Search Results (1,311)

Non-invasive, real-time biomass estimation is critical for smart aquaculture, yet high computational latency and the cost of specialized optical sensors remain significant bottlenecks. This study proposes an ultra-low-cost, edge-deployable stereo-vision framework utilizing a dual-webcam architecture synchronized with a lightweight YOLOv11n-pose model. To address the spatial uncertainties in non-rigid fish locomotion, we integrated advanced spatial loss functions to achieve precise anatomical keypoint extraction. These coordinates are processed through a three-point Bézier curve interpolation and a mathematically derived Dynamic Shape Factor (K) to correct for optical refraction and morphological variations. As a proof-of-concept, the proposed system was validated on a live multi-species cohort (N = 10), achieving a Mean Absolute Percentage Error (MAPE) of 8.64% and an R² of 0.92 under strict Leave-One-Out Cross-Validation (LOOCV), drastically outperforming traditional naive volumetric baselines (MAPE > 54%). Requiring only 6.7 GFLOPs and 5.5 MB of memory, the model achieves 111.6 FPS. These results demonstrate the feasibility of highly efficient, cost-effective AI solutions for precision aquaculture while clearly defining the validity boundaries and statistical constraints for future large-scale deployment. Full article

Pitch-based foam carbon, a novel lightweight material, boasts excellent mechanical and thermoelectric properties, and tantalum film deposition on its surface can further enhance its performance. However, this deposition process often suffers from non-uniform deposition and suboptimal coating quality. To address these issues, this study systematically optimized the furnace structure by tuning pipe diameter, tilt angle, and porous media height. Numerical simulations of 216 models were conducted to evaluate the effects of these parameters on axial velocity, turbulence intensity (quantified by the vortex criterion Q > 1), and reactant concentration uniformity. The results showed that pipe diameters below 70 mm increased the mean axial velocity by 8-fold compared to larger diameters, whereas tilt angles of 15° and porous media heights of 60–80 mm yielded limited velocity enhancements of only 2%. Pipe diameter was identified as the dominant factor governing flow stability, inducing up to a 300% variation in the volume fraction of Q > 1, with minimal turbulence observed at the maximum diameter. In contrast, adjustments to tilt angle and porous media height had weaker effects, altering the Q > 1 volume fraction by 26% and 5%, respectively. Smaller pipe diameter (70–80 mm) also optimized TaCl₅ concentration uniformity; tilt angles between 0° and 30° showed negligible influence, while porous media height exhibited no definitive trend. Guided by the practical priorities of process evaluation, a multi-objective optimization was performed. The globally optimal structural parameters were determined to be a pipe diameter of 70 mm, a tilt angle of 15°, and a porous media height of 60 mm, which comprehensively balance deposition uniformity, process stability, and deposition efficiency. These findings establish pipe diameter as the pivotal factor for deposition homogeneity and provide a reference scheme for the structural design of industrial tantalum deposition furnaces and lay a foundation for subsequent multi-physics coupling studies and experimental validation. Full article

The increase in delay-sensitive application tasks requires heterogeneous edge clusters to maintain low online latency and energy efficiency without relying on rigid scheduling policies. To address this, we propose HERO (Hybrid Energy-aware Ranking and Optimization), a lightweight collaborative scheduling framework. HERO utilizes a perturbation-based communication-aware multi-layer perceptron (MLP) predictor to quantify global time sensitivity and discover latent time slack in non-critical paths. A hybrid budget mechanism then converts this slack into customized DVFS decisions. These decisions are based on the inherent computational load and topological criticality to optimize energy consumption. A communication-aware hole-filling strategy dynamically recovers sporadic idle times fragmented by heterogeneous communication overhead. Extensive simulations were conducted across varying DAG depths, parallelism levels, and system utilizations. Compared to state-of-the-art algorithms (NSGA-II, SSA, TOM, and DPMC), HERO reduced the completion time by an average of 10.89% under high-density topologies, and achieved up to 4.04% energy savings across varying task depths. Full article

