Virtual Booth

Aquilaria species produce essential oils vital to perfumery and traditional medicine, but their chemical similarities complicate accurate identification. Reliable classification is crucial for authenticity, quality control, and sustainability, yet current methods remain inadequate. To address this gap, this study introduces Aquilassify is an AI-driven system utilizing Gas Chromatography-Mass Spectrometry (GC-MS) coupled with Gas Chromatography-Flame Ionization Detection (GC-FID), and Artificial Neural Networks (ANNs) to classify Aquilaria species. Significant compounds were identified via Self-Organizing Maps (SOM), and a Multilayer Perceptron (MLP) trained with Levenberg-Marquardt (LM) achieved 100% accuracy. Aquilassify enhances real-time authentication, reduces fraud, and promotes sustainability in the essential oils industry.