Search Results (5,929)

The development of intrusion detection and network security solutions for securing Internet of Things (IoT) networks is constrained by the limited availability of representative network security datasets. Many existing datasets rely on centralised traffic collection and do not capture the non-Independent and Identically Distributed (non-IID) characteristics inherent to edge environments. To address this limitation, this work presents a device-level IoT network dataset generated using the open-source Gotham testbed, a virtualised smart city environment. Network traffic is collected in a distributed manner at the interfaces of 78 heterogeneous IoT devices operating across multiple protocols, including MQTT, CoAP, and RTSP. The dataset comprises over 31.8 million packet-level records, each described by 22 features. It includes both benign traffic and multiple attack classes, namely Network Scanning, Brute Force, Infection, Denial of Service (DoS), and Command and Control (C&C) Communication. Ground-truth labels are assigned using a deterministic process based on orchestration logs. The dataset preserves device-level traffic distributions and captures non-IID characteristics without artificial partitioning. It is publicly available and can be used to support reproducible evaluation of intrusion detection approaches and network analysis tasks in both centralised and distributed learning settings. Full article

Contemporary intensive care operates in an environment with high-complexity cases, large volumes of information, and vast physiological, biological, and therapeutic data, collected from laboratory results, investigations, and therapies for organ support, as well as from systems that operate in parallel. The lack of interoperability contributes to information overload, alarm fatigue, and delayed decision-making. The Smart ICU concept has been developed to address these limitations by integrating medical devices, information systems, and artificial intelligence into a unified system that allows interoperable data integration and predictive analytics. Aim: The purpose of this article is to provide a narrative review of the Smart ICU concept, with a specific focus on the cardiac intensive care unit. It summarizes Smart ICU architecture, data integration, clinical support, and applicability in monitoring perioperative inflammation in cardiac surgery. We describe the Smart ICU architecture, from data acquisition to storage and analytics, highlighting the differences between Smart ICU, artificial intelligence, and Tele-ICU, and we underline predictive analytics as a supportive tool, as well as its influence on clinical outcomes. Cardiac ICU application: Cardiac ICUs offer a data-dense, temporally well-defined model following cardiac surgery with cardiopulmonary bypass, where data concerning patients’ hemodynamics, perfusion data, and biological and inflammatory markers intertwine. Cardiac Smart ICU models could recognize early signs of hemodynamic compromise and low cardiac output states and identify early indicators of post-cardiac surgery complications. Neutrophil activation and complete blood count-derived indices may be used as dynamic biological data for Smart Cardiac ICU models. Conclusion: The Smart Cardiac ICU may support earlier risk stratification, and therefore earlier diagnostic and therapeutic interventions, but its clinical value requires prospective, multicenter validation. Cardiopulmonary bypass-induced inflammation may offer an ideal setting to integrate physiological, procedural, and immunological data into bedside predictive models. Full article

Advanced Metering Infrastructure (AMI) systems require bidirectional wireless communication for remote meter reading, disconnection, and demand–response management across large numbers of smart meters. LoRaWAN Class-C is a strong candidate for large-scale AMI due to its long range, low infrastructure cost, and native downlink support, but gateway placement must simultaneously satisfy uplink Pure-ALOHA capacity, downlink duty-cycle limits, and geographic coverage constraints in non-uniform device distributions. This paper proposes a greedy capacity-coverage gateway placement algorithm for a LoRaWAN AMI deployment serving 89,350 smart meters in Lam Luk Ka district, Pathum Thani Province, Thailand, based on real GIS building-footprint data. The algorithm seeds each gateway at the densest unserved 300 m grid cell, assigns devices within the planning radius R up to the tighter of the uplink Pure-ALOHA capacity and the downlink duty-cycle capacity, both computed for a 98% packet delivery target, and continues placing gateways until 98% of devices are geographically covered. For the 15 min reporting interval, the algorithm yields K* = 137 gateways, only 7% above the arithmetic lower bound of 128, and requires 2.9× fewer gateways than iterative K-means under the same placement constraints. An interval-based scenario analysis across five reporting periods of 5, 10, 15, 30, and 60 min reveals that 15 min is the crossover design point where longer intervals are limited by the downlink duty-cycle and shorter intervals are limited by uplink Pure-ALOHA collision, making 15 min the point at which both constraints are simultaneously near-binding. RX2 reconfiguration from SF10 to SF7 is shown to be essential: the default configuration yields only 121 devices/gateway at the 15 min rate, requiring 739 gateways, while SF7 reconfiguration raises capacity 5.8x to 702 devices/gateway. A Monte Carlo simulation with Urban Okumura–Hata path loss and log-normal shadowing validates the placement, achieving a mean uplink PDR of 98.0% and downlink PDR of 99.9%, both meeting the 98% design target. Class-C energy consumption is 112,787 mJ per 900 s reporting cycle, 434x that of Class-A (260 mJ), confirming that Class-C bidirectional AMI is feasible only for mains-powered smart meters. Full article