Electrical Impedance Tomography (EIT) is a promising non-invasive sensing technique, yet its practical application in resource-constrained environments is often limited by the high computational cost of inverse image reconstruction. To address this challenge, we focus on specific sensing objectives rather than full image recovery. In this study, we propose a lightweight, task-oriented inference framework for object localization in EIT that bypasses the need to solve computationally expensive inverse reconstruction problems. This approach addresses the high computational demands and hardware complexity of conventional iterative methods, which often hinder real-time monitoring in resource-constrained edge computing environments. Training datasets were generated via finite element method (FEM) simulations for Opposite and Adjacent current injection configurations. A feedforward neural network was developed to independently estimate the radial and angular object positions as probability distributions. Our systematic evaluation revealed that the localization performance depends on the injection configuration and model depth; notably, the Opposite method achieved perfect classification accuracy (1.00) for radial estimation with an optimized architecture of four hidden layers, whereas the Adjacent method exhibited higher ambiguity. Results quantitatively evaluated using the Wasserstein distance show that the Opposite configuration produces more localized, unimodal probability distributions than the Adjacent configuration by utilizing current fields that traverse the entire domain. Compared with existing image-based reconstruction methods, including the conventional electrical impedance tomography and diffuse optical tomography reconstruction software (EIDORS ver.3.12), the proposed framework reduced energy consumption from 3.09 to 0.96 Wh, demonstrating an approximately 70% improvement in energy efficiency while maintaining a high localization accuracy without the need for iterative Jacobian updates. This task-oriented framework enables reliable, high-speed, and energy-efficient localization, making it well-suited for low-power EIT applications in mobile and embedded sensor systems. Full article

Maritime search and rescue (SAR) is a time-critical public safety mission that increasingly relies on unmanned vehicles to localize persons overboard. However, reliable onboard perception is challenged by extreme scale variation and heavy sea clutter under strict latency and compute budgets. We present R-DET, a deployment-oriented end-to-end Transformer detector built on the RT-DETR paradigm, featuring three rescue-oriented designs: (i) a lightweight backbone (Rescue-Net) preserving multi-scale cues, (ii) a bounded-cost global-context module (Rescue Attention) suppressing sea clutter, and (iii) an efficient fusion module (Rescue-FPN) injecting high-resolution details for tiny targets. We further introduce MarineRescue-8K, a benchmark collected from real maritime operations with a mission-aligned ignore region protocol that reduces the influence of non-critical clutter during optimization and evaluation. On MarineRescue-8K, R-DET achieves 84.1% mAP@0.5 with only 14.5 M parameters at 63.2 FPS (RTX 2080 SUPER), demonstrating a favorable accuracy–efficiency trade-off for deployment-oriented maritime SAR perception. Full article

This study presents experimental modal analysis of an ultra-lightweight composite structure representative of UAV application and to evaluate the suitability of different testing approaches for reliable identification of its dynamics characteristics. The investigated structure is a winglet made of carbon fiber reinforced polymer (CFRP) with a lightweight foam core. The experiment was based on impact hammer excitation combined with triaxial accelerometer measurements. Modal tests were performed under three different boundary conditions: free–free suspension using elastic cords, free–free approximation using compliant foam support, and fixed conditions reflecting the operational mounting of the winglet. The results confirm that boundary conditions constitute the dominant factor governing the dynamic response. Transition from free–free to fixed support shifted the dominant bending modal frequency from 331.5 Hz (single-sided response) and 329.9 Hz (double-sided response) 421.2 Hz in the fixed configuration, demonstrating a frequency increase of nearly 27%. Reciprocity and double-sided measurements revealed measurable frequency deviations (e.g., 116.3 Hz to 117.6 Hz) attributed to accelerometer mass loading and geometric misalignment. The 1 g triaxial accelerometer mass was shown to be non-negligible relative to the modal mass of the structure, producing observable shifts in higher-order modes. Full article

