GU Zhigang,SUN Fengli.Particle swarm optimized ridgelet neural network based on plane targets recognition[J].Journal of Yanbian University,2014,40(04):346-351.
基于粒子群脊波神经网络的飞机目标识别
- Title:
- Particle swarm optimized ridgelet neural network based on plane targets recognition
- Keywords:
- ridgelet; neural network; particle swarm optimization algorithm; support vector machine; shelly-nearest neighbored algorithm
- 分类号:
- TP391.4
- 文献标志码:
- A
- 摘要:
- 针对传统的基于梯度的脊波神经网络训练算法存在效率低、网络规模大、后期容易震荡等缺点,提出了一种粒子群网络训练算法,网络结构采取逐步递增隐层神经元的方法加以确定,对粒子群个体参数取不同的位置边界,并对粒子飞行速度进行限制,在合理设定粒子群算法各参数值的情况下实现了网络快速而有效的训练.仿真试验将该网络用于6类空中飞机目标的识别,并与传统的识别手段进行了比较,结果表明粒子群算法训练的脊波神经网络具有规模小、学习和泛化能力强、网络可控性好等优点.
- Abstract:
- Aiming at the disadvantages of the conventional gradient-based approaches, lower efficiency, larger network size, and post-concussion etc, a particle swarm optimized ridgelet neural network is researched in this paper, which structure is determined by means of incremental method. By setting different location bound and limiting the velocities of particle parameters, the network is trained quickly and efficiently in case of the parameters of particle swarm algorithm rational-defined. The stimulation experiment, utilizing this network to classification of 6 kinds of plane targets, shows that the particle swarm optimized ridgelet neural network has the prominent advantages of smaller size, more powerful abilities of learning and generalizing, better controllability etc, in comparison with conventional methods.
参考文献/References:
[1] Candès E J. Ridgelets: theory and applications[D]. USA: Department of Statistics, Stanford University, 1998.
[2] 杨淑媛,焦李成,王敏.一种自适应脊波网络模型[J].西安电子科技大学学报:自然科学版,2005,32(6):890-894.
[3] 杨淑媛,焦李成,王敏.一种新的方向多分辨脊波网络[J].西安电子科技大学学报:自然科学版,2006,33(4):557-562.
[4] Yang Shuyuan, Wang Ming, Jiao Licheng. Incremental constructive ridgelet neural network[J]. Neurocomputing, 2008,72:367-377.
[5] Amjady N, Keynia F, Zareipour H. Short-term wind power forecasting using ridgelet neural network[J]. Electric Power Systems Research, 2011,81(12):2099-2107.
[6] Zheng N, Tan H F. SAR image classification based on brushlet and self-adaptive ridgelet neural network[J]. Applied Mechanics and Materials, 2013,347:3024-3028.
[7] 孙锋利,何明一,高全华.基于自适应脊波网络的高光谱遥感图像分类[J].计算机科学,2011,38(8):260-264.
[8] Kennedy J, Eberhart R C. Particle swarm optimization[J]. IEEE Conference on Neural Networks, 1995:1942-1948.
[9] Eberhart R C, Kennedy J. A new optimizer using particle swarm theory[J]. Institute of Electrical and Electronics Engineers, 1995,10:39-43.
[10] Shi Y, Eberhart R C. A modified particle swarm optimizer[J]. Institute of Electrical and Electronics Engineers, 1998,5:69-73.
[11] 夏婷,周卫平,李松毅,等.一种新的Pseudo-Zernike矩的快速算法[J].电子学报,2005,33(7):1295-1298.
[12] 钟智,朱曼龙,张晨,等.最近邻分类方法的研究[J].计算机科学与探索,2011,5(5):467-473.
相似文献/References:
[1]关键,何良华*.一种基于视频的手势识别算法[J].延边大学学报(自然科学版),2013,39(03):211.
GUAN Jian,HE Lianghua*.A gesture recognition algorithm based on video[J].Journal of Yanbian University,2013,39(04):211.
[2]陈修辉,孙铭霞.基于HKBFO优化神经网络的悬索桥动载识别[J].延边大学学报(自然科学版),2015,41(03):257.
CHEN Xiuhui,SUN Mingxia.Identification of moving load on the suspension bridge based on HKBFO optimized neural network[J].Journal of Yanbian University,2015,41(04):257.
[3]黄朝辉,闻辉*,车艳.基于势函数聚类的改进RBF网络算法研究[J].延边大学学报(自然科学版),2020,46(02):145.
HUANG Chaohui,WEN Hui*,CHE Yan.Research on improved RBF network algorithm based onpotential function clustering[J].Journal of Yanbian University,2020,46(04):145.
[4]金丹丹,闻辉*.基于RBF -BP神经网络融合的医学数据分类研究[J].延边大学学报(自然科学版),2021,47(01):70.
JIN Dandan,WEN Hui*.Research on medical data classification based on RBF -BP neural network fusion[J].Journal of Yanbian University,2021,47(04):70.
备注/Memo
收稿日期: 2014-07-26*通信作者: 谷志刚(1975—),男,副教授,研究方向为信号与信息处理、模式识别等.