Flexible capacitive humidity sensors are pivotal for next-generation wearable electronics and Internet of Things (IoT) applications. However, conventional devices suffer from severe salt leaching and delamination of hygroscopic sensing materials, alongside poor interfacial adhesion and mechanical fragility of metallic electrodes. Herein, an innovative in situ strategy is reported for constructing LiCl-CH₃COOK/laser-induced graphene (LIG) composite flexible electrodes via single-step laser direct writing. This approach simultaneously patterns three-dimensional (3D) porous LIG interdigitated networks on polyimide substrates and drives deep infiltration of the LiCl-CH₃COOK hygroscopic phase within the graphene pores. The 3D interconnected LIG skeleton not only provides abundant physical anchoring sites and rapid water vapor transport channels but also effectively suppresses the physical loss and leaching of the deliquesced salts through micro-nanoscale spatial confinement, yielding remarkable interfacial stability and cycling lifetime. Benefiting from the synergistic deliquescence of the composite salts, the sensor delivers an exceptional sensitivity of 65,570% (ΔC/C₀), moderate response/recovery times of 75/90 s, and ultralow hysteresis of 0.981%. Furthermore, the streamlined laser-scribing route replaces conventional costly microfabrication sequences, enabling low-cost, high-precision customization. Demonstrations in human respiration monitoring and smart agriculture validate the sensor’s superior reliability and practical applicability, establishing a novel pathway for miniaturized, highly integrated, and robust flexible humidity detection systems. Full article

The rapid deployment of Internet of Things (IoT) devices across smart cities, healthcare systems, industrial automation, transportation networks, smart grids, and cyber-physical infrastructures has expanded the modern cyberattack surface. IoT devices are often constrained by limited processing capacity, memory, battery power, and communication bandwidth, making conventional security mechanisms difficult to deploy consistently at scale. Intrusion detection systems (IDSs) provide an important defensive layer; however, many machine-learning-based IDSs are developed under static assumptions and may experience performance degradation as traffic distributions evolve due to firmware changes, device onboarding, protocol updates, user behavior variation, or adaptive attacks. This paper presents a hybrid IDS framework that integrates supervised Random Forest classification, unsupervised Isolation Forest anomaly monitoring, and Kolmogorov–Smirnov (KS)-based concept drift monitoring. In the experimental pipeline, Isolation Forest is trained exclusively on benign traffic to ensure that the anomaly detector models normal behavior rather than an attack-dominated training distribution. The evaluation uses a large-scale chronologically sampled subset of the CICIoT2023 dataset containing 3,890,621 records while preserving the natural class distribution of 2.35% benign traffic and 97.65% attack traffic. The chronological 80/20 train/test split is established first at the file level, followed by systematic sampling within each split to reduce the risk of leakage across the evaluation boundary. On the 746,094-record test set, the proposed hybrid IDS achieved 99.73% accuracy, 99.89% precision, 99.83% recall, 99.86% F1-score, and a false positive rate of 4.77%. The corresponding confusion matrix contains TN = 16,683, FP = 836, FN = 1205, and TP = 727,370, yielding 95.23% specificity and 97.53% balanced accuracy. Standalone Random Forest marginally outperformed the hybrid model in raw accuracy and false positive rate; therefore, the contribution of the proposed framework is centered on deployment-oriented anomaly monitoring, drift awareness, and generalization rather than absolute superiority in static classification metrics. A leave-one-attack-family-out experiment withholding MITM-ArpSpoofing from training showed that the hybrid model detected 85.26% of the unseen attack-family samples, compared with 85.18% for Random Forest alone and 7.05% for Isolation Forest alone. These findings provide initial evidence of generalization to one held-out attack family but should not be interpreted as proof of broad zero-day detection capability. The framework is therefore positioned as a competitive IDS that combines supervised detection with anomaly monitoring and concept drift awareness for deployment-oriented IoT security. Full article

