Mohammed Aljammal

• Maintain and monitor CCTV systems across multiple branches to ensure continuous security
coverage.
• Provide technical support for computers, networks, system updates, and troubleshooting.
• Handle hardware/software maintenance and operational IT support.
• Diagnosed and repaired specialized jewelry manufacturing equipment, enhancing operational
reliability and reducing unexpected production halts.
• Monitored and calibrated precision tools to maintain consistent product quality, contributing
to enhanced craftsmanship and customer satisfaction.

• Maintain and monitor CCTV systems across multiple branches to ensure continuous security coverage.
• Provide technical support for computers, networks, system updates, and troubleshooting.
• Handle hardware/software maintenance and operational IT support.
• Diagnosed and repaired specialized jewelry manufacturing equipment, enhancing operational reliabil
ity and reducing unexpected production halts.
• Monitored and calibrated precision tools to maintain consistent product quality, contributing to en
hanced craftsmanship and customer satisfaction.

• Led the development and publication ofMediScanDL, an AI-driven system for automated
lung disease diagnosis using deep learning, contributing 90% of the research paper and system
design.
• Designed and implemented a custom Convolutional Neural Network (CNN) to classify chest
X-ray images into COVID-19, pneumonia, tuberculosis, and normal cases.
• and curated a dataset of 50, 000+ medical images, preprocessing and balancing to 31, 972
high-quality samples for optimal model performance.
• Achieved ˜93% test accuracy and 97% overall performance across multi-class classification
tasks. Grad-CAM visualize decisions enhance clinical

Published Research Paper
• Led the development and publication of MediScanDL, an AI-driven system for automated lung disease
diagnosis using deep learning, contributing 90% of the research paper and system design.
• Designed and implemented a custom Convolutional Neural Network (CNN) to classify chest X-ray
images into COVID-19, pneumonia, tuberculosis, and normal cases.
• Built and curated a dataset of 50, 000+ medical images, preprocessing and balancing to 31, 972 high
quality samples for optimal model performance.
• Achieved ∼93% test accuracy and 97% overall performance across multi-class classification tasks.
• Integrated Grad-CAM explainability to visualize model decisions and enhance clinical interpretability.
• Developed a full-stack web application using Flask, HTML, CSS, and JavaScript for real-time diag
nosis and user interaction.
• Implemented secure system features including OTP authentication and role-based dashboards for
doctors, patients, and admins.

• Completed intensive full-stack training: HTML, CSS, JavaScript, React, Node.js & Databases.
• Built practical front-end and back-end projects following industry best practices.
• Earned a Certificate of Achievement.

• Assisted in web development projects and basic network configuration tasks.
• Gained hands-on exposure to real-world networking and web deployment environments.