Predicting IoT failures with Bayesian workflow

• Autorzy: Baranowski Jerzy

Identyfikatory

DOI

10.17531/ein.2022.2.6

• Języki publikacji: EN

Abstrakty

EN

IoT networks are so voluminous that they cannot be treated as individual devices, but as populations. Main aim of the paper is to create a comprehensive method for predicting failures taking device variance into consideration. We propose using data fusion of happenstance observations (resets and failures) to better estimate device parameters. We propose using methods of population analysis in Bayesian statistics to estimate failure times investigating only a part of the population. For this purpose, we use multilevel hierarchical Bayesian model and provide it with post stratification. We propose model assumptions, construct the model and evaluate it, and perform computations using Hamiltonian Monte Carlo. This method is known as the Bayesian workflow. We have analyzed three different models showing that, in case of small device variance, it can be ignored, or at least compensated, while significant differences require hierarchical modeling. We also show that hierarchical model shows significant robustness to a small amount of data. We have shown attractiveness of Bayesian approach to modeling failures of IoT devices. Ability to diagnose and tune models, and assure their computational fidelity is a great advantage of Bayesian workflow.

Słowa kluczowe

EN

IoT failures; Bayesian workflow; post-stratification; Hamiltonian Monte Carlo

• Wydawca: Polskie Naukowo-Techniczne Towarzystwo Eksploatacyjne
• Czasopismo: Eksploatacja i Niezawodność
• Rocznik: 2022
• Tom: Vol. 24, no. 2
• Strony: 248--259
• Opis fizyczny: Bibliogr. 27 poz., rys., tab.

Twórcy

autor

Baranowski Jerzy

• AGH University of Science & Technology; Al. A. Mickiewicza 30, 30-059 Kraków, Poland

