Bayesian Model for Evaluating Real-World Adaptation Progress of a Cyber-Physical System

Cyber-physical systems, also known as CPS, have come to stay. There is no doubt, CPS would one day outnumber humans in industries. How do we evaluate the adaptation progress of these systems considering changing environmental conditions? A failed implementation of a CPS can result to a loss. Since CPSs are designed to automate industrial activities, which are centred on the use of several technologies, collaboration with humans may sometimes be inevitable. CPSs are needed to automate several processes and thus help firms compete favourably within an industry. This chapter focuses on the adaptation of CPS in diverse work environment. Considering the ecosystem of the CPS, the authors present a Bayesian model evaluating the progress of adaptation of a CPS given some known conditions.

Artificial Intelligence-Based Solutions for Cyber Security Problems

Due to its nature, cyber security is one of the fields that can benefit most from the techniques of artificial intelligence (AI). Under normal circumstances, it is difficult to write software to defend against cyber-attacks that are constantly developing and strengthening in network systems. By applying artificial intelligence techniques, software that can detect attacks and take precautions can be developed. In cases where traditional security systems are inadequate and slow, security applications developed with artificial intelligence techniques can provide better security against many complex cyber threats. Apart from being a good solution for cyber security problems, it also brings usage problems, legal risks, and concerns. This study focuses on how AI can help solve cyber security issues while discussing artificial intelligence threats and risks. This study also aims to present several AI-based techniques and to explain what these techniques can provide to solve problems in the field of cyber security.

Explainable Artificial Intelligence (xAI) Approaches and Deep Meta-Learning Models for Cyber-Physical Systems

Today, the effects of promising technologies such as explainable artificial intelligence (xAI) and meta-learning (ML) on the internet of things (IoT) and the cyber-physical systems (CPS), which are important components of Industry 4.0, are increasingly intensified. However, there are important shortcomings that current deep learning models are currently inadequate. These artificial neural network based models are black box models that generalize the data transmitted to it and learn from the data. Therefore, the relational link between input and output is not observable. For these reasons, it is necessary to make serious efforts on the explanability and interpretability of black box models. In the near future, the integration of explainable artificial intelligence and meta-learning approaches to cyber-physical systems will have effects on a high level of virtualization and simulation infrastructure, real-time supply chain, cyber factories with smart machines communicating over the internet, maximizing production efficiency, analysis of service quality and competition level.

Engineering AI Systems

Artificial intelligence (AI) and machine learning (ML) are increasingly broadly adopted in industry. However, based on well over a dozen case studies, we have learned that deploying industry-strength, production quality ML models in systems proves to be challenging. Companies experience challenges related to data quality, design methods and processes, performance of models as well as deployment and compliance. We learned that a new, structured engineering approach is required to construct and evolve systems that contain ML/DL components. In this chapter, the authors provide a conceptualization of the typical evolution patterns that companies experience when employing ML as well as an overview of the key problems experienced by the companies that they have studied. The main contribution of the chapter is a research agenda for AI engineering that provides an overview of the key engineering challenges surrounding ML solutions and an overview of open items that need to be addressed by the research community at large.

Multiplier for DSP Application in CPS System

A cyber-physical system over field-programmable gate array with optimized artificial intelligence algorithm is beneficial for society. Multiply and accumulate (MAC) unit is an integral part of a DSP processor. This chapter is focused on improving its performance parameters MAC based on column bypass multiplier. It highlights DSP's design for intelligent applications and the architectural setup of the broadly useful neuro-PC, based on the economically available DSP artificial intelligence engine (AI-engine). Adaptive hold logic in the multipliers section determines whether another clock cycle is required to finish multiplication. Adjustment in algorithm reduced the aging impact over cell result in the processor last longer and has increased its life cycle.

Machine Learning in Cyber-Physical Systems in Industry 4.0

Cyber-physical systems (CPS) have emerged with development of most great applications in the modern world due to their ability to integrate computation, networking, and physical process. CPS and ML applications are widely used in Industry 4.0, military, robotics, and physical security. Development of ML techniques in CPS is strongly linked according to the definition of CPS that states CPS is the mechanism of monitoring and controlling processes using computer-based algorithms. Optimizations adopted with ML in CPS include domain adaptation and fine tuning of current systems, boosting, introducing more safety and robustness by detection and reduction of vulnerabilities, and reducing computation time in time-critical systems. Generally, ML helps CPS to learn and adapt using intelligent models that are generated from training of large-scale data after processing and analysis.

Applying a Methodology in Data Transmission of Discrete Events From the Perspective of Cyber-Physical Systems Environments

Most of the decisions taken in and around the world are based on data and information. Therefore, the chapter aims to develop a method of data transmission based on discrete event concepts, being such methodology named CBEDE, and using the MATLAB software, where the memory consumption of the proposal was evaluated, presenting great potential to intermediate users and computer systems, within an environment and scenario with cyber-physical systems ensuring more speed, transmission fluency, in the same way as low memory consumption, resulting in reliability. With the differential of this research, the results show better computational performance related to memory utilization with respect to the compression of the information, showing an improvement reaching 95.86%.

IoT Applications in Smart Home Security

Robotization has changed into a fundamental piece of our lives. Everybody is completely subject to mechanization whether it is an extraordinary bundling or home robotization. So as to bring home automation into thought, everybody now needs a heterogeneous state security, and in our task on residential robotization, such high security highlights are completely on the best possible consumption. Piezoelectric sensors are compelling for sharpening appropriated wellbeing checking and structures. An intrusion detection system (IDS) is a structure that screens for suspicious movement and issues alarms when such advancement is found. Some obstruction divulgence structures are fit to take practice when poisonous improvement or peculiar action is perceived.

Malicious URL Detection Using Machine Learning

Recently, with the increase in Internet usage, cybersecurity has been a significant challenge for computer systems. Different malicious URLs emit different malicious software and try to capture user information. Signature-based approaches have often been used to detect such websites and detected malicious URLs have been attempted to restrict access by using various security components. This chapter proposes using host-based and lexical features of the associated URLs to better improve the performance of classifiers for detecting malicious web sites. Random forest models and gradient boosting classifier are applied to create a URL classifier using URL string attributes as features. The highest accuracy was achieved by random forest as 98.6%. The results show that being able to identify malicious websites based on URL alone and classify them as spam URLs without relying on page content will result in significant resource savings as well as safe browsing experience for the user.

A Survey on Network Intrusion Detection Using Deep Generative Networks for Cyber-Physical Systems

In the present computing world, network intrusion detection systems are playing a vital part in detecting malicious activities, and enormous attention has been given to deep learning from several years. During the past few years, cyber-physical systems (CPSs) have become ubiquitous in modern critical infrastructure and industrial applications. Safety is therefore a primary concern. Because of the success of deep learning (DL) in several domains, DL-based CPS security applications have been developed in the last few years. However, despite the wide range of efforts to use DL to ensure safety for CPSs. The major challenges in front of the research community are developing an efficient and reliable ID that is capable of handling a large amount of data, in analyzing the changing behavioral patterns of attacks in real-time. The work presented in this manuscript reviews the various deep learning generative methodologies and their performance in detecting anomalies in CPSs. The metrics accuracy, precision, recall, and F1-score are used to measure the performance.