• Proposes a Chaos-LSTM model that integrates chaotic systems with LSTM neural networks to generate chaotic sequences with high spectral entropy (SE) complexity, effectively addressing periodicity issues in traditional chaos-based encryption.
• Introduces the chaos sequence proliferation (CSP) algorithm to overcome computational accuracy limitations, enabling the generation of long chaotic sequences suitable for encrypting large-scale geographic data.
• Implements a complete geographic information encryption system on the ZYNQ hardware platform, combining chaotic proliferation sequences with scrambling and diffusion algorithms for enhanced confidentiality.
• Demonstrates excellent confidentiality performance and scalability through both software testing and hardware experiments, confirming its practical value for securing diverse encryption objects.