Skip to content
View bokiiiiiii's full-sized avatar
:octocat:
🏎️🏎️🏎️
:octocat:
🏎️🏎️🏎️
7 followers · 4 following

Achievements

Achievement: QuickdrawAchievement: Pull Sharkx2Achievement: YOLO

Achievements

Achievement: QuickdrawAchievement: Pull Sharkx2Achievement: YOLO

Highlights

  • Pro

Block or report bokiiiiiii

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
bokiiiiiii/README.md

👋 Hi, I'm Bo-Yi Lin

🏎 Portfolio: Featured Motorsport Projects

1. F1 Strategy Optimizer (Race Strategy Intern) 🔒 Under NDA

  • Core Technology: Gaussian Hidden Markov Model (HMM)
  • Summary: Engineered a strategy tool to solve the crossover problem during variable weather. Utilised a Gaussian HMM $p(x_t | z_t = k) = \mathcal{N}(x_t | \mu_k, \Sigma_k)$ to decode latent track states from noisy grip signals, identifying the optimal pit stop window.

2. F1 Race Replay (Open Source Contributor)

  • Core Technology: Bayesian State-Space Model, Kalman Filter
  • Summary: Integrated a Bayesian framework $x_k = F_k x_{k-1} + B_k u_k + w_k$ to derive latent tyre health from low-frequency telemetry. Developed a real-time interactive visualisation system to track grip potential and degradation.

3. Formula 1 Data Analysis (Sole Developer)

  • Core Technology: Gaussian Processes (GP), Monte Carlo Simulation
  • Summary: Automated an end-to-end FastF1 data pipeline. Employed Gaussian Processes $f(t) \sim \mathcal{GP}(m(t), k(t, t'))$ for tyre degradation modelling and built a Monte Carlo Simulator to predict probability distributions for optimal pit stop timing.

4. Sim Racing RL Driving Agent (Sole Developer)

  • Core Technology: Deep Reinforcement Learning (PPO), UDP Telemetry
  • Summary: Trained an autonomous RL driving agent for continuous vehicle control in high-fidelity simulations. Integrated real-time UDP telemetry acquisition to provide live operating corrections and driving line analysis.

📜 Certifications

📫 Contact Me

Pinned Loading

  1. Formula-1-Data-Analysis Formula-1-Data-Analysis Public

    Formula 1 Data Analysis and Visualisations

    Python 2

  2. Sim-Racing-Game-Reinforcement-Learning-Driving-Agent-and-Telemetry-Data-Analysis Sim-Racing-Game-Reinforcement-Learning-Driving-Agent-and-Telemetry-Data-Analysis Public

    Analyse Assetto Corsa Competizione telemetry data for lap time improvement suggestions based on reinforcement learning driving agent

    Python 3

  3. Deep-Learning-Based-Suspension-Dynamic-Performance-Prediction Deep-Learning-Based-Suspension-Dynamic-Performance-Prediction Public

    Deep Learning-Based Prediction of Suspension Dynamics Performance in Multi-Axle Vehicles

    Python 8

  4. Analysis-of-Centrifugal-Clutches-in-Automatic-Transmissions-with-Deep-Learning-Engagement-Prediction Analysis-of-Centrifugal-Clutches-in-Automatic-Transmissions-with-Deep-Learning-Engagement-Prediction Public

    Analysis of Centrifugal Clutches in Two-Speed Automatic Transmissions with Multilayer Perceptron Neural Network-Based Engagement Prediction

    MATLAB 1