Search Results (28)

Adversarial patch attacks pose a tangible physical-world threat to traffic sign recognition in autonomous driving systems. Current state-of-the-art defenses based on image reconstruction require dual-model deployment and add per-frame inference latency, making them impractical for resource-constrained embedded platforms such as mass-produced ADAS systems and aftermarket dashcams. This paper proposes a two-component defense that separates detection from mitigation. PatchGuard-Freq leverages frequency-domain analysis to detect attacked images with high accuracy, while adversarial fine-tuning enables the detector to recover most of its detection performance under attack without adding any inference module or architectural change. Experimental results show that the approach is effective in the latency regime targeted by this study: on the evaluated stop-sign and nine-class LISA benchmarks, under the evaluated detection placement (a fresh $110\times 110$ patch at a uniformly random position), the detector achieves AUC = 1.0 with zero false positives across all four dataset configurations and all combined frequency variants, while the frequency-only arm of the ablation separates the data only where the patch covers almost the entire input, and adversarial fine-tuning recovers attacked mAP@0.5 on the COCO stop-sign test set from 19.4% to 68.4% on the $110\times 110$-patch configuration while degrading clean mAP by only about 0.7 points. We further show that PatchGuard-Freq is vulnerable to adaptive (defense-aware) attacks and introduce defense-aware training that restores detection of such attacks to 100% without increasing false alarms. This work characterizes the complementary relationship between reconstruction-based and robustness-based paradigms in the accuracy–efficiency design space under the evaluated conditions: the former suits compute-unconstrained scenarios while the latter serves latency-constrained deployments. All quantitative results were obtained on desktop-grade GPUs; embedded-platform latency, memory, and energy were not measured, and the embedded discussion is limited to hardware-independent parameter and FLOP counts. Full article

This paper presents a real-time browser-based platform for thermohydraulic characterization of a compact laboratory heating system, developed using the PolyVR research-grade virtual reality engine. Experimental measurements are retrieved at 1 Hz from a cloud-based database and processed via browser-native computational framework that continuously performs thermophysical modeling, hydraulic analysis and energy balance evaluation. The system calculates the rate of heat transfer ($h$), overall heat transfer coefficient ($U$), dimensionless numbers ($Re, Pr, Gr, Nu$), pump performance, heater efficiency and cumulative thermal energy. PolyVR provides the immersive environment in which the partial digital twin functionality is integrated alongside the browser-based thermohydraulic calculations. The whole system includes support for animations regarding flow diagrams, valve state indicators, thermal field visualization and manipulation of system elements. The system architecture is designed to work on desktops, head-mounted devices, as well as in CAVE (cave automatic virtual environment) systems with remote connection made possible via using ngrok tunnels. The experiments were separated into three categories (steady-state, dynamic and validation). Steady-state and dynamic datasets show that the browser computation with PolyVR achieves high-fidelity thermohydraulic analysis similar to that done in laboratory settings. The steady-state and transient datasets illustrate that browser-based computation provides highly accurate thermohydraulic simulation close to that of the laboratory reference computations. For all experiments performed on the platform, the deviation of measurements does not exceed $\pm$0.5 $\mathrm{K}$ in temperature, $\pm$5$\%$ in flow rate and $\pm$1$\%$ in pressure. The energy balance is closed with a deviation of $\pm$2–3$\%$. Full article

Traditional engineering practical education faces high equipment expenditure, limited hands-on practice, material-resource consumption, and inequitable access to high-quality training, impeding progress toward UN SDG 4 (Quality Education) and SDG 9 (Industry, Innovation, and Infrastructure). To address these bottlenecks, this paper constructs a closed-loop desktop VR-blended learning system (VBLS) for diesel engine assembly using Unity3D and high-fidelity 3D models of seven core engine subsystems. Guided by experiential learning and cognitive load theories, the platform supports pre-lab structural preview, dual-mode assembly, and post-training online knowledge assessment. An exploratory post-test comparison was conducted between two intact classes (n = 30 per class): one class used VR-blended teaching and the other received conventional lab instruction. The blended group achieved a numerically higher average score (81.47 vs. 77.83) with a moderate effect size (Cohen‘s d = 0.48), 95% CI [−0.33, 7.61], with 63% scoring above 80 versus 43% in the control group. Questionnaire feedback (n = 30) from the blended-teaching group showed satisfactory usability, self-reported learning engagement, and students’ self-perceived raised awareness of sustainable engineering practices. Although virtual simulation avoids engine-related component wear and physical consumable use, these sustainability advantages stem from system design and require further empirical validation. Given experimental limitations, this study provides a replicable simulation-based prototype with prospective value for sustainable engineering education through lower training expenditure and improved accessibility. Full article

