Search Results (45)

Stress is a pervasive global health concern that adversely contributes to morbidity and reduced productivity, yet it often remains unquantified due to its subjective and variant presentation. Although artificial intelligence offers an encouraging path toward automated monitoring of mental states, current state-of-the-art approaches are challenged by the reliance on single-source data, sparsity of labeled samples, and significant class imbalance. This paper proposes NeuroStrainSense, a novel deep multimodal stress detection model that integrates three complementary datasets—WESAD, SWELL-KW, and TILES—through a Transformer-based feature fusion architecture combined with a Variational Autoencoder for generative data augmentation. The Transformer architecture employs four encoder layers with eight multi-head attention heads and a hidden dimension of 512 to capture complex inter-modal dependencies across physiological, audio, and behavioral modalities. Our experiments demonstrate that NeuroStrainSense achieves a state-of-the-art performance with accuracies of 87.1%, 88.5%, and 89.8% on the respective datasets, with F1-scores exceeding 0.85 and AUCs greater than 0.89, representing improvements of 2.6–6.6 percentage points over existing baselines. We propose a robust evaluation framework that quantifies discrimination among stress types through clustering validity metrics, achieving a Silhouette Score of 0.75 and Intraclass Correlation Coefficient of 0.76. Comprehensive ablation experiments confirm the utility of each modality and the VAE augmentation module, with physiological features contributing most significantly (average performance decrease of 5.8% when removed), followed by audio (2.8%) and behavioral features (2.1%). Statistical validation confirms all findings at the p < 0.01 significance level. Beyond binary classification, the model identifies five clinically relevant stress profiles—Cognitive Overload, Burnout, Acute Stress, Psychosomatic, and Low-Grade Chronic—with an expert concordance of Cohen’s κ = 0.71 (p < 0.001), demonstrating the strong ecological validity for personalized well-being and occupational health applications. External validation on the MIT Reality Mining dataset confirms the generalizability with minimal performance degradation (accuracy: 0.785, F1-score: 0.752, AUC: 0.849). This work underlines the potential of integrated multimodal learning and demographically aware generative AI for continuous, precise, and fair stress monitoring across diverse populations and environmental contexts. Full article

Dynamic heterogeneous redundancy (DHR) architectures combine heterogeneity, redundancy, and dynamism to create security-centric frameworks that can be used to mitigate network attacks that exploit unknown vulnerabilities. However, conventional DHR architectures rely on centralized control modules for scheduling and adjudication, leading to significant single-point failure risks and trust bottlenecks that severely limit their deployment in security-critical scenarios. To address these challenges, this paper proposes a decentralized DHR architecture based on the Raft consensus algorithm. It deeply integrates the Raft consensus mechanism with the DHR execution layer to build a consensus-centric control plane and designs a dual-log pipeline to ensure all security-critical decisions are executed only after global consistency via Raft. Furthermore, we define a multi-dimensional attacker model—covering external, internal executor, internal node, and collaborative Byzantine adversaries—to analyze the security properties and explicit defense boundaries of the architecture under Raft’s crash-fault-tolerant assumptions. To assess the effectiveness of the proposed architecture, a prototype consisting of five heterogeneous nodes was developed for thorough evaluation. The experimental results show that, for non-Byzantine external and internal attacks, the architecture achieves high detection and isolation rates, maintains high availability, and ensures state consistency among non-malicious nodes. For stress tests in which a minority of nodes exhibit Byzantine-like behavior, our prototype preserves log consistency and prevents incorrect state commitments; however, we explicitly treat these as empirical observations under a restricted adversary rather than a general Byzantine fault tolerance guarantee. Performance testing revealed that the system exhibits strong security resilience in attack scenarios, with manageable performance overhead. Instead of turning Raft into a Byzantine-fault-tolerant consensus protocol, the proposed architecture preserves Raft’s crash-fault-tolerant guarantees at the consensus layer and achieves Byzantine-resilient behavior at the execution layer through heterogeneous redundant executors and majority-hash validation. To support evaluation during peer review, we provide a runnable prototype package containing Docker-based deployment scripts, pre-built heterogeneous executors, and Raft control-plane images, enabling reviewers to observe and assess the representative architectural behaviors of the system under controlled configurations without exposing the internal source code. The complete implementation will be made available after acceptance in accordance with institutional IP requirements, without affecting the scope or validity of the current evaluation. Full article

