A secured accreditation and equivalency certification using Merkle mountain range and transformer based deep learning model for the education ecosystem.

An Accreditation and equivalency certificate Verification System is required to ensure integrity, trust, and recognition of qualifications within the education ecosystem. However, most verification procedures are costly, hard, opaque, and time-consuming. This paper introduces a secured blockchain-based Accreditation and Equivalency certification prototype that effectively mitigates credential and equivalency frauds. Initially, a novel transformer-based convolutional recurrent network (TCRN) is proposed to automate and enhance the equivalency estimation process by analyzing large datasets of educational records and providing equivalence certificates. TCRN employs Bi-GRU to retain long-term academic trends, Depth-wise separable convolutions (DSC) to concentrate on course-specific information, and BERT to capture global semantic context. The suggested approach utilizes an enhanced MD5 hash method to uniquely fingerprint Degree Details (DD), ID/Transcript Details (ITD), and equivalency certificates, storing them in a Merkle Mountain Range (MMR) structure to ensure data integrity. Verification of credentials is made easier as third parties can now access and verify data using QR codes incorporated in physical certificates through the Cerberus + + network. Cerberus + + uses a sampling-based strategy to reduce resource usage throughout the verification process and improves conventional blockchain architecture for increased computing efficiency. The proposed platform sets a globally reliable foundation for comparability of the grading scale of higher education and ensures easy transfer and recognition of academic credentials. According to simulation results, the system can estimate academic equivalency with over 95% accuracy and allows for resource-efficient, real-time verification.