AutoXchange (Exchanger Machine)

Abstract

This project presents the design and implementation of an Automated Currency Exchanger Machine that performs real-time conversion between Jordanian Dinar (JOD) and Israeli Shekel (ILS). The system integrates hardware, AI, and web technologies to deliver a fast, secure, and user-friendly exchange experience. Users initiate transactions by scanning a QR code and verifying their identity via RFID ID cards. A web application built with Next.js and Supabase provides access to live exchange rates, a secure sign-in flow, transaction history, a digital wallet for fractional amounts, and an interactive chatbot assistant powered by Chatbase. For banknote input, a camera module and a custom-trained Convolutional Neural Network (CNN) verify currency and denomination under controlled lighting. Accepted notes are sorted into storage bins. Dispensing is handled by a vacuum-based Y-Z gantry for notes and a servo-driven coin module for 1 ILS coins, ensuring precise payout— even for values between 1–19 ILS. Testing showed high classification accuracy (>95%) and reliable transaction flow. While limited by budget and time constraints, the system successfully demonstrates a practical and scalable solution for smart currency exchange. Recommendations include expanding coin handling capabilities, addin