The development of detection and identification technologies for biofouling organisms on marine aquaculture cages is of paramount importance for the automation and intelligence of cleaning processes by Autonomous Underwater Vehicles (AUVs). The present study proposes a methodology for the detection of fouling shellfish on marine aquaculture cages. This methodology is based on an improved version of a symmetric Faster R-CNN: The original Visual Geometry Group 16-layer (VGG16) network is replaced with a 50-layer Residual Network with Aggregated Transformations (ResNeXt50) architecture, incorporating a Convolutional Block Attention Module (CBAM) to enhance feature extraction capabilities; In addition, the anchor box dimensions must be optimised concurrently with the Intersection over Union (IoU) threshold. This is to ensure the adaptation to the scale of the object; combined with the Multi-Scale Retinex with Single Scale Component and Color Restoration (MSRCR) algorithm with a view to achieving image enhancement. Experiments demonstrate that the enhanced model attains an average precision of 94.27%, signifying a 10.31% augmentation over the original model whilst necessitating a mere one-fifth of the original model’s weight. At an intersection-over-union (IoU) value of 0.5, the model attains a mean average precision (mAP) of 93.14%, surpassing numerous prevalent detection models. Furthermore, the employment of an image-enhanced dataset during the training of detection models has been demonstrated to yield an average precision that is 11.72 percentage points higher than that achieved through training with the original dataset. In summary, the technical approach proposed in this paper enables accurate and efficient detection and identification of fouling shellfish on marine aquaculture cages. Full article

A Multi-Layer Perceptron (MLP), as the basic structure of neural networks, is an important component of various deep learning models such as CNNs, RNNs, and Transformers. Nevertheless, MLP training faces significant challenges, with a large number of saddle points and local minima in its non-convex optimization space, which can easily lead to gradient vanishing and premature convergence. Compared with traditional heuristic algorithms relying on a population-based parallel search, such as GA, GWO, DE, etc., the Besiege and Conquer Algorithm (BCA) employs a one-spot update strategy that provides a certain level of global optimization capability but exhibits clear limitations in search flexibility. Specifically, it lacks fast detection, fast adaptation, and fast convergence. First, the fixed sinusoidal amplitude limits the accuracy of fast detection in complex regions. Second, the combination of a random location and fixed perturbation range limits the fast adaptation of global convergence. Finally, the lack of a hierarchical adjustment under a single parameter (BCB) hinders the dynamic transition from exploration to exploitation, resulting in slow convergence. To address these limitations, this paper proposes a Flexible Besiege and Conquer Algorithm (FBCA), which improves search flexibility and convergence capability through three new mechanisms: (1) the sine-guided soft asymmetric Gaussian perturbation mechanism enhances local micro-exploration, thereby achieving a fast detection response near the global optimum; (2) the exponentially modulated spiral perturbation mechanism adopts an exponential spiral factor for fast adaptation of global convergence; and (3) the nonlinear cognitive coefficient-driven velocity update mechanism improves the convergence performance, realizing a more balanced exploration–exploitation process. In the IEEE CEC 2017 benchmark function test, FBCA ranked first in the comprehensive comparison with 12 state-of-the-art algorithms, with a win rate of 62% over BCA in 100-dimensional problems. It also achieved the best performance in six MLP optimization problems, showing excellent convergence accuracy and robustness, proving its excellent global optimization ability in complex nonlinear MLP optimization training. It demonstrates its application value and potential in optimizing neural networks and deep learning models. Full article

