Projects | Junfei Zhan's Website

Daily Productivity Tracker

Sun, 05 Apr 2026 00:00:00 +0000

A personal daily productivity and diary tracker with a beautiful, animated UI. Features include a unified work clock, task management, daily theme editing, and an immersive full-screen zen mode with time-aware scenes (sunrise, daytime clouds, sunset, starry night), celestial body animations, and procedurally generated ambient sounds (rain, wheat fields, summer frogs, fireplace).

Key features:

Zen Focus Mode: Full-screen immersive environment with real-time clock, nature scenery that matches the actual time of day
Ambient Sound Engine: Four procedurally generated sounds using Web Audio API — no external audio files needed
Task Management: Create, track, and focus on individual tasks with dedicated focus mode
Bilingual Support: Chinese/English toggle with full i18n
Data Persistence: All data saved locally via localStorage

MPPI with Control Barrier Functions for F1/10: Robust Safety Under Real-World Uncertainty

Wed, 07 May 2025 00:00:00 +0000

This project implements Shield-MPPI, a novel integration of Control Barrier Functions (CBFs) with Model Predictive Path Integral (MPPI) control, on the F1/10 autonomous racing platform to achieve robust, safe navigation under real-world uncertainty.

Key contributions include:

Safety Assurance: Enforced via discrete-time CBFs ensuring forward invariance of a predefined safe set.
Cost Augmentation and Control Filtering: Augmented MPPI trajectory costs with CBF penalties and applied gradient-based filtering to guarantee real-time safety.
Robustness Evaluation: Assessed system under disturbances, noise, and model mismatch in simulated and physical racing environments.
Computational Feasibility: Validated Shield-MPPI’s real-time performance on resource-limited platforms.

The approach demonstrates significant improvement over baseline MPPI in terms of collision avoidance, track adherence, and robustness.

RL for Stochastic Vaccine Allocation on Contact Networks

Mon, 17 Mar 2025 00:00:00 +0000

Bridged deterministic optimal control and reinforcement learning to develop a stochastic vaccine allocation strategy on individual-level contact networks, enabling robust pandemic response modeling.

Highlights

Modeled epidemic spread using a high-dimensional continuous-time Markov process (CTMP) on a contact graph.
Designed a vaccination policy using policy gradient-based RL, warm-started from a mean-field ODE solution.
Evaluated policies on metrics like mortality and hospitalizations across synthetic and real-world network topologies.

Tools

Python, PyTorch, NetworkX, OpenAI Gym

Audio-based Material Classification Using Hybrid CNN and Logistic Regression

Sun, 15 Dec 2024 00:00:00 +0000

Developed a hybrid model for classifying audio recordings of knocking sounds from seven materials (e.g., table, glass, blackboard). The model combines 1D CNN on raw audio, 2D CNN on MFCC features, and logistic regression into an ensemble system. Achieved 94% accuracy and a weighted F1-score of 0.9426 on evaluation data.

Collected 520 real-world samples using smartphone recordings with varying knock strengths. Applied noise reduction and feature extraction (MFCC, temporal, spectral features). Evaluated over diverse CNN combinations, demonstrating effective integration of deep learning with traditional methods. Proposed improvements include attention mechanisms, mixup augmentation, and expanded data collection for better generalization.