Smart buildings increasingly depend on dense, distributed sensing infrastructures to improve energy efficiency, indoor environmental quality and operational flexibility. However, large-scale IoT/WSN deployment is still constrained by wiring effort, battery maintenance and limited access to sensing locations. Energy harvesting (EH) offers a promising approach toward low-maintenance and partly autonomous sensing, but its practical value in building automation depends on more than the output of individual transducers. This article presents a structured review of EH for IoT/WSN and edge-enabled building automation, focusing on smart-building, Building Management System (BMS) and Building Automation and Control System (BACS) contexts. Light-based, thermoelectric, mechanical, RF/wireless-power-transfer and hybrid harvesting technologies are interpreted through a system-oriented chain linking energy sources, power management, storage, communication, adaptive operation, gateways, diagnostics and edge intelligence. The synthesis shows that EH is most promising for low-duty-cycle environmental monitoring, envelope and façade sensing, occupancy and human–building interaction, airflow-related sensing, technical monitoring and retrofit automation. The main challenges concern the transition from device autonomy to sensing-service autonomy, complete-node evaluation under real building conditions, interoperability with supervisory systems and diagnostic interpretation of intermittent operation. Further research is also needed on lifecycle value assessment and safe transferability toward remote, temporary, resilient and closed ecological infrastructure applications. Full article

Accurate fault diagnosis and protection of series-compensated transmission lines remain challenging due to the nonlinear behavior of series capacitors and associated protective devices, which degrade the performance of conventional protection relays under varying operating conditions. To address these challenges, this paper proposes an intelligent ensemble learning-based protection framework for fault detection, fault classification, fault section identification, and fault location estimation in fixed series-compensated transmission networks. The proposed framework integrates an Artificial Neural Network (ANN) and a random subspace ensemble classifier (RSEC), where the ANN performs fault detection, classification, and location estimation, while the RSEC identifies the faulted section using a majority-weighted voting strategy. In addition, four fault indices are formulated to effectively characterize fault conditions and improve diagnostic performance. The proposed framework is evaluated on a 400 kV, 50 Hz series-compensated transmission system under diverse fault scenarios and varying operating conditions, including different fault types, fault resistances, fault locations, compensation levels, and noisy measurements. The results demonstrate an average fault detection time of 4.05 ms, 100% fault classification accuracy, 98.646% fault section identification efficiency, a mean signed fault location error of −0.02988%, and a mean absolute location error of 0.0791%, indicating negligible systematic bias and high localization accuracy. Furthermore, real-time validation using the OPAL-RT digital real-time simulator confirms the computational feasibility of the proposed framework, demonstrating its potential as a reliable, accurate, and computationally efficient solution for intelligent protection and monitoring of modern smart transmission networks. Full article

Continuous monitoring of Activities of daily living (ADLs) requires sensing systems that are privacy-preserving, low-power, and robust to environmental variation. Ambient sensing technologies provide an alternative to RGB video and wearable devices, but individual sensing modalities exhibit characteristic limitations. Sparse mmWave radar provides strong motion sensitivity but limited posture detail, low-resolution thermal sensing preserves posture-related spatial information, and smart plug telemetry captures only appliance-mediated behavioural interaction. To address these limitations, this paper proposes a layered multimodal ambient-sensing framework comprising a sparse-track 24-GHz FMCW radar, a $32\times 24$ low-resolution thermal sensor, and a Moko smart plug. It experimentally evaluates a radar–thermal HAR branch together with a separate smart plug appliance-recognition branch. The framework proposes three streams to enable continuous non-wearable monitoring while maintaining redundancy and reduced privacy exposure for intelligent-building and ambient assisted living environments. Radar and thermal streams are jointly evaluated on binary motion and four-class posture and activity recognition tasks collected across multiple environmental configurations using recording-grouped cross-validation, while the appliance stream is evaluated using per-plug telemetry from residential-grade appliances. The radar–thermal streams use a single-subject, fixed-placement dataset of binary-motion windows and four-class posture and motion windows collected across six furniture configurations. The separate intrusive load monitoring stream utilises smart plugs to classify appliances. Regarding binary motion recognition, radar $(F_{1,\mathrm{Transformer}}=0.882\pm 0.034)$ and thermal $(F_{1,\mathrm{XGBoost}}=0.870\pm 0.069)$ pipelines achieved similar macro F1 performance. On the four-class posture and activity recognition task, thermal features $(F_{1,\mathrm{thermal}}=0.775\pm 0.053)$ substantially outperformed radar $(F_{1,\mathrm{radar}}=0.609\pm 0.110)$. Weighted late fusion produced only modest descriptive gains. Separately, smart plug telemetry demonstrated strong appliance recognition performance using lightweight tree-based models suitable for constrained edge deployment. The results support a scoped redundancy argument. Sparse track-level radar carries gross motion, while low-resolution thermal sensing carries posture. The smart plug appliance monitoring extends the framework toward appliance-mediated instrumental activity of daily living (IADL) monitoring, with lightweight tree-based models achieving strong recognition performance under constrained edge deployment conditions. The findings support a layered multimodal sensing architecture for privacy-preserving ADL monitoring, where radar contributes motion-sensitive coverage, thermal sensing contributes posture-aware spatial context, and smart plug telemetry contributes appliance-level behavioural evidence within intelligent healthcare and ambient assisted living environments. Full article