Accurate and reliable extraction of building footprints from LiDAR point clouds is a fundamental task in remote sensing and urban scene reconstruction. Building footprints serve as essential geospatial products that support GIS database updating, land-use monitoring, disaster management, and digital twin development. Traditional image-based methods enable large-scale mapping but suffer from 2D perspective limitations and radiometric distortions, while airborne or vehicle-borne LiDAR systems often face single-viewpoint constraints that lead to incomplete or fragmented footprints. Recently, backpack mobile laser scanning (MLS) has emerged as a flexible platform for capturing dense urban geometry at the pedestrian level. However, the high noise, point sparsity, and structural complexity of MLS data make reliable footprints delineation particularly challenging. To address these issues, this study proposes a Deep Line-Segment Detection–Driven Building Footprints Extraction Framework that integrates multi-layer accumulated occupancy mapping, deep geometric feature learning, and structure-aware regularization. The accumulated occupancy maps aggregate stable wall features from multiple height slices to enhance contour continuity and suppress random noise. A deep line-segment detector is then employed to extract robust geometric cues from noisy projections, achieving accurate edge localization and reduced false responses. Finally, a structural chain-based completion and redundancy filtering strategy repairs fragmented contours and removes spurious lines, ensuring coherent and topologically consistent footprints reconstruction. Extensive experiments conducted on two campus scenes containing 102 buildings demonstrate that the proposed method achieves superior performance with an average Precision of 95.7%, Recall of 92.2%, F1-score of 93.9%, and IoU of 88.6%, outperforming existing baseline approaches by 4.5–7.8% in F1-score. These results highlight the strong potential of backpack LiDAR point clouds, when combined with deep line-segment detection and structural reasoning, to complement traditional remote sensing imagery and provide a reliable pathway for large-scale urban scene reconstruction and geospatial interpretation. Full article

Since the beginning of the 21st century, major epidemics and pandemics such as SARS, H1N1pdm09, Ebola, and COVID-19 have repeatedly challenged global systems of disease diagnostics and control. These crises exposed the weaknesses of traditional diagnostic models, including long turnaround times, uneven resource distribution, and supply chain bottlenecks. As a result, there is an urgent need for more advanced diagnostic technologies and integrated diagnostics strategies. Our review summarizes key lessons learned from four recent major outbreaks and highlights advances in diagnostic technologies. Among these, molecular techniques such as loop-mediated isothermal amplification (LAMP), transcription-mediated amplification (TMA), recombinase polymerase amplification (RPA), and droplet digital polymerase chain reaction (ddPCR) have demonstrated significant advantages and are increasingly becoming core components of the detection framework. Antigen testing plays a critical role in rapid screening, particularly in settings such as schools, workplaces, and communities. Serological assays provide unique value for retrospective outbreak analysis and assessing population immunity. Next-generation sequencing (NGS) has become a powerful tool for identifying novel pathogens and monitoring viral mutations. Furthermore, point-of-care testing (POCT), enhanced by miniaturization, biosensing, and artificial intelligence (AI), has extended diagnostic capacity to the front lines of epidemic control. In summary, the future of epidemic and pandemic response will not depend on a single technology, but rather on a multi-layered and complementary system. By combining laboratory diagnostics, distributed screening, and real-time monitoring, this system will form a global diagnostic network capable of rapid response, ensuring preparedness for the next global health crisis. Full article

Currently, deepfake detection has garnered widespread attention as a key defense mechanism against the misuse of deepfake technology. However, existing deepfake detection networks still face challenges such as insufficient robustness, limited generalization capabilities, and a single feature extraction domain (e.g., using only spatial domain features) when confronted with evolving algorithms or diverse datasets, which severely limits their application capabilities. To address these issues, this study proposes a deepfake detection network named EFIMD-Net, which enhances performance by strengthening feature interaction and integrating spatial and frequency domain features. The proposed network integrates a Cross-feature Interaction Enhancement module (CFIE) based on cosine similarity, which achieves adaptive interaction between spatial domain features (RGB stream) and frequency domain features (SRM, Spatial Rich Model stream) through a channel attention mechanism, effectively fusing macro-semantic information with high-frequency artifact information. Additionally, an Enhanced Multi-scale Feature Fusion (EMFF) module is proposed, which effectively integrates multi-scale feature information from various layers of the network through adaptive feature enhancement and reorganization techniques. Experimental results show that compared to the baseline network Xception, EFIMD-Net achieves comparable or even better Area Under the Curve (AUC) on multiple datasets. Ablation experiments also validate the effectiveness of the proposed modules. Furthermore, compared to the baseline traditional two-stream network Locate and Verify, EFIMD-Net significantly improves forgery detection performance, with a 9-percentage-point increase in Area Under the Curve on the CelebDF-v1 dataset and a 7-percentage-point increase on the CelebDF-v2 dataset. These results fully demonstrate the effectiveness and generalization of EFIMD-Net in forgery detection. Potential limitations regarding real-time processing efficiency are acknowledged. Full article

