Houfu Chen

ML Engineer | Digital Twin Researcher | PhD Candidate

> Explore Arch
[ OK ] Started System Logging Service.
[ OK ] Reached target System Initialization.
[ OK ] Started Kernel Logging Service.
Mounting /boot/efi...
Starting hc-core-services.service...
[ OK ] Started HC Core Services.
Loading MOTD...
⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⣀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀ ⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⣿⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀ ⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠛⠻⣶⡆⠀⠿⠀⣶⠒⠊⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀ ⠀⠀⠀⠀⠀⠀⠀⠀⢀⣀⣴⠾⠛⢹⣶⡤⢶⣿⡟⠶⠦⠄⠀⠀⠀⠀⠀⠀⠀⠀ ⠀⠀⠀⠀⠀⣠⣶⣤⣤⣤⣤⣴⠂⠸⠋⢀⣄⡉⠓⠀⠲⣶⣾⣿⣷⣄⠀⠀⠀⠀ ⠀⠀⠀⢀⣾⡿⠋⠁⣠⣤⣿⡟⢀⣠⣾⣿⣿⣿⣷⣶⣤⣼⣿⣿⣿⣿⣆⠀⠀⠀ ⠀⠀⠀⣾⡟⠀⣰⣿⣿⣿⣿⣷⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⡄⠀⠀ ⠀⠀⢸⡿⠀⣼⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⡇⠀⠀ ⠀⠀⢸⡇⢰⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⡇⠀⠀ ⠀⠀⢸⣿⣾⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⡇⠀⠀ ⠀⠀⠸⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⠁⠀⠀ ⠀⠀⠀⢻⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⠃⠀⠀⠀ ⠀⠀⠀⠀⠙⢿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⠟⠁⠀⠀⠀⠀ ⠀⠀⠀⠀⠀⠀⠉⠛⠿⢿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⡿⠟⠋⠀⠀⠀⠀⠀⠀⠀ ⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠉⠉⠉⠉⠉⠉⠁⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀

I am a PhD candidate and systems engineer. True to my engineering background, my approach is strictly practical: making complex simulation systems actually work...

  • > Building living digital twins for heterogeneous environments.
  • > Integrating machine learning, signal filtering, and probabilistic state estimation.
  • > Bridging the gap between noisy data and mechanistic biological models to turn theoretical WIPs into functional realities.
~/about_me $ ls

Education

  • MEng in Electrical and Computer Engineering University of Toronto (Graduated March 2025)
  • BASc in Nanotechnology Engineering University of Waterloo (Graduated June 2023, With Distinction)
  • Featured alumni in the Data Analytics and Machine Learning Emphasis at UofT. Read more here.

Industry Experience

Teaching & Research

Project Highlights

Greenhouse-Level Digital Twin Framework

> Status: Active PhD Research (Publication Pending)

  • Designing a probabilistic state-estimation framework to create a living digital twin of a heterogeneous greenhouse environment.
  • The Core Architecture: Bridging the gap between mechanistic biological predictions and noisy real-world sensor data.
  • Mathematical Frameworks: Implementing dynamic Flux Balance Analysis (dFBA) and Kalman Filtering to continuously track and correct hidden biomass states across multiple spatial zones.
  • Tech Stack: Python, COBRApy, State-Space Models, NumPy, SciPy

System Capabilities

  • [SYS] Languages: Python, C++, JavaScript, TypeScript, Java, C#, R, SQL
  • [ML] Machine Learning: PyTorch, TensorFlow, Scikit-learn, DeepFace, MediaPipe, State-Space Models
  • [DAT] Data & Analysis: Pandas, NumPy, SciPy, COBRApy, Data Visualization
  • [CFG] Frameworks & Tools: React, Node.js, Git, Docker, AWS, Azure, Selenium

Where I've Been

~/experience $ ls -l

Management / Consulting

Complaints Management & Operational Consulting @ FAW-Volkswagen

Dispute Resolution, Risk Prevention

May 2024 – July 2025

  • Handled high-risk complaints escalated by frontline agents.
  • Assessed solution fairness and determined fault through cross-functional coordination.
  • Built and maintained QBI Kanban boards to track complaint progress.

CAN Tech Industry

Performance Testing Engineer @ Ford Motor Company

Ubuntu, iperf3, TCP/IP, Selenium

May 2022 – August 2022

QA-Developer @ Manulife

JavaScript, React, WebDriver IO

January 2020 – April 2020

QA Automation Specialist @ Teranet CMS

C#, Selenium

September 2020 – December 2020

Teaching Experience

APS1070 (Foundations of Data Analytics and ML) @ UofT

  • Graded more than 200 projects per term
  • Led 10+ Tutorials per term

MIE370 (Introduction to ML) @ UofT

  • Created 2 Projects, 2 Tutorials, 2 Exam Questions

Research Experience

Research Assistant @ Prof. Yuning Li's Lab, UWaterloo

Chromatography, UV Testing, Organic Solar Cells

May 2019 – August 2019

  • Conducted chromatography and UV testing for organic solar cell research.

What I've Built

~/projects $ ls -l

Emotion Detection (Face+Voice+Gestures)

DeepFace, MediaPipe, Ollama

  • Implemented IoU-based face tracking with multi-modal analysis combining facial expressions, voice tone, and body language.
  • Created custom Ollama endpoints with temporal emotion smoothing using a 0.5-second rolling window to enhance accuracy.
[GitHub Repo]
emo1 emo2

Building Smart Evacuation Maps

ACO, LLM, Dijkstra

  • Integrated LLMs with Dijkstra's algorithm and Ant Colony Optimization (ACO)-inspired routing.
  • Consistently outperforming simple Dijkstra in 'majority evacuation' scenarios.
[GitHub Repo] [Medium Article]

S.W.I.M (Sequential Wave Imprinting Machine)

Arduino, Hardware, Sponsored by Prof. Steve Mann

  • Use Arduino, LED strip, and time-lapse photography to print digital pictures into the real world.
[GitHub Repo]
swim1 swim2

Food Recommendation System

LLM, Yelp API, Maps API

  • Developed a food recommendation engine using LLMs, Yelp API, and Google Maps for personalized suggestions.
[GitHub Repo] [Medium Article] Launch Web App ->

LLM-Powered Financial Tracker

Data Analysis, LLM Processing

  • Built a tool to analyze personal finances using LLMs for flexible categorization and insights into spending patterns.
[GitHub Repo]

Autonomous Robot

LEGO Mindstorms

  • Designed and programmed a LEGO Mindstorms robot, showcasing retrieval and tracking capabilities. Achieved 3rd place!
robo1 robo3 robo4 robo5

Matrix Calculator

Python, UI

  • Solves n-variable systems of equations using Python with a clean GUI.
[GitHub Repo]

Off The Clock

~/personal_logs $ ls -a

Computer Science PhD Journey

Status: Current PhD @ University of Waterloo

  • Research Focus: Digital Twins & Systems Architecture
  • Department: Chemical Engineering
  • Supervisors: Prof. Nasser Mohieddin Abukhdeir & Prof. Christian Euler

Knowledge Base

A collection of my thoughts, articles, and book notes.

  • Computer Vision & AI: Notes from recent deep dives.
  • Algorithms: Problem-solving patterns and optimizations.
  • How to Be an Imperfectionist: Key takeaways on productivity.

Get in Touch

Currently researching Digital Twins and Computational Modeling as a PhD student at UWaterloo. Always open to collaborations and technical discussions. My inbox is always open. ^_−