Search

Intrusion and attacks have consistently challenged the Industrial Internet of Things (IIoT). Although artificial intelligence (AI) rapidly develops in attack detection and mitigation, building convincing trust is difficult due to its black-box nature. Its unexplained outcome inhibits informed and adequate decision-making of the experts and stakeholders. Explainable AI (XAI) has emerged to help with this problem. However, the ease of comprehensibility of XAI interpretation remains an issue due to the complexity and reliance on statistical theories. This study integrates agnostic post-hoc LIME and SHAP explainability approaches on intrusion detection systems built using representative AI models to explain the model's decisions and provide more insights into interpretability. The decision and confidence impact ratios assessed the significance of features and model dependencies, enhancing cybersecurity experts' trust and informed decisions. The experimental findings highlight the importance of these explainability techniques for understanding and mitigating IIoT intrusions with recourse to significant data features and model decisions.

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 rapid integration of the Internet of Artificial Intelligence and Internet of Things (AI-IoT) technologies has given rise to a pivotal element of the upcoming digital era, the Metaverse. This confluence has significantly impacted virtual learning platforms by introducing enhanced, immersive, and interactive environments for learners, educators, and institutions. However, the growing reliance on Metaverse necessitates robust cybersecurity measures to detect and mitigate cyber threats and ensure the safety of users. This paper proposes an explainable deep neural network (DNN) designed to identify and address network intrusion attacks within Metaverse learning environments. By leveraging the latest cybersecurity IoT datasets and employing an effective feature selection method, this study provides a visually interpretable, trustworthy, and quantitative explanation of the network intrusion detection system (NIDS) model using Shapley Additive exPlanations (SHAP) and local interpretable model-agnostic explanation (LIME) explainability methods. The adopted explainable DNN, capable of processing network traffic features from interconnected Metaverse devices and IoT sensors, can facilitate accurate and comprehensible remediation of anomalous from benign activities within Metaverse. The NIDS model yields a high performing accuracy of 99.9% for establishing a more secure and trustworthy metaverse learning environment.

In the smart grid, it is critical to collect dynamic and time-dependent information on energy demand and consumption and compare it to current supply conditions. The decentral smart grid control (DSGC) system manages frequency, a Smart grid element. It connects energy costs to grid frequency, allowing access to both consumers and producers. This work proposes a pruning of the convolution layers and neurons of 1-dimensional time-aware convolutional neural network (1D CNN) analysis of grid frequency stability to determine efficient energy costs. The proposed solution evaluated augmented grid stability datasets in addition to two other publicly available datasets to ascertain the approach’s feasibility in various scenarios; the simulation demonstrated a minimal train and prediction time of 124.37 s and 17.67 s efficiency over compared models, with prediction accuracy of 99.79% and 0.01 MFLOPs. Matthew’s correlation coefficient was applied to evaluate further the performance of the proposed 1D CNN to ascertain its applicability in various scenarios.

This study presents a fuzzy decision-making trial and evaluation laboratory (DEMATEL) analysis of the internet challenges of the internet of things (IoT) implementation of construction projects in Nigeria. The identification of the IoT challenges was carried out through a thorough literature search and discussions with 27 built environmental experts. In addition, DEMATEL, an expert judgement-based tool, was used to pick, design, and evaluate a structural model consisting of a causal relationship between defined IoT challenges. Subsequently, the fuzzy DEMATEL was deployed with a view to constructing a structural relationship between the various challenging factors by visualising the dynamic associations between them. Based on the findings of the literature survey and expert evaluation, 18 obstacles to the implementation of IoT in construction projects were classified into cause and effect classes based on their relative parameters of impact. The results suggest that 8 challenges were categorised into the cause group, while 10 were listed into the impact group. The results of this study will enable construction companies, construction industry experts, project managers in Nigeria to enhance their search to design and execute an effective and productive IoT application for their construction projects.