To mitigate the impact on detection performance caused by insufficient input information in 3D object detection based on single LiDAR data, this study designs three innovative modules based on the PointRCNN framework. Firstly, addressing the issue of the Multi-Layer Perceptron (MLP) in PointNet++ failing to effectively capture local features during the feature extraction phase, we propose the Adaptive Multilayer Perceptron (AMLP). Secondly, to prevent the problem of gradient vanishing due to the increased parameter scale and computational complexity of AMLP, we introduce the Channel Aware Residual module (CA-Res) in the feature extraction layer. Finally, in the head layer of the subsequent processing stage, we propose the Dynamic Attention Head (DA-Head) to enhance the representation of key features in the process of target detection. A series of experiments conducted on the KITTI validation set demonstrate that in complex scenarios, for the small target “Pedestrian”, our model achieves performance improvements of 2.08% and 3.46%, respectively, at the “Medium” and “Difficult” detection difficulty levels. To further validate the generalization capability of the Enhanced DetNet network, we deploy the trained model on the KITTI server and conduct a comprehensive evaluation of detection performance for the “Car”, “Pedestrian”, and “Cyclist” categories. Full article

In container terminal operations, truck lifting accidents pose a serious threat to the safety and efficiency of automated equipment. Traditional detection methods using visual cameras and single-line Light Detection and Ranging (LiDAR) are insufficient for capturing three-dimensional spatial features, leading to reduced detection accuracy. Moreover, the boundary features of key accident objects, such as containers, truck chassis, and wheels, are often blurred, resulting in frequent false and missed detections. To tackle these challenges, this paper proposes an accident detection method based on multi-line LiDAR and an improved PointNet++ model. This method uses multi-line LiDAR to collect point cloud data from operational lanes in real time and enhances the PointNet++ model by integrating a multi-layer perceptron (MLP) and a mixed attention mechanism (MAM), optimizing the model’s ability to extract local and global features. This results in high-precision semantic segmentation and accident detection of critical structural point clouds, such as containers, truck chassis, and wheels. Experiments confirm that the proposed method achieves superior performance compared to the current mainstream algorithms regarding point cloud segmentation accuracy and stability. In engineering tests across various real-world conditions, the model exhibits strong generalization capability. Full article

For tropical rainforest regions with dense vegetation cover, the development of effective large-scale soil mapping methods is crucial to improve soil management practices to replace the time-consuming and laborious conventional approaches. While machine learning (ML) algorithms demonstrate superior predictability of soil properties over linear models, their practical and automated application for predicting soil properties using remote sensing data requires further assessment. Therefore, this study aims to integrate Unmanned Aerial Vehicles (UAVs)-based hyperspectral images and Light Detection and Ranging (LiDAR) points to predict the soil properties indirectly in two tropical rainforest mountains (Diaoluo and Limu) in Hainan Province, China. A total of 175 features, including texture features, vegetation indices, and forest parameters, were extracted from two study sites. Six ML models, Partial Least Squares Regression (PLSR), Random Forest (RF), Adaptive Boosting (AdaBoost), Gradient Boosting Decision Trees (GBDT), Extreme Gradient Boosting (XGBoost), and Multilayer Perceptron (MLP), were constructed to predict soil properties, including soil acidity (pH), total nitrogen (TN), soil organic carbon (SOC), and total phosphorus (TP). To enhance model performance, a Bayesian optimization algorithm (BOA) was introduced to obtain optimal model hyperparameters. The results showed that compared with the default parameter tuning method, BOA always improved models’ performances in predicting soil properties, achieving average R² improvements of 202.93%, 121.48%, 8.90%, and 38.41% for soil pH, SOC, TN, and TP, respectively. In general, BOA effectively determined the complex interactions between hyperparameters and prediction features, leading to an improved model performance of ML methods compared to default parameter tuning models. The GBDT model generally outperformed other ML methods in predicting the soil pH and TN, while the XGBoost model achieved the highest prediction accuracy for SOC and TP. The fusion of hyperspectral images and LiDAR data resulted in better prediction of soil properties compared to using each single data source. The models utilizing the integration of features derived from hyperspectral images and LiDAR data outperformed those relying on one single data source. In summary, this study highlights the promising combination of UAV-based hyperspectral images with LiDAR data points to advance digital soil property mapping in forested areas, achieving large-scale soil management and monitoring. Full article