Improving the performance of computer networks using seamless Wi-Fi can be achieved by implementing a number of strategies and technologies. Strategies include, first of all, the optimal location of routers and access points, the use of a multi-band network or routers supporting different bands. Routers with support for beamforming technology, which directs the Wi-Fi signal directly to connected devices, allow you to improve the signal quality and data transfer speed. Increasing the performance of Wi-Fi computer networks is also provided by the use of network monitoring and management software, which allows you to monitor its performance and respond to possible problems in the network infrastructure. This is an important task, because it determines the quality and convenience of access to network resources. First of all, it allows you to achieve a high data transfer rate, which is especially important in conditions of high traffic necessary for demanding applications. Seamless Wi-Fi technologies also promote increased mobility and flexibility of users, allowing them to connect to the network in any place with a good signal without having to use wired connections. Network management becomes more efficient with automatic switching between access points and increased fault tolerance in the face of changing traffic usage scales. Quantitative results: Implementation of the Wi-Fi roaming mechanism using the IEEE 802.11 specification; Wi-Fi performance measurements obtained for various IEEE 802.11n HT20 and IEEE 802.11a client ratios; the original test environment included 50 laptops and netbooks from various manufacturers, equipped with various operating systems and wireless network adapters; seamless Wi-Fi technologies based on IEEE 802.11k, IEEE 802.11v, and IEEE 802.11r improve communication continuity during device mobility and support real-time AI-based decision making; Wi-Fi based on local communication standards (WLAN-Wireless Local Area Network). It allows data transmission speeds from 1 Mb∙s⁻¹ to 6.75 Gb∙s⁻¹. Indoors, the Wi-Fi range is 20 m, and outdoors 100 m; WiMax (Worldwide Interoperability for Microwave Access) is a built-in set of wireless broadband standards that provide a constant data rate of 1 Gb∙s⁻¹ and 100 Mb∙s⁻¹ in a cellular network; LR-WPANs (Low-Rate Wireless Personal Area Networks) are standards that are the basis for higher communication protocols, ZigBee. They offer data rates ranging from 40 kb to 250 kb∙s⁻¹. In devices with limited resources, these standards operate at 2.4 GHz at higher transmission speeds and 868/915 MHz at lower. The novelty in the article is the implementation of the Wi-Fi roaming mechanism, presentation of Wi-Fi scenarios, discussion of module generations, indication of integrated agriculture in terms of modern digitalization technologies, and characteristics of smart farming. Full article

Occupancy detection is fundamental to the operational intelligence of smart buildings, driving critical functions in energy management, HVAC automation, and physical security. While modern Deep Learning (DL) models have achieved high accuracy in parsing complex environmental sensor data, they remain highly vulnerable to adversarial examples, imperceptibly perturbed inputs designed to deceive neural networks. These vulnerabilities pose severe real-world risks, ranging from energy sabotage, in which systems heat empty rooms, to critical security breaches in which intruders go undetected. To address this security gap, we propose ADS-Guard, a novel Adversarial Detection and Sanitization (ADS) framework rooted in sequence-to-sequence autoencoder purification. Unlike standard denoising techniques, ADS-Guard incorporates a latent consistency regularization mechanism that encourages alignment between clean and adversarial representations in the latent feature space. We evaluated ADS-Guard using a comprehensive experimental pipeline comprising five distinct DL architectures (LSTM, GRU, 1D-CNN, MLP, and Transformer) across three diverse datasets: (1) The UCI Occupancy dataset (20,699 samples) for standard binary detection; (2) Building59 dataset (7200 samples) for three-class occupancy-level classification (Low, Medium, High); and (3) Room Occupancy dataset (10,129 samples), representing a highly imbalanced binary occupancy-detection task. We evaluate ADS-Guard against both Fast Gradient Sign Method (FGSM) and Projected Gradient Descent (PGD) attacks across diverse occupancy datasets and model architectures. We further assess the framework under adaptive white-box attacks and compare its performance with FGSM-based and PGD-based adversarial training baselines. Our results demonstrate that adversarial attacks can substantially degrade occupancy-detection performance across datasets and model architectures. ADS-Guard consistently improves robustness relative to undefended models against both FGSM and PGD attacks, recovering a substantial portion of the lost performance in binary occupancy tasks and providing meaningful gains in the more challenging multi-class setting. Furthermore, ADS-Guard remains effective under stronger adaptive threat models while providing a practical retraining-free defense that can be integrated with existing occupancy-detection systems without modifying downstream classifiers. Full article

