Anomaly detection in Aviation CPS is critical to ensuring safety and reliability. This systematic literature review explores the landscape of machine learning techniques used for anomaly detection in Aviation CPS, analyzing studies published between 2014 and 2024. The review identifies a strong preference for unsupervised learning methods, driven by the challenges of acquiring labeled data in aviation contexts. Additionally, it highlights the emerging trend of hybrid models that combine supervised and unsupervised techniques, offering improved detection accuracy and robustness. However, the review also reveals significant obstacles, such as the limited availability of publicly accessible datasets, which hampers research progress and the ability to benchmark models. Moreover, while accuracy is the most commonly reported performance metric, the need for a broader evaluation framework that includes precision, recall, and other metrics is emphasized. The findings suggest several directions for future research, including developing standardized datasets, optimizing hybrid models, and integrating explainable AI (XAI) to enhance model interpretability. This review contributes to the field by synthesizing current knowledge and providing insights that could guide the development of more effective and reliable anomaly detection systems for Aviation CPS.

The integration of wireless antenna sensors for cyber-physical systems has become increasingly prevalent in various biosimilar applications due to the escalating need for monitoring techniques that are efficient, accurate, and reliable. The primary objective of this comprehensive investigation is to offer a scholarly examination of the present advancements, challenges, and potentialities in the realm of wireless antenna sensor technology for monitoring biosimilars. Specifically, the focus will be on the current state of the art in wireless antenna sensor design, manufacturing, and implementation along with the discussion of cyber security trends. The advantages of wireless antenna sensors, including increased sensitivity, real-time data gathering, and remote monitoring, will next be discussed in relation to their use in a variety of biosimilar applications. Furthermore, we will explore the challenges of deploying wireless antenna sensors for biosimilar monitoring, such as power consumption, signal integrity, and biocompatibility concerns. To wrap things off, there will be a discussion about where this subject is headed and why collaborative work is essential to advancing wireless antenna sensor technology and its applications in biosimilar monitoring. Providing an in-depth overview of the present landscape and potential developments, this article aims to be an asset for academics and professionals in the fields of antenna sensors, biosimilar development, wireless communication technologies, and cyber physical systems.

The main challenges in smart home systems and cyber-physical systems come from not having enough data and unclear interpretation; thus, there is still a lot to be done in this field. In this work, we propose a practical approach called Discrete Human Activity Recognition (DiscHAR) based on prior research to enhance Human Activity Recognition (HAR). Our goal is to generate diverse data to build better models for activity classification. To tackle overfitting, which often occurs with small datasets, we generate data and convert them into discrete forms, improving classification accuracy. Our methodology includes advanced techniques like the R-Frame method for sampling and the Mixed-up approach for data generation. We apply K-means vector quantization to categorize the data, and through the elbow method, we determine the optimal number of clusters. The discrete sequences are converted into one-hot encoded vectors and fed into a CNN model to ensure precise recognition of human activities. Evaluations on the OPP79, PAMAP2, and WISDM datasets show that our approach outperforms existing models, achieving 89% accuracy for OPP79, 93.24% for PAMAP2, and 100% for WISDM. These results demonstrate the model’s effectiveness in identifying complex activities captured by wearable devices. Our work combines theory and practice to address ongoing challenges in this field, aiming to improve the reliability and performance of activity recognition systems in dynamic environments.

WiFi-enabled Power Line Communications (PLC) range extenders can extend coverage in homes and enterprises. However, a dense deployment of a large number of PLC extenders in enterprise settings can cause an inefficient sharing of the PLC capacity, where many extenders contend for a share of access to the backhaul network comprising of the electrical wiring (power lines), thereby drastically impacting any gains from using these extenders on the wireless part of the network. In this paper, we address this issue by developing a framework, Priza, for clustering the WiFi-PLC extenders to intelligently form a DAS (distributed antenna system) to mitigate the inefficiency of sharing the PLC backhaul. By appropriately managing clustering and reuse, Priza improves the PLC backhaul sharing, while at the same time, harnessing the power pooling and diversity gains from DAS on the wireless part of the network, to boost user throughputs. We evaluate Priza via real testbed experiments and high-fidelity simulations and demonstrate that it can increase the aggregate throughput by up to 131.5% over the non-DAS reuse baseline, 74% over the best DAS baseline that constructs equally-sized DAS cells based on extender proximity, and 331.3% over a greedy DAS baseline that creates as large DAS cells as possible.

The rapidly changing digitalization of the energy sector, fueled by smart grids, the Industrial Internet of Things (IIoT), Advanced Metering Infrastructure (AMI), and Supervisory Control and Data Acquisition (SCADA) systems, is leading to a great and symmetrical improvement in workflow and the ability to have real-time insights. In parallel, the massive adoption of low-power and resource-constrained devices that are still connected makes cybersecurity threats more serious and thus necessitates lightweight authentication mechanisms to have safe, secure, and symmetrical communicative. Selecting the right authentication method involves a challenging multi-criteria decision-making (MCDM) process where various factors such as security aspects, computation power needed, communication capabilities that can be delivered, and deployment-related aspects are considered together, along with inherent uncertainties in expert evaluations. This paper proposes a Hesitant Fuzzy (HF)-based hybrid method that combines the Analytic Network Process (ANP) with the Technique for Order Preference by Similarity to the Ideal Solution (TOPSIS) for the evaluation of lightweight authentication systems in the energy domain. This symmetrical HF-ANP is used for the modeling of the interrelations between major evaluation criteria such as security strength, computation efficiency, communication effectiveness, and deployment scalability. It can also handle the experts’ hesitant and uncertain preferences. The calculated weighting factors are then input to the HF-TOPSIS method to rank five different lightweight authentication protocols: Hash-Based Authentication, Elliptic Curve Cryptography (ECC)-Based Lightweight Authentication, Physical Unclonable Function (PUF)-Based Authentication, Blockchain-Assisted Lightweight Authentication, and Certificate-less Lightweight Authentication. Furthermore, sensitivity analysis and comparison analysis are conducted to verify the strength, symmetry, consistency, and reliability of the proposed framework. Our results indicate that the integrated HF-ANP and TOPSIS procedure provides a symmetrical, comprehensive, and systematic decision-making tool to appraise lightweight authentication techniques amid uncertainties. The proposed method will be very beneficial for different types of energy industrial players, system designers, and security experts to pick secure, efficient, and scalable methods of authentication to protect the critical energy facilities against the new generation of cyber threats.