Alsumayt Albandari, El-Haggar Nahla, Amouri Lobna, Alfawaer Zeyad M, Aljameel Sumayh S
Computer Science Department, Applied College, Imam Abdulrahman Bin Faisal University, P.O. Box 1982, Dammam 31441, Saudi Arabia.
Saudi Aramco Cybersecurity Chair, Department of Computer Science, College of Computer Science and Information Technology, Imam Abdulrahman Bin Faisal University, P.O. Box 1982, Dammam 31441, Saudi Arabia.
Sensors (Basel). 2023 May 28;23(11):5148. doi: 10.3390/s23115148.
Global warming and climate change are responsible for many disasters. Floods pose a serious risk and require immediate management and strategies for optimal response times. Technology can respond in place of humans in emergencies by providing information. As one of these emerging artificial intelligence (AI) technologies, drones are controlled in their amended systems by unmanned aerial vehicles (UAVs). In this study, we propose a secure method of flood detection in Saudi Arabia using a Flood Detection Secure System (FDSS) based on deep active learning (DeepAL) based classification model in federated learning to minimize communication costs and maximize global learning accuracy. We use blockchain-based federated learning and partially homomorphic encryption (PHE) for privacy protection and stochastic gradient descent (SGD) to share optimal solutions. InterPlanetary File System (IPFS) addresses issues with limited block storage and issues posed by high gradients of information transmitted in blockchains. In addition to enhancing security, FDSS can prevent malicious users from compromising or altering data. Utilizing images and IoT data, FDSS can train local models that detect and monitor floods. A homomorphic encryption technique is used to encrypt each locally trained model and gradient to achieve ciphertext-level model aggregation and model filtering, which ensures that the local models can be verified while maintaining privacy. The proposed FDSS enabled us to estimate the flooded areas and track the rapid changes in dam water levels to gauge the flood threat. The proposed methodology is straightforward, easily adaptable, and offers recommendations for Saudi Arabian decision-makers and local administrators to address the growing danger of flooding. This study concludes with a discussion of the proposed method and its challenges in managing floods in remote regions using artificial intelligence and blockchain technology.
全球变暖和气候变化是许多灾害的罪魁祸首。洪水构成严重风险，需要立即进行管理并制定策略以实现最佳响应时间。在紧急情况下，技术可以通过提供信息来代替人类做出响应。作为这些新兴人工智能（AI）技术之一，无人机在其改进系统中由无人驾驶飞行器（UAV）控制。在本研究中，我们提出了一种在沙特阿拉伯使用基于深度主动学习（DeepAL）分类模型的洪水检测安全系统（FDSS）进行洪水检测的安全方法，该模型基于联邦学习，以最小化通信成本并最大化全局学习精度。我们使用基于区块链的联邦学习和部分同态加密（PHE）进行隐私保护，并使用随机梯度下降（SGD）来共享最优解。星际文件系统（IPFS）解决了区块链中块存储有限以及信息高梯度传输带来的问题。除了增强安全性外，FDSS还可以防止恶意用户破坏或更改数据。利用图像和物联网数据，FDSS可以训练用于检测和监测洪水的本地模型。使用同态加密技术对每个本地训练的模型和梯度进行加密，以实现密文级别的模型聚合和模型过滤，这确保了在保持隐私的同时可以验证本地模型。所提出的FDSS使我们能够估计洪水淹没区域并跟踪大坝水位的快速变化，以评估洪水威胁。所提出的方法简单直接、易于适应，并为沙特阿拉伯的决策者和地方管理人员提供了应对日益增长的洪水危险的建议。本研究最后讨论了所提出的方法及其在使用人工智能和区块链技术管理偏远地区洪水方面所面临的挑战。
