispectral Satellite Imagery from INSAT-3D using Neural Networks

Key Courses (Computer Science): Principles of Machine Learning, Cloud Computing, Theory of Computation, Data Structure and Algorithm, Design & analysis of Algorithm, Computer Network Design, Database Management System, Object Oriented Programming, Microprocessor Theory and Application

Key Courses (Mathematics): Discrete Structures, Numerical Analysis, Transform and Probability, Higher Mathematics (Contour Integration and Vector Differentiation), Applied Mathematics -I (Linear Algebra and Differential Equation), Applied Mathematics -II (Partial Differentiation and Multiple Integration)

Professional Experience

Indian Institute of Technology, Delhi | Junior Research Fellow

Sep 2021 – Present
  • Developing Mobility Assistant for Visually Impaired
  • Developing real-time face and object detection networks for Raspberry Pi accelerated using Intel Neural Compute Stick
  • Porting TensorFlow/PyTorch Model in OpenVINO

Indian Institute of Information Technology, Allahabad | Research Intern

Dec 2020 – Feb 2021
  • Worked on the development of Explainable AI model for Seizure Detection using EEG data.
  • Reviewed literature on Explainable AI techniques.
  • Designed Residual Depthwise Separable convolution-based architecture for seizure detection.

King Fahd University of Petroleum & Minerals, Dhahran | Research Intern

Jun 2020 – Nov 2020
  • Worked on File Fragment Classification which is part of digital forensics and data carving.
  • Developed a Depthwise Separable Convolution based model for efficient classification of data fragments, the model is 24 times faster than the current state-of-the-art.

Interdisciplinary Biotechnology Unit, AMU | Undergrad Researcher

Dec 2019 – March 2020
  • Worked on the localisation of intrinsically disordered regions in protein sequence given in Fasta format using residual ConvLSTM network.
  • Reviewed literature on deep learning techniques for drug repurposing specifically for Covid-19.

Olcademy | Web Development Intern

Jun 2019 – Aug 2019
  • Developed course card for e-learning platform with course title, subtitle, and ratings dynamically fetched from SQL database.
  • Build signup form, with various input data validations, checked through JavaScript.

Arabic Computer Systems | Management Intern

Apr 2019 – Jun 2019
  • Acted as an intermediate for business partnership between Arabic Computer System and other MNCs.
  • Collected partnership requirements and benefits of various companies and presented them to make better business partnership decisions.

Contact Me

Location:

Assistech Lab, Room No. 009
Amar Nath and Shashi Khosla School of IT
Indian Institute of Technology, Hauz Khas, New Delhi – 110016

Call:

+91 7895935973