Building Robust Prediction Models for Defective Sensor Data Using Artificial Neural Networks

被引:1
|
作者
de Sa, Claudio Rebelo [1 ]
Shekar, Arvind Kumar [2 ]
Ferreira, Hugo [3 ]
Soares, Carlos [4 ]
机构
[1] Twente Univ, Enschede, Netherlands
[2] Robert Bosch GmbH, Stuttgart, Germany
[3] INESC TEC, Porto, Portugal
[4] Univ Porto, Fac Engn, Porto, Portugal
关键词
REGRESSION;
D O I
10.1007/978-3-030-20055-8_14
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Sensors are susceptible to failure when exposed to extreme conditions over long periods of time. Besides they can be affected by noise or electrical interference. Models (Machine Learning or others) obtained from these faulty and noisy sensors may be less reliable. In this paper, we propose a data augmentation approach for making neural networks more robust to missing and faulty sensor data. This approach is shown to be effective in a real life industrial application that uses data of various sensors to predict the wear of an automotive fuel-system component. Empirical results show that the proposed approach leads to more robust neural network in this particular application than existing methods.
引用
收藏
页码:142 / 153
页数:12
相关论文
共 50 条
  • [1] Building Energy Prediction using Artificial Neural Networks (LSTM)
    Goswami, Sankhanil
    [J]. PROCEEDINGS OF THE ASME 2020 POWER CONFERENCE (POWER2020), 2020,
  • [2] Prediction of building energy consumption by using artificial neural networks
    Ekici, Betul Bektas
    Aksoy, U. Teoman
    [J]. ADVANCES IN ENGINEERING SOFTWARE, 2009, 40 (05) : 356 - 362
  • [3] Prediction of building's temperature using neural networks models
    Ruano, AE
    Crispim, EM
    Conceiçao, EZE
    Lúcio, MMJR
    [J]. ENERGY AND BUILDINGS, 2006, 38 (06) : 682 - 694
  • [4] Robust Prediction of Shear Strength of SFRC Using Artificial Neural Networks
    Odeh, Ruba
    Alawadi, Roaa
    [J]. SUSTAINABILITY, 2022, 14 (14)
  • [5] Building energy prediction using artificial neural networks: A literature survey
    Lu, Chujie
    Li, Sihui
    Lu, Zhengjun
    [J]. ENERGY AND BUILDINGS, 2022, 262
  • [6] Strategies for building robust prediction models using data unavailable at prediction time
    Yang, Haoyu
    Tourani, Roshan
    Zhu, Ying
    Kumar, Vipin
    Melton, Genevieve B.
    Steinbach, Michael
    Simon, Gyorgy
    [J]. JOURNAL OF THE AMERICAN MEDICAL INFORMATICS ASSOCIATION, 2021, 29 (01) : 72 - 79
  • [7] Autocompletion of Design Data in Semantic Building Models using Link Prediction and Graph Neural Networks
    Eisenstadt, Viktor
    Bielski, Jessica
    Langenhan, Christoph
    Althoff, Klaus-Dieter
    Dengel, Andreas
    [J]. CO-CREATING THE FUTURE: INCLUSION IN AND THROUGH DESIGN, ECAADE 2022, VOL 1, 2022, : 501 - 510
  • [8] Robust parametric estimation for nonlinear models using artificial neural networks
    Silva, IN
    Amaral, WC
    Arruda, LVR
    [J]. SMC '97 CONFERENCE PROCEEDINGS - 1997 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN, AND CYBERNETICS, VOLS 1-5: CONFERENCE THEME: COMPUTATIONAL CYBERNETICS AND SIMULATION, 1997, : 3813 - 3816
  • [9] A Review of Research on Building Energy Consumption Prediction Models Based on Artificial Neural Networks
    Yin, Qing
    Han, Chunmiao
    Li, Ailin
    Liu, Xiao
    Liu, Ying
    [J]. SUSTAINABILITY, 2024, 16 (17)
  • [10] ARTIFICIAL NEURAL NETWORK MODELS FOR BUILDING ENERGY PREDICTION
    Ahn, Ki Uhn
    Park, Cheol Soo
    [J]. 2017 WINTER SIMULATION CONFERENCE (WSC), 2017, : 2708 - 2716