Commercial pacemaker (PCM) analyzers are often expensive, proprietary, and difficult to adapt for experimental biomedical research and educational applications. This work presents a low-cost modular platform for the generation, acquisition, and real-time analysis of pacemaker-related electrical signals. The proposed system consists of two independent printed circuit boards: a digital-to-analog (DAC) board for generation of controlled atrial and ventricular test waveforms and an analog-to-digital (ADC) board for multi-channel signal acquisition and wireless data transmission. A dedicated Qt-based desktop application provides real-time visualization and storage of the acquired signals. Experimental validation was performed using a single commercial dual-chamber pacemaker operating in the DDD mode. For the DAC subsystem, pacing-rate errors remained below 2% over the investigated range of 60–120 BPM, with coefficients of determination exceeding 0.99998 between programmed and measured pacing rates. The ADC subsystem demonstrated relative amplitude errors ranging from 0.96% to 7.19% over the investigated input range of −1000 to −2000 mV. For a programmed atrioventricular delay of 200 ms, the ADC-derived delay was 205.53 ± 1.24 ms, corresponding to a relative error of 2.77%. Combined DAC–ADC operation further demonstrated generation of a controlled atrial test signal, pacemaker sensing and ventricular pacing response, and subsequent acquisition of the response by the ADC subsystem. The developed platform provides a configurable and modular experimental environment in which signal generation and acquisition can be operated either independently or jointly. Its low implementation cost, wireless data transmission, and customizable hardware and software architecture make it suitable for laboratory research, education, and prototype development involving cardiac pacing systems. Full article

Twin Rotor Multi-Input Multi-Output (TRMS) platforms combine strong aerodynamic cross-coupling, gravitational loading on the vertical axis, friction-dominated horizontal dynamics, and systematic mismatch between idealised models and laboratory hardware. The platform provides only two optical encoders, so the angular rates and the rotor states are unavailable for feedback. This paper presents an observer-based output-feedback architecture that addresses both difficulties. A high-gain observer built on the fully coupled six-state model, including the gyroscopic terms that the control design cannot retain, reconstructs the four unmeasured states from the two encoder angles. The reconstructed states drive a Hybrid Backstepping–Super-Twisting (B-STA) controller in which a second-order continuous sliding mode is embedded at the final recursive step through a composite surface. Because backstepping requires strict-feedback structure, which the centralised coupled model does not possess, the controller is synthesised on a decentralised design model and the residual coupling is rejected as a matched perturbation of the sliding variable. Closed-loop behaviour is analysed as a three-stage cascade covering observer error, sliding variable, and tracking error, yielding practical stability under bounded residuals with an explicit input-to-state gain. The residual bounds are evaluated numerically from the actuator saturation limit and the identified coefficients rather than assumed, and the resulting figures are shown to predict the marked difference in sliding-variable behaviour observed between the two axes. A second architecture applies a windowed Grey Wolf Optimiser (B-GWO) to the backstepping gains, in which each candidate is applied to the plant for a fixed test window, scored on its own accumulated integral of time-weighted absolute error, and followed by a settle window at the incumbent best. We prove that this windowing is a requirement rather than a convenience: a fitness evaluated at a single sample is common to all candidates, cancels from the population ranking, and reduces the search to the minimiser of its own regularisation term. Both schemes are implemented on a physical TRMS through a Simulink Desktop Real-Time interface at a control period of $10\mathrm{ms}$. On a $100\mathrm{s}$ experimental run, B-STA attains a pitch tracking error of $0.0318\mathrm{rad}$ RMS, $7.94\%$ of the reference amplitude, and the lowest control energy on both axes among the strategies compared, reducing pitch control energy by $72.9\%$ relative to a first-order Backstepping–Sliding Mode baseline recorded on the same interface. Numerical disturbance rejection tests on the fully coupled model confirm the mechanism: under a matched actuator step the super-twisting integrator state migrates to a new steady level that cancels the disturbance, driving the residual pitch error to $2\times {10}^{-4}\mathrm{rad}$, whereas the same recursive law without the second-order injection retains a permanent offset of $0.28\mathrm{rad}$. Full article

