Learning Algorithm Recommendation Framework for IS and CPS Security

Abstract

Artificial intelligence and machine learning have recently made outstanding contributions to the performance of information system and cyber--physical system security. There has been a plethora of research in this area, resulting in an outburst of publications over the past two years. Choosing the right algorithm to solve a complex security problem in a very precise industrial context is a challenging task. Therefore, in this paper, we propose a Learning Algorithm Recommendation Framework that, for a clearly defined situation, guides the selection of learning algorithm and scientific discipline (e.g. RNN, GAN, RL, CNN,...) which have sparked great interest to the scientific community and which therefore offers preponderant elements and benefits for further deployments. This framework has the advantage of having been generated from an extensive analysis of the literature, as illustrated by this paper for the recurrent neural networks and their variations.

Towards a Multidimensional Ontology Model for DIH-Based Organisations

“…This CPS extension claims that CPS are composed of a Cyber Process entity, which is a type of Process and of a Physical Resource entity, which is a type of Resource (Imeri et al, 2018). According to Bertoli et al (2021), the key characteristics of a CPS are the Sensors, the Actuators, and the HMI for the Physical part, and the Computing, The Software Communication and the Data storing and analytics for the Cyber part (Feltus, 2022), as represented in Figure 3 (extracted from Bertoli et al, 2021).…”

“…Accordingly, and as it is usual to do in the academic field, many authors have produced state-of-the-art advancements in this field. Some of these are strong and well documented, including: Kim et al (2017), which analysed CPS through two criteria: CPS's characteristics and architectures; Kumar et al (2020), which stresses how attacks on cyber-physical systems (CPS) continue to grow in frequency and, accordingly, identifies a set of relevant research opportunities; and Sun et al (2018), which specifically focuses on CPS security and service portfolio (Asplund et al, 2021) and describes future research directions to secure critical CPS (Blangenois et al, 2013, andFeltus et al, 2022).…”

Cyber-attacks in Cyber Physical Microgrid Systems : A comprehensive Review

“…To overcome this the models like Long-Short Term Memory (LSTM) and Gated Recurrent Unit (GRU) are introduced that contain the memory element and the network architecture also differs from the classical RNN [65]. Generative adversarial networks (GaN) and autoencoders are unsupervised techniques in deep learning, where the outputs are not specified.…”

Research on Water Quality Prediction of Mine Surroundings Based on Improved Machine Learning Algorithm

“…Technologies such as Recurrent Neural Networks (RNN), Gated Recurrent Units (GRU), Long Short-Term Memory Networks (LSTM), and Improved Particle Swarm Optimization (IPSO) provide robust data analytics and predictive capabilities (Feltus, 2022;Aslan et al, 2022). RNNs excel in handling time-series data and are widely used for modeling and predicting water quality uctuations (Wang et al, 2022).…”