The deployment of deep learning-based vision systems on edge devices introduces a complex trade-off between computational efficiency and detection accuracy. In this work, we investigate this trade-off in the context of a multi-stage Automatic License Plate Recognition (ALPR) pipeline, evaluated in two heterogeneous edge execution environments: a general-purpose Raspberry Pi 5 single-board computer and the ARTPEC-8 system-on-chip integrated into an Axis smart camera, where neural network inference is accelerated by the on-chip DLPU. All experiments were performed using pre-recorded images loaded from the file system; neither the Axis camera sensor nor a live video stream was used. This study evaluates the impact of model architecture, numerical precision, and input resolution on both inference latency and detection performance. YOLOv5- and YOLOv8-based models were analyzed under multiple quantization schemes (FP32, FP16, dynamic, and INT8), while a cross-platform benchmark was conducted to assess the benefits and limitations of hardware acceleration. The results show that dedicated accelerators provide significant latency reduction at higher resolutions; however, this advantage is accompanied by reduced flexibility and increased sensitivity to quantization effects. In contrast, CPU-based execution enables the use of more recent and quantization-robust model architectures, which can partially compensate for the lack of hardware acceleration when combined with resolution scaling. Furthermore, the analysis hig ights the importance of hybrid-resolution processing in multi-stage pipelines, where different stages can operate at different input resolutions to balance accuracy and performance. The findings demonstrate that optimal system design requires a joint consideration of hardware characteristics, model architecture, and quantization strategy, rather than relying on a single optimization dimension. The presented results provide practical insights for the design of efficient and robust edge-based ALPR systems, with direct implications for real-world industrial deployments. Full article

Indoor positioning using commodity Wi-Fi infrastructure is attractive for smart buildings and Internet of Things applications, but the practical accuracy of Wi-Fi Fine Timing Measurement (FTM) remains limited by non-line-of-sight propagation, multipath delay, access-point-dependent ranging bias, and unstable anchor geometry. This paper proposes a measurement-reliability learning and geometry-constrained fusion framework, termed MRL-GCF, for robust horizontal Wi-Fi FTM indoor localization. MRL-GCF learns the reliability of each access-point observation from a multi-factor representation that includes Received Signal Strength Indicator (RSSI), logarithmic FTM range, short-window range stability, RSSI fluctuation, access-point visibility, abnormal-range tendency, and coarse anchor geometry. A lightweight heteroscedastic neural calibrator estimates both range bias and observation uncertainty. A supervised reliability-regime head is further trained from residual-regime soft targets, and its entropy is used as a propagation-ambiguity measure. The learned uncertainty is fused with propagation ambiguity, map obstruction, material-aware obstruction cues, and anchor geometry to select reliable anchors and construct a trust-weighted nonlinear least-squares localization objective. To avoid overestimating performance from repeated scans at identical survey points, both scan-level and point-held-out protocols were adopted. Experiments were conducted in a lobby, a classroom, and a dormitory using 4410 synchronized RSSI-FTM scans. On 882 scan-level test queries, MRL-GCF achieved mean absolute errors of 0.88 m, 0.55 m, and 1.20 m, with sub-3 m success rates of 98.0%, 99.0%, and 96.5%, respectively. Additional replay-based dynamic, temporal, cross-device, AP-density, uncertainty-calibration, map-availability, and coefficient-sensitivity analyses were included to examine deployment-oriented robustness. These results indicate that learning measurement reliability while preserving geometric constraints provides a practical and interpretable solution for robust Wi-Fi FTM indoor positioning. Full article