Public speaking training and public speaking anxiety (PSA) treatment increasingly rely on technology-mediated systems, including web, mobile, desktop, and immersive virtual reality (VR) tools. This comprehensive review identifies and maps information and communication technology (ICT)-based public speaking interventions for educational training and anxiety-oriented treatment, focusing on platform choice, audience simulation, feedback timing, physiological and behavioral sensing, therapeutic framing, practitioner involvement, and evaluation methods. A PRISMA-inspired process documented identification and screening across Scopus, Web of Science, PubMed, IEEE Xplore, and ERIC for English-language journal articles and conference papers published between 1 February 2015 and 1 February 2025. From 6602 records, 82 participant-validated studies were included. No formal risk-of-bias assessment was conducted. VR accounted for 82.93% of interventions, while research prototypes comprised 72.0% of the evidence base, demonstrating the field’s strong emphasis on immersive and experimental development. At the same time, 64.6% of interventions provided no automated feedback and 36.6% used no physiological or behavioral sensing, highlighting opportunities for more responsive and data-informed systems. The findings can guide the development of future public-speaking training and treatment systems by highlighting recurring design components, promising implementation patterns, and priorities for stronger comparative validation. Full article

To address the sampling misalignment and detail loss caused by fixed-grid downsampling for small-scale defects, as well as the insufficient differentiated modeling and interaction of defect details and structural context in UAV-acquired power-line images, an enhanced lightweight YOLOv8n-based framework for power-line defect detection is developed. First, a content-adaptive downsampling (CAD) module is developed to predict input-dependent sampling offsets and normalized aggregation weights and to perform differentiable resampling. Combined with local-global interactive depthwise separable convolution, CAD improves the preservation of small-object details while maintaining relatively low computational complexity. Second, a dynamic subspace gated exchange (DSGE) module is proposed to adaptively partition features into a high-frequency detail subspace and a low-frequency structural subspace according to the input content. Heterogeneous branches and bidirectional gated exchange are then employed to jointly model fine-grained details and structural context. In addition, the lightweight mixed local channel attention (MLCA) mechanism is incorporated in the detection head as an auxiliary feature-enhancement component. Experimental results show that the proposed model achieves mAP@0.50 and mAP@0.50:0.95 values of 92.3% and 62.9%, respectively, outperforming the compared models under the current evaluation protocol. With 1.90 M parameters and 5.6 G FLOPs, the model reaches an inference speed of 134.7 FPS on the desktop GPU platform, demonstrating that content-adaptive sampling and dynamic detail–structure interaction can improve small-defect detection and complex-background suppression while maintaining relatively low model complexity. Full article

Remote photoplethysmography (rPPG) enables contactless estimation of cardiovascular signals from video, but most existing studies assume a fixed, stationary camera. This study investigates the feasibility of performing real-time moving-average rPPG (MA-rPPG) using a drone-mounted camera, where platform motion, vibration, and viewing distance introduce additional challenges. Building on our previously validated real-time MA-rPPG smart mirror platform, we reuse the smart mirror interface as a unified frontend for visualization, synchronization, and logging while adapting the MA-rPPG pipeline to operate on live video streamed from an off-the-shelf DJI Tello micro-drone. Feasibility experiments were conducted with 10 participants under controlled indoor lighting and constrained flight conditions, where the drone maintained a stable hover in front of a standing subject and facial video was processed in real time to estimate heart rate from a forehead region of interest. To avoid cross-modality bias and clarify the effect of the aerial imaging platform, drone-derived MA-rPPG outputs were compared against a fixed desktop-camera MA-rPPG reference using the same trained model, enabling a controlled, like-for-like evaluation. The results indicate that continuous heart-rate estimation from a drone camera is feasible in our controlled hover-only setup, while agreement tended to vary with hover stability and effective facial resolution. This work is presented strictly as a feasibility-stage investigation and does not claim clinical validity. The findings provide an experimental baseline and operating-envelope insight for future motion-robust rPPG on mobile and aerial health-sensing platforms. Full article

