XTRACTIS for Safety & Security

Passive Magnetic Identification of Land Mines

Benchmark vs. Logistic Regression, Random Forests, Boosted Trees & Neural Networks

Design an AI-based decision system that accurately detects land mines and identifies the type of mine only from a few variables, to instantly deliver the appropriate rational decision.
Goals & benefits

Find the cause-and-effect relationships between the relevant predictors among the 3 parameters of this study, and the actual presence of a mine and its type.

Enhance demining technicians and military experts’ knowledge by understanding the strategies to identify the type of mine.

Help engineers to design enhanced mine detectors, manual or autonomous, embedding a classifier making explainable and accurate automated decisions.

Assist the military profession in making a more reliable decision, thanks to rapid, systematic, explainable, and safer detection process with a passive magnetic sensor.

  • The top-model is a decision system composed of 29 gradual rules without chaining, aggregated into 3 disjonctive fuzzy rules.
  • Each rule uses 1 to 3 variables that XTRACTIS confirmed as significant.
  • Only a few rules are triggered at a time to compute the decision.

It has a good Real Performance (on unknown data).

It computes real-time predictions up to 70,000 decisions/second, offline or online (API).

UC16 scores graph
LoR=Logistic Regression
RFo=Random Forests
BT=Boosted Trees
NN=Neural Networks

Detailed results and explanations in full document

Use Case 2024/02 (v3.0)

Powered by XTRACTIS® REVEAL 13.0.44978 (2023/02)


  1. Problem Definition
  2. XTRACTIS-induced Decision System
  3. XTRACTIS Process
  4. Top-Model Induction
  5. Explained Predictions for 3 unkown cases
  6. Top-Models Benchmark
  7. Appendices