基于追逐粒子与自适应变异的PSO-SVM算法 与养殖水质评价研究
PDF下载 (11332)魏 超1,张 刚1*,韩祥兰2,蔡永胜1,冯志敏1.基于追逐粒子与自适应变异的PSO-SVM算法 与养殖水质评价研究[J].宁波大学学报(理工版),2018,31(3):20-26.DOI:
WEI Chao1,ZHANG Gang1*,HAN Xiang-lan2,CAI Yong-sheng1,FENG Zhi-min1.PSO-SVM algorithm based on chasing particle and adaptive mutation and evaluation of aquaculture water quality[J].Journal of Ningbo University(Natural Science & Engineering Edition),2018,31(3):20-26.DOI:
| Title: | PSO-SVM algorithm based on chasing particle and adaptive mutation and evaluation of aquaculture water quality |
| 作者: | 魏 超1, 张 刚1*, 韩祥兰2, 蔡永胜1, 冯志敏1 |
| Author(s): | WEI Chao1, ZHANG Gang1*, HAN Xiang-lan2, CAI Yong-sheng1, FENG Zhi-min1 |
| 关键词: | 水质评价; 支持向量机; 粒子群算法; 自适应变异 |
| Keywords: | water quality evaluation; support vector machine; particle swarm algorithm; adaptive mutation |
| 分类号: | X824 |
| 文献标识码: | A |
| 摘要: | 为提高标准PSO算法对SVM参数优化选取的精度和速度, 提出以粒子群适应度均方差为判别依据, 用追逐粒子位置替代陷入局部优化时的群体最优位置, 对粒子的速度进行自适应调整; 利用两个距离最远的粒子位置构成的圆形区域作为最优位置的吸引域, 引入位置变异因子, 使粒子随着迭代次数有规律地跳出局部最优位置吸引域, 从而对粒子位置进行自适应变异. 通过对4种不同适应度函数迭代100次的收敛测试, 并与另外2类不同粒子群算法比较, 结果表明改进算法收敛精度提高了20倍以上. 将改进的PSO-SVM算法与另外3种分类算法对采集的5439组养殖水质数据按照从优到差5个级别进行水质评价分类试验, 发现改进的PSO-SVM算法收敛速度和收敛精度最高, 对水质评价的错误率为1.54%, 能有效地满足实际水质分类需求. |
| Abstract: | Aim to improve the accuracy and speed of SVM classification in water quality evaluation, the PSO optimization method is applied to optimize the key parameters of SVM algorithm in this paper. A new adaptive adjustment of particle velocity method is proposed, which is based on the consideration of taking particle swarm fitness variance as evaluation criterion and using chasing particle position to replace local optimization particle position. First, an attracting domain is defined by the distance between farthest two particles. Then, by position variation factor making the particle jump out of the local optimal attracting domain regularly with the constantly iterations. Thus, the particle location can be adaptively mutated. Convergence tests on four different functions shows that the proposed improved algorithm is increased by more than 20 times in convergence accuracy comparing to another two kinds of particle swarm algorithm. Last, the improved PSO-SVM is applied in five-level water quality classification test based on the collected 5439 group water quality data. Contrast with the other three classification methods, the improved PSO-SVM algorithm has the highest convergence rate and convergence accuracy. The error rate of water quality evaluation is 1.54%, which can effectively meet the actual water quality classification requirements. |
| 参考文献 /References: | [1] 董楠楠. 世界水产品贸易竞争力与产业内贸易分析[J]. 宁波大学学报(理工版), 2007, 20(2):262-267. [2] 胡金有, 王靖杰, 张小栓, 等. 水产养殖信息化关键技术研究现状与趋势[J]. 农业机械学报, 2015, 46(7): 251-263. [3] Costea R I. ISO/TC 234-fisheries and aquaculture[J]. Aquaculture Aquarium Conservation & Legislation, 2009, 2(1):51-56. [4] 管军, 徐立中, 石爱业. 基于支持向量机的水质监测数据处理及状况识别与评价方法[J]. 计算机应用研究, 2006, 22(9):36-38. [5] 陈耀宁, 朱刚刚, 唐清华, 等. 基于支持向量机的白云湖水质评价[J]. 环境工程学报, 2014, 8(12):5535-5540. [6] 刘帮, 秦斌, 王欣, 等. PSO-LIBSVM在污水水质建模中的应用[J]. 湖南工业大学学报, 2015, 29(2):89-93. [7] 王道明, 鲁昌华, 蒋薇薇, 等. 基于粒子群算法的决策树SVM多分类方法研究[J]. 电子测量与仪器学报, 2015, 29(4):611-615. [8] 高立群, 吴沛峰, 邹德旋. 基于变异策略的粒子群算法[J]. 东北大学学报(自然科学版), 2010, 31(11):1530-1533. [9] Liu W, Wang G Y, Fu J Y, et al. Water quality prediction based on improved wavelet transformation and support vector machine[J]. Advanced Materials Research, 2013, 2480(726):3547-3553. [10] 吴一全, 殷骏, 戴一冕, 等. 基于蜂群优化多核支持向量机的淡水鱼种类识别[J]. 农业工程学报, 2014, 30(16):312-319. [11] Ayed S, Mahamed G H, Omran M C, et al. Improving the performance of comprehensive learning particle swarm optimizer[J]. Journal of Intelligent & Fuzzy Systems, 2015, 30(2):735-746. [12] 王东风, 孟丽, 赵文杰. 基于自适应搜索中心的骨干粒子群算法[J]. 计算机学报, 2016, 39(12):2652-2667. [13] 纪震, 廖惠连, 吴青华. 粒子群算法及应用[M]. 北京: 科学出版社, 2009:74-78. [14] GB11607-89. 渔业水质标准[S]. [15] 黄衍标, 罗广岳, 何铭金. BP神经网络在巡逻机器人多传感器数据融合中的应用[J]. 传感技术学报, 2016, 29(12):1936-1940. |
| 备注/Memo: | 收稿日期: 2017?12?05. 宁波大学学报（理工版）网址: http://journallg.nbu.edu.cn/ 基金项目: 国家自然科学基金（51675286）; 宁波市自然科学基金（2017A610085）; 浙江省公益技术项目（2017C32014）. 第一作者: 魏超（1993－）, 男, 安徽六安人, 在读硕士研究生, 主要研究方向: 轮机工程. E-mail: 1608317146@qq.com *通信作者: 张刚（1976－）, 男, 四川遂宁人, 博士/高级工程师, 主要研究方向: 船舶自动化与机电控制. E-mail: zhanggang@nbu.edu.cn 宁波大学学报（理工版）网址：http://journallg.nbu.edu.cn/ |
