Insaf Hamdi

• I have been selected as a student trainee at A2SV - Africa to Silicon Valley, where I have had the opportunity to immerse myself in Python software engineering and coding contests. A2SV is a pioneering nonprofit social enterprise committed to empowering talented young software engineers in Africa to address the continent's most pressing challenges through technology.

• MLAct is the first third party ML Community that is officially supported by Google in Tunisia among +105 ML Communities in the world.

• My project was among the 170 projects admitted out of 223 submissions and I received a score of 36/50.

• Conducted security testing for chatbots, identifying vulnerabilities using tools like Burp Suite and ZAP. • Automated security tests and scenarios with Robot Framework to ensure robust security measures. • Created security scenarios and identified flaws to enhance the chatbot's resistance to potential cyber-attacks. • Collaborated in an Agile/Scrum environment, contributing to the team’s sprints and adapting to the iterative development process. • Gained hands-on experience in web security, automation, and QA, which broadened my expertise in safeguarding online platforms.

• Collaborated with startup Deaf Square on adaptive learning projects, leveraging my expertise in data science and artificial intelligence. Developed an emotion recognition model to enhance communication tools for the deaf community.

• Finalist in a prestigious competition, resulting in a fully-funded trip to an international event. • Collaborated with students from Columbia Business School on innovative projects, enhancing skills in teamwork, leadership, and cross-disciplinary collaboration while focusing on technology and entrepreneurship. • Selected as one of only 36 solo talents in the OST program, recognizing emerging leaders in technology and innovation.

• Project 1: Myanmar Chapter - COVID-19 Detection from Chest X-ray Images using Deep Learning Developed a deep learning model to detect COVID-19 from chest X-ray images, utilizing convolutional neural networks (CNNs) to enhance diagnostic accuracy during the pandemic. This project involved pre-processing a dataset of X-ray images and training the model to achieve a high accuracy rate in identifying COVID-19 cases. • Project 2: Analyzing Maternal Health in Nigeria using Machine learning Analyzed maternal health data in Nigeria using machine learning techniques to identify key factors affecting maternal health outcomes. Collected and pre-processed a comprehensive dataset, applying various machine learning algorithms to uncover patterns and insights. Additionally, we developed an interactive dashboard to visualize the findings and present actionable recommendations aimed at improving maternal healthcare services and addressing disparities.

• Conducted comprehensive data analysis, developed interactive dashboards using Power BI, and improved data visualization for clear insights.