Angelic Charles
@visionbyangelicComputational Neuroscience Β· ML Β· Brains, machines, and everything in between. π§
Language Breakdown
Lines of code distribution across 24 owned repositories
I-Shaped Developer
I-shapedSpecialist β deep expertise in Jupyter Notebook
Collaboration Network
Global Impact visualization
Repos
27
PRs
0
Growth
+18%
Top Collaborators
No collaborator data yet.
Coding Streak
Contribution activity over the past year
Top Repositories
GitHub README
A playground for my creative experiments! This repository houses a collection of miscellaneous projects, ranging from interactive frontend web effects to standalone Python scripts. It serves as a sandbox for testing logic, UI/UX concepts, and visual algorithms.
The Elizabethan Lover is a full-stack Generative AI application that simulates a "Snapchat" experience with historical figures. Unlike generic chatbots, this project enforces rigid historical personas (Shakespeare, Romeo, Juliet) using System Prompt Engineering and Google's Gemini 2.5 Flash architecture.
A curated collection of machine learning projects exploring Natural Language Processing (NLP), Emotion AI, and Multimodal Deep Learning. These projects demonstrate model training, fine-tuning, and real-world application deployment.
A curated collection of computer vision projects built using Python, OpenCV, and MediaPipe. These projects explore real-time image processing, gesture recognition, object tracking, and augmented overlays.
A multi-agent AI system that analyses the LinkedIn Job Postings dataset to surface in-demand skills, top-paying roles, and actionable career strategies β with a built-in chat interface to ask follow-up questions about the data. The system ingests LinkedIn job postings data, runs it through four specialised agents, produces a structured JSON
A Deep Learning Safety System that analyzes raw EEG data from consumer-grade hardware (the $200 Muse Headband) to detect fatigue before subjective awareness. The system applies rigorous signal processing and a 1D-CNN to learn the brain's specific "fatigue fingerprint" directly from the raw time-series β no manual feature extraction required.
Emotiwave is a research project investigating how well AI systems can recognise human emotions from video when one or more sensors fail. The core question: if you lose the audio, or the camera, or the transcript β does the system fall apart, or does it adapt?
This repository documents projects, code, and publications from my 6-month intensive internship with DataraFlow β covering Data Science, Machine Learning, and Generative AI. Graduated valedictorian (1 of 365 applicants).
Open Source Impact
Contributions to external projects
