Search Results (83)

The use of resource-constrained Low-Power and Lossy Networks (LLNs), where the IPv6 Routing Protocol for LLNs (RPL) is the de facto routing standard, has increased due to the Internet of Things’ (IoT) explosive growth. Because of the dynamic nature of IoT deployments and the lack of in-protocol security, RPL is still quite susceptible to routing-layer attacks like Blackhole, Lowered Rank, version number manipulation, and Flooding despite its lightweight architecture. Lightweight, data-driven intrusion detection methods are necessary since traditional cryptographic countermeasures are frequently unfeasible for LLNs. However, the lack of RPL-specific control-plane semantics in current cybersecurity datasets restricts the use of machine learning (ML) for practical anomaly identification. In order to close this gap, this work models both static and mobile networks under benign and adversarial settings by creating a novel, large-scale multiclass RPL attack dataset using Contiki-NG’s Cooja simulator. To record detailed packet-level and control-plane activity including DODAG Information Object (DIO), DODAG Information Solicitation (DIS), and Destination Advertisement Object (DAO) message statistics along with forwarding and dropping patterns and objective-function fluctuations, a protocol-aware feature extraction pipeline is developed. This dataset is used to evaluate fifteen classifiers, including Logistic Regression (LR), Support Vector Machine (SVM), Decision Tree (DT), k-Nearest Neighbors (KNN), Random Forest (RF), Extra Trees (ET), Gradient Boosting (GB), AdaBoost (AB), and XGBoost (XGB) and several ensemble strategies like soft/hard voting, stacking, and bagging, as part of a comprehensive ML-based detection system. Numerous tests show that ensemble approaches offer better generalization and prediction performance. With overfitting gaps less than 0.006 and low cross-validation variance, the Soft Voting Classifier obtains the greatest accuracy of 99.47%, closely followed by XGBoost with 99.45% and Random Forest with 99.44%. Full article

This review systematically examines research on indoor thermal comfort for older adults conducted in China since 2010. It highlights several existing research gaps, including the lack of a systematic understanding of environmental and individual influences, limitations of thermal comfort models, challenges in their optimization, and inadequate integration of intelligent technologies. Results indicate that environmental factors usually exert a greater impact on the elderly’s neutral temperature than individual factors. Thermal comfort models differ in predictive accuracy, data requirements, and applicability. The adaptive predicted mean vote (aPMV) model is better suited for group-level assessments. Machine learning (ML) models, featuring high flexibility and accuracy, are more appropriate for personalized predictions. In addition, physiological parameters could play a critical role in thermal assessments. When integrated with ML models, physiological parameters could further improve predictive accuracy. When integrated into artificial intelligence (AI) and Internet of Things (IoT) systems, forehead and back skin temperatures could act as early-warning indicators during heat exposure, while lower-limb temperatures are more indicative of thermal discomfort during cold exposure. Overall, this review summarizes current progress and limitations, offering a reference for the development of user-friendly modeling and intelligent temperature-control systems. Full article

The growing global demand for secure, transparent, and efficient electoral systems has highlighted the limitations of traditional voting methods, which remain susceptible to voter impersonation, ballot tampering, long queues, logistical challenges, and delayed result processing. To address these issues, this study presents the design and implementation of a Radio Frequency Identification (RFID)-based electronic voting framework that integrates robust voter authentication, encrypted vote processing, and decentralized real-time monitoring. The system is developed as a scalable, cost-effective solution suitable for both urban and resource-constrained environments, especially those with limited infrastructure or inconsistent internet connectivity. It employs RFID-enabled smart voter cards containing encrypted unique identifiers, with each voter authenticated via an RC522 reader that validates their UID against an encrypted whitelist stored locally. Upon successful verification, the voter selects a candidate via a digital interface, and the vote is encrypted using AES-128 before being stored either locally on an SD card or transmitted through GSM to a secure backend. To ensure operability in offline settings, the system supports batch synchronization, where encrypted votes and metadata are uploaded once connectivity is restored. A tamper-proof monitoring mechanism logs each session with device ID, timestamps, and cryptographic checksums to maintain integrity and prevent duplication or external manipulation. Simulated deployments under real-world constraints tested the system’s performance against common threats such as duplicate voting, tag cloning, and data interception. Results demonstrated reduced authentication time, improved voter throughput, and strong resistance to security breaches—validating the system’s resilience and practicality. This work offers a hybrid RFID-based voting framework that bridges the gap between technical feasibility and real-world deployment, contributing a secure, transparent, and credible model for modernizing democratic processes in diverse political and technological landscapes. Full article