High-intensity focused ultrasound (HIFU) thermal therapy exploits concentrated acoustic energy to ablate pathological tissues with millimetric precision deep in the body. Accurate prediction of thermal effects is essential for tuning the treatment shooting parameters—such as source pressure amplitude and sonication time—as well as for maximizing efficacy and preserving surrounding healthy tissue. This study presents a computational model developed in COMSOL Multiphysics to simulate the physics of HIFU thermal phenomena, accounting for acoustic propagation and heat diffusion in biological tissues. The model was validated through experimental tests on ex vivo chicken breast tissue within a robotic ultrasound-guided HIFU (USgHIFU) platform, with lesion dimensions serving as the primary metric for validation. Building upon the validated simulation, we define a polynomial-based model that analytically predicts lesion dimensions based on the input shooting parameters. This approach significantly reduces the COMSOL computational cost and execution time, making it well-suited for integration into a real-time treatment planning workflow for clinical use. A desktop application implementing the inverse formulation of the polynomial model was developed, allowing shooting parameters to be computed from target lesion dimensions through a simple and intuitive interface. By enabling a rapid estimation of lesion size, this solution supports a more standardized strategy for non-invasive oncological therapies. Full article

External spur gear pumps are widely employed in hydraulic systems for their simplicity, efficiency, and cost-effectiveness; however, the conventional CAD-based methods used to design these components remain time-intensive and prone to inconsistencies, particularly during iterative structural analysis and optimization. To address these limitations, this study presents a parametric, automated design platform for external spur gear pumps by integrating the SOLIDWORKS API with a custom C# desktop application. The tool automatically generates 3D solid models and facilitates strength analysis and housing wall-thickness optimization through a user-friendly interface. Geometric and hydraulic inputs are used to define model parameters and simulation conditions, into which an empirical pressure distribution model, derived from prior experimental data, is embedded to establish accurate boundary conditions. This integrated configuration enables structural analysis in SOLIDWORKS Simulation, allowing systematic variation of wall thickness and geometry within prescribed constraints. Results from the case study yielded a configuration achieving an 18.42% reduction in housing mass while maintaining a minimum factor of safety of 3.948 and a maximum deformation of 0.012 mm. The system effectively reduces design time, improves repeatability, and minimizes human error, while demonstrating robustness across varied design scenarios. Overall, the proposed approach provides a practical and efficient solution for automated design and optimization of external gear pumps, supporting parametric flexibility and advancing CAD/CAE integration in hydraulic component design workflows. Full article

Harvesting winter jujubes is a key step in production, yet traditional manual approaches are labor-intensive and inefficient. To overcome these challenges, we propose SCC-YOLO, a lightweight method for winter jujube detection, 3D localization, and cross-platform deployment, aiming to support intelligent harvesting. In this study, RGB-D cameras were integrated with an improved YOLOv11 network optimized by ShuffleNetV2, CBAM, and a redesigned C2f_WTConv module, which enables joint spatial–frequency feature modeling and enhances small-object detection in complex orchard conditions. The model was trained on a diversified dataset with extensive augmentation to ensure robustness. In addition, the original localization loss was replaced with DIoU to improve bounding box regression accuracy. A robotic harvesting system was developed, and an Eye-to-Hand calibration-based 3D localization pipeline was implemented to map fruit coordinates to the robot workspace for accurate picking. To validate engineering applicability, the SCC-YOLO model was deployed on both desktop (PyTorch and ONNX Runtime) and mobile (NCNN with Vulkan+FP16) platforms, and FPS, latency, and stability were comparatively analyzed. Experimental results showed that SCC-YOLO improved mAP by 5.6% over YOLOv11, significantly enhanced detection precision and robustness, and achieved real-time performance on mobile devices while maintaining peak throughput on high-performance desktops. Field and laboratory tests confirmed the system’s effectiveness for detection, localization, and harvesting efficiency, demonstrating its adaptability to diverse deployment environments and its potential for broader agricultural applications. Full article

