|
|
基于投影寻踪模拟退火的多传感信息融合技术
|
Abstract:
本文吸取加权平均法、概率统计法等算法的优点，设计了基于投影寻踪模拟退火法的多传感器信息融合算法。设计创新点在于对投影权值调整过程中加入概率窗口约束及聚类约束，使系统的计算复杂度减少41.6%，得出的结果符合峰值回归判断。本设计对于解决系统的多传感器信息融合有了新的改进，对于实时性和适用范围均有了一定的提升。
Based on the advantages of weighted average method and probability statistics method, a multi-sensor information fusion algorithm based on projection pursuit simulated annealing method is designed in this paper. The innovation of the design lies in the addition of probability window constraint and clustering constraint in the process of projection weight adjustment to reduce the computational complexity of the system by 41.6%, and the results obtained are in line with the peak regression judgment. This design has a new improvement to solve the multi-sensor information fusion of the system, and has a certain improvement to the real-time and applicable range.
| [1] | 赵宗贵. 信息融合技术现状、概念与结构模型[J]. 中国电子科学研究院学报, 2006(4): 305-312. |
| [2] | Zhou, Y.H., Zuo, Z.T. and Xu, F.R. (2019) Origin Identification of Panax Notoginseng by Multi-Sensor Information Fusion Strategy of Infrared Spectra Combined with Random Forest. Spectrochimica Acta-Part A: Molecular and Biomolecular Spectroscopy, Vol. 226, 5 February 2019. https://doi.org/10.1016/j.saa.2019.117619 |
| [3] | 刘国凯. 基于多传感信息融合的旋转机械故障诊断研究[D]: [硕士学位论文]. 贵阳: 贵州大学, 2018. |
| [4] | 赵毅. 数字滤波的算术平均法和加权平均法[J]. 仪表技术, 2001(4): 41-44. |
| [5] | 周治利. 基于概率假设密度的多传感器多目标跟踪技术研究[D]: [硕士学位论文]. 杭州: 杭州电子科技大学, 2017. |
| [6] | ？árka, B., Peter, F., Thomas, O., Christian, B. and Maia, R. (2019) Robust and Sparse K-Means Clustering for High Dimensional Data. |
| [7] | 张欣莉, 丁晶, 李祚泳, 金菊良. 投影寻踪新算法在水质评价模型中的应用[J]. 中国环境科学, 2000(2): 187-189. |
| [8] | 王顺久, 张欣莉, 丁晶, 侯玉. 投影寻踪聚类模型及其应用[J]. 长江科学院院报, 2002(6): 53-55+61. |
| [9] | 金菊良, 魏一鸣, 付强, 丁晶. 农业生产力综合评价的投影寻踪模型[J]. 农业系统科学与综合研究, 2001(4): 241-243. |
| [10] | 任恒妮. 大数据K-means聚类算法的研究与应用[J]. 信息技术, 2019, 43(11): 20-23. |
| [11] | 饶太春, 兰林强, 罗伟林. 模拟退火法在协同优化中的应用[J]. 福州大学学报(自然科学版), 2018, 46(3): 379-385. |