Graphene-enhanced surface plasmon resonance (SPR) biosensors offer promising advancements in viral detection, particularly for SARS-CoV-2. This study presents the design and optimization of a multilayer SPR biosensor incorporating silver, silicon nitride, single-layer graphene, and thiol-tethered ssDNA to achieve high sensitivity and specificity. Key metrics, including SPR angle shift (Δθ), sensitivity (S), detection accuracy (DA), and figure of merit (FoM), were assessed across SARS-CoV-2 concentrations from 150 to 525 mM. The optimized biosensor achieved a sensitivity of 315.91°/RIU at 275 mM and a maximum Δθ of 4.2° at 400 mM, demonstrating strong responsiveness to virus binding. The sensor maintained optimal accuracy and figure of merit at lower concentrations, with a linear sensitivity response up to 400 mM, after which surface saturation limited further responsiveness. These results highlight the suitability of the optimized biosensor for real-time, point-of-care SARS-CoV-2 detection, particularly at low viral loads, supporting its potential in early diagnostics and epidemiological monitoring. Full article

Simple, instantaneous, contactless, multiple-point metamaterial-inspired microwave sensors, composed of multi-band, low-profile metamaterial-inspired antennas, were developed to detect and identify meningioma tumors, the most common primary brain tumors. Based on a typical meningioma tumor size of 5–20 mm, a higher operating frequency, where the wavelength is similar or smaller than the tumor target, is crucial. The sensors, designed for the microwave Ku band range (12–18 GHz), where the electromagnetic property values of tumors are available, were implemented in this study. A seven-layered head phantom, including the meningioma tumors, was defined using actual electromagnetic parametric values in the frequency range of interest to mimic the actual human head. The reflection coefficients can be recorded and analyzed instantaneously, reducing high electromagnetic radiation consumption. It has been shown that a single-band detection point is not adequate to classify the nonlinear tumor and head model parameters. On the other hand, dual-band and tri-band metamaterial-inspired antennas, with additional detecting points, create a continuous function solution for the nonlinear problem by adding extra observation points using multiple-band excitation. The point mapping values can be used to enhance the tumor detection capability. Two-point mapping showed a consistent trend between the S₁₁ value order and the tumor size, while three-point mapping can also be used to demonstrate the correlation between the S₁₁ value order and the tumor size. This proposed multi-detection point technique can be applied to a sensor for other nonlinear property targets. Moreover, a set of antennas with different polarizations, orientations, and arrangements in a network could help to obtain the highest sensitivity and accuracy of the whole system. Full article

