Smartphone-Based Non-Invasive Aflatoxin Detection in Groundnuts Using BGYF Fluorescence Imaging and Machine Learning: A Field-Deployable Screening Tool for LDC Food Safety System

---

Project period: 01 April 2026   To: 31 December 2026

Project details

This project aims to develop and validate a smartphone-based, non-invasive aflatoxin detection system for groundnuts by integrating Bright Greenish-Yellow Fluorescence (BGYF) imaging with machine learning techniques. The system is designed as a rapid, low-cost, and field-deployable screening tool suitable for use in low-resource environments, particularly within Malawi’s groundnut value chain. The proposed platform will enable real-time, non-destructive detection of aflatoxin contamination, addressing critical gaps in current food safety systems where laboratory infrastructure is limited. The system will be rigorously benchmarked against established laboratory methods, specifically VICAM fluorometric analysis, and validated under real-world conditions. In addition to technology development, the project seeks to strengthen national food safety capacity through training, development of standard operating procedures (SOPs), and stakeholder engagement. The work builds on LUANAR’s existing expertise and infrastructure , positioning the innovation for scaling across similar low- and middle-income country (LMIC) contexts. Dr. Dackson Masiyano (UNIMA) provides leadership in instrumentation design, optical system optimization, and end-to-end system integration, ensuring that the proposed AI-enabled fluorescence detection platform is robust, field-deployable, and scalable within low-resource food safety systems.