Skip to content
View GoldenSection0618's full-sized avatar

Highlights

  • Pro

Block or report GoldenSection0618

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 is supported. This note will only be visible to you.
Report abuse

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

Report abuse
GoldenSection0618/README.md

Lihan YANG (杨立晗)

Undergraduate student in Software Engineering at Wuhan University of Technology.
Interested in machine learning, AI agents, robotics, optimization, and biomedical AI.

About

I am a B.Eng. candidate with project experience in data modeling, machine learning, optimization algorithms, robotics simulation, and GPU-accelerated signal processing. My recent work focuses on building reproducible modeling pipelines, evaluating model performance, and connecting algorithmic methods with practical decision-making or perception tasks.

I am currently strengthening my research foundation in reinforcement learning, AI agents, and learning-based decision-making systems.

Research Interests

  • Large language models, generative AI, and AI agents
  • Machine learning for decision-making and optimization
  • Robotics perception, simulation, and embodied AI
  • Biomedical AI and interpretable data modeling
  • GPU acceleration and radar / sensor signal processing

Selected Projects

Biomedical Data Modeling and Screening Pipeline

Built a multi-stage modeling pipeline covering feature preprocessing, segmented regression, timing optimization, and classification. The project used GA-DP, NSGA-DP, XGBoost, SMOTE, class weighting, PR/ROC analysis, and SHAP-based interpretability.

GPU-Accelerated CFAR and MVDR Operators

Developed OpenCL-based GPU-parallelized operators for maritime radar signal processing. Work included CFAR pipeline optimization, memory-layout adaptation, workload tiling, and latency reduction for small-input real-time processing scenarios.

ROS 2 / Gazebo Autonomous Lunar Rover System

Developed ROS 2 modules in Gazebo for autonomous navigation, sensor integration, sample collection, and return-to-base task execution. The system combined vision-based object recognition, mmWave radar perception, obstacle handling, and task-level path planning.

Biomedical Image Segmentation Exploration

Exploring Cellpose / Cellpose-SAM for cell and nucleus segmentation workflows, with an emphasis on understanding image preprocessing, segmentation baselines, and evaluation settings.

Technical Skills

Programming and Data Processing
Python, Java, C/C++, SQL, NumPy, pandas, scikit-learn, XGBoost, imbalanced-learn, SHAP, basic PyTorch

Modeling and Optimization
Regression, LASSO, GA, NSGA-II, Dynamic Programming, Monte Carlo Simulation, Sensitivity Analysis, Cross-validation, PR/ROC Analysis, F1-score Evaluation

Systems, Robotics, and GPU
Linux, Git, Docker, OpenCL, ROS 2, Gazebo

Research Workflow
LaTeX, Markdown, reproducible experiment documentation, technical report writing


github contribution grid snake animation

Pinned Loading

  1. cellpose cellpose Public

    Forked from MouseLand/cellpose

    a generalist algorithm for cellular segmentation with human-in-the-loop capabilities

    Python

  2. HGSFusion HGSFusion Public

    Forked from garfield-cpp/HGSFusion

    [AAAI 2025] HGSFusion: Radar-Camera Fusion with Hybrid Generation and Synchronization for 3D Object Detection

    Python

  3. reactive-resume reactive-resume Public

    Forked from amruthpillai/reactive-resume

    A one-of-a-kind resume builder that keeps your privacy in mind. Completely secure, customizable, portable, open-source and free forever. Try it out today!

    TypeScript