arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2303.09068cs.CVcs.LGeess.IV
收藏

Vortex Feature Positioning:连接表格型 IIoT 数据与基于图像的深度学习

Vortex Feature Positioning: Bridging Tabular IIoT Data and Image-Based Deep Learning

Carnegie Mellon University(卡内基梅隆大学);Chung-Ang University(中央大学);University of Essex(埃塞克斯大学)

Jong-Ik Park, Sihoon Seong, JunKyu Lee, Cheol-Ho Hong

AI总结:

针对表格型 IIoT 数据图像化中的固定尺寸浪费与过拟合问题,提出按相关性涡旋排布特征、尺寸随属性数变化的 VFP,并在七个数据集上验证其优于传统方法。

摘要:

来自 IIoT 设备的表格数据通常使用基于决策树的机器学习技术进行分析,而这些技术难以处理高维数值数据。为克服这些局限,研究者开发了将表格数据转换为图像的技术,以利用卷积神经网络等基于图像的深度学习方法的优势。这些方法将相似特征聚类到固定尺寸的不同图像区域中,而不考虑特征数量,使其类似真实照片。然而,这会增加过拟合的可能性,因为在表格格式中经过谨慎选择后,相似特征往往会被丢弃以防止该问题。此外,固定图像尺寸在特征较少时会导致像素浪费,从而造成计算效率低下。我们提出 Vortex Feature Positioning(VFP)来解决这些问题。VFP 根据特征的相关性排列特征,将相似特征从图像中心开始以涡旋图案间隔开,图像尺寸由属性数量决定。在七个具有不同实值属性数量的数据集上进行的测试中,VFP 优于传统机器学习方法和现有转换技术。

英文摘要:

Tabular data from IIoT devices are typically analyzed using decision tree-based machine learning techniques, which struggle with high-dimensional and numeric data. To overcome these limitations, techniques converting tabular data into images have been developed, leveraging the strengths of image-based deep learning approaches such as Convolutional Neural Networks. These methods cluster similar features into distinct image areas with fixed sizes, regardless of the number of features, resembling actual photographs. However, this increases the possibility of overfitting, as similar features, when selected carefully in a tabular format, are often discarded to prevent this issue. Additionally, fixed image sizes can lead to wasted pixels with fewer features, resulting in computational inefficiency. We introduce Vortex Feature Positioning (VFP) to address these issues. VFP arranges features based on their correlation, spacing similar ones in a vortex pattern from the image center, with the image size determined by the attribute count. VFP outperforms traditional machine learning methods and existing conversion techniques in tests across seven datasets with varying real-valued attributes.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