Ouf Shimaa, Ahmed Soha, Helmy Yehia
Information Systems Department, Faculty of Commerce and Business Administration, Helwan University, Cairo, Egypt.
Sci Rep. 2025 Jun 4;15(1):19519. doi: 10.1038/s41598-025-03688-z.
In the contemporary digital age, education is no longer limited to traditional educational environments. Many educational institutions shifted to depend on the smart learning process but expressed concern about this solution due to its various challenges in securing the learning process and learners' data. By virtue of the most recent technologies like blockchain and artificial intelligence, which played a significant role in solving many challenges that faced the educational sector and overcoming issues like fake certificates, manipulation, tracking learners' activities, and predicting learners' academic performance. The study proposed a smart framework based on blockchain and deep learning to enhance smart learning processes and provide solutions for challenges in the field. The framework is intended to store the learner's data on the blockchain through the interplanetary file system and reap the benefits of securing the learner's data and ensuring its integrity, as well as ensuring the confidentiality and authentication of the users through the wallets that are created on the Ethereum private blockchain platform. Then apply the deep learning model to this secured data to predict the learner's performance. The smart contract functions also play a role in enabling the university to issue learners' certificates that are stored on the blockchain to be available and verifiable by all the nodes in the network. Based on the experimental results, deep neural networks were used to model the encrypted data that was stored on the blockchain and predict the learner's performance and achieved a high degree of accuracy (91.29%) and low loss (about 0.18) in comparison to other studies that depended on the centralized nature of the data. As well, the university blockchain's functionality was tested, and it successfully returned all the functional requirements and showed its legitimacy.
在当代数字时代，教育不再局限于传统的教育环境。许多教育机构转向依赖智能学习过程，但由于其在保障学习过程和学习者数据方面存在各种挑战，对这一解决方案表示担忧。借助区块链和人工智能等最新技术，这些技术在解决教育部门面临的许多挑战以及克服诸如假证书、操纵、跟踪学习者活动和预测学习者学业成绩等问题方面发挥了重要作用。该研究提出了一个基于区块链和深度学习的智能框架，以增强智能学习过程并为该领域的挑战提供解决方案。该框架旨在通过星际文件系统将学习者的数据存储在区块链上，并获得保障学习者数据安全并确保其完整性的好处，以及通过在以太坊私有区块链平台上创建的钱包确保用户的机密性和身份验证。然后将深度学习模型应用于这些安全数据以预测学习者的表现。智能合约功能还在使大学能够发行存储在区块链上的学习者证书，以供网络中的所有节点使用和验证方面发挥作用。基于实验结果，与其他依赖数据集中性质的研究相比，使用深度神经网络对存储在区块链上的加密数据进行建模并预测学习者的表现，实现了高度的准确性（91.29%）和低损失（约0.18）。此外，对大学区块链的功能进行了测试，它成功地满足了所有功能要求并显示了其合法性。
