Variational restricted Boltzmann machines to automated anomaly detection

Demertzis, Konstantinos; Iliadis, Lazaros; Pimenidis, Elias; Kikiras, Panagiotis

Abstract

Data-driven methods are implemented using particularly complex scenarios that reflect in-depth perennial knowledge and research. Hence, the available intelligent algorithms are completely dependent on the quality of the available data. This is not possible for real-time applications, due to the nature of the data and the computational cost that is required. This work introduces an Automatic Differentiation Variational Inference (ADVI) Restricted Boltzmann Machine (RBM) to perform real-time anomaly detection of industrial infrastructure. Using the ADVI methodology, local variables are automatically transformed into real coordinate space. This is an innovative algorithm that optimizes its parameters with mathematical methods by choosing an approach that is a function of the transformed variables. The ADVI RBM approach proposed herein identifies anomalies without the need for prior training and without the need to find a detailed solution, thus making the whole task computationally feasible.

• Journal Article Type: Article
• Acceptance Date: Feb 5, 2022
• Online Publication Date: Mar 1, 2022
• Publication Date: 2022-09
• Deposit Date: Mar 16, 2022
• Publicly Available Date: Mar 2, 2023
• Journal: Neural Computing and Applications
• Print ISSN: 0941-0643
• Electronic ISSN: 1433-3058
• Publisher: Springer (part of Springer Nature)
• Peer Reviewed: Peer Reviewed
• Volume: 34
• Pages: 15207–15220
• DOI: https://doi.org/10.1007/s00521-022-07060-4
• Keywords: Automatic differentiation variational inference; Restricted Boltzmann machines; Condition monitoring; Anomalies detection; Predictive maintenance; Industry 40
• Public URL: https://uwe-repository.worktribe.com/output/9087749