[1]佘雅莉,周 良.基于改进在线序列学习机的危险源识别算法[J].计算机技术与发展,2018,28(09):72-77.[doi:10.3969/ j. issn.1673-629X.2018.09.016]
　SHE Ya-li,ZHOU Liang.Hazard Identification Algorithm Based on Improved Online Sequential Extreme Learning Machine[J].,2018,28(09):72-77.[doi:10.3969/ j. issn.1673-629X.2018.09.016]
点击复制

基于改进在线序列学习机的危险源识别算法()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
28
期数:
2018年09期
页码:
72-77
栏目:
智能、算法、系统工程
出版日期:
2018-09-10

文章信息/Info

Title:
Hazard Identification Algorithm Based on Improved Online Sequential Extreme Learning Machine
文章编号:
1673-629X(2018)09-0072-06
作者:
佘雅莉; 周 良
南京航空航天大学 计算机科学与技术学院,江苏 南京 210016
Author(s):
SHE Ya-li; ZHOU Liang
School of Computer Science and Technology,Nanjing University of Aeronautics and Astronautics,Nanjing 210016,China
关键词:
危险源识别; 在线学习; 极限学习机; 差分进化
Keywords:
hazards identification; online learning; extreme learning machine; adaptive differential evolution
分类号:
TP183
DOI:
10.3969/ j. issn.1673-629X.2018.09.016
文献标志码:
A
摘要:
危险源是影响飞行安全的重要因素,如何正确地识别危险源并采取对应措施确保飞行安全是民航空管必不可少的关键环节。 这要求危险源识别算法在保证识别准确度的前提下还需具备在线处理数据的性能。 据此,提出了一种基于改进在线序列学习机的危险源识别算法 HI-OSELM。 将当前新到达的危险源数据添加到网络结构中,实时更新学习机输出权值,对危险源进行在线识别,并用全局寻优能力较好的自适应差分进化方法对输入权值和隐层偏置进行优化;通过随机生成多组初始值,用实际输出与理想输出之间的均方根误差作为适应度指标进行训练,不断进化直至达到最大种群迭代次数,最终获得最优的网络输入权值和隐层偏置,使 HI-OSELM 有更好的泛化性能,算法的识别结果准确性更高。
Abstract:
Hazards identification is an important factor that affects flight safety. How to correctly identify hazards and take corresponding measures to ensure flight safety is an essential part of the management of air traffic,which requires that the hazard identification algorithm must have the capability to process data online while ensuring the accuracy of identification. Therefore,we propose a hazard identification algorithm based on improving online sequential extreme learning machine (HI-OSELM). HI-OSELM adds newly arrived data into the training network,and then updates the network outputs weight,in order to realize the online identification. In addition,It uses the global optimization ability of adaptive differential evolution to optimize network input weights and hidden layer bias by randomly generating a plurality of sets of initial values and using root mean square error between the actual outputs and the desired outputs as the fitness index for training,and then gradually evolves until it reaches the maximum iterations. Finally the optimal network input weights and hidden layer bias are obtained,which makes the HI-OSELM has better generalization and accuracy of recognition results.

相似文献/References:

[1]王雪松 申群太.基于多Agent系统的自调节及协同工作的组合投资模型[J].计算机技术与发展,2010,(05):117.
　WANG Xue-song,SHEN Qun-tai.Combination Investment Model of Auto-Adjustment and Cooperate with Work Based on Multi-Agent System[J].,2010,(09):117.
[2]王娟 柴玉梅.基于多议题协商的贝叶斯学习[J].计算机技术与发展,2006,(02):154.
　WANG Juan,CHAI Yu-mei.A Bayesian Learning Based on Multi- Issues Negotiation[J].,2006,(09):154.
[3]郭新. 一种改进的短期交通流量预测算法研究[J].计算机技术与发展,2015,25(02):103.
　GUO Xin. Research on an Improved Prediction Algorithm for Short-term Traffic Flow [J].,2015,25(09):103.
[4]何利雪,陈健. 基于ERBAC模式的在线考试模型研究与实现[J].计算机技术与发展,2015,25(04):139.
　HE Li-xue,CHEN Jian. Research and Realization of Online Test/Examination System Based on an ERBAC Model[J].,2015,25(09):139.
[5]徐新瑞,孟彩霞,周雯,等. 一种基于Spark时效化协同过滤推荐算法[J].计算机技术与发展,2015,25(06):48.
　XU Xin-rui,MENG Cai-xia,ZHOU Wen,et al. A Real-time Collaborative Filtering Recommendation Algorithm Based on Spark[J].,2015,25(09):48.
[6]吴 垒,于哲舟.基于概率神经网络的在线分类器[J].计算机技术与发展,2019,29(12):14.[doi:10. 3969 / j. issn. 1673-629X. 2019. 12. 003]
　WU Lei,YU Zhe-zhou.An Improved Classifier Based on Probabilistic Neural Network[J].,2019,29(09):14.[doi:10. 3969 / j. issn. 1673-629X. 2019. 12. 003]
[7]覃忠台,张明军.基于协同过滤算法的学习资源推荐模型研究[J].计算机技术与发展,2021,31(09):31.[doi:10. 3969 / j. issn. 1673-629X. 2021. 09. 006]
　QIN Zhong-tai,ZHANG Ming-jun.Research on Learning Resource Recommendation Model Based on Collaborative Filtering Algorithm[J].,2021,31(09):31.[doi:10. 3969 / j. issn. 1673-629X. 2021. 09. 006]
[8]马 华,黄卓轩*,唐文胜.面向个性化学习的认知诊断模型及其应用综述[J].计算机技术与发展,2021,31(11):35.[doi:10. 3969 / j. issn. 1673-629X. 2021. 11. 006]
　MA Hua,HUANG Zhuo-xuan*,TANG Wen-sheng.Review on Cognitive Diagnosis Model and Its Application forPersonalized Learning[J].,2021,31(09):35.[doi:10. 3969 / j. issn. 1673-629X. 2021. 11. 006]
[9]姚 远,徐晶晶,朱小倩.基于 2D 和 3D 图像处理技术的在线学习评估[J].计算机技术与发展,2021,31(12):128.[doi:10. 3969 / j. issn. 1673-629X. 2021. 12. 022]
　YAO Yuan,XU Jing-jing,ZHU Xiao-qian.Online Learning Evaluation Based on Processing Technologies in 2D and 3D Images[J].,2021,31(09):128.[doi:10. 3969 / j. issn. 1673-629X. 2021. 12. 022]
[10]祁天龙,任美睿,赵建宇,等.基于聚类的协作学习分组方法[J].计算机技术与发展,2023,33(06):189.[doi:10. 3969 / j. issn. 1673-629X. 2023. 06. 028]
　QI Tian-long,REN Mei-rui,ZHAO Jian-yu,et al.Collaborative Learning Grouping Method Based on Clustering[J].,2023,33(09):189.[doi:10. 3969 / j. issn. 1673-629X. 2023. 06. 028]

更新日期/Last Update: 2018-09-10