Over the past decade, distributed acoustic sensing has been utilized for structural health monitoring in various applications, owing to its continuous measurement capability in both time and space and its ability to deliver extensive data on the conditions of large structures using just a single optical cable. This work aims to evaluate the performance of distributed acoustic sensing for monitoring a multilayer structure on a laboratory scale. The proposed structure comprises four layers: a medium-density fiberboard and three rigid polyurethane foam slabs. Three different damages were emulated in the structure: two in the first layer of rigid polyurethane foam and another in the medium-density fiberboard layer. The results include the detection of the mechanical wave, comparing the response with point sensors used for reference, and evaluating how the measured signal behaves in time and frequency in the face of different damages in the multilayer structure. The tests demonstrate that evaluating signals in both time and frequency domains presents different characteristics for each condition analyzed. The supervised support vector machine classifier was used to automate the classification of these damages, achieving an accuracy of 93%. The combination of distributed acoustic sensing with this learning algorithm creates the condition for developing a smart tool for monitoring multilayer structures. Full article

Cameras and LiDAR are important sensors in autonomous driving systems that can provide complementary information to each other. However, most LiDAR-only methods outperform the fusion method on the main benchmark datasets. Current studies attribute the reasons for this to misalignment of views and difficulty in matching heterogeneous features. Specially, using the single-stage fusion method, it is difficult to fully fuse the features of the image and point cloud. In this work, we propose a 3D object detection network based on the multi-layer and multi-modal fusion (3DMMF) method. 3DMMF works by painting and encoding the point cloud in the frustum proposed by the 2D object detection network. Then, the painted point cloud is fed to the LiDAR-only object detection network, which has expanded channels and a self-attention mechanism module. Finally, the camera-LiDAR object candidates fusion for 3D object detection(CLOCs) method is used to match the geometric direction features and category semantic features of the 2D and 3D detection results. Experiments on the KITTI dataset (a public dataset) show that this fusion method has a significant improvement over the baseline of the LiDAR-only method, with an average mAP improvement of 6.3%. Full article

We aimed to provide an in-depth analysis with respect to three turning points in pancreas involvement in primary hyperparathyroidism (PHP): hypercalcemia-induced pancreatitis (HCa-P), MEN1 (multiple endocrine neoplasia)-related neuroendocrine tumors (NETs), and insulin resistance (IR). This was a comprehensive review conducted via a PubMed search between January 2020 and January 2024. HCa-P (n = 9 studies, N = 1375) involved as a starting point parathyroid NETs (n = 7) or pancreatitis (n = 2, N = 167). Case report-focused analysis (N = 27) showed five cases of pregnancy PHP-HCa-P and three reports of parathyroid carcinoma (female/male ratio of 2/1, ages of 34 in women, men of 56). MEN1-NET studies (n = 7) included MEN1-related insulinomas (n = 2) or MEN1-associated PHP (n = 2) or analyses of genetic profile (n = 3), for a total of 877 MEN1 subjects. In MEN1 insulinomas (N = 77), the rate of associated PHP was 78%. Recurrence after parathyroidectomy (N = 585 with PHP) was higher after less-than-subtotal versus subtotal parathyroidectomy (68% versus 45%, p < 0.001); re-do surgery was 26% depending on surgery for pancreatic NETs (found in 82% of PHP patients). MEN1 pathogenic variants in exon 10 represented an independent risk factor for PHP recurrence. A single pediatric study in MEN1 (N = 80) revealed the following: a PHP rate of 80% and pancreatic NET rate of 35% and 35 underlying germline MEN1 pathogenic variants (and 3/35 of them were newly detected). The co-occurrence of genetic anomalies included the following: CDC73 gene variant, glucokinase regulatory protein gene pathogenic variant (c.151C>T, p.Arg51*), and CAH-X syndrome. IR/metabolic feature-focused analysis identified (n = 10, N = 1010) a heterogeneous spectrum: approximately one-third of adults might have had prediabetes, almost half displayed some level of IR as reflected by HOMA-IR > 2.6, and serum calcium was positively correlated with HOMA-IR. Vitamin D deficiency was associated with a higher rate of metabolic syndrome (n = 1). Normocalcemic and mildly symptomatic hyperparathyroidism (n = 6, N = 193) was associated with a higher fasting glucose and some improvement after parathyroidectomy. This multilayer pancreas/parathyroid analysis highlighted a complex panel of connections from pathogenic factors, including biochemical, molecular, genetic, and metabolic factors, to a clinical multidisciplinary panel. Full article