Online Anomaly Explanation: A Case Study on Predictive Maintenance

被引：3

作者：

Ribeiro, Rita P. ^{[1
,2
]}

Mastelini, Saulo Martiello ^{[3
]}

Davari, Narjes ^{[1
]}

Aminian, Ehsan ^{[1
]}

Veloso, Bruno ^{[1
,2
,4
,5
]}

Gama, Joao ^{[1
,2
,5
]}

机构：

[1] INESC TEC, P-4200465 Porto, Portugal

[2] Univ Porto, Fac Sci, P-4169007 Porto, Portugal

[3] Univ S Paulo, ICMC, BR-13566590 Sao Carlos, Brazil

[4] Univ Portucalense, P-4200072 Porto, Portugal

[5] Univ Porto, Fac Econ, P-4200464 Porto, Portugal

来源：

MACHINE LEARNING AND PRINCIPLES AND PRACTICE OF KNOWLEDGE DISCOVERY IN DATABASES, ECML PKDD 2022, PT II | 2023年 / 1753卷

基金：

巴西圣保罗研究基金会;

关键词：

Explainable AI; Rare events; Predictive maintenance;

D O I：

10.1007/978-3-031-23633-4_25

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Predictive Maintenance applications are increasingly complex, with interactions between many components. Black-box models are popular approaches due to their predictive accuracy and are based on deep-learning techniques. This paper presents an architecture that uses an online rule learning algorithm to explain when the black-box model predicts rare events. The system can present global explanations that model the black-box model and local explanations that describe why the black-box model predicts a failure. We evaluate the proposed system using four real-world public transport data sets, presenting illustrative examples of explanations.

引用

页码：383 / 399

页数：17

共 17 条

[1] Chebyshev approaches for imbalanced data streams regression models [J].

Aminian, Ehsan ;

Ribeiro, Rita P. ;

Gama, Joao .

DATA MINING AND KNOWLEDGE DISCOVERY, 2021, 35 (06) :2389-2466

[2]

Bifet A, 2007, PROCEEDINGS OF THE SEVENTH SIAM INTERNATIONAL CONFERENCE ON DATA MINING, P443

[3] A Survey of Predictive Modeling on Im balanced Domains [J].

Branco, Paula ;

Torgo, Luis ;

Ribeiro, Rita P. .

ACM COMPUTING SURVEYS, 2016, 49 (02)

[4] Adaptive Model Rules From High-Speed Data Streams [J].

Duarte, Joao ;

Gama, Joao ;

Bifet, Albert .

ACM TRANSACTIONS ON KNOWLEDGE DISCOVERY FROM DATA, 2016, 10 (03)

[5]

Finch T, 2009, Technical Report

[6] A Survey of Methods for Explaining Black Box Models [J].

Guidotti, Riccardo ;

Monreale, Anna ;

Ruggieri, Salvatore ;

Turin, Franco ;

Giannotti, Fosca ;

Pedreschi, Dino .

ACM COMPUTING SURVEYS, 2019, 51 (05)

[7]

Hall P., 2019, An Introduction to Machine Learning Interpretability, V2nd ed.

[8]

Lundberg SM, 2017, ADV NEUR IN, V30

[9] Using dynamical quantization to perform split attempts in online tree regressors [J].

Mastelini, Saulo Martiello ;

de Leon Ferreira de Carvalho, Andre Carlos Ponce .

PATTERN RECOGNITION LETTERS, 2021, 145 :37-42

[10]

Molnar C., 2022, INTERPRETABLE MACHIN

← 1 2 →