Contraband: AI efficiently detects anomalies in shipping containers
• A team from Tuft’s University has developed an artificial intelligence system based on a self-supervised learning framework that can detect contraband hidden in cargo flows.
• Researchers projected synthetic 3D anomalies in X-rays to train the model to distinguish between normal cargo and contraband with an impressive accuracy of score of 98%.
• The innovative approach adopted by the project could also be adapted for applications in other fields, including microscopy, medical research and industrial quality control.
Read the article
• Researchers projected synthetic 3D anomalies in X-rays to train the model to distinguish between normal cargo and contraband with an impressive accuracy of score of 98%.
• The innovative approach adopted by the project could also be adapted for applications in other fields, including microscopy, medical research and industrial quality control.
“I lost track of time”: how we get caught up in digital applications?
Read the article
Explainability of artificial intelligence systems: what are the requirements and limits?
Read the article
