The effect of probability on risk perception and risk preference in decision making

Industrial IoT (IIoT) in Industry 4.0 integrates everything at the level of information technology with the level of technology of operation and aims to improve Business to Business (B2B) services (from production to public services). It includes Machine to Machine (M2M) interaction either for process control (e.g., factory processes, fleet tracking) or as part of self-organizing cyber-physical distributed control systems without human intervention. A critical factor in completing the abovementioned actions is the development of intelligent software systems in the context of automatic control of the business environment, with the ability to analyze in real-time the existing equipment through the available interfaces (hardware-in-the-loop). In this spirit, this paper presents an advanced intelligent approach to real-time monitoring of the operation of industrial equipment. A hybrid novel methodology that combines memory neural networks is used, and Bayesian methods that examine a variety of characteristic quantities of vibration signals that are exported in the field of time, with the aim of real-time detection of abnormalities in active IIoT equipment are also used.

…”

Section: Proposed Methodologymentioning

confidence: 99%

Online Anomaly Detection of Industrial IoT Based on Hybrid Machine Learning Architecture

Guo

Shen

2022

“…The danger of financial loss, interruption, or harm to an organization's reputation because of a breakdown of its information technology systems is known as cyber risk [ 8 , 11 ]. A deliberate and unauthorized security breach to acquire access to information systems for espionage, extortion, or humiliation might be an example of such a danger.…”

Section: Related Literaturementioning

confidence: 99%

“…Combining the selected actions of the users and the reaction of the system in the form of QoE, we calculate the probability of rewarding. This probability is the penetration of the R x composition and is expressed by the relation [ 11 , 37 , 38 ]

…”

Section: Modelingmentioning

confidence: 99%

Cyber Risk Recommendation System for Digital Education Management Platforms

Yin¹,

Chen²

2022

Covid-19 pandemic has ushered in a new school and academic year for students in a distance learning regime. This new daily routine was unprecedented and undoubtedly unusual, especially for the younger ones. At this point and at these ages, the risk of cyber fraud is even greater. The transition from the physical environment to the Internet took place quickly without the appropriate time to control potential risks and the proper information and training of teachers and students. Some common threats that need to be addressed to protect learners and their data when using e-learning methods are malicious remote access, malware, phishing, cyber fraud, etc. Considering the above situation, this work presents an innovative cyber risk recommendation system for digital education management platforms. The system in question is a distributed two-stage algorithm based on game theory and machine learning, which is trained by the constant change in the choice of recommendations by users to maximize security. We examine the algorithm’s ability to simulate a user system in which everyone independently selects a user recommendation, assesses the environment and the implications of this choice, and then concludes whether it will continue to have that recommendation fixed. The methodology with which we have represented the digital e-learning system has been done with an approach that directly corresponds with their general view as a cyber-physical-social system. We consider the digital school as an environment that brings limitations, leading us to a pretty demanding personalization problem. Users coexist in this environment, in which everyone acts voluntarily but influences and is influenced by the surrounding environment. Our results lead us to conclude that this algorithm responds in a fully effective, flexible, and efficient way to the needs of protection and risk assessment of e-learning education systems.

“…For a simulated sample of 500 observations and actual values p =0.7 and ( μ 1, μ 2) = (0, 2.5), the logarithm of probability has two peaks. Applying the algorithm to this model, we have that the total probability is [ 20 , 49 , 50 ]

where its logarithm is

…”

Section: Experiments and Resultsmentioning

confidence: 99%

Leakage Prediction in Machine Learning Models When Using Data from Sports Wearable Sensors

Qi-zheng

2022

One of the major problems in machine learning is data leakage, which can be directly related to adversarial type attacks, raising serious concerns about the validity and reliability of artificial intelligence. Data leakage occurs when the independent variables used to teach the machine learning algorithm include either the dependent variable itself or a variable that contains clear information that the model is trying to predict. This data leakage results in unreliable and poor predictive results after the development and use of the model. It prevents the model from generalizing, which is required in a machine learning problem and thus causes false assumptions about its performance. To have a solid and generalized forecasting model, which will be able to produce remarkable forecasting results, we must pay great attention to detecting and preventing data leakage. This study presents an innovative system of leakage prediction in machine learning models, which is based on Bayesian inference to produce a thorough approach to calculating the reverse probability of unseen variables in order to make statistical conclusions about the relevant correlated variables and to calculate accordingly a lower limit on the marginal likelihood of the observed variables being derived from some coupling method. The main notion is that a higher marginal probability for a set of variables suggests a better fit of the data and thus a greater likelihood of a data leak in the model. The methodology is evaluated in a specialized dataset derived from sports wearable sensors.