Illegal drone intrusion near airport runways poses a critical threat to civil aviation safety, creating an urgent need for runway-side vision systems that can detect intruding UAVs early enough for safety warning and collision-risk mitigation. However, the development of such detectors is severely hindered by the scarcity of annotated real-world data in this high-security scenario. To address this bottleneck, we present SynthAirDrone, the first high-fidelity synthetic dataset for UAV intrusion detection in airport runway environments, together with an intelligent data generation framework integrating scene-aware placement and multi-criteria quality assessment. The proposed method uses sky-region segmentation to guide physically plausible drone placement, and combines perspective-aware scaling, Poisson image editing, and a four-dimensional quality scoring system—covering sky overlap, lighting consistency, size plausibility, and edge continuity—to improve visual plausibility and semantic consistency. The resulting dataset comprises 6500 high-quality images, all annotated in YOLO-compatible format. Using the lightweight YOLOv11n model, we show that models trained solely on SynthAirDrone exhibit non-trivial cross-domain transfer to Anti-UAV, while mixed training with limited real data provides the strongest real-world performance under the present setting. Ablation studies further confirm that a quality threshold of $\tau =0.6$ achieves the best trade-off between diversity and fidelity. Overall, this work delivers a reproducible and efficient synthetic data solution for UAV detector development in high-security, data-scarce airport-runway scenarios. Full article

Background: Myocardial ischemia (MI) is a major cause of morbidity and mortality worldwide and requires timely and reliable detection. Although Spin-Exchange Relaxation-Free (SERF) magnetocardiography (MCG) provides femtotesla-level sensitivity for identifying non-linear cardiac repolarization anomalies, its clinical deployment is currently impeded by the computational bottlenecks inherent to portable edge platforms. Methods: We propose a “Sensor-to-Image” Edge-AI framework that links quantum sensing with computer vision. Single-channel SERF-MCG signals from a large cohort of 2118 subjects (1135 Healthy, 983 Ischemia) were transformed into phase-space images using three distinct encoding modalities: Recurrence Plots (RP), Gramian Angular Summation Fields (GASF), and Markov Transition Fields (MTF). These visual representations were subsequently analyzed by a streamlined MobileNetV3-Small architecture, optimized for low-latency inference. To maximize diagnostic precision, an adaptive weighted fusion mechanism was engineered to combine the chaotic specificity captured by RP with the morphological sensitivity of GASF through a validation-optimized fixed global weighting strategy. Results: In our experiments, the fusion model achieved an Area Under the Curve (AUC) of 0.865, which was higher than the 1D-CNN baseline (AUC 0.857) and the single-modality models. Notably, the fusion strategy significantly elevated sensitivity to 88.3% while maintaining a specificity of 66.5%. Although specificity is moderate, this trade-off prioritizes high sensitivity to minimize false negatives in pre-hospital screening scenarios. The average inference time was 4.7 ms per sample on a standard CPU, suggesting suitability for real-time Point-of-Care (PoC) scenarios under further on-device validation. Conclusions: The results suggest that multi-view phase-space fusion can capture subtle spatio-temporal changes associated with ischemia. The proposed lightweight framework may support the development of portable SERF-MCG systems with embedded AI screening. Full article

To address the challenges of high miss detection rates and accuracy degradation in UAV-based insulator defect detection—primarily stemming from complex background interference and the loss of fine-grained features—this paper presents an optimized lightweight detection framework based on an improved YOLOv8 model. The integration of a Spatial-to-Depth Convolution (SPDConv) module strengthens the extraction of fine-grained features for microscopic defects, while the incorporation of an SCConv module suppresses computational redundancy, leading to a 2.80% accuracy improvement. This architecture is further enhanced by a Channel and Spatial Reconstruction Attention Module (CSRAM), which dynamically prioritizes target-related regions and mitigates noise from vegetation and infrastructure. To improve regression robustness against low-quality annotations and blurred boundaries, a Focal-WIoU loss function utilizing a dynamic non-monotonic focusing mechanism is introduced. Experimental results on complex insulator datasets demonstrate that the proposed model achieves an mAP@0.5 of 91.75% and an mAP@0.5:0.95 of 59.86%, representing a 4.40% and 5.04% increase over the YOLOv8 baseline, respectively. Notably, while maintaining a lightweight profile with only 11.14 M parameters and 28.66 G FLOPs, the model achieves a high inference speed of 376.56 FPS, effectively enabling precise multi-scale defect recognition under extreme operational conditions. Full article

