Jiahong’s PhD Journal — notes from the intersection of data science, machine learning, and air cargo logistics. I share paper takeaways, experiments, engineering practice (MLOps, deployment, visualization, security), and learning paths in clear, reusable formats.

What you’ll get

  • Deep dives, clearly explained: close reads, method breakdowns, reproductions, and lessons learned.
  • Project logs & code patterns: end-to-end templates from data collection to deployment and monitoring.
  • Air-cargo insights: executive summaries of industry & academic trends (5–10 min reads).
  • Learning roadmaps: step-by-step plans and tool lists for DS/MLOps/LLMs/cybersecurity.

Why subscribe

  • No algorithm, no noise: updates via email only.
  • Full archive access: all past and future posts and downloadables.
  • Focused community: readers who care about Data Science × Air Cargo.

Topics I write about

  • ADS-B data & flight delay (trajectory prediction, features, metrics)
  • Motion-sensor analytics (accel/gyro/pressure) with explainability (XAI)
  • MLOps: DVC, MLflow, Docker, reproducible pipelines & deployments
  • Visualization, dashboards, academic writing, reproducible research
  • Practical networking & security for research/deployment

Who am I

I’m Jiahong Que, a PhD researcher at Frankfurt University of Applied Sciences (Digital Testbed Air Cargo). I focus on data science + deep learning for air cargo and share reusable practices from teaching and projects.
Contact: jiahong.que@fra-uas.de (optional)

Publishing cadence

  • Weekly-ish longforms or project notes (flexible around experiments/travel)
  • Themed series (e.g., CNN/LSTM, XAI in practice, ADS-B specials)
  • Newsletter with highlights and links for quick scanning

Support & ethics

  • Verifiable sources, runnable examples, clear experiment conditions
  • Proper citation and copyright; email me about any issues
  • Your email is used only for this publication; unsubscribe anytime

Start here

  • Collections: PhD Literature Review, Cyber Security Picks
  • For hands-on work: Playbooks and Templates

Independent notes on Data Science × Cyber Security: reproducible ML/DL, MLOps, and practical PhD lessons—clear and reusable. Subscribe for concise, no-noise updates.