当前位置: X-MOL 学术IEEE Sens. J. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
MCSP-SSS: A Domain Adaptive Framework for High-Accuracy Sensor Data Classification
IEEE Sensors Journal ( IF 4.3 ) Pub Date : 2021-10-11 , DOI: 10.1109/jsen.2021.3119320
Ran Liu , Xi Chen , Fengchun Tian , Junhui Qian , Feifei Wang , Lin Yi

Due to sensor drift, instrumental variation, or change of measurement object, the distributions of the datasets (domains) acquired by the sensors are often different. A domain adaptive framework called MCSP-SSS is proposed to reduce the distribution discrepancy across domains for high-accuracy sensor data classification. The framework consists of two key parts: Multi-Constraint Subspace Projection (MCSP) and Source Sample Selection (SSS). MCSP is a subspace-projection-based approach, which introduces four constraints to get an optimized projection matrix: Principal Component Analysis (PCA) is used to reduce the redundancy of features; Mean Distribution Discrepancy (MDD) is applied to minimize the difference between source and target data; Hilbert-Schmidt Independence Criterion (HSIC) is adopted to maximizing the dependence between features and labels; A so-called weighted-within-class scatter matrix is introduced to minimize the within-class variance to avoid samples with different labels to overlap in the subspace. SSS is designed to remove the outliers in projected source samples so as to reduce distribution discrepancy between the source and target samples projected by MCSP. Experimental results show that our framework can achieve the best accuracies in all classification tasks in comparison with other state-of-the-art approaches. The accuracy of MCSP-SSS is 3.57 percentage points (pps) higher on average than that of the second best approach for single-source domain adaptation, and 7.00 pps for multi-source domain adaptation. Source code is available at https://github.com/threedteam/tsc_subspace_projection .

中文翻译:

MCSP-SSS:用于高精度传感器数据分类的域自适应框架

由于传感器漂移、仪器变化或测量对象的变化,传感器获取的数据集(域)的分布往往不同。提出了一种称为 MCSP-SSS 的域自适应框架,以减少跨域的分布差异,以实现高精度传感器数据分类。该框架由两个关键部分组成:多约束子空间投影(MCSP)和源样本选择(SSS)。MCSP 是一种基于子空间投影的方法,它引入了四个约束来获得优化的投影矩阵: 主成分分析(PCA)用于减少特征的冗余;均值分布差异 (MDD) 用于最小化源数据和目标数据之间的差异;采用 Hilbert-Schmidt Independence Criterion (HSIC) 来最大化特征和标签之间的依赖关系;引入了一个所谓的加权类内散布矩阵来最小化类内方差,以避免不同标签的样本在子空间中重叠。SSS 旨在去除投影源样本中的异常值,以减少 MCSP 投影的源样本和目标样本之间的分布差异。实验结果表明,与其他最先进的方法相比,我们的框架可以在所有分类任务中达到最佳精度。MCSP-SSS 的准确率比单源域适应的次优方法平均高 3.57 个百分点(pps),多源域适应的准确率平均高 7.00 pps。源代码可在 引入了一个所谓的加权类内散布矩阵来最小化类内方差,以避免不同标签的样本在子空间中重叠。SSS 旨在去除投影源样本中的异常值,以减少 MCSP 投影的源样本和目标样本之间的分布差异。实验结果表明,与其他最先进的方法相比,我们的框架可以在所有分类任务中达到最佳精度。MCSP-SSS 的准确率比单源域适应的次优方法平均高 3.57 个百分点(pps),多源域适应的准确率平均高 7.00 pps。源代码可在 引入了一个所谓的加权类内散布矩阵来最小化类内方差,以避免不同标签的样本在子空间中重叠。SSS 旨在去除投影源样本中的异常值,以减少 MCSP 投影的源样本和目标样本之间的分布差异。实验结果表明,与其他最先进的方法相比,我们的框架可以在所有分类任务中达到最佳精度。MCSP-SSS 的准确率比单源域适应的次优方法平均高 3.57 个百分点(pps),多源域适应的准确率平均高 7.00 pps。源代码可在 SSS 旨在去除投影源样本中的异常值,以减少 MCSP 投影的源样本和目标样本之间的分布差异。实验结果表明,与其他最先进的方法相比,我们的框架可以在所有分类任务中达到最佳精度。MCSP-SSS 的准确率比单源域适应的次优方法平均高 3.57 个百分点(pps),多源域适应的准确率平均高 7.00 pps。源代码可在 SSS 旨在去除投影源样本中的异常值,以减少 MCSP 投影的源样本和目标样本之间的分布差异。实验结果表明,与其他最先进的方法相比,我们的框架可以在所有分类任务中达到最佳精度。MCSP-SSS 的准确率比单源域适应的次优方法平均高 3.57 个百分点(pps),多源域适应的准确率平均高 7.00 pps。源代码可在 平均比单源域适应的次优方法高 57 个百分点 (pps),多源域适应高 7.00 pps。源代码可在 平均比单源域适应的次优方法高 57 个百分点 (pps),多源域适应高 7.00 pps。源代码可在https://github.com/threedteam/tsc_subspace_projection .
更新日期:2021-11-16
down
wechat
bug