👋简介
我是重庆师范大学智能科学与技术专业的学生。我的研究方向包括机器学习算法中的隐私保护、机器学习优化算法和非线性动力学。作为一个 ENFP，我热衷于探索新想法和新技术，喜欢与他人合作解决具有挑战性的问题。我相信持续学习的力量，并始终渴望迎接新的挑战。
📚学术成果
A simple method for constructing a class of discrete conservative chaotic maps
Dengwei Yan, Qiang Jiang, Zhengran Cao, Yi Yuan, Lidan Wang, Shukai Duan
Physica Scripta, Vol. 100 (10), pp. 105228, 2025
Conservative systems play a critical role in high-reliability chaotic encryption due to their phase-space conservation and stable dynamic behavior during long-term evolution. However, research on discrete chaotic mappings with conservative properties remains scarce. To address this gap, this paper proposes a class of 2D discrete-time conservative chaotic systems via nonlinear reconstruction of the generalized Gumowski-Mira mappings. Specifically, their conservative nature is rigorously verified through Liouville's theorem, demonstrating phase-conservation properties and symmetric Lyapunov exponents. For deeper analysis, we select a representative model (2D-DTC) from this class, which transitions from a stable fixed point to multiple unstable states through parameter variations. The system's rich dynamic behavior is illustrated using bifurcation diagrams, symmetric Lyapunov exponential spectra, and parameter-space chaos diagrams. Notably, heterogeneous coexisting chaotic orbits emerge under initial value perturbations, while complexity quantification using spectral entropy (SE) and permutation entropy (PE) validates their nonlinear characteristics. For practical implementation, an FPGA-based platform is designed for chaotic sequence generation and image encryption that integrates diffusion and permutation. Experimental results demonstrate superior encryption performance and effectiveness.
A Rapid Sand Gradation Detection Method Based on Dual-Camera Fusion
Shihao Zhang, Yang Zhang, Song Sun, Xinghai Yuan, Haoxuan Sun, Heng Wang, Yi Yuan, Dan Luo, Chuanyun Xu
Buildings, Vol. 15 (14), pp. 2404, 2025
Precise grading of manufactured sand is vital to concrete performance, yet standard sieve tests, though accurate, are too slow for online quality control. Thus, we devised an image-based inspection method combining a dual-camera module with a Temporal Interval Sampling Strategy (TISS) to enhance throughput while maintaining precision. In this design, a global wide-angle camera captures the entire particle field, whereas a local high-magnification camera focuses on fine fractions. TISS selects only statistically representative frames, effectively eliminating redundant data. A lightweight segmentation algorithm based on geometric rules cleanly separates overlapping particles and assigns size classes using a normal-distribution classifier. In tests on ten 500 g batches of manufactured sand spanning fine, medium, and coarse gradations, the system processed each batch in an average of 7.8 min using only 34 image groups. It kept the total gradation error within 12% and the fineness-modulus deviation within ±0.06 compared to reference sieving. These results demonstrate that the combination of complementary optics and targeted sampling can provide a scalable, real-time solution.
💼项目经历
🏆荣誉奖项
🎓教育经历
重庆师范大学
2023 - Now本科 · 智能科学与技术
计算机与信息科学学院