The widespread integration of third-party components (TPCs) in Internet of Things (IoT) firmware significantly increases the risk of software vulnerabilities, especially in resource-constrained devices deployed in sensitive environments. Binary Code Similarity Detection (BCSD) techniques, particularly those based on deep neural networks, have emerged as powerful tools for identifying vulnerable functions without access to source code. However, individual models, such as Graph Neural Networks (GNNs), Convolutional Neural Networks (CNNs), and Transformer-based methods, often exhibit limitations due to their differing focus on structural, spatial, or semantic features. To address this, we propose VoteSim, a novel ensemble framework that integrates multiple BCSD models using an inverse average rank voting mechanism. VoteSim combines the strengths of individual models while reducing the impact of model-specific false positives, leading to more stable and accurate vulnerability detection. We evaluate VoteSim on a large-scale real-world IoT firmware dataset comprising over 800,000 binary functions and 10 high-risk CVEs. Experimental results show that VoteSim consistently outperforms state-of-the-art BCSD models in both Recall@10 and Mean Reciprocal Rank (MRR), achieving improvements of up to 14.7% in recall. Our findings highlight the importance of model diversity and rank-aware aggregation for robust binary-level vulnerability detection in heterogeneous IoT firmware. Full article

Federated learning is increasingly recognized as a viable solution for deploying distributed intelligence across resource-constrained platforms, including smartphones, wireless sensor networks, and smart home devices within the broader Internet of Things ecosystem. However, traditional federated learning approaches face serious challenges in resource-constrained settings due to high processing demands, substantial memory requirements, and high communication overhead, rendering them impractical for battery-powered IoT environments. These factors increase battery consumption and, consequently, decrease the operational longevity of the network. This study proposes a streamlined, single-shot federated learning approach that minimizes communication overhead, enhances energy efficiency, and thereby extends network lifetime. The proposed approach leverages the k-nearest neighbors (k-NN) algorithm for edge-level pattern recognition and utilizes majority voting at the server/base station to reach global pattern recognition consensus, thereby eliminating the need for data transmissions across multiple communication rounds to achieve classification accuracy. The results indicate that the proposed approach maintains competitive classification accuracy performance while significantly reducing the required number of communication rounds. Full article

Information is the primary driver of progress in today’s world, especially given the vast amounts of data available for extracting meaningful knowledge. The motivation for addressing the problem of forensic analysis—specifically the validity of decision making in multi-criteria contexts—stems from its limited coverage in the existing literature. Methodologically, machine learning and ensemble models represent key trends in this domain. Datasets used for such purposes can be either real or synthetic, with synthetic data becoming particularly valuable when real data is unavailable, in line with the growing use of publicly available Internet data. The integration of these two premises forms the central challenge addressed in this paper. The proposed solution is a three-layer ensemble model: the first layer employs multi-criteria decision-making methods; the second layer implements multiple machine learning algorithms through an optimized asymmetric procedure; and the third layer applies a voting mechanism for final decision making. The model is applied and evaluated through a case study analyzing the U.S. Army’s decision to replace the Colt 1911 pistol with the Beretta 92. The results demonstrate superior performance compared to state-of-the-art models, offering a promising approach to forensic decision analysis, especially in data-scarce environments. Full article

Electronic voting allows people to participate more easily in their country’s electoral events. Nevertheless, its adoption is still far from widespread. In this paper, we provide a detailed survey of the state of adoption worldwide and investigate which socio-economic factors may influence such an adoption. Its usage is wider in North and South America, while remaining considerably lower in Europe and Asia and practically absent in Africa. We distinguish between e-voting, which maintains the traditional polling station structure while adding technological components, and i-voting, which enables remote participation from any location using personal devices. Five factors (country’s surface and population, Gross Domestic Product, Internet Usage, and Democracy Index) are investigated to predict adoption, and an accuracy of over 79% is achieved through a machine learning random forest model. Larger, wealthier, and more democratic countries are typically associated with a larger adoption of internet voting. Full article

The emergence of the Internet of Vehicles (IoV) has revolutionized intelligent transportation and communication systems. However, IoV presents many complex and ever-changing security challenges and thus requires robust cybersecurity protocols. This paper comprehensively describes and evaluates ensemble learning approaches for multi-class intrusion detection systems in the IoV environment. The study evaluates several approaches, such as stacking, voting, boosting, and bagging. A comprehensive review of the literature spanning 2020 to 2025 reveals important trends and topics that require further investigation and the relative merits of different ensemble approaches. The NSL-KDD, CICIDS2017, and UNSW-NB15 datasets are widely used to evaluate the performance of Ensemble Learning-Based Intrusion Detection Systems (ELIDS). ELIDS evaluation is usually carried out using some popular performance metrics, including Precision, Accuracy, Recall, F1-score, and Area Under Receiver Operating Characteristic Curve (AUC-ROC), which were used to evaluate and measure the effectiveness of different ensemble learning methods. Given the increasing complexity and frequency of cyber threats in IoV environments, ensemble learning methods such as bagging, boosting, and stacking enhance adaptability and robustness. These methods aggregate multiple learners to improve detection rates, reduce false positives, and ensure more resilient intrusion detection models that can evolve alongside emerging attack patterns. Full article

