Search Results (3,978)

This paper presents Aerokinesis, an IoT-based software–hardware system for intuitive gesture-driven control of quadcopter unmanned aerial vehicles (UAVs), developed within the Robot Operating System 2 (ROS2) framework. The proposed system addresses the challenge of providing an accessible human–drone interaction interface for operators in scenarios where traditional remote controllers are impractical or unavailable. The architecture comprises two hierarchical control levels: (1) high-level discrete command control utilizing a fully connected neural network classifier for static gesture recognition, and (2) low-level continuous flight control based on three-dimensional hand keypoint analysis from a depth camera. The gesture classification module achieves an accuracy exceeding 99% using a multi-layer perceptron trained on MediaPipe-extracted hand landmarks. For continuous control, we propose a novel approach that computes Euler angles (roll, pitch, yaw) and throttle from 3D hand pose estimation, enabling intuitive four-degree-of-freedom quadcopter manipulation. A hybrid signal filtering pipeline ensures robust control signal generation while maintaining real-time responsiveness. Comparative user studies demonstrate that gesture-based control reduces task completion time by 52.6% for beginners compared to conventional remote controllers. The results confirm the viability of vision-based gesture interfaces for IoT-enabled UAV applications. Full article

This paper develops a mathematically grounded neuro-fuzzy control framework for IoT-enabled irrigation systems in precision agriculture. A discrete-time, physically motivated model of soil moisture is formulated to capture the nonlinear water dynamics driven by evapotranspiration, irrigation, and drainage in the crop root zone. A Mamdani-type fuzzy controller is designed to approximate the optimal irrigation strategy, and an equivalent Takagi–Sugeno (TS) representation is derived, enabling a rigorous stability analysis based on Input-to-State Stability (ISS) theory and Linear Matrix Inequalities (LMIs). Online parameter estimation is performed using a Recursive Least Squares (RLS) algorithm applied to real IoT field data collected from a drip-irrigated orchard. To enhance prediction accuracy and long-term adaptability, the fuzzy controller is augmented with lightweight artificial neural network (ANN) modules for evapotranspiration estimation and slow adaptation of membership-function parameters. This work provides one of the first mathematically certified neuro-fuzzy irrigation controllers integrating ANN-based estimation with Input-to-State Stability (ISS) and LMI-based stability guarantees. Under mild Lipschitz continuity and boundedness assumptions, the resulting neuro-fuzzy closed-loop system is proven to be uniformly ultimately bounded. Experimental validation in an operational IoT setup demonstrates accurate soil-moisture regulation, with a tracking error below 2%, and approximately 28% reduction in water consumption compared to fixed-schedule irrigation. The proposed framework is validated on a real IoT deployment and positioned relative to existing intelligent irrigation approaches. Full article

Background/Objectives: Accurate identification of dental malocclusions from routine clinical photographs can be time-consuming and subject to interobserver variability. A YOLOv11-based deep learning approach is presented and evaluated for automatic malocclusion detection on routine intraoral photographs, testing the hypothesis that training on a structured annotation protocol enables reliable detection of multiple clinically relevant malocclusions. Methods: An anonymized dataset of 5854 intraoral photographs (frontal occlusion; right/left buccal; maxillary/mandibular occlusal) was labeled according to standardized instructions derived from the Index of Orthodontic Treatment Need (IOTN) A total of 17 clinically relevant classes were annotated with bounding boxes. Due to an insufficient number of examples, two malocclusions (transposition and non-occlusion) were excluded from our quantitative analysis. A YOLOv11 model was trained with augmented data and evaluated on a held-out test set using mean average precision at IoU 0.5 (mAP50), macro precision (macro-P), and macro recall (macro-R). Results: Across 15 analyzed classes, the model achieved 87.8% mAP50, 76.9% macro-P, and 86.1% macro-R. The highest per-class AP₅₀ was observed for Deep bite (98.8%), Diastema (97.9%), Angle Class II canine (97.5%), Anterior open bite (92.8%), Midline shift (91.8%), Angle Class II molar (91.1%), Spacing (91%), and Crowding (90.1%). Moderate performance included Anterior crossbite (88.3%), Angle Class III molar (87.4%), Head bite (82.7%), and Posterior open bite (80.2%). Lower values were seen for Angle Class III canine (76%), Posterior crossbite (75.6%), and Big overjet (75.3%). Precision–recall trends indicate earlier precision drop-off for posterior/transverse classes and comparatively more missed detections in Posterior crossbite, whereas Big overjet exhibited more false positives at the chosen threshold. Conclusion: A YOLOv11-based deep learning system can accurately detect several clinically salient malocclusions on routine intraoral photographs, supporting efficient screening and standardized documentation. Performance gaps align with limited examples and visualization constraints in posterior regions. Larger, multi-center datasets, protocol standardization, quantitative metrics, and multimodal inputs may further improve robustness. Full article

A comfortable, reliable, safe and environmentally friendly high-speed train journey that saves time and offers an unforgettable experience for passengers is not a dream. Passengers can enjoy panoramic views, delicious cuisine and use their mobile devices without restrictions. High-speed trains, powered by environmentally friendly methods, are a sustainable form of transport, reducing harmful emissions. Integrating intelligent control and management into railway networks has the capacity to increase efficiency and improve reliability and safety, as well as reduce development and maintenance costs. Future intelligent railway network architectures are expected to focus on integrated, multi-layered systems that deeply embed artificial intelligence (AI), the Internet of Things (IoT) and advanced communication technologies (5G/6G) to ensure intelligent operation, improved reliability and increased safety. Distributed intelligent control in railways refers to an advanced approach in which decision-making capabilities are distributed across network components (trains, stations, track sections, control centers) rather than being concentrated in a single central location. The recent advances in AI in railways are associated with numerous scientific papers that enable intelligent traffic management, automatic train control, and predictive maintenance, with each of the proposed intelligent solutions being evaluated in terms of key performance indicators such as latency, reliability, and accuracy. This study focuses on how different intelligent solutions in railways can be implemented in network components based on the requirements for real-time control, near-real-time control, and non-real-time operation. The analysis of related works is focused on the proposed intelligent railway frameworks and architectures. The description of typical use cases for implementing intelligent control aims to summarize latency requirements and the possible distribution of control logic between network components, taking into account time constraints. The considered use case of automatic train protection aims to evaluate the added latency of communication. The requirements for the nodes that host and execute the control logic are identified. Full article

To address the challenges of low data validity and limited energy efficiency in agricultural IoT, we propose a deep predictive agricultural variable-frequency sensing method. First, we construct a hybrid prediction model, denoted as SVMD-TCN-R-GRU-T (STRGT). This model integrates successive variational mode decomposition (SVMD) with an optimized TCN-GRU architecture, thereby improving prediction accuracy. Building on this framework, we design a frequency conversion sampling method under dual detection analysis (FCSDDA). This approach employs wavelet transform to determine the minimum sampling rate and incorporates dynamic time warping evaluate data variation. The dual detection mechanism enables real-time adjustment of sensor acquisition frequency. Experimental results demonstrate that the proposed model significantly outperforms conventional models in terms of RMSE, MAE, and MAPE. When the STRGT outputs are applied as inputs to the FCSDDA algorithm, the system achieved optimal improvements in energy efficiency improvement rate (84.61%) and data value density (0.3368), exceeding the performance of other prediction model variants. These findings confirm that prediction accuracy directly influences adaptive sensing performance. This indicates that the method can effectively achieve dual optimization of energy saving and data validity in testing scenarios. In the future, more agricultural sensing scenarios can be validated. Full article

The convergence of Artificial Intelligence (AI) and the Internet of Things (IoT), known as Artificial Intelligence of Things (AIoT), has emerged as a transformative paradigm for enabling intelligent, data-driven, and context-aware decision-making in urban environments to reduce the carbon footprint of mobility and industry. This review examines the conceptual foundations, and state-of-the-art developments of AIoT, with a particular emphasis on its applications in smart cities and its relevance to climate change management. AIoT integrates sensing, connectivity, and intelligent analytics to provide optimized solutions in transportation systems, energy management, waste collection, and environmental monitoring, directly influencing urban sustainability. Beyond urban efficiency, AIoT can play a critical role in addressing the global challenges and management of climate change by (a) precise measurements and autonomously remote monitoring; (b) real-time optimization in renewable energy distribution; and (c) developing prediction models for early warning of climate disasters. This paper performs a literature review and bibliometric analysis to identify the current landscape of AIoT research in smart city contexts. Over 1885 articles from Web of Sciences and over 1854 from Scopus databases, published between 1993 and January 2026, were analyzed. The results reveal a strong and accelerating growth in research activity, with publication output doubling in the most recent two years compared to 2023. Waste management and air quality monitoring have emerged as leading application domains, where AIoT-based optimization and predictive models demonstrate measurable improvements in operational efficiency and environmental impact. Altogether, these support faster and more effective decisions for reducing greenhouse gas emissions and ensuring the sustainable use of resources. The reviewed studies reveal rapid advancements in edge intelligence, federated learning, and secure data sharing through the integration of AIoT with blockchain technologies. However, significant challenges remain regarding scalability, interoperability, privacy, ethical governance, and the effective translation of research outcomes into policy and citizen-oriented tools such as climate applications, insurance models, and disaster alert systems. By synthesizing current research trends, this article highlights the potential of AIoT to support sustainable, resilient, and citizen-centric smart city ecosystems while identifying both critical gaps and promising directions for future investigations. Full article

The construction industry relies on the Internet of Things (IoT) and wearable technologies to enhance workplace safety. This research investigates the use of IoT and wearable technology among Saudi Arabian construction sector employees, analyzing their implementation difficulties and the factors contributing to successful implementation. A structured questionnaire was distributed to 567 construction professionals across different roles and projects. Frequency analysis was used to study adoption patterns, chi-square tests to study demographic factors, and principal component analysis for exploratory factor analysis to discover hidden adoption factors. The findings show that smart safety vests and helmets receive the highest level of recognition. On the other hand, advanced monitoring systems, including fatigue and environmental sensors, are not used enough. Group differences in device adoption were investigated in terms of years of experience, academic qualification, job role, and project budget. The findings from factor analysis show that three main factors determine adoption rates, which include (1) safety and operational effectiveness, (2) worker acceptance and support structures, and (3) technical and adoption barriers. A data-driven system is created to help policymakers and industry leaders accelerate construction safety digitalization efforts. Full article

The continued downscaling of transistors has exacerbated aging mechanisms such as bias temperature instability (BTI) and hot-carrier injection (HCI), posing significant reliability challenges for nanoscale integrated circuits. These effects are particularly critical to flip-flops operating at low supply voltages, which are essential for ultra-low-power applications including the Internet of Things (IoT) and biomedical implants. In this work, we address the aging issue in low-voltage Split-Controlled Flip-Flops (SCFFs) by proposing a novel transistor-level mitigation technique specifically tailored to this architecture within a domestic 14 nm process library. Through a detailed analysis of aging-critical transistors, three targeted enhancement strategies are introduced. Simulation results demonstrate that the improved SCFF achieves more than a 60% reduction in PMOS threshold voltage degradation and a 40% reduction in timing delay, while maintaining robust operation at a supply voltage as low as 0.4 V. These results highlight the effectiveness of the proposed approach in mitigating aging effects and enhancing reliability under low-voltage operation. Full article

Quantum Key Distribution (QKD) is a process to establish a symmetric key between two parties using the principles of quantum mechanics. Currently, commercial QKD systems are still expensive, they require specific infrastructure, and they are impractical for deployment in portable or resource-constrained devices. In this article, we introduce the Butterfly Protocol (and its extended version) that enables QKD to be offered as a service to non-QKD-capable (portable or IoT) devices. Our key contributions include (1) resilience to the compromise of any single classical link, (2) protection against malicious QKD users, (3) implicit mutual authentication between users without relying on large post-quantum certificates, and (4) the Double Butterfly extension, which secures communication even when the underlying QKD network cannot be fully trusted. We also demonstrate how to integrate the Butterfly Protocol into TLS 1.3 and provide its initial security analysis. We present preliminary performance results and discuss the main bottlenecks in the Butterfly Protocol implementation. We believe that our solution represents a practical step toward integrating QKD into classical networks and extending its use to portable devices. Full article

Federated Graph Neural Networks (FedGNNs) have emerged as a promising paradigm for decentralized graph learning across distributed data silos. However, the influence of underlying communication topologies on model accuracy and efficiency remains underexplored. This study presents a topology-aware benchmarking framework for federated GNNs, systematically evaluating the impact of network structure and aggregation strategy on performance and communication overhead. The proposed framework functions as a synthetic, communication-level digital twin that emulates Federated Learning interactions and topology-dependent dynamics under controlled conditions. Four learning schemes—Centralized, Local, FedAvg, and FedAvg-Fedadam—were assessed across three representative topologies: Barabási–Albert (BA), Watts–Strogatz (WS), and Erdős–Rényi (ER). Results demonstrate that centralized training achieved the highest mean ROC-AUC (0.63), while FedAvg-Fedadam attained the best F1-score (0.038), balancing local adaptation and global convergence. Among topologies, BA and WS yielded higher average AUC values (approximately 0.57 and 0.56, respectively) than ER (approximately 0.39). Communication analysis revealed FedAvg as the most efficient strategy, requiring only approximately 3.8 × 10⁵ bytes cumulatively. These findings highlight key trade-offs between accuracy, robustness, and communication efficiency in federated graph learning and provide empirical guidance for topology-aware optimization of distributed GNNs. While the experiments rely on representative synthetic topologies, the insights offer indicative relevance and potential applicability to Internet-of-Things (IoT), vehicular, and cyber-physical networks, where communication structure and bandwidth constraints critically influence collaborative intelligence. By modeling canonical connectivity patterns and releasing our code and data, the proposed benchmarking framework offers a reproducible basis for comparing emerging federated graph architectures under constrained communication conditions. Full article

With the rapid advancement of technology in recent years, signatures on contracts and documents have increasingly shifted from traditional handwritten forms on paper to digital handwritten signatures executed on devices (hereafter referred to as digital tablets). This transition introduces new challenges for forensic document examination due to the differences in writing instruments. According to the European Network of Forensic Science Institutes (ENFSI), a Digital Capture Signature (DCS) refers to data points captured during the writing process on digital devices such as tablets, smartphones, or signature pads. In addition to retaining the visual image of the signature, DCS provides more information previously unavailable, including pen pressure, stroke order, and writing speed. These features possess potential forensic value and warrant further study and evaluation. This study employs three devices—Samsung Galaxy Tab S10, Apple iPad Pro, and Apple iPad Mini—together with their respective styluses as experimental tools. Using custom-developed handwriting capture software for both Android and iOS platforms, we simulated signature-writing scenarios common in the financial and insurance industries. Thirty participants were asked to provide samples of horizontal Chinese, English, and number writings (FUJ-IRB NO: C113187), which were subsequently normalized and segmented into characters. For analysis, we adopted distance-based time-series alignment algorithms (FastDTW and SC-DTW) to match writing data across different instances (intra- and inter-writer). The accumulated distances between corresponding data points, such as coordinates and pressure, were used to assess handwriting stability and to study the differences between same-writer and different-writer samples. The findings indicate that preprocessing through character centroid alignment, followed by the analysis, substantially reduces the average accumulated distance of handwriting. This procedure quantifies the stability of an individual’s handwriting and enables differentiation between same-writer and different-writer scenarios based on the distribution of DCS distances. Furthermore, the use of styluses provides more precise distinctions between same- and different-writer samples compared with direct finger-based writing. In the context of rapid advancements in artificial intelligence and emerging technologies, this preliminary study aims to contribute foundational insights into the forensic application of digital signature examination. Full article

The deployment of Vision-Language Models (VLMs) in Satellite IoT scenarios is critical for real-time disaster assessment but is often hindered by the substantial memory and compute requirements of state-of-the-art models. While parameter-efficient fine-tuning (PEFT) enables adaptation, with minimal computational overhead, standard supervised methods often fail to ensure robustness and reliability on resource-constrained edge devices. To address this, we propose EdgeV-SE, a self-reflective fine-tuning framework that significantly enhances the performance of VLM without introducing any inference-time overhead. Our framework incorporates an uncertainty-aware self-reflection mechanism with asymmetric dual pathways: a generative linguistic pathway and an auxiliary discriminative visual pathway. By estimating uncertainty from the linguistic pathway using a log-likelihood margin between class verbalizers, EdgeV-SE identifies ambiguous samples and refines its decision boundaries via consistency regularization and cross-pathway mutual learning. Experimental results on hurricane damage assessment demonstrate that our approach improves image classification accuracy, enhances image–text semantic alignment, and achieves superior caption quality. Notably, our work achieves these gains while maintaining practical deployment on a commercial off-the-shelf edge device such as NVIDIA Jetson Orin Nano, preserving the inference latency and memory footprint. Overall, our work contributes a unified self-reflective fine-tuning framework that improves robustness, calibration, and deployability of VLMs on edge devices. Full article

Automotive dashboard cameras are widely used to record driving events and often serve as critical evidence in accident investigations and insurance claims. However, the availability of free and low-cost editing tools has increased the risk of video tampering, underscoring the need for reliable methods to verify video authenticity. Temporal tampering typically involves manipulating frame order through insertion, deletion, or duplication. This paper proposes a computationally efficient framework that transforms high-dimensional video into compact one-dimensional temporal signals and learns tampering patterns using a shallow one-dimensional convolutional neural network (1D-CNN). Five complementary features are extracted between consecutive frames: frame-difference magnitude, structural similarity drift (SSIM drift), optical-flow mean, forward–backward optical-flow consistency error, and compression-aware temporal prediction error. Per-video robust normalization is applied to emphasize intra-video anomalies. Experiments on a custom dataset derived from D²-City demonstrate strong detection performance in single-attack settings: 95.0% accuracy for frame deletion, 100.0% for frame insertion, and 95.0% for frame duplication. In a four-class setting (non-tampered, insertion, deletion, duplication), the model achieves 96.3% accuracy, with AUCs of 0.994, 1.000, 0.997, and 0.988, respectively. Efficiency analysis confirms near real-time CPU inference (≈12.7–12.9 FPS) with minimal memory overhead. Cross-dataset tests on BDDA and VIRAT reveal domain-shift sensitivity, particularly for deletion and duplication, highlighting the need for domain adaptation and augmentation. Overall, the proposed multi-feature 1D-CNN provides a practical, interpretable, and resource-aware solution for temporal tampering detection in dashcam videos, supporting trustworthy video forensics in IoT-enabled transportation systems. Full article

Network intrusion behaviors exhibit high concealment and diversity, making intrusion detection methods based on single-behavior modeling unable to accurately characterize such activities. To overcome this limitation, we propose SGMT-IDS, a dual-branch semi-supervised intrusion detection model based on Graph Neural Networks (GNNs) and Transformers. By constructing two views of network attacks, namely structural and behavioral semantics, the model performs collaborative analysis of intrusion behaviors from both perspectives. The model adopts a dual-branch architecture. The SGT branch captures the structural embeddings of network intrusion behaviors, and the GML-Transformer branch extracts the semantic information of intrusion behaviors. In addition, we introduce a two-stage training strategy that optimizes the model through pseudo-labeling and contrastive learning, enabling accurate intrusion detection with only a small amount of labeled data. We conduct experiments on the NF-Bot-IoT-V2, NF-ToN-IoT-V2, and NF-CSE-CIC-IDS2018-V2 datasets. The experimental results demonstrate that SGMT-IDS achieves superior performance across multiple evaluation metrics. Full article

Background/Objectives: The purpose of this study was to evaluate the reliability and diagnostic accuracy of smartphone-based photogrammetry for the assessment of pes planus and to determine its agreement with standard radiographic measurements. Methods: This prospective diagnostic study included 100 skeletally mature patients (50 males, 50 females; mean age 43.4 years) who underwent standardized lateral weight-bearing foot radiographs and smartphone-based foot photography. The calcaneal pitch angle (CPA) was measured on radiographs, and a corresponding photographic arch pitch angle (P-APA) was measured from standardized smartphone photographs using digital software (Angle Meter iOS v1.9.8). Three independent observers performed each measurement twice. Inter- and intra-observer reliability was assessed using intraclass correlation coefficients (ICC). Agreement between methods was evaluated with Pearson correlation, Lin’s concordance correlation coefficient (CCC), Bland–Altman analysis, and Deming regression. Receiver operating characteristic (ROC) analysis was performed to determine the diagnostic accuracy of calibrated P-APA, with the radiographic threshold of 18° serving as the reference standard for pes planus classification. Results: All measurements demonstrated excellent intra- and inter-observer reliability (ICC ≥ 0.900). P-APA values were systematically higher than radiographic values (31.8° ± 4.3 vs. 21.8° ± 5.5; p < 0.001). A strong correlation was observed between the two methods (r = 0.799, p < 0.001), but concordance was poor (CCC = 0.222). Bland–Altman analysis revealed a mean bias of +10.1° with wide limits of agreement (3.8° to 16.4°). Deming regression yielded the calibration equation Radiographic CPA = (P-APA × 1.371) − 21.883. ROC analysis of calibrated values yielded an AUC of 0.885 (95% CI, 0.820–0.951), with an optimal cutoff of 22.8° (sensitivity, 100%; specificity, 61.1%), corresponding to 32.6° on the uncalibrated photographic scale. Conclusions: Conventional weight-bearing radiography remains the reference standard for diagnosis and clinical decision-making in pes planus. The smartphone-derived photographic arch pitch angle is a non-equivalent surrogate measure that shows substantial systematic bias and limited agreement with radiographic calcaneal pitch, and therefore cannot replace weight-bearing radiographs. Smartphone photogrammetry may be used only as a complementary tool for preliminary screening or telemedicine support; any positive or equivocal findings require radiographic confirmation. Full article