According to the classic Karush-Kuhn-Tucker(KKT)theorem,at every step of incremental support vector machine(SVM)learning,the newly adding sample which violates the KKT conditions will be a new support vector(SV)and mi...According to the classic Karush-Kuhn-Tucker(KKT)theorem,at every step of incremental support vector machine(SVM)learning,the newly adding sample which violates the KKT conditions will be a new support vector(SV)and migrate the old samples between SV set and non-support vector(NSV)set,and at the same time the learning model should be updated based on the SVs.However,it is not exactly clear at this moment that which of the old samples would change between SVs and NSVs.Additionally,the learning model will be unnecessarily updated,which will not greatly increase its accuracy but decrease the training speed.Therefore,how to choose the new SVs from old sets during the incremental stages and when to process incremental steps will greatly influence the accuracy and efficiency of incremental SVM learning.In this work,a new algorithm is proposed to select candidate SVs and use the wrongly predicted sample to trigger the incremental processing simultaneously.Experimental results show that the proposed algorithm can achieve good performance with high efficiency,high speed and good accuracy.展开更多
锂电池作为一种电化学设备,在发生故障前的特征较为复杂,难以分析,并且生产环境中故障样本数量较少,正负样本比例严重不平衡。针对以上问题,本工作提出基于改进的在线迁移学习算法的电池高压故障预警。首先,引入下采样技术,解决样本不...锂电池作为一种电化学设备,在发生故障前的特征较为复杂,难以分析,并且生产环境中故障样本数量较少,正负样本比例严重不平衡。针对以上问题,本工作提出基于改进的在线迁移学习算法的电池高压故障预警。首先,引入下采样技术,解决样本不均衡问题,从而降低计算资源的使用。在电池高压故障预警场景下,设计分段下采样策略,使得算法模型在故障发生前能学习到更多细微的特征。其次,提出基于分批增量学习的在线迁移学习方法(homogeneous online transfer learning under incremental training,HomOTL-UIT),源域中训练的离线分类器需要在合适的时间进行更新,以此来适应目标域中不断变化的数据分布,解决数据分布偏移和在线迁移学习退化为在线学习的问题。分批处理降低多次训练带来的计算资源的开销,通过增量学习,不断从目标域中学习,从而不断提高离线分类器的准确度。然后,设计一种滑动窗口下的F1-score评分方法,解决模型权重缓慢失衡问题,从而提高模型的准确性。最后,通过储能集装箱的运行数据验证所提出方法的有效性和准确性,在正负样本严重不均衡时,F1-score达到0.88。展开更多
为进一步降低样本成本并加快模型收敛速度,提出基于探索和开发的指数加权算法(exponential-weight algorithm for exploration and exploitation,EXP3)和增量微调卷积神经网络(fine-tuning convolutional neural networks,FCNN)的入侵...为进一步降低样本成本并加快模型收敛速度,提出基于探索和开发的指数加权算法(exponential-weight algorithm for exploration and exploitation,EXP3)和增量微调卷积神经网络(fine-tuning convolutional neural networks,FCNN)的入侵检测系统(EXP3-FCNN)。利用EXP3算法自适应选择最佳主动学习策略,代替单一的主动学习算法,提高样本质量;利用增量微调卷积神经网络提取流量数据更深层次的特征;使用AWID数据集作为实验数据。实验结果表明,该方案在保证模型精确度、召回率等性能指标的基础上,降低了样本成本,提高了模型的收敛效率。展开更多
基金supported by the National Natural Science Foundation of China(Nos.U1509207 and 61325019)
文摘According to the classic Karush-Kuhn-Tucker(KKT)theorem,at every step of incremental support vector machine(SVM)learning,the newly adding sample which violates the KKT conditions will be a new support vector(SV)and migrate the old samples between SV set and non-support vector(NSV)set,and at the same time the learning model should be updated based on the SVs.However,it is not exactly clear at this moment that which of the old samples would change between SVs and NSVs.Additionally,the learning model will be unnecessarily updated,which will not greatly increase its accuracy but decrease the training speed.Therefore,how to choose the new SVs from old sets during the incremental stages and when to process incremental steps will greatly influence the accuracy and efficiency of incremental SVM learning.In this work,a new algorithm is proposed to select candidate SVs and use the wrongly predicted sample to trigger the incremental processing simultaneously.Experimental results show that the proposed algorithm can achieve good performance with high efficiency,high speed and good accuracy.
文摘锂电池作为一种电化学设备,在发生故障前的特征较为复杂,难以分析,并且生产环境中故障样本数量较少,正负样本比例严重不平衡。针对以上问题,本工作提出基于改进的在线迁移学习算法的电池高压故障预警。首先,引入下采样技术,解决样本不均衡问题,从而降低计算资源的使用。在电池高压故障预警场景下,设计分段下采样策略,使得算法模型在故障发生前能学习到更多细微的特征。其次,提出基于分批增量学习的在线迁移学习方法(homogeneous online transfer learning under incremental training,HomOTL-UIT),源域中训练的离线分类器需要在合适的时间进行更新,以此来适应目标域中不断变化的数据分布,解决数据分布偏移和在线迁移学习退化为在线学习的问题。分批处理降低多次训练带来的计算资源的开销,通过增量学习,不断从目标域中学习,从而不断提高离线分类器的准确度。然后,设计一种滑动窗口下的F1-score评分方法,解决模型权重缓慢失衡问题,从而提高模型的准确性。最后,通过储能集装箱的运行数据验证所提出方法的有效性和准确性,在正负样本严重不均衡时,F1-score达到0.88。
文摘为进一步降低样本成本并加快模型收敛速度,提出基于探索和开发的指数加权算法(exponential-weight algorithm for exploration and exploitation,EXP3)和增量微调卷积神经网络(fine-tuning convolutional neural networks,FCNN)的入侵检测系统(EXP3-FCNN)。利用EXP3算法自适应选择最佳主动学习策略,代替单一的主动学习算法,提高样本质量;利用增量微调卷积神经网络提取流量数据更深层次的特征;使用AWID数据集作为实验数据。实验结果表明,该方案在保证模型精确度、召回率等性能指标的基础上,降低了样本成本,提高了模型的收敛效率。
