Search Results (455)

Additive manufacturing has recently become a key enabling technology in industrial fields, ranging from customized products for everyday usage to aerospace applications and small-batch industrial tooling. The future prospects extend up to the biofabrication of human organs. Ensuring the quality and repeatability of this process requires a systematic and comprehensive investigation of the underlying physical phenomena. In particular, melt-pool evolution is a critical feature, since irregularities in its spatial profile can influence microstructural evolution and weaken the integrity of the manufactured part. Microscale defects arising from balling and keyhole phenomena, often associated with recoil pressure, can severely degrade the quality of the resulting scanned track. This paper reviews the current state of optical approaches for melt-pool characterization and feature monitoring relevant to industrial laser additive manufacturing for process control and quality improvement, with a special focus on pyrometry and high-speed imaging. A single high-speed camera was generally used in experiments for melt-pool feature extraction, but two cameras were used to bypass emissivity values, which are otherwise difficult to obtain. Mathematical models were introduced to provide complementary information about melt-pool features, while artificial intelligence algorithms were used in other cases to process optical information. New melt-pool imaging databases and classifiers are expected in the near future to enable fast selection of appropriate process parameter windows, eliminating costly trial-and-error experiments. Full article

Bio-inspired quadrupedal robots exhibit superior adaptability and mobility in unstructured environments, making them suitable for complex