Advanced Outlier Detection Using Unsupervised Learning for Screening Potential Customer Returns
Advanced Outlier Detection Using Unsupervised Learning for Screening Potential Customer Returns
复制标题
DOI：
10.1109/itc44778.2020.9325225
复制
发表时间：
2020-11
期刊：
影响因子：
--
通讯作者：
Hanbin Hu;Nguyen Nguyen-Nguyen;Chen He;Peng Li
中科院分区：
文献类型：
--
作者：
Hanbin Hu;Nguyen Nguyen-Nguyen;Chen He;Peng Li
由于客户故障数据的极度稀缺性，在相关参数测量测量结果形成的高维输入特征空间中可靠地筛选出这些罕见缺陷是一项挑战。在本文中，我们根据六个工业测试数据集研究了几种无监督的学习技术，并建议通过通过一组转换来自行标记培训数据来培训更强大的无监督学习模型。使用标记的数据，我们通过监督培训来培训多级分类器。多类别分类对看不见的输入数据的好处被用作缺陷异常的正态性评分。此外，我们建议使用可逆信息无损转换来保留数据信息并提高所提出的自标记方法的性能和鲁棒性。
Due to the extreme scarcity of customer failure data, it is challenging to reliably screen out those rare defects within a high-dimensional input feature space formed by the relevant parametric test measurements. In this paper, we study several unsupervised learning techniques based on six industrial test datasets, and propose to train a more robust unsupervised learning model by self-labeling the training data via a set of transformations. Using the labeled data we train a multi-class classifier through supervised training. The goodness of the multiclass classification decisions with respect to an unseen input data is used as a normality score to defect anomalies. Furthermore, we propose to use reversible information lossless transformations to retain the data information and boost the performance and robustness of the proposed self-labeling approach.