The Internet of Things (IoT) and cyber–physical systems (CPS) are driving digital transformation and automation. An essential component of CPS is digital twin (DT) technology, which enables real-time synchronization between physical assets and their virtual counterparts. Battery management systems (BMS) in electric vehicles (EVs) face challenges in handling large volumes of sensor data, often leading to reduced accuracy in battery-state estimation. To address these challenges, DTs have been explored to aid real-time diagnosis and monitoring. One critical step toward the success of DTs is to have practical reference architectures. This paper presents proposes a novel six-layer DT architecture tailored for BMS, extending existing CPS/DT-BMS models by integrating high-fidelity electrochemical modeling, robust nonlinear state estimation, and interactive 3D visualization in a Metaverse environment. The architecture is designed with scalability in mind, supporting deployment on lightweight embedded platforms or via cloud-hosted rendering for resource-limited devices. We validate the approach using MATLAB to develop a thermally coupled SPMe-based DT of a lithium-ion NMC battery, synchronized with a virtual battery model in Unreal Engine for immersive visualization. Experimental results demonstrate accurate state-of-charge estimation (RMSE 0.23%) and low-latency real-time monitoring, highlighting the framework’s potential for deployment in large-scale EV BMS applications.

As the Metaverse progresses, its security measures must evolve to safeguard users from cyberattacks. To this end, Artificial Intelligence (AI)-powered Network Intrusion Detection Systems (NIDSs) have been implemented at the network layer to detect and respond to threats in real-time. Our survey -MetaWatch provides a comprehensive overview and analysis of relevant literature, focusing on studies that have explored NIDSs in the Metaverse. Unlike other surveys that have addressed Metaverse security issues more broadly, MetaWatch specifically provides a taxonomy of detection paradigms and defense mechanisms within Metaverse NIDS from 2021 to 2024. Additionally, MetaWatch identifies and discusses the key challenges and problems that impact the development of trustworthy, explainable, scalable, and robust Metaverse NIDS. Overall, the survey provides readers with a concise and informative summary of NIDS issues in the Metaverse and highlights open security problems worth exploring.

The accelerated industrial transformation has witnessed the supervisory control and data acquisition (SCADA) transit from monolithic to the Internet of Things (IoT-SCADA). The development also transformed conventional specialized serial-based to transmission control protocol/internet protocol reliant standard communication protocols, such as IEC-60870-5-104 (IEC-104), thereby increasing vulnerability to attacks and intrusions. Maintaining the reliability and availability of IoT-SCADA demands versatile and robust monitoring of network traffic. This study proposes a monitoring technique to detect and characterize the IEC-104 IoT-SCADA network traffic. The proposed trees bootstrap aggregation monitoring technique of GridSearchCV() hyperparameter tuning of 11 n-estimator, 20 max-depth, and 5-k cross-validation achieved early detection and characterization. Experimental results demonstrate its sensitivity and precision in detecting and classifying various network traffic and application types at a minimal execution time while reducing false alarm rates, which is vital for mitigating intrusions in heterogeneous IoT-SCADA networks.

The pervasiveness in the industrial internet of things (IIoT) due to the application of supervisory control and data acquisition (SCADA) has led to the growth of heterogeneous sensor data, thereby increasing the risk of intrusions and attacks. The existence and effect of intruders and their innovative attack techniques are on the rise. Existing intrusion detection systems (IDS) tend to be computationally expensive with this form of data due to the presence of noise. In real-time domains, available methods lag, necessitating additional research into effective feature extraction schemes, which is fundamental in machine learning (ML) for time exigency. This study, in a comparative analysis of some feature selection techniques (FS), proposes a combination of an efficient ML classifier and an agnostic feature selection (FS) scheme for attack detection and classification in a real-time SCADA network. The flexibility and interoperability of the proposed approach resolve the computational complexity of vulnerability detection schemes while reducing false alarm rates (FAR) and overall model execution time. With the view of an online preprocessing, the proposed technique is phased thus: (i) data preparatory consisting of data cleansing and normalization followed by (ii) the combination of a pre-pruned decision tree (DT) algorithm and an agnostic Chi-square FS approach built to obtain an optimal subset of data features for efficient IDS. (iii) Evaluation of proposed agnostic DT-CH and other FS candidates for anomaly detection.