The rise of the Internet of Medical Things (IoMT) has enhanced healthcare delivery but also exposed critical cybersecurity vulnerabilities. Detecting attacks in such environments demands accurate, interpretable, and cost-efficient models. This paper addresses the critical challenges in network security, particularly in IoMT, through advanced machine learning (ML) approaches. We propose a high-performance cybersecurity framework leveraging a carefully fine-tuned XGBoost classifier to detect malicious attacks with superior predictive accuracy while maintaining interpretability. Our comprehensive evaluation compares the proposed model with a well-regularized Logistic Regression baseline using key performance metrics. Additionally, we analyze the security-cost trade-off in designing ML systems for threat detection and employ SHAP (SHapley Additive exPlanations) to identify key features driving predictions. We further introduce a late fusion approach based on max voting that effectively combines the strengths of both models. Results demonstrate that while XGBoost achieves higher accuracy (0.97) and recall (1.00) compared to Logistic Regression, our late fusion model provides a more balanced performance with improved precision (0.98) and reduced false negatives, making it particularly suitable for security-sensitive applications. This work contributes to developing robust, interpretable, and efficient ML solutions for addressing evolving cybersecurity challenges in networked environments. Full article

Current methods for identifying unknown Internet of Things (IoT) devices are relatively limited. Most approaches can identify only one type of the unknown IoT devices at a time and with a relatively low accuracy. Herein, we propose a method for unknown IoT device identification (UDI) based on cost-sensitive contrastive loss (CSCL)-Siamese networks and a weighted-voting clustering ensemble (WVE). First, we integrate data visualization techniques with a permutation sample-pairing strategy to generate a complete and nonredundant set of positive–negative sample pairs. Then, we present an algorithm to generate permutation positive–negative sample pairs to provide a rich set of contrastive training data. To overcome the bias in the decision boundary caused by an insufficient number of positive sample pairs, we developed a Siamese network based on CSCL. The CSCL-Siamese network is used to identify known IoT devices and establish an embedded vector database for known IoT devices. Next, we extract the embedding vectors of unknown IoT devices using the trained CSCL-Siamese network and the embedded vector database. Finally, combining weighting factors with a voting ensemble strategy, we develop a UDI algorithm based on a WVE. This presented algorithm integrates the clustering capabilities of multiple unsupervised clustering algorithms to perform clustering on the extracted embedding vectors of unknown IoT devices, thereby enhancing the identification capability of the CSCL-WVE-UDI method. Experimental results demonstrate that the CSCL-WVE-UDI method can effectively identify multiple types of unknown IoT devices at the same time. Full article

As the world moves toward a low-carbon future, a key challenge is improving buildings’ energy performance while maintaining occupant thermal comfort. Emerging digital tools such as the Internet of Things (IoT) and Building Information Modeling (BIM) offer significant potential, enabling precise monitoring and control of building systems. However, integrating these technologies into a unified Digital Twin (DT) framework remains underexplored, particularly in relation to thermal comfort. Additionally, real-world case studies are limited. This paper presents a DT-based system that combines BIM and IoT sensors to monitor and control indoor comfort in real time through an easy-to-use web platform. By using BIM spatial and geometric data along with real-time data from sensors, the system visualizes thermal comfort using a simplified Predicted Mean Vote (sPMV) index. Furthermore, it also uses a hybrid machine learning model that combines Facebook Prophet and Long Short-Term Memory (LSTM) to predict the future indoor environmental parameters. The framework enables Model Predictive Control (MPC) while providing building managers with a scalable tool to collect, analyze, visualize, and optimize thermal comfort data in real time. Full article

The number of services on the internet has experienced explosive growth, and the rapid and accurate discovery of required services among a vast array of similarly functioning services with differing degrees of quality has become a critical and challenging aspect of service computing. In this paper, we propose a trusted service discovery algorithm based on an ant colony system (TSDA-ACS). The algorithm integrates a credibility-based trust model with the ant colony search algorithm to facilitate the discovery of trusted web services. During the evaluation process, the trust model employs a pseudo-stochastic proportion to select nodes, where nodes with higher reputation have a greater probability of being chosen. The ant colony uses a voting method to calculate the credibility of service nodes, factoring in both credibility and non-credibility from the query node’s perspective. The algorithm employs an information acquisition strategy, a trust information merging strategy, a routing strategy, and a random wave strategy to guide ant search. To evaluate the effectiveness of the TSDA-ACS, this paper introduces the random walk search algorithm (RW), the classic max–min ant colony algorithm (MMAS), and a trustworthy service discovery based on a modified ant colony algorithm (TSDMACS) for comparison with the TSDA-ACS algorithm. The experiments demonstrate that this method can achieve the discovery of trusted web services with high recall and precision rates. Finally, the efficacy of the proposed algorithm is validated through comparison experiments across various network environments. Full article