Background/Objectives: The human brain is responsible for controlling various physiological functions, and hence, the presence of tumors in the brain is a major concern in the medical field. The correct identification and categorization of tumors in the brain using Magnetic Resonance Imaging (MRI) is a major requirement for the diagnosis and treatment of a tumor. The proposed research will focus on designing a CNN model that is optimized for tumor image classification. Methods: This research proposes an optimized CNN model featuring strategically placed dropout layers and hyperparameter optimization. This study uses a dataset of 640 MRI scans (320 tumor and 320 non-tumor) collected from a private hospital in Saudi Arabia. The proposed method utilizes a learning rate of 0.001 in combination with the Adam optimizer to ensure stable and efficient convergence. Its performance was benchmarked against established architectures, including VGG-19, Inception V3, ResNet-10, and ResNet-50, with evaluation based on classification accuracy and computational cost. Results: The experimental results show that the optimized CNN proposed in this work performs much better than the deeper architectures. The network reached a maximum training accuracy of 97.77% and a final test accuracy of 95.35% with a small test loss of 0.2223. The test accuracy of the optimized VGG-19 and Inception V3 networks was much lower, with a training time per epoch that was several orders of magnitude higher. The validation stability of the proposed network was high (92.25% to 95.35%) during the final stages of training. Conclusions: The conclusion drawn from this study is that hyperparameter optimization and strategic regularization are more advantageous for tumor classification using MRI images than the mere depth of the model. The accuracy of 95.35% with low computational complexity makes this lightweight CNN model a feasible solution for real-time applications. Full article

Brain tumor classification from magnetic resonance imaging, which is also known as MRI, plays a sensitive role in computer-assisted diagnosis systems. In recent years, deep learning models have achieved high classification accuracy. However, their sensitivity to adversarial perturbations has become an important reliability concern in medical applications. This study suggests a robust brain tumor classification framework that combines non-negative matrix factorization (NNMF or NMF), lightweight convolutional neural networks (CNNs), and diffusion-based feature purification. Initially, MRI images are preprocessed and converted into a non-negative data matrix, from which compact and interpretable NNMF feature representations are extracted. Statistical metrics, including AUC, Cohen’s d, and p-values, are used to rank and choose the most discriminative components. Then, a lightweight CNN classifier is trained directly on the selected feature groups. To improve adversarial robustness, a diffusion-based feature-space purification module is introduced. A forward noise method followed by a learned denoiser network is used before classification. System performance is estimated using both clean accuracy and robust accuracy under powerful adversarial attacks created by AutoAttack. The experimental results show that the proposed framework achieves competitive classification performance while significantly enhancing robustness against adversarial perturbations. The findings presuppose that combining interpretable NNMF-based representations with a lightweight deep approach and diffusion-based defense technique supplies an effective and reliable solution for medical image classification under adversarial conditions. Full article

This paper presents a lightweight MATLAB-based framework with a graphical interface for modeling, 3D simulation, trajectory generation, and experimental validation of a 6-DOF industrial robot. The platform integrates kinematic modeling using the rigidBodyTree structure, animated visualization, and both predefined and user-defined trajectory planning within a unified environment. A central aspect of the proposed approach is the implementation of a ROS-compatible TCP/IP communication protocol that avoids the need for a full ROS core installation while preserving compatibility with ROS-Industrial standards. This enables bidirectional data exchange between MATLAB and the robot controller within a simplified architecture. Communication performance tests indicate round-trip latency in the tens-of-milliseconds range and consistent StateServer update rates, supporting monitoring, trajectory execution, and digital twin synchronization in non-real-time conditions. Experiments conducted on an ABB IRB120 robot demonstrate a close correspondence between simulated and real motion, with RMSE below 0.0075 rad and MAE below 0.0065 rad across all joints. All data are stored in JSON format to support reproducibility and further analysis. By integrating simulation and real robot execution within a modular architecture, the proposed framework provides a practical tool for education, rapid prototyping, and experimental research in industrial robotics, while offering a basis for future extensions toward advanced control strategies and digital twin applications. Full article

