Hi
I am
DON
Biomedical Engineer, Coder
I am a highly motivated and passionate medical engineering student working diligently towards a PhD and a career in the application of machine learning in brain signals. Driven by curiosity and guided by a philosophy of hard-work and perseverance I am highly competent in engineering, research design, python, R, machine learning and specifically deep neural networks for imaging and signal processing. I continuously strive to improve my skills and the quality of my work, where I am open to academic scrutiny and constructive feedback.
Education
Master of Research (MRes) - Neurotech (Neural Engineering) @ Imperial College London2023 - Current-
London, UK
Ongoing. Biomimetic Neural Networks for Signal Denoising at Kozlov lab. Modules include Neuroscience, Biomimetics, Brain-Computer Interface
Master of Research (MRes) - Biomedical Engineering @ King's College London2022-2023-
Bachelor of Science (BSc) - Psychology @ University of Bristol2018-2022-
Public Health Short Course @ Pontificia Universidad Javeriana2022+
Projects
Medical Imaging & Machine Learning
UNet Ensemble Learning
Scored 93% in advanced machine learning course where I used 3D U-Net and ensemble learning to segment lung tumors in MRI images (Medical Segmentation Decathlon dataset). To do this, I focused on optimization of hyperparameters, data augmentation, and ensembling methods
Multi-Modal Phenotyping for Tuberculous Meningitis
Developed, tested and refined multi-modal models designed to phenotype brain lesions in patients with Tuberculous Meningitis and HIV, and predict their clinical outcomes. Publication is forthcoming where my hope is that this research will eventually improve medical care and save lives
Surgical Path Planning with Robotic Operating System (ROS)
ROS for Surgical Path Planning. The project involves: 1. compute the trajectory that acheives critical structure avoidance, 2. minimizes the distance to the target 3. move the robot arm along the trajectory
VAE-GAN
Image example for the VAE-GAN project
VAE-GAN
The aim of this project is to implement and validate a VAE-GAN as per the original paper by ABL Larsen et al. (2015) and to apply it to X-ray images of hands
Predicting gestational age at scan and birth for neonates from the developing Human Connectome Project
Predict the gestational age at scan and birth for neonates using data from the developing Human Connectome Project. A pre-activation ResNet architecture (He, 2015) is used, integrating confounds to enhance prediction performance. The training process included data augmentation, weighted sampling to manage class imbalances, and early stopping for training
Classification of prematurity using structural connectivity using PCA
Predict neonatal prematurity using brain connectivity matrices as features. Initial logistic regression models showed high specificity but low sensitivity due to dataset imbalance; however, adjusting for class weights improved the model's performance in predicting preterm births. Visualization using PCA demonstrated the separation between term and preterm samples, both for true and predicted labels, with the updated model showing better alignment with the actual data
Neural Networks & Cognitive Science
MindSet
Contributed to development and testing of datasets to determine whether neural networks exhibit visual illusions (MindSet). This will enable the understanding of the difference and similarity between human vision and artificial system.
Measuring Perceptual Similarity in Neural Networks
A schematics animation made using manim, for MindSet project and the Orthographic DNN project. Click play to watch the animation
Orthographic Deep Neural Networks
Convolutional Neural Networks accounts for priming effect surprisingly well - better than dedicated psychological models
Other Projects
LLMs for Healthcare Records (Details are Confidential)
Current electronic healthcare record (EHR) systems encounter several issues, notably concerning accessibility and mobility of data, and the effective use of emerging technologies. A promising solution to these challenges is the application LLMs
Tensor Spectacle
A python package for visualizing a Sequence of Tensors
Clustering-Based Approximation for the Travelling Salesman Problem (TSP)
A hierarchical clustering-based approximation that proves to be significantly faster than genetic algorithm, especially with larger datasets - 974 times better solution (path length) and 1.22 times less computation time
Generative Model Art Plotter Pipeline
Using generative model for producing art, and reinforcement learning agent and a plotter for drawing it
Gesture Code
A project that aims to create simple, pythonic and intuitive syntax for gesture recognition
Skills
Machine Learning
Python
🐍 I love python! I have around 8,000+ hours spent on it!
Pytorch
🔦 I use pytorch as my main deep neural network framework because it is very pythonic and research friendly
MONAI
💉 Medical Open Network for Artificial Intelligence. Absolutely fantastic package for medical imaging processing!
Computer Vision
Medical Image Segmentation
Distributed Hyperparameter Tuning
🧮 I am developing a package that allows the user to define the dependencies between hyperparameters using very pythonic syntax
High Performance Computing
🖥️ I have 3 years experience with HPCs (training, finetuning etc.)
Generative Models
🤖 Trained a model to write poems at around 2019 (way before GBT era).
Embeddings
🤖 For information retrival in healthcare systems
Robot Operating System
Did a project on surgical path planning with it
Reinforcement Learning
🦾 Trained (and training) some models in drawing stuff with a mechanical plotter using DQN; worked with actor-critic method; currently trying to find a way to make the model produces large number of decision tensors (where I struggle the most)
Data Science
R & Statistics
💬 My first programming language, spent some good 3 years with it before python
Streamlit
🎛️ I use it for making quick dashboard for posters and presentations without having to use Javascript
Dash
🎛️ A little fancier than Streamlit, for making dashboard
Manim
📺 This is a package for making 3blue1brown-like animations. I am a community contributer - fix some bugs for the package sometimes
Development
Bash
I do shell scripting for various purposes 🚀
PyScript
🚀🐍 Python running in browsers
React JS
I use React JS for some dashboard applications with component-based architectures if I'd want to make it proper (like this one) 🌐
Git
Git is my go-to version control system for tracking changes in code 📝
Flask
Django
SQL
📊 I use it in some of my projects that involve relational database. Don't have too much to say about it
MongoDB
Structural databases, storing data in JSON-like format 📄
RESTful API
SSH
Encrypted communication with servers 🛡️
Continuous Integration
🔄 CI helps me automate the building and testing of code every time a change is commit. Saves a lot of time
C++
🖥️ I don't use it often, but can do if we need speedy code
MATLAB
📐 I don't use it often as I find most of things can be done in python, but can do when needed (wink)
Personal Skills & Values
Collaboration
Transparency
Honesty
Openess
Hard Working
Efficiency
Perseverance
Respect
Work Experience
Researcher @ University of Bristol2022 - Current-
Remote (Bristol, UK)
Coding and training models using distributed cloud computation; Carefully designing, generating and maintained datasets and GitHub repository for testing cognitive phenomenon in artificial neural networks; Contributed to publications in high-impact journals
Co-Founder & Tech Lead @ Across Medical2023 - Current-
London, UK
Provided constructive support to interns and junior staff members; Responsible for developing and testing initial prototype technology; Currently seeking first-round funding in collaboration with King’s College
Machine learning Engineer @ Amine Cyber2021+
Research Intern (Biomedical Engineering) @ King's College London2022 - 2023+
Used multi-modal (on image and non-image data) models to phenotype brain lesions in patients with Tuberculous Meningitis
Data analytics (Reverse Engineering & Optimisation) @ Youta Shengshi Tech2020+
Shengzheng, China
Challenged self to understand cutting-edge interpretation methods for compiled code; Results published on developer website