Abdul Moiz

PROFESSIONAL PROFILE I am an aspiring AI and machine learning professional with hands-on experience across research, development, and practical applications. During my internship at NCAI, TUKL, I focused on EEG analysis and explainable AI, developing deep learning models to classify normal and abnormal EEG segments, applying interpretability techniques such as Grad-CAM, LIME, and SHAP, and building a pipeline for automated EEG report generation using large language models (LLMs). At RheinMain University of Applied Sciences, I worked on super-resolution of satellite images, leveraging diffusion-based generative models to enhance image clarity and preserve fine-grained details. In addition to my internships, I have completed freelance projects in AI and web development, building end-to-end solutions that demonstrate my skills in both machine learning and full-stack development. EDUCATION Software Engineering SEECS , Islamabad , 3.14 (2022) INTERNSHIP EXPERIENCE NCAI TUKL 03-Jun-2024 - 31-May-2025 During my internship, I worked on multiple interdisciplinary projects involving machine learning, computer vision, and explainable AI. I developed explainable AI models for EEG abnormality analysis and automated report generation using large language models (LLMs). I also built and trained models on time-series and image data collected from a Wacom IoT device, applying deep learning techniques for pattern recognition. Additionally, I worked with eye-tracking data to identify user focus regions and integrated multiple computer vision techniques for data analysis and visualization. This experience strengthened my skills in end-to-end model development, data processing, and the practical application of AI in real-world healthcare and human–computer interaction scenarios. Rhienmanin University of applied sciences(DAAD Internship) 11-Jun-2025 - 09-Oct-2025 During my internship at RheinMain University of Applied Sciences, I worked on enhancing the resolution of satellite images with a focus on diffusion-based super-resolution models. I explored state-of-the-art generative techniques to improve image clarity and preserve fine-grained details, experimenting with different model architectures and training strategies. This work allowed me to gain hands-on experience in applying deep learning for remote sensing and image enhancement, as well as understanding the challenges of high-resolution satellite imagery. FINAL YEAR PROJECT NeuroXplain I am currently working on my final year project focused on EEG analysis and automated report generation. I am developing deep learning models to classify normal and abnormal EEG segments and applying explainable AI techniques such as Grad-CAM, LIME, and SHAP to identify and visualize clinically significant abnormal regions. Alongside this, I am building a pipeline that converts model predictions and extracted EEG features into structured, human-readable reports using large language models (LLMs). This work aims to make EEG analysis more transparent and clinically interpretable, bridging the gap between AI predictions and actionable insights for healthcare professionals. TECHNICAL EXPERTISE Machine Learning & Deep Learning

I am an aspiring AI and machine learning professional with hands-on experience across research, development, and practical applications. During my internship at NCAI, TUKL, I focused on EEG analysis and explainable AI, developing deep learning models to classify normal and abnormal EEG segments, applying interpretability techniques such as Grad-CAM, LIME, and SHAP, and building a pipeline for automated EEG report generation using large language models (LLMs). At RheinMain University of Applied Sciences, I worked on super-resolution of satellite images, leveraging diffusion-based generative models to enhance image clarity and preserve fine-grained details. In addition to my internships, I have completed freelance projects in AI and web development, building end-to-end solutions that demonstrate my skills in both machine learning and full-stack development.