AAAI22-SJDL-Vehicle: Semi-supervised Joint Defogging Learning for Foggy Vehicle Re-identification

Remaining useful life prediction. Degradation path approximation (DPA) is a highly easy-to-understand and brand-new solution way for data-driven RUL prediction. Many research directions on DPA can be further studied.

An interpretable battery health engine that detects hidden points of no return instead of just predicting health %. It models stress, buffer, and degradation intensity, discovers Stable/Drifting/Irreversible regimes via GMM, and learns simple Decision Tree thresholds, with a Streamlit app for diagnostics and what-if scenarios.

Battery data analysis tools in Python

The code that powers my thesis

Official Implementation of "Deep Hybrid Model for Fault Diagnosis of Ship's Main Engine"

Add randomizable real Degradations/Compression Artifacts in Vapoursynth.

A Streamlit-based application for fitting and visualizing pseudo-first-order kinetic models in photocatalytic degradation studies. Includes support for experimental parameter input, real-time plotting, and basic error analysis.

A LEO satellite fleet health management platform using real ISS telemetry to demonstrate predictive maintenance, anomaly detection, and operational decision support capabilities.

Image restoration in spatial domain

Interpretability Metrics