Raphael Wallsberger, Tim Dieter Eberhardt, Paul-Albert Bartlau, Maurice Lucas Dörnte, Tim Lukas Schröter, S. Matzka
{"title":"Explainable Artificial Intelligence for a high dimensional condition monitoring application using the SHAP Method","authors":"Raphael Wallsberger, Tim Dieter Eberhardt, Paul-Albert Bartlau, Maurice Lucas Dörnte, Tim Lukas Schröter, S. Matzka","doi":"10.1109/AI4I54798.2022.00024","DOIUrl":null,"url":null,"abstract":"In this paper, a new visualization-based method for understanding industrial machine learning models trained on high dimensional data is proposed. For a view that includes all dimensions, a dimensionality reduction towards a 2D projection, the UMAP method, is used. With the TreeSHAP algorithm the most important features for each machine condition are identified, visualized and evaluated. A closer look at different data points of the most important features provides more information about the behavior of the model. In addition, this knowledge is used to derive a class-optimized 2D visualization to increase trustworthiness of individual classification results for domain experts.","PeriodicalId":345427,"journal":{"name":"2022 5th International Conference on Artificial Intelligence for Industries (AI4I)","volume":"444-445 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 5th International Conference on Artificial Intelligence for Industries (AI4I)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/AI4I54798.2022.00024","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
In this paper, a new visualization-based method for understanding industrial machine learning models trained on high dimensional data is proposed. For a view that includes all dimensions, a dimensionality reduction towards a 2D projection, the UMAP method, is used. With the TreeSHAP algorithm the most important features for each machine condition are identified, visualized and evaluated. A closer look at different data points of the most important features provides more information about the behavior of the model. In addition, this knowledge is used to derive a class-optimized 2D visualization to increase trustworthiness of individual classification results for domain experts.
京公网安备 11010802042870号
京ICP备2023020795号-1
分享
求助内容：
应助结果提醒方式：
扫码关注我们
