Profile banner
Sankalp Mallappa

Sankalp Mallappa

AI Engineer focused on deep learning and computer vision

Hyderabad, India
Joined April 2026
Favicon imagein.linkedin.com
Favicon imagescholar.google.com
Favicon imageresearchgate.net
Favicon imageorcid.org
Favicon imageresearcher.manipal.edu

Network

235 connections
📊
HR Operations Management
🤝
Talent Acquisition Leaders
💡
AI/ML Founders
⚕️
Healthcare AI Innovators
🏗️
AI Startup Builders
🧠
Applied AI Scientists
🌐
...

Summary

Research-focused early-career engineer with demonstrated work in deep learning for medical image analysis. Co-authored peer-reviewed work (IEEE Access) on YOLOv5-based models for intracranial hematoma detection and contributed to a conference paper on window-based stacking with YOLOv5. ieee+2
Practical AI engineering experience across startups, freelance engagements, and internships, with roles described as AI Engineer, freelance data scientist, and machine learning intern. rocketreach
Background in electronics, instrumentation, and robotics from undergraduate training and hands-on roles with Mars Rover Manipal, contributing to electronics and control systems work and related conference contributions. proceedings+1
Collaborative contributor across multidisciplinary teams, as evidenced by co-authorship with engineers and clinicians on imaging research and multiple co-authored publications indexed in academic profiles. dblp+2

Work

Education

Projects

Writing

YOLOv5s-CAM: A Deep Learning Model for Automated Detection and Classification for Types of Intracranial Hematoma in CT Images

January 1, 2023

IEEE Access journal article presenting a YOLOv5s-CAM deep learning model for locating and classifying types of intracranial hematoma in CT images; includes evaluation metrics and collaborative authorship across engineering and medical institutions.

Favicon imageieeexplore.ieee.org

An Efficient Detection of Intracranial Hematoma Using Window-Based Stacking and YOLOv5 Framework

January 1, 2023

Conference paper (2023) describing a windowing approach combined with YOLOv5 and feature processing techniques for automated intracranial hematoma detection in CT images with reported high mAP, precision, and recall.

Favicon imageieeexplore.ieee.org