projects.txt

Projects

Personal

CruxCam
  • Built a real-time pose estimation app using MediaPipe and OpenCV to analyze climbing video and score technique efficiency
  • Engineered a joint angle and center-of-mass calculation pipeline to generate an efficiency score based on body position
  • Deployed as an interactive Streamlit web app with video output, live efficiency overlays, and adjustable detection thresholds
  • Architected clean separation between pose analysis and video I/O logic via a modular core package
PythonComputer VisionMediaPipeOpenCVStreamlit
Super Resolution Paper Implementation
  • Implemented a PyTorch-based FSRCNN super-resolution model and trained it end-to-end on custom image datasets
  • Built reusable data loading and preprocessing pipelines to support efficient training and evaluation
  • Evaluated model performance using PSNR and achieved results consistent with published benchmarks
  • Deployed the model via a Flask service and containerized the system with Docker for reproducibility
Computer VisionPyTorchFlaskDocker
SpaceX CRS-10 Telemetry Analysis
  • Investigated three unsupervised anomaly detection methods (Z-score, IQR, Rolling Z-score) on high-frequency SpaceX CRS-10 rocket telemetry, using 5 known flight events as ground truth
  • Built a cluster-based evaluation framework to group detected anomalies and score each method on precision, recall, and F1, enabling direct comparison across techniques
  • Discovered through grid search that the optimal Z-score threshold (0.7) was far below the conventional 2.0–2.5 range, revealing the signal's compressed variance as a key driver
  • Concluded that locally-adaptive methods consistently outperform global statistics on non-stationary signals, a finding with direct implications for real-world sensor data pipelines
PythonTime-SeriesAnomaly Detection

Work

AI Report Summarization System
  • LLM-powered pipeline that automated summarization of transfer pricing reports, reducing processing time by ~98% (4 hours → 5 minutes). Built with Python, Azure, and GPT-4.
PythonLLMNLPAzure
Personnel Operations Dashboard
  • Power BI dashboard built for the San Mateo County Bar Association to track personnel metrics, headcount, and operational KPIs for leadership decision-making.
Power BISQLPython