The dynamic nature of the vehicular space exposes it to distributed malicious attacks irrespective of the integration of enabling technologies. The software-defined network (SDN) represents one of these enabling technologies, providing an integrated improvement over the traditional vehicular ad-hoc network (VANET). Due to the centralized characteristics of SDN, they are vulnerable to attacks that may result in life-threatening situations. Securing SDN-based VANETs is vital and requires incorporating artificial intelligence (AI) techniques. Hence, this work proposed an intrusion detection model (IDM) to identify Distributed Denial-of-Service (DDoS) attacks in the vehicular space. The proposed solution employs the radial basis function (RBF) kernel of the support vector machine (SVM) classifier and an exhaustive parameter search technique called grid search cross-validation (GSCV). In this framework, the proposed architecture can be deployed on the onboard units (OBUs) of each vehicle, which receive the vehicular data and run intrusion detection tasks to classify a message sequence as a DDoS attack or benign. The performance of the proposed algorithm compared to other ML algorithms using key performance metrics. The proposed framework is validated through experimental simulations to demonstrate its effectiveness in detecting DDoS intrusion. Using the GridSearchCV, optimal values of the RBF-SVM kernel parameters “C” and “gamma”$(\gamma)$of 100 and 0.1, respectively, gave the optimal performance. The proposed scheme showed an overall accuracy of 99.33%, a detection rate of 99.22%, and an average squared error of 0.007, outperforming existing benchmarks.

The goal of this study is to offer a novel fog data prediction and recovery (FDPR) algorithm that uses deep learning (DL) to forecast and recover missing sensor data in an Internet of Things (IoT) network. Because of the fog layer’s unique qualities compared to other IoT environment layers, the FDPR algorithm is employed in this layer. The most recent studies generally concentrate on data recovery or prediction, with few assessment metrics. In this work, an algorithm that can handle both data prediction and recovery is provided. With the proposed FDPR approach, data prediction and recovery are dealt with by an effective DL network, namely, a deep concatenated multilayer perceptron (DC-MLP). The algorithm consists of a prediction function that forecasts future sensor data for a specified round of data transmission and a recovery function that recover one or two missing data points. The evaluation of the proposed algorithm is performed with simulation and experimental works. Initially, a data set is collected, preprocessed, and fed to various DL models using$K$-fold cross-validation. These DL models are then converted and embedded into a fog layer in the experimental work with nine edge devices. In both simulation and experimental evaluation, the FDPR with DC-MLP can predict future data and recover missing data with an average accuracy of 99.89% while slightly increasing network delay by 2.5 ms compared to traditional IoT. Aside from a slightly increased delay, a 121% improvement in IoT device lifetime is achieved using the FDPR algorithm due to data transmission reduction.

Falsification detection is a critical advance in ensuring that real-time information about vehicles and their movement states is certified on the Internet of Vehicles (IoV). Thus, detecting nodes that are propagating inaccurate information is a requirement for the successful deployment of IoV services although only a few research studies have been carried out on Basic Safety Message (BSM) falsification. As such, this paper proposes a Randomized Search Optimization Ensemble-based Falsification Detection Scheme (RSO-FDS). The RSO technique was used to construct the proposed Ensemble-based Random Forest (RF) model. The evaluation was performed on three different datasets developed to evaluate falsification in IoV. In addition, the six most popular supervised learning (SL) algorithms were investigated to evaluate the capability of the proposed RSO-FDS, which had the best performance across all datasets. The performance metrics considered are computational efficiency in terms of prediction time, validation accuracy for overall attack classification, precision, recall, and F1 scores. For validation, the performance of the proposed RSO-FDS was further compared with results from recent works. Furthermore, the irrelevance of data balancing was illustrated for real-life IoV scenarios. The result shows that the proposed model outperformed state-of-the-art algorithms implemented in this work and related works.