Knee joint moment is an important biomechanical parameter for sports assessment, rehabilitation monitoring, and human–machine interaction. However, direct measurement is often restricted to laboratory-based settings. Surface electromyography (sEMG) offers a non-invasive alternative for indirect joint moment estimation, but many existing deep learning models remain too computationally demanding for potential wearable edge deployment. To address this gap, this study proposes Topo2DCNN-LSTM, a lightweight two-dimensional (2D) convolutional neural network model, designed for sagittal-plane knee flexion moment estimation. The model used a feature-based sequential representation, transforming raw sEMG signals into compact Root Mean Square (RMS) feature frames. The input was processed by a lightweight 2D convolutional neural network (CNN) encoder and paired with long short-term memory (LSTM) units. The model was trained on a public walking dataset of healthy subjects with synchronized sEMG and joint kinetics at two treadmill speeds. When compared with selected deep learning baselines, the quantized model achieved a mean RMS Error of 0.088 ± 0.020 Nm/kg at 1.2 m/s and 0.114 ± 0.034 Nm/kg at 1.8 m/s. On a SparkFun Thing Plus–SAMD51, it achieved an average inference latency of 28 ms using 71,316 bytes of random-access memory (RAM) and 257,172 bytes of flash. These results support its use as a proof of concept for personalized unilateral knee moment estimation with isolated on-device inference feasibility under resource-constrained and limited walking conditions. Full article

The urgent global need for sustainable infrastructure drives the demand for high-value buildings and waste removal. This paper studies the feasibility of using recycled foam concrete aggregate (FCA) as a substitute for natural coarse aggregate (NCA) in concrete and studies its impact on rheology, mechanical degradation, shear resistance, and the full-range replacement ratio (0–100). The experimental results show that the monotonic change in the workability of fresh concrete determines the lubrication threshold at 60% replacement, which is driven by the volume proportion effect. Beyond this value, capillary suction dominates, and the viscosity rises rapidly. From a mechanical perspective, the porous structure of FCA is conducive to “internal curing” so that moisture is released from the drying interface, but it also becomes a source of defects that change the fault topology. Specifically, the critical transition of the shear failure mode shifts from the debonding of the interface to the crushing of the cross-particle aggregate. At this time, the shear capacity decreases substantially, experiencing a reduction of 71.8% when completely replaced. There is a strong correlation between ultrasonic pulse velocity (UPV), rebound number, and compressive strength, and a multivariate nonlinear regression model (R² > 0.85) with non-destructive strength prediction is ultimately obtained. Based on the balance between mechanical capacity and resource cyclability, an optimal alternative zone of 20% to 40% is proposed. This work not only provides a mechanism for multi-scale coupling between pore structure and structural properties but also provides a data-driven method for the safety assessment of lightweight recycled aggregate concrete (RAC). Full article

Deep learning models represent one of the most advanced and effective approaches in predictive modeling. Their hierarchical architectures enable the extraction of complex, non-linear feature relationships and the identification of latent patterns within data, making them highly suitable for tasks involving high-dimensional or unstructured inputs. However, these models are computationally demanding, requiring significant processing resources and time. Furthermore, their predictive performance is largely contingent upon the availability of large-scale datasets. In this study, a Deep Green Framework is employed for the prediction of two computer vision tasks. CIFAR-10 and CIFAR-00 have been taken for image classification. Fifteen convolutional neural network (CNN) variants categorized into light-weight and heavy-weight are trained for the prediction of these two datasets. Based on energy footprint, time, memory usage, Top-1 accuracy, Top-3 accuracy, model size, and model parameters. The study highlights that MobileNetV3-Small produces the best outcomes when compared to other trained models having low task latency and higher efficiency, making it highly suitable for edge environments where resources are scarce. Full article