• https://orcid.org/0000-0003-3313-581X

Bibliografia

• 1. Aleš Z, Pavlů J, Legát V et al. Methodology of overall equipment effectiveness calculation in the context of Industry 4.0 environment. Eksploatacja i Niezawodnosc - Maintenance and Reliability 2019; 21(3): 411–418, https://doi.org/10.17531/ein.2019.3.7.
• 2. Andrzejczak K, Bukowski L. A method for estimating the probability distribution of the lifetime for new technical equipment based on expert judgement. Eksploatacja i Niezawodnosc - Maintenance and Reliability 2021; 23(4): 757–769, https://doi.org/10.17531/ein.2021.4.18.
• 3. Betancourt M. A Conceptual Introduction to Hamiltonian Monte Carlo. arXiv:1701.02434 [stat] 2018.
• 4. Broderick T, Giordano R, Meager R. An Automatic Finite-Sample Robustness Metric: When Can Dropping a Little Data Make a Big Difference? arXiv:2011.14999 [econ, stat] 2021.
• 5. Browne W J, Draper D. A comparison of Bayesian and likelihood-based methods for fitting multilevel models. Bayesian Analysis 2006, https://doi.org/10.1214/06-BA117.
• 6. Bürkner P-C. Advanced Bayesian Multilevel Modeling with the R Package brms. The R Journal 2018; 10(1): 395, https://doi.org/10.32614/RJ-2018-017.
• 7. Carpenter B, Gelman A, Hoffman M D et al. Stan : A Probabilistic Programming Language. Journal of Statistical Software 2017, https://doi.org/10.18637/jss.v076.i01.
• 8. Diro A A, Chilamkurti N. Distributed attack detection scheme using deep learning approach for Internet of Things. Future Generation Computer Systems 2018; 82: 761–768, https://doi.org/10.1016/j.future.2017.08.043.
• 9. Fahim M, Sillitti A. Anomaly Detection, Analysis and Prediction Techniques in IoT Environment: A Systematic Literature Review. IEEE Access 2019; 7: 81664–81681, https://doi.org/10.1109/ACCESS.2019.2921912.
• 10. Gabry J, Simpson D, Vehtari A et al. Visualization in Bayesian workflow. Journal of the Royal Statistical Society: Series A (Statistics in Society) 2019; 182(2): 389–402, https://doi.org/10.1111/rssa.12378.
• 11. Gelman A, Carlin J B, Stern H S et al. Bayesian Data Analysis, Third Edition. Taylor & Francis: 2013.
• 12. Gelman A. Parameterization and Bayesian Modeling. Journal of the American Statistical Association 2004; 99(466): 537–545, https://doi.org/10.1198/016214504000000458.
• 13. Gelman A, Vehtari A, Simpson D et al. Bayesian Workflow. arXiv:2011.01808 [stat] 2020.
• 14. Hasan M, Islam Md M, Zarif M I I, Hashem M M A. Attack and anomaly detection in IoT sensors in IoT sites using machine learning approaches. Internet of Things 2019; 7: 100059, https://doi.org/10.1016/j.iot.2019.100059.
• 15. Kaya A, Keçeli A S, Catal C, Tekinerdogan B. Sensor Failure Tolerable Machine Learning-Based Food Quality Prediction Model. Sensors 2020; 20(11): 3173, https://doi.org/10.3390/s20113173.
• 16. Lin Y-B, Lin Y-W, Lin J-Y, Hung H-N. SensorTalk: An IoT Device Failure Detection and Calibration Mechanism for Smart Farming. Sensors 2019; 19(21): 4788, https://doi.org/10.3390/s19214788.
• 17. Makhshari A, Mesbah A. IoT Bugs and Development Challenges. 2021 IEEE/ACM 43rd International Conference on Software Engineering (ICSE), Madrid, ES, IEEE: 2021: 460–472, https://doi.org/10.1109/ICSE43902.2021.00051.
• 18. Manimurugan S, Al-Mutairi S, Aborokbah M M et al. Effective Attack Detection in Internet of Medical Things Smart Environment Using a Deep Belief Neural Network. IEEE Access 2020; 8: 77396–77404, https://doi.org/10.1109/ACCESS.2020.2986013.
• 19. Mikkola P, Martin O A, Chandramouli S et al. Prior knowledge elicitation: The past, present, and future. arXiv:2112.01380 [stat] 2021.
• 20. Moghaddam M T, Muccini H. Fault-Tolerant IoT: A Systematic Mapping Study. In Calinescu R, Di Giandomenico F (eds): Software Engineering for Resilient Systems, Cham, Springer International Publishing: 2019; 11732: 67–84, https://doi.org/10.1007/978-3-030-30856-8_5.
• 21. Stief A, Ottewill J R, Baranowski J, Orkisz M. A PCA and Two-Stage Bayesian Sensor Fusion Approach for Diagnosing Electrical and Mechanical Faults in Induction Motors. IEEE Transactions on Industrial Electronics 2019; 66(12): 9510–9520, https://doi.org/10.1109/TIE.2019.2891453.
• 22. Talts S, Betancourt M, Simpson D et al. Validating Bayesian Inference Algorithms with Simulation-Based Calibration. arXiv:1804.06788[stat] 2020.
• 23. Vangipuram R, Gunupudi R K, Puligadda V K, Vinjamuri J. A machine learning approach for imputation and anomaly detection in IoT environment. Expert Systems 2020, https://doi.org/10.1111/exsy.12556.
• 24. Vehtari A, Gelman A, Gabry J. Practical Bayesian model evaluation using leave-one-out cross-validation and WAIC. Statistics and Computing 2017; 27(5): 1413–1432, https://doi.org/10.1007/s11222-016-9696-4.
• 25. Wang J, Pambudi S, Wang W, Song M. Resilience of IoT Systems Against Edge-Induced Cascade-of-Failures: A Networking Perspective. IEEE Internet of Things Journal 2019; 6(4): 6952–6963, https://doi.org/10.1109/JIOT.2019.2913140.
• 26. Wang W, Rothschild D, Goel S, Gelman A. Forecasting elections with non-representative polls. International Journal of Forecasting 2015; 31(3): 980–991, https://doi.org/10.1016/j.ijforecast.2014.06.001.
• 27. Xing L. Cascading Failures in Internet of Things: Review and Perspectives on Reliability and Resilience. IEEE Internet of Things Journal 2021; 8(1): 44–64, https://doi.org/10.1109/JIOT.2020.3018687.

Uwagi

Opracowanie rekordu ze środków MEiN, umowa nr SONP/SP/546092/2022 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2022-2023).