The constant development and deployment of the supervisory control and data acquisition (SCADA) in the industrial internet of things (IIoT) have enabled vast communication leading to the generation of large volumes of sensor data. This phenomenon has increased SCADA’s susceptibility to vulnerability and attacks which calls for attack detection mechanisms. Existing systems only aim at detection accuracy without considering the effect of false alarm rates in large sensor data. To resolve this issue, we propose a Rational Quadratic Gaussian Process Regression (RQGPR) for the effective reduction of false alarm rate and improved prediction precision. In this algorithm, a Gaussian process regression model is trained with recourse to kernel functions to precisely predict attacks and reduce false alarms. The RQGPR outperforms all other kernels in the reduction of false alarm rates. Through simulations, we show that the proposed model reduces the false alarm rate up to 71.73% higher than other kernels. This result was validated by evaluating the CIRA-CIC-DoHBrw-2020 datasets, which also had a reduction rate of 67.61%. In addition, it also showed superior performance when compared with other state-of-the-art models.

The metaverse is a virtual world that is based on numerous technologies. One of such technologies is the wireless communication system. Specifically, 5G wireless communication will have a role to play in the development of the metaverse. Since the metaverse has features that require certain service requirements, it is necessary to analyze the specific benefits that 5G has to offer. The aim of this paper is to discuss the features of the metaverse, the service offerings of 5G standards of communication, and how 5G can help make the metaverse a reality.

Ensuring secured and reliable dissemination of information for a mission-critical system such as the Internet of Vehicle (IoV) in real-time is of utmost importance. In this work, a False Location Detection System (FLDS) based on an optimized Ensemble Random Forest (Ens.RF) was proposed. The performance of the Ens.RF was compared with four other Machine Learning (ML) algorithms, using the Veremi dataset where five (5) different location falsification categories and one benign category were modeled. To validate the idea in this work, a performance comparison with recent work was presented. The result shows that the proposed Ens.RF outperformed other algorithms modeled in this work as well as related works with an accuracy of 99.92%

With the expanding diversity of Internet of Things (IoT), more IoT networks are now being attacked easily by aggressors without being easily distinguished as they adapt network traffic characteristics similar to the victim's network. The consequences are the opportunities to gain control of the secure communication antagonistically, influencing internal information and prompting harms to the physical components of the IoT framework without being distinguished quickly. Anomaly-based Identification (AID) has enabled the possibility of solving this problem by helping to detect novel attacks by skimming and authenticating the IoT network designs, with higher accuracy using machine learning (ML) classification. In this work, a stacked ensemble (SE) machine learning classification approach is utilized to investigate IoT network traffic characteristics for improving novel detection of malware and noxious exercise in gadgets. The SE classifier was composed of base and meta-classifiers. The base level consisted of four classifiers; decision tree (DT), gaussian support vector machine (GSVM), ensemble DT, and naive bayes (NB). This classifiers are applied to IoT Network Intrusion Dataset from HCRLab, Korea University and sent trained data to meta classifier which was further employed to detect binary classification on test data. The experimental results shows that SE classifier achieved 99.8% accuracy with lower loss value 0.0020861 and 0.9994 precision. This application can be promising insights into the AID-based security of IoT for effective industry and/or smart factory management.

Industrial image processing and computer vision play significant role in factory automation since industries now employ human-robot interaction for the monitoring of products in areas considered risky and dangerous for humans. The challenge however, is to ensure reliability in image processing such that image sizes and image similarity index are expected to be perfect representation of actual objects. This paper investigated the statistical relationship between the image ratio size and similarity index after compression. Using correlation analysis, a statistical relationship was established between the image size ratio and similarity index of selected images under review. It was observed that an inverse and high correlation existed between the image similarity index and image size ratio of compressed images. The result of the validation shows that the proposed regression model has predictability or good fit of 95%.