For employers

Hire this AI Trainer

Sign in or create an account to invite AI Trainers to your job.

LoginCreate account
Invite to Job
H

Himanshu Bhisikar

Anomaly detection in astronomical imaging data (Research Experience)

India flagNagpur, India
Expert

Key Skills

Software

No software listed

Top Subject Matter

Astronomical imaging data
Astronomical image data
galaxy morphology

Top Data Types

ImageImage

Top Task Types

Classification

Freelancer Overview

Anomaly detection in astronomical imaging data (Research Experience). Brings 6+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include PyTorch, scikit-learn, and SExtractor. Education includes Bachelor of Science - Master of Science Dual Degree, Indian Institute of Science Education and Research, Pune (2022). AI-training focus includes data types such as Image and labeling workflows including Classification.

Expert

Labeling Experience

Anomaly detection in astronomical imaging data (Research Experience)

ImageClassification
Developed and applied a deep CNN-based feature extractor to identify anomalous images (e.g., background gradients, diffraction) in astronomical datasets. Labeled images as either regular or anomalous based on pre-defined threshold criteria. Used dimension reduction and clustering for anomaly classification. • Image anomalies were flagged for further review. • Utilized principal component analysis and Gaussian mixture models. • Assisted in curating datasets for machine learning model training. • Focused on data derived from the SDSS database.

Developed and applied a deep CNN-based feature extractor to identify anomalous images (e.g., background gradients, diffraction) in astronomical datasets. Labeled images as either regular or anomalous based on pre-defined threshold criteria. Used dimension reduction and clustering for anomaly classification. • Image anomalies were flagged for further review. • Utilized principal component analysis and Gaussian mixture models. • Assisted in curating datasets for machine learning model training. • Focused on data derived from the SDSS database.

2024 - Present

ML classification of Compact Massive and Normal Elliptical Galaxies

ImageClassification
Led ML pipeline development for classifying compact massive and normal elliptical galaxies. Used extracted structural parameters from imaging data to generate labeled datasets. Supervised feature selection and model training for accurate morphological classification. • Employed Astropy and scikit-learn as core libraries. • Achieved high labeling precision (≥97% accuracy). • Applied Fisher scores for dataset refinement. • Morphological drivers of compactness were quantified through feature importance analysis.

Led ML pipeline development for classifying compact massive and normal elliptical galaxies. Used extracted structural parameters from imaging data to generate labeled datasets. Supervised feature selection and model training for accurate morphological classification. • Employed Astropy and scikit-learn as core libraries. • Achieved high labeling precision (≥97% accuracy). • Applied Fisher scores for dataset refinement. • Morphological drivers of compactness were quantified through feature importance analysis.

2022 - 2023

Data labeling for star-forming regions in NGC4571

ImageClassification
Performed source detection and aperture photometry to identify and label star-forming clumps in multi-wavelength galaxy images. Used labeling to associate molecular gas distributions with star-forming activity. Labeled key structures for subsequent spatial trend analysis in astronomical research. • Applied SExtractor, sep, and photutils during the process. • Annotated UV, optical, and sub-mm imaging datasets. • Labeling informed subsequent feature correlation studies. • Supported galaxy-wide morphological investigations.

Performed source detection and aperture photometry to identify and label star-forming clumps in multi-wavelength galaxy images. Used labeling to associate molecular gas distributions with star-forming activity. Labeled key structures for subsequent spatial trend analysis in astronomical research. • Applied SExtractor, sep, and photutils during the process. • Annotated UV, optical, and sub-mm imaging datasets. • Labeling informed subsequent feature correlation studies. • Supported galaxy-wide morphological investigations.

2021 - 2022

Education

I

Indian Institute of Science Education and Research, Pune

Bachelor of Science - Master of Science Dual Degree, Physics

Bachelor of Science - Master of Science Dual Degree
2016 - 2022

Work History

I

Indian Institute Of Astrophysics

Project Associate

Bengaluru
2024 - Present
I

Indian Institute Of Technology

Research Intern

Indore
2024 - 2024