Mr. Samir Younis | Machine Learning | Best Researcher Award

Machine Learning Engineer, Arab Academy for Science and Technology, Egypt

Samir Younis is a dynamic Data Scientist from Alexandria, Egypt, with a strong foundation in computer engineering and a passion for leveraging machine learning to solve real-world problems. With a track record of impactful projects and a commitment to innovation, he has quickly established himself in the field. 🌟💻

 Profile

Google Scholar

Education

Samir earned his Bachelor’s degree in Computer Engineering from the Arab Academy For Science and Technology in June 2023, graduating with a GPA of 3.2. His academic journey provided him with a solid grounding in engineering principles and advanced computational techniques. 🎓📚

Experience

 

• Machine Learning Engineer, Upwork (May 2023 – Present)
  Samir builds and deploys custom machine learning models to address complex business challenges for clients on Upwork. His projects include an Atrial Fibrillation Detection System, an Autism Spectrum Disorder Early Detection Model, Transfer Learning Benchmarking Research, and an Automated Attendance System Using Facial Recognition.
• Data Scientist Intern, Encryptix (May 2024 – June 2024)
  During his internship, Samir applied machine learning techniques to various prediction and classification tasks, enhancing his practical experience in the field. 🔍🤖

Research Interests

Samir’s research interests lie in machine learning applications in healthcare and image recognition. He focuses on developing robust algorithms for early disease detection and facial recognition, showcasing his versatility and commitment to advancing technology. 🧠🔬

Awards and Honors

Samir was honored by the Information Technology Industry Development Agency (ITIDA) as a Pre-Incubation Winner on a national scale for his innovative contributions to technology and research. This recognition underscores his potential and impact in the field. 🏆🎉

Publications Top Notes

• Evaluating Convolutional Neural Networks and Vision Transformers for Baby Cry Sound Analysis
  Published in MDPI’s ‘Future Internet’ journal, this paper presents an advanced algorithm achieving a 98.3% accuracy rate in detecting the reasons behind baby crying, marking significant advancements in machine learning applications for infant care. Link, 2023.
• IBM Capstone Project Utilizing AI for Early Lung Disease Detection
  This project involved data curation, quality assessment, and the implementation of the Compacted Convolutional Transformer (CCT) for robust medical image classification, contributing to improved healthcare outcomes. Link, 2024.
• One Shot Face Recognition System
  Samir implemented a facial recognition system capable of recognizing individuals from just one image per person, utilizing pre-trained deep learning models and OpenCV for face detection and embedding generation. Link, 2023.