In this publication we investigate in depth the design, architecture and implementation of a bio and cultural guiding system with augmented capabilities. Our platform will be able to provide a flexible and user-friendly application for smart mobile devices with Android OS, which will be able to provide to the user the ability to discover nearby places of interest such as museums, archeological sites, religious sites, natural beauty sites, etc. In addition, our application is able to offer users an enhanced, comprehensive and augmented tour experience, based on visual and audio smartphone services, using asynchronous and real-time user–server communication mechanisms, thus eliminating the need for a human tour guide operator in cases of a remote area, guiding service cost or unavailable time slot. The proposed platform integrates visual overlays, audio narration, Geolocation services, and cloud-based data management to enable users to explore cultural, historical, and natural points of interest without the need for a human tour guide. A modular, layered system architecture is developed, combining Firebase Realtime Database, RESTful web services, OpenStreetMap-based navigation, and Android-native components to ensure scalability, flexibility, and real-time responsiveness. UML modeling, including class and sequence diagrams, is employed to formally describe system structure and behavior, while a mathematical data model validates the consistency of the underlying database schema. The implementation demonstrates how AR guiding systems can enhance spatial understanding, accessibility, and user engagement while supporting sustainable tourism practices and efficient destination management. The results indicate that the proposed solution is technically feasible, user-centered, and adaptable to diverse bio-cultural contexts, contributing to the advancement of intelligent, inclusive, and sustainable digital tourism platforms. Full article

Manual visual diagnosis of apple diseases suffers from low efficiency, strong subjectivity and poor scalability for large commercial orchards. Existing research mainly targets diseases on single plant organs, whereas full-growth-cycle detection has to cope with extreme multi-scale differences among lesions. For instance, Valsa canker on tree trunks leads to extensive cortical necrosis, while early-stage anthracnose on fruits appears as tiny spots spanning only a few pixels. These significant scale gaps necessitate robust spatial feature aggregation and anti-noise ability to resist complex background interference. Aiming to achieve rapid and precise detection of diseases on multiple apple organs including leaves, fruits, trunks and branches, this work presents an enhanced YOLOv11 model equipped with the Information Integration Attention (IIA) module. The IIA module is embedded into the key fusion layers of the backbone and neck networks. It strengthens the extraction of fine-grained lesion features, recovers spatial location information via a bidirectional attention mechanism, and suppresses noise induced by uneven lighting and intricate backgrounds. To guarantee stable convergence on low-resource computing devices, a tailored training scheme is designed. Experimental results on a seven-category dataset with 7406 images demonstrate that YOLOv11-IIA reaches a precision of 0.763, a recall of 0.819, mAP@50 of 0.857 and mAP@50-95 of 0.699, which achieves clear performance improvements over the original YOLOv11 (mAP@50 improved from 0.485 to 0.857) and other attention-augmented detectors. The model operates stably on an NVIDIA GTX 1050 4GB GPU with an inference speed of 16 FPS for 640 × 640 input images; comprehensive quantitative computational metrics including parameter count, FLOPs and memory consumption will be fully measured in subsequent UAV deployment experiments. The proposed method provides a reliable technical reference for intelligent apple disease monitoring in smart orchard systems. Full article

The growing reliance of Internet of Energy (IoE)-enabled smart city infrastructures has significantly intensified the complexity of modern urban energy environments due to the integration of renewable resources, electric vehicles, and interconnected IoT devices. These highly dynamic environments introduce critical challenges related to power stability, operational reliability, and intelligent energy management. Therefore, developing accurate, adaptive, and explainable monitoring frameworks has become essential for ensuring resilient urban energy infrastructures. This paper proposes an Explainable Artificial Intelligence (XAI)-driven deep learning framework integrating Multi-Head Attention and SHapley Additive exPlanations (SHAP) for intelligent power stability monitoring in IoE-enabled smart cities. The proposed framework employs an attention-based deep learning architecture to classify stable and unstable operational conditions using multivariate operational power parameters. Furthermore, SHAP-based explainability analysis is incorporated to improve model transparency and identify influential operational factors affecting stability behavior. Using the Electrical Grid Stability Simulated Dataset, the proposed framework achieved 97.35% accuracy and 0.997 ROC-AUC, outperforming several traditional machine learning and deep learning baselines. The explainability results show that temporal response parameters have the strongest impact on stability decisions. This work offers not only high predictive performance but also valuable interpretability, which is essential for practical deployment in real-world smart city energy systems. Full article