Malware remains one of the most critical threats in the digital ecosystem, targeting both mobile and desktop platforms. Traditional signature-based detection techniques face limitations in identifying polymorphic and zero-day variants. This study proposes a static analysis-based approach using machine learning classifiers, focusing on Random Forest, Decision Tree, and Support Vector Machine (SVM). The dataset was collected from MalwareBazaar, and static features such as PE headers, entropy, and API calls were extracted. Experimental results show that SVM achieved the highest accuracy at 53.2%, while Decision Tree obtained the best F1-score at 61.1%, indicating stronger recall capabilities. Random Forest provided balanced results across all metrics with a shorter training time of 0.23 s, highlighting its efficiency for practical use. These findings demonstrate that while no single classifier dominates across all metrics, Random Forest offers a trade-off between performance and efficiency, making it suitable for large-scale static malware detection systems. Full article

In complex marine environments, ramp-based recovery systems for autonomous underwater vehicles (AUVs) often encounter engineering challenges such as reduced docking accuracy and success rate due to disturbances in the capture window attitude. In this study, a desktop-scale physical experimental platform for recovery compensation was designed and constructed. The system integrates attitude feedback provided by an attitude sensor and dual-motor actuation to achieve active roll and pitch compensation of the capture window. Based on the structural and geometric characteristics of the platform, a dual-channel closed-loop control strategy was proposed utilizing midpoint tracking of the capture window, accompanied by multi-level software limit protection and automatic centering mechanisms. The control algorithm was implemented using a discrete-time PID structure, with gain parameters optimized through experimental tuning under repeatable disturbance conditions. A first-order system approximation was adopted to model the actuator dynamics. Experiments were conducted under various disturbance scenarios and multiple control parameter configurations to evaluate the attitude tracking performance, dynamic response, and repeatability of the system. The results show that, compared to the uncompensated case, the proposed compensation mechanism reduces the $MSE$ by up to 76.4% and the $MaxAE$ by 73.5%, significantly improving the tracking accuracy and dynamic stability of the recovery window. The study also discusses the platform’s limitations and future optimization directions, providing theoretical and engineering references for practical AUV recovery operations. Full article

In microscopic imaging, the key to obtaining a fully clear image lies in effectively extracting and fusing the sharp regions from different focal planes. However, traditional multi-focus image fusion algorithms have high computational complexity, making it difficult to achieve real-time processing on embedded devices. We propose an efficient high-resolution real-time multi-focus image fusion algorithm based on multi-aggregation. we use a difference of Gaussians image and a Laplacian pyramid for focused region detection. Additionally, the image is down-sampled before the focused region detection, and up-sampling is applied at the output end of the decision map, thereby reducing 75% of the computational data volume. The experimental results show that the proposed algorithm excels in both focused region extraction and computational efficiency evaluation. It achieves comparable image fusion quality to other algorithms while significantly improving processing efficiency. The average time for multi-focus image fusion with a 4K resolution image on embedded devices is 0.586 s. Compared with traditional algorithms, the proposed method achieves a 94.09% efficiency improvement on embedded devices and a 21.17% efficiency gain on desktop computing platforms. Full article

This paper presents a real-time remote-control platform for small wind turbines (SWTs) equipped with a permanent magnet synchronous generator (PMSG). The proposed system integrates a DC–DC boost converter controlled by an Arduino^® microcontroller, a Raspberry Pi^® hosting a WebSocket server, and a desktop application developed using MATLAB^® App Designer (version R2024b). The platform enables seamless remote monitoring and control by allowing upper layers to select the turbine’s operating mode—either Maximum Power Point Tracking (MPPT) or Power Curtailment—based on real-time wind speed data transmitted via the WebSocket protocol. The communication architecture follows the IEC 61400-25 standard for wind power system communication, ensuring reliable and standardized data exchange. Experimental results demonstrate high accuracy in controlling the turbine’s operating points. The platform offers a user-friendly interface for real-time decision-making while ensuring robust and efficient system performance. This study highlights the potential of combining open-source hardware and software technologies to optimize SWT operations and improve their integration into distributed renewable energy systems. The proposed solution addresses the growing demand for cost-effective, flexible, and remote-control technologies in small-scale renewable energy applications. Full article