This paper presents a test bed demonstration of NeuroEdge computing for face recognition using a novel neuromorphic chip-NM500. First, a general description and important specifications of the NM500 are presented. Second, a face recognition test-bed case study is used to demonstrate the efficacy and efficiency of the chip. Neuromorphic technology offers scalability and consistent recognition time, which is required by real-time networked systems, and presents a considerable advantage for real-time computations, making them virtually independent of the dataset size. In this study, intelligent edge computing technology was introduced using NeuroEdge. The performance was verified using a face recognition test. The results demonstrated that using neuromorphic technology, such as the NM500 chip, saves the time needed for training systems and does not impose the burden of requiring many datasets for effective training.

In this paper, end devices are considered here as agent, which makes its decisions on whether the network will offload the computation tasks to the edge devices or not. To tackle the resource allocation and task offloading, paper formulated the computation resource allocation problems as a sum cost delay of this framework. An optimal binary computational offloading decision is proposed and then reinforcement learning is introduced to solve the problem. Simulation results demonstrate the effectiveness of this reinforcement learning based scheme to minimize the offloading cost derived as computation cost and delay cost in industrial internet of things scenarios.

The industrial internet of things (IIoT) and supervisory control and data acquisition (SCADA) have experienced ubiquitous growth recently. This growth comes with the challenge of an increased number of unusual attacks constituting threats. The existence and effect of intruders and their innovative attack techniques are rising. Although the existing intrusion detection systems (IDS) safeguard the networks, they have been computationally expensive. In real-time domains, available methods lag, necessitating additional research into effective feature extraction schemes with time exigency. An IDS with a fused feature selection (FS) approach for detecting and classifying attacks in a real-time SCADA network is imperative. It is to enable the resolution of computationally complex vulnerability detection schemes. The proposed technique is in three (3) phases: (a) data preparation which involves data cleansing and normalization, and (b) a fused feature selection approach built to obtain an optimal subset of features using Chi-square. (c) deployment of the modified decision tree (MDT) for anomaly detection and classification. Lastly, the reliability of the proposed model was validated, demonstrating suitability in precisely detecting abnormalities while minimizing computational time. This improvement enables adaptability for the IDS deployment scheme in a real-time situation, which could be in the control center. The validation results reveal that when the proposed chi-square-based (fused) feature extraction is employed, it performs optimally to other FS techniques and ML classifiers, compared across four (4) publicly available datasets. Cohen’s kappa coefficient (CKC) further validates the proposed model’s reliability. Further demonstrating the experimental results with recourse to false positive rates (FPR), the Mathews correlation coefficient (MCC) was employed. It also shows the resilience of the proposed model performance on an imbalanced dataset validating its suitability in real scenarios.

Nowadays, research works into the dynamic and static human activities on Smart spaces abounds. Artificial Intelligence (AI) and low cost non-privacy invasive ambient sensors have made this ubiquitous. This review presents a state-of-the-art analysis, performance evaluation, and future research direction. One of the aims of activity recognition (especially that of humans) systems using thermal sensors and AI is the safety of persons in Smart spaces. In a Smart home, human activity detection systems are put in place to ensure the safety of persons in such an environment. This system should have the ability to monitor issues like fall detection, a common home-related accident. In this work, a review of trends in thermal sensor deployment, an appraisal of the popular datasets, AI algorithms, testbeds, and critical challenges of the recent works was provided to direct the research focus. In addition, a summary of AI models and their performance under various sensor resolutions was presented.

Detection of nodes disseminating false data is a prerequisite for effective deployment of Internet of Vehicles (IoV) services. This work proposed a novel hyper-tuned ensemble Random Forest (Ens. RF) algorithm to detect false basic safety messages in IoV.  Performance evaluation was done using the Vehicular Reference Misbehavior (VeReMi) dataset comprising data-centric misbehavior evaluation for vehicular networks. For validation, a comparative analysis of the performance of the proposed “Ens. RF” model, five machine learning algorithms implemented in this work, and state-of-the-art ML models from related literature was presented. The performance metrics considered are time efficiency and validation accuracy for overall misbehavior classification. Also, the results confirmed the irrelevance of data balancing in real-life scenarios. Finally, we assess the performance of our proposed system for detecting each falsification scenario using precision and recall. The result shows that the proposed algorithm outperformed others with a validation accuracy of 99.60%and a negligible 604 misclassifications out of 153730 points.