According to recent global public health studies, chronic kidney disease (CKD) is becoming more and more recognized as a serious health risk as many people are suffering from this disease. Machine learning techniques have demonstrated high efficiency in identifying CKD, but their opaque decision-making processes limit their adoption in clinical settings. To address this, this study employs a generative adversarial network (GAN) to handle missing values in CKD datasets and utilizes few-shot learning techniques, such as prototypical networks and model-agnostic meta-learning (MAML), combined with explainable machine learning to predict CKD. Additionally, traditional machine learning models, including support vector machines (SVM), logistic regression (LR), decision trees (DT), random forests (RF), and voting ensemble learning (VEL), are applied for comparison. To unravel the “black box” nature of machine learning predictions, various techniques of explainable AI, such as SHapley Additive exPlanations (SHAP) and local interpretable model-agnostic explanations (LIME), are applied to understand the predictions made by the model, thereby contributing to the decision-making process and identifying significant parameters in the diagnosis of CKD. Model performance is evaluated using predefined metrics, and the results indicate that few-shot learning models integrated with GANs significantly outperform traditional machine learning techniques. Prototypical networks with GANs achieve the highest accuracy of 99.99%, while MAML reaches 99.92%. Furthermore, prototypical networks attain F1-score, recall, precision, and Matthews correlation coefficient (MCC) values of 99.89%, 99.9%, 99.9%, and 100%, respectively, on the raw dataset. As a result, the experimental results clearly demonstrate the effectiveness of the suggested method, offering a reliable and trustworthy model to classify CKD. This framework supports the objectives of the Medical Internet of Things (MIoT) by enhancing smart medical applications and services, enabling accurate prediction and detection of CKD, and facilitating optimal medical decision making. Full article

In the context of smart cities with advanced Internet of Things (IoT) systems, ensuring the sustainability and safety of freshwater resources is pivotal for public health and urban resilience. This study introduces EWAIS (Ensemble Learning and Explainable AI System), a novel framework designed for the smart monitoring and assessment of water quality. Leveraging the strengths of Ensemble Learning models and Explainable Artificial Intelligence (XAI), EWAIS not only enhances the prediction accuracy of water quality but also provides transparent insights into the factors influencing these predictions. EWAIS integrates multiple Ensemble Learning models—Extra Trees Classifier (ETC), K-Nearest Neighbors (KNN), AdaBoost Classifier, decision tree (DT), Stacked Ensemble, and Voting Ensemble Learning (VEL)—to classify water as drinkable or non-drinkable. The system incorporates advanced techniques for handling missing data and statistical analysis, ensuring robust performance even in complex urban datasets. To address the opacity of traditional Machine Learning models, EWAIS employs XAI methods such as SHAP and LIME, generating intuitive visual explanations like force plots, summary plots, dependency plots, and decision plots. The system achieves high predictive performance, with the VEL model reaching an accuracy of 0.89 and an F1-Score of 0.85, alongside precision and recall scores of 0.85 and 0.86, respectively. These results demonstrate the proposed framework’s capability to deliver both accurate water quality predictions and actionable insights for decision-makers. By providing a transparent and interpretable monitoring system, EWAIS supports informed water management strategies, contributing to the sustainability and well-being of urban populations. This framework has been validated using controlled datasets, with IoT implementation suggested to enhance water quality monitoring in smart city environments. Full article

The objective of this study was to develop an artificial intelligence (AI)-driven model for the detection of helmet usage among workers in tractor and agricultural machinery factories with the aim of enhancing occupational safety. A transfer learning approach was employed, utilizing nine pre-trained neural networks for the extraction of deep features. The following neural networks were employed: MobileNetV2, ResNet50, DarkNet53, AlexNet, ShuffleNet, DenseNet201, InceptionV3, Inception-ResNetV2, and GoogLeNet. Subsequently, the extracted features were subjected to iterative neighborhood component analysis (INCA) for feature selection, after which they were classified using the k-nearest neighbor (kNN) algorithm. The classification outputs of all networks were combined through iterative majority voting (IMV) to achieve optimal results. To evaluate the model, an image dataset comprising 662 images of individuals wearing helmets and 722 images of individuals without helmets sourced from the internet was constructed. The proposed model achieved an accuracy of 90.39%, with DenseNet201 producing the most accurate results. This AI-driven helmet detection model demonstrates significant potential in improving occupational safety by assisting safety officers, especially in confined environments, reducing human error, and enhancing efficiency. Full article