{"title":"人工智能分类算法中类不平衡的鲁棒性","authors":"J. Lian, Laura J. Freeman, Yili Hong, Xinwei Deng","doi":"10.1080/00224065.2021.1963200","DOIUrl":null,"url":null,"abstract":"Abstract Artificial intelligence (AI) algorithms, such as deep learning and XGboost, are used in numerous applications including autonomous driving, manufacturing process optimization and medical diagnostics. The robustness of AI algorithms is of great interest as inaccurate prediction could result in safety concerns and limit the adoption of AI systems. In this paper, we propose a framework based on design of experiments to systematically investigate the robustness of AI classification algorithms. A robust classification algorithm is expected to have high accuracy and low variability under different application scenarios. The robustness can be affected by a wide range of factors such as the imbalance of class labels in the training dataset, the chosen prediction algorithm, the chosen dataset of the application, and a change of distribution in the training and test datasets. To investigate the robustness of AI classification algorithms, we conduct a comprehensive set of mixture experiments to collect prediction performance results. Then statistical analyses are conducted to understand how various factors affect the robustness of AI classification algorithms. We summarize our findings and provide suggestions to practitioners in AI applications.","PeriodicalId":54769,"journal":{"name":"Journal of Quality Technology","volume":null,"pages":null},"PeriodicalIF":2.6000,"publicationDate":"2021-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"8","resultStr":"{\"title\":\"Robustness with respect to class imbalance in artificial intelligence classification algorithms\",\"authors\":\"J. Lian, Laura J. Freeman, Yili Hong, Xinwei Deng\",\"doi\":\"10.1080/00224065.2021.1963200\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Abstract Artificial intelligence (AI) algorithms, such as deep learning and XGboost, are used in numerous applications including autonomous driving, manufacturing process optimization and medical diagnostics. The robustness of AI algorithms is of great interest as inaccurate prediction could result in safety concerns and limit the adoption of AI systems. In this paper, we propose a framework based on design of experiments to systematically investigate the robustness of AI classification algorithms. A robust classification algorithm is expected to have high accuracy and low variability under different application scenarios. The robustness can be affected by a wide range of factors such as the imbalance of class labels in the training dataset, the chosen prediction algorithm, the chosen dataset of the application, and a change of distribution in the training and test datasets. To investigate the robustness of AI classification algorithms, we conduct a comprehensive set of mixture experiments to collect prediction performance results. Then statistical analyses are conducted to understand how various factors affect the robustness of AI classification algorithms. We summarize our findings and provide suggestions to practitioners in AI applications.\",\"PeriodicalId\":54769,\"journal\":{\"name\":\"Journal of Quality Technology\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":2.6000,\"publicationDate\":\"2021-08-30\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"8\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Quality Technology\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://doi.org/10.1080/00224065.2021.1963200\",\"RegionNum\":2,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"ENGINEERING, INDUSTRIAL\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Quality Technology","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.1080/00224065.2021.1963200","RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENGINEERING, INDUSTRIAL","Score":null,"Total":0}
Robustness with respect to class imbalance in artificial intelligence classification algorithms
Abstract Artificial intelligence (AI) algorithms, such as deep learning and XGboost, are used in numerous applications including autonomous driving, manufacturing process optimization and medical diagnostics. The robustness of AI algorithms is of great interest as inaccurate prediction could result in safety concerns and limit the adoption of AI systems. In this paper, we propose a framework based on design of experiments to systematically investigate the robustness of AI classification algorithms. A robust classification algorithm is expected to have high accuracy and low variability under different application scenarios. The robustness can be affected by a wide range of factors such as the imbalance of class labels in the training dataset, the chosen prediction algorithm, the chosen dataset of the application, and a change of distribution in the training and test datasets. To investigate the robustness of AI classification algorithms, we conduct a comprehensive set of mixture experiments to collect prediction performance results. Then statistical analyses are conducted to understand how various factors affect the robustness of AI classification algorithms. We summarize our findings and provide suggestions to practitioners in AI applications.
期刊介绍:
The objective of Journal of Quality Technology is to contribute to the technical advancement of the field of quality technology by publishing papers that emphasize the practical applicability of new techniques, instructive examples of the operation of existing techniques and results of historical researches. Expository, review, and tutorial papers are also acceptable if they are written in a style suitable for practicing engineers.
Sample our Mathematics & Statistics journals, sign in here to start your FREE access for 14 days