Skip to content

feat: Implement Smart Adaptive Prediction using K-Means and Hysteresis#49

Open
whitestorm007 wants to merge 2 commits intogommzystudio:masterfrom
whitestorm007:feat/adaptive-thresholds
Open

feat: Implement Smart Adaptive Prediction using K-Means and Hysteresis#49
whitestorm007 wants to merge 2 commits intogommzystudio:masterfrom
whitestorm007:feat/adaptive-thresholds

Conversation

@whitestorm007
Copy link

I've upgraded the core detection engine to solve the static threshold limitations mentioned in the original research.

Key Improvements:

  • Dynamic Clustering: Implemented K-Means to automatically learn the network's specific "Online" vs "Standby" RTT profiles.
  • Noise Filtering: Added Interquartile Range (IQR) analysis to filter out random network jitter/spikes.
  • Stability: Introduced a Hysteresis loop (3-strike rule) to eliminate state flickering.
  • UX: Updated dashboard to visualize confidence levels and cluster separation.

@whitestorm007 whitestorm007 force-pushed the feat/adaptive-thresholds branch from a034f3a to a006fc7 Compare January 1, 2026 11:17
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant