Search Results (39)

This study proposes a novel hybrid forecasting approach designed explicitly for long-horizon financial time series. It incorporates LMD (Local Mean Decomposition), SD (Signal Decomposition), and sophisticated machine learning methods. The framework for the NASDAQ Composite Index begins by decomposing the original time series into stochastic and deterministic components using the LMD approach. This method effectively separates linear and nonlinear signal structures. The stochastic components are modeled using ARIMA to represent linear temporal dynamics, while the deterministic components are projected using cutting-edge machine learning methods, including XGBoost, Random Forest (RF), Artificial Neural Networks (ANNs), and Support Vector Machines (SVMs). This study employs various statistical metrics to evaluate the predictive ability across both short-term noise and long-term trends, including Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), and Directional Statistic (DS). Furthermore, the Diebold–Mariano test is used to determine the statistical significance of any forecast improvements. Empirical results demonstrate that the hybrid LMD–ARIMA–SD–XGBoost model consistently outperforms alternative configurations in terms of prediction accuracy and directional consistency. These findings demonstrate the advantages of integrating decomposition-based signal filtering with ensemble machine learning to improve the robustness and generalizability of long-term forecasting. This study presents a scalable and adaptive approach for modeling complex, nonlinear, and high-dimensional time series, thereby contributing to the enhancement of intelligent forecasting systems in the economic and financial sectors. As far as the authors are aware, this is the first study to combine XGBoost and LMD in a hybrid decomposition framework for forecasting long-horizon stock indexes. Full article

Infrared small-target detection remains a critical challenge in military reconnaissance, environmental monitoring, forest-fire prevention, and search-and-rescue operations, owing to the targets’ extremely small size, sparse texture, low signal-to-noise ratio, and complex background interference. Traditional convolutional neural networks (CNNs) struggle to detect such weak, low-contrast objects due to their limited receptive fields and insufficient feature extraction capabilities. To overcome these limitations, we propose a Multi-Scale Edge-Aware Convolution (MEAC) module that enhances feature representation for small infrared targets without increasing parameter count or computational cost. Specifically, MEAC fuses (1) original local features, (2) multi-scale context captured via dilated convolutions, and (3) high-contrast edge cues derived from differential Gaussian filters. After fusing these branches, channel and spatial attention mechanisms are applied to adaptively emphasize critical regions, further improving feature discrimination. The MEAC module is fully compatible with standard convolutional layers and can be seamlessly embedded into various network architectures. Extensive experiments on three public infrared small-target datasets (SIRSTD-UAVB, IRSTDv1, and IRSTD-1K) demonstrate that networks augmented with MEAC significantly outperform baseline models using standard convolutions. When compared to eleven mainstream convolution modules (ACmix, AKConv, DRConv, DSConv, LSKConv, MixConv, PConv, ODConv, GConv, and Involution), our method consistently achieves the highest detection accuracy and robustness. Experiments conducted across multiple versions, including YOLOv10, YOLOv11, and YOLOv12, as well as various network levels, demonstrate that the MEAC module achieves stable improvements in performance metrics while slightly increasing computational and parameter complexity. These results validate the MEAC module’s significant advantages in enhancing the detection of small and weak objects and suppressing interference from complex backgrounds. These results validate MEAC’s effectiveness in enhancing weak small-target detection and suppressing complex background noise, highlighting its strong generalization ability and practical application potential. Full article

With the increasing significance of deep-sea resource development, Forward-Looking Sonar (FLS) has become an essential technology for real-time environmental mapping and navigation in deep-sea mining vehicles (DSMV). However, FLS images often suffer from a limited field of view, uneven imaging, and complex noise sources, making single-frame images insufficient for providing continuous and complete environmental awareness. Existing mosaicking methods typically rely on external sensors or controlled laboratory conditions, often failing to account for the high levels of uncertainty and error inherent in real deep-sea environments. Consequently, their performance during sea trials tends to be unsatisfactory. To address these challenges, this study introduces a robust FLS image mosaicking framework that functions without additional sensor input. The framework explicitly models the noise characteristics of sonar images captured in deep-sea environments and integrates bidirectional cyclic consistency filtering with a soft-weighted feature refinement strategy during the feature-matching stage. For image fusion, a radial adaptive fusion algorithm with a protective frame is proposed to improve edge transitions and preserve structural consistency in the resulting panoramic image. The experimental results demonstrate that the proposed framework achieves high robustness and accuracy under real deep-sea conditions, effectively supporting DSMV tasks such as path planning, obstacle avoidance, and simultaneous localization and mapping (SLAM), thus enabling reliable perceptual capabilities for intelligent underwater operations. Full article

Aerial tracking is an important service for many Unmanned Aerial Vehicle (UAV) applications. Existing work has failed to provide robust solutions when handling target disappearance, viewpoint changes, and tracking drifts in practical scenarios with limited UAV resources. In this paper, we propose a closed-loop framework integrating three key components: (1) a lightweight adaptive detection with multi-scale feature extraction, (2) spatiotemporal motion modeling through Kalman-filter-based trajectory prediction, and (3) autonomous decision-making through composite scoring of detection confidence, appearance similarity, and motion consistency. By implementing dynamic detection-tracking coordination with quality-aware feature preservation, our system enables real-time operation through performance-adaptive frequency modulation. Evaluated on VOT-ST2019 and OTB100 benchmarks, the proposed method yields marked improvements over baseline trackers, achieving a 27.94% increase in Expected Average Overlap (EAO) and a 10.39% reduction in failure rates, while sustaining a frame rate of 23–95 FPS on edge hardware. The framework achieves rapid target reacquisition during prolonged occlusion scenarios through optimized protocols, outperforming conventional methods in sustained aerial surveillance tasks. Full article

Situation awareness (SA) involves analyzing sensory data, such as audio signals, to identify anomalies. While acoustic features are widely used in audio analysis, existing methods face critical limitations; they often overlook the relevance of SA audio segments, failing to capture the complex relational patterns in audio data that are essential for SA. In this study, we first propose a graph neural network (GNN) with an attention mechanism that models SA audio features through graph structures, capturing both node attributes and their relationships for richer representations than traditional methods. Our analysis identifies suitable audio feature combinations and graph constructions for SA tasks. Building on this, we introduce a situation awareness gated-attention GNN (SAGA-GNN), which dynamically filters irrelevant nodes through max-relevance neighbor sampling to reduce redundant connections, and a learnable edge gated-attention mechanism that suppresses noise while amplifying critical events. The proposed method employs sigmoid-activated attention weights conditioned on both node features and temporal relationships, enabling adaptive node emphasizing for different acoustic environments. Experiments reveal that the proposed graph-based audio features demonstrate superior representation capacity compared to traditional methods. Additionally, both proposed graph-based methods outperform existing approaches. Specifically, owing to the combination of graph-based audio features and dynamic selection of audio nodes based on gated-attention, SAGA-GNN achieved superior results on two real datasets. This work underscores the importance and potential value of graph-based audio features and attention mechanism-based GNNs, particularly in situational awareness applications. Full article

Federated learning enables privacy-preserving model training across distributed clients, yet real-world deployments face statistical, system, and behavioral heterogeneity, which degrades performance and increases vulnerability to adversarial clients. Existing incentive mechanisms often neglect participant credibility, leading to unfair rewards and reduced robustness. To address these issues, we propose a Trust-Aware Incentive Mechanism (TAIM), which evaluates client reliability through a multi-dimensional trust model incorporating participation frequency, gradient consistency, and contribution effectiveness. A trust-weighted reward allocation is formulated via a Stackelberg game, and a confidence-based soft filtering algorithm is introduced to mitigate the impact of unreliable updates. Experiments on FEMNIST, CIFAR-10, and Sent140 demonstrate that TAIM improves accuracy by up to 4.1%, reduces performance degradation under adaptive attacks by over 35%, and ensures fairer incentive distribution with a Gini coefficient below 0.3. TAIM offers a robust and equitable FL framework suitable for heterogeneous edge environments. Full article

Delivering compelling presentations is a critical skill across academic, professional, and public domains—yet many presenters struggle with structuring content, maintaining visual consistency, and engaging their audience effectively. Existing tools offer isolated support for design or delivery but fail to promote long-term skill development. This paper presents a novel intelligent application, the Presentation Advisor application, powered by a personalized recommendation engine that goes beyond fixing slide content and visualization, enabling users to build presentation competence. The recommendation engine leverages a model based on hybrid multi-tower neural network architecture enhanced with temporal encoding, problem sequence modeling, and utility-based scoring to deliver adaptive context-aware feedback. Unlike current tools, the presented system analyzes user-submitted presentations to detect common issues and delivers curated educational content tailored to user preferences, presentation types, and audiences. The system also incorporates strategic cold-start mitigation, ensuring high-quality recommendations even for new users or unseen content. Comprehensive experimental evaluations demonstrate that the suggested model significantly outperforms content-based filtering, collaborative filtering, autoencoders, and reinforcement learning approaches across both accuracy and personalization metrics. By combining cutting-edge recommendation techniques with a pedagogical framework, the Presentation Advisor application enables users not only to improve individual presentations but to become consistently better presenters over time. Full article

Real-time Global Navigation Satellite System (GNSS) deformation monitoring is crucial for structural safety but is challenged by long-term, high-amplitude noise and trend-like anomalies. To address these issues, we propose a low-complexity forward–backward reliable filtering algorithm (FBRFF) tailored for edge environments. FBRFF integrates trend-aware correction and confidence-based fusion within a sliding window framework to effectively suppress non-stationary disturbances while preserving true deformation signals. Its architecture compensates for the inadequate performance of existing filters under persistent large-amplitude noise, enabling early anomaly correction before deformation analysis. In addition, it significantly reduces system computational load and complexity when processing massive multi-source data, while allowing easy integration with other filtering algorithms for enhanced robustness. Experiments using real-world GNSS data from the Usnisa Palace monitoring project validate that FBRFF improves positioning accuracy by up to 82% over baseline methods and maintains real-time responsiveness on resource-constrained platforms. These results demonstrate that FBRFF provides a lightweight, robust, and scalable solution for real-time GNSS monitoring, offering practical value for early-warning systems and infrastructure safety management. Full article

Despite significant progress in fall detection systems, many of the proposed algorithms remain difficult to implement in real-world applications. A common limitation is the lack of location awareness, especially in outdoor scenarios where accurately determining the fall location is crucial for a timely emergency response. Moreover, the complexity of many existing algorithms poses a challenge for deployment on edge devices, such as wearable systems, which are constrained by limited computational resources and battery life. As a result, these solutions are often impractical for long-term, continuous use in practical settings. To address the aforementioned issues, we developed a portable, wearable device that integrates a microcontroller (MCU), an inertial sensor, and a chip module featuring Global Positioning System (GPS) and Narrowband Internet of Things (NB-IoT) technologies. A low-complexity algorithm based on a finite-state machine was employed to detect fall events, enabling the module to meet the requirements for long-term outdoor use. The proposed algorithm is capable of filtering out eight types of daily activities—running, walking, sitting, ascending stairs, descending stairs, stepping, jumping, and rapid sitting—while detecting four types of falls: forward, backward, left, and right. In case a fall event is detected, the device immediately transmits a fall alert and GPS coordinates to a designated server via NB-IoT. The server then forwards the alert to a specified communication application. Experimental tests demonstrated the system’s effectiveness in outdoor environments. A total of 6750 samples were collected from fifteen test participants, including 6000 daily activity samples and 750 fall events. The system achieved an average sensitivity of 97.9%, an average specificity of 99.9%, and an overall accuracy of 99.7%. The implementation of this system provides enhanced safety assurance for elderly individuals during outdoor activities. Full article

Due to the construction damage of high-density polyethylene film (HDPE) during the early stages of landfill construction and missed or faulty welding, this paper proposes a method based on the synchronous characteristic temperature differences between defective and intact areas of HDPE film. An image feature-edge-picking algorithm was used to detect various defects. First, under the action of a continuous heat source, infrared images of different types of defects on the surface of HDPE films were collected, and we recorded the temperature of different areas on the film surface. We also analyzed the changes in the temperatures of the complete and defect areas over time and extracted the temperature characteristic curves. Second, the contour characteristics of hidden defects in the weld area were analyzed. The image with the most substantial temperature difference resolution was selected and preliminary noise reduction was performed. Further enhancement of the edges was carried out using the guided image-filtering (GIF) algorithm, which was improved by using the edge-aware weighting in weighted guided image filtering (WGIF) and the weighted aggregation mechanism in weighted aggregated guided image filtering (WAGIF). Finally, the Canny operator was used to detect the edges of the processed images to recognize the contour of the welding defect. The best pixel image was extracted, the pixel comparison relationship was used to quantitatively detect the defect size of the HDPE film and the error between the image defect size and the actual size was analyzed. The experimental results show that the model could identify the surface defects on HDPE film during construction and could obtain the approximate outline and size of the hidden defects in the welding area. Full article

Edge-computing applications demand ultra-low-power architectures for both feature extraction and classification tasks. In this manuscript, a Keyword Spotting (KWS) system tailored for energy-constrained portable environments is proposed. A 16-channel analog filter bank is employed for audio feature extraction, followed by a digital Gated Recurrent Unit (GRU) classifier. The filter bank is behaviorally modeled, making use of second-order band-pass transfer functions, simulating the analog front-end (AFE) processing. To enable efficient deployment, the GRU classifier is trained using a Learned Step Size (LSQ) and Look-Up Table (LUT)-aware quantization method. The resulting quantized model, with 4-bit weights and 8-bit activation functions (W4A8), achieves 91.35% accuracy across 12 classes, including 10 keywords from the Google Speech Command Dataset v2 (GSCDv2), with less than 1% degradation compared to its full-precision counterpart. The model is estimated to require only 34.8 kB of memory and 62,400 multiply–accumulate (MAC) operations per inference in real-time settings. Furthermore, the robustness of the AFE against noise and analog impairments is evaluated by injecting Gaussian noise and perturbing the filter parameters (center frequency and quality factor) in the test data, respectively. The obtained results confirm a strong classification performance even under degraded circuit-level conditions, supporting the suitability of the proposed system for ultra-low-power, noise-resilient edge applications. Full article

The Monit4Healthy system is an IoT-enabled health monitoring solution designed to address critical challenges in real-time biomedical signal processing, energy efficiency, and data transmission. The system’s modular design merges wireless communication components alongside a number of physiological sensors, including galvanic skin response, electromyography, photoplethysmography, and EKG, to allow for the remote gathering and evaluation of health information. In order to decrease network load and enable the quick identification of abnormalities, edge computing is used for real-time signal filtering and feature extraction. Flexible data transmission based on context and available bandwidth is provided through a hybrid communication approach that includes Bluetooth Low Energy and Wi-Fi. Under typical monitoring scenarios, laboratory testing shows reliable wireless connectivity and ongoing battery-powered operation. The Monit4Healthy system is appropriate for scalable deployment in connected health ecosystems and portable health monitoring due to its responsive power management approaches and structured data transmission, which improve the resiliency of the system. The system ensures the reliability of signals whilst lowering latency and data volume in comparison to conventional cloud-only systems. Limitations include the requirement for energy profiling, distinctive hardware miniaturizing, and sustained real-world validation. By integrating context-aware processing, flexible design, and effective communication, the Monit4Healthy system complements existing IoT health solutions and promotes better integration in clinical and smart city healthcare environments. Full article

In Follow-Me Mobile Edge Cloud (FMEC) environments, Virtual Network Function (VNF) instances dynamically move in tandem with user mobility. For latency-sensitive applications, hot backups aim to reduce service downtimes during primary VNF instance failures. However, as the distance between VNF instances and their hot backups shifts due to user mobility, recovery latency can sometimes exceed user expectations, leading to certain backups being perceived as unavailable. To maintain VNF reliability, it becomes essential to either deploy additional hot backups closer to the VNF instances or migrate the deemed unavailable backups to proximity, reinstating their usability. How to effectively leverage both the VNF and its failed hot backups to ensure VNF reliability, meet users’ recovery latency demands, and minimize the overall cost of hot backup migration and redeployment is a challenging problem. To address this challenge, we propose a hybrid approach combining an optimized Kuhn–Munkres algorithm and dynamic strategy selection for cost-efficient hot backup migration. The problem is first formulated as an integer linear programming model and proven Non-deterministic Polynomial-time hard (NP-hard). To address computational complexity, we propose an optimized Kuhn–Munkres algorithm with dynamic strategy selection. The Kuhn–Munkres algorithm accelerates backup migration through network preprocessing and multi-constraint candidate filtering, while adaptively choosing between migration and redeployment via real-time cost analysis. Through extensive experiments, our hybrid migration algorithm achieves equivalent user demand satisfaction as traditional methods while reducing backup VNF (BVNF) migration costs by 15%. The proposed approach combines an optimized Kuhn–Munkres algorithm for efficient candidate selection with dynamic cost-aware strategy switching, ensuring reliable latency-sensitive service in mobile edge environments. Full article

Fraud detection in large-scale graphs presents significant challenges, especially in heterophilic graphs where linked nodes often belong to dissimilar classes or exhibit contrasting attributes. These asymmetric interactions, combined with class imbalance and limited labeled data, make it difficult to fully leverage node labels in semi-supervised learning frameworks. This study aims to address these challenges by proposing a novel framework, Spectrum-Constrained and Skip-Enhanced Graph Fraud Detection (SCSE-GFD), designed specifically for fraud detection in heterophilic graphs. The primary objective is to enhance fraud detection performance while maintaining computational efficiency. SCSE-GFD integrates several key components to improve performance. It employs adaptive polynomial convolution to capture multi-frequency signals and utilizes relation-specific spectral filtering to accommodate both homophilic and heterophilic structures. Additionally, a relation-aware mechanism is incorporated to differentiate between edge types, which enhances feature propagation across diverse graph connections. To address the issue of over-smoothing, skip connections are used to preserve both low- and high-level node representations. Furthermore, supervised edge classification is used to improve the structural understanding of the graph. Extensive experiments on real-world datasets, including Amazon and YelpChi, demonstrate SCSE-GFD’s effectiveness. The framework achieved state-of-the-art AUC scores of 96.21% on Amazon and 90.58% on YelpChi, significantly outperforming existing models. These results validate SCSE-GFD’s ability to improve fraud detection accuracy while maintaining efficiency. Full article

The ability to segment moving objects from three-dimensional (3D) LiDAR scans is critical to advancing autonomous driving technology, facilitating core tasks like localization, collision avoidance, and path planning. In this paper, we introduce a novel deep neural network designed to enhance the performance of 3D LiDAR point cloud moving object segmentation (MOS) through the integration of image gradient information and the principle of motion consistency. Our method processes sequential range images, employing depth pixel difference convolution (DPDC) to improve the efficacy of dilated convolutions, thus boosting spatial information extraction from range images. Additionally, we incorporate Bayesian filtering to impose posterior constraints on predictions, enhancing the accuracy of motion segmentation. To handle the issue of uneven object scales in range images, we develop a novel edge-aware loss function and use a progressive training strategy to further boost performance. Our method is validated on the SemanticKITTI-based LiDAR MOS benchmark, where it significantly outperforms current state-of-the-art (SOTA) methods, all while working directly on two-dimensional (2D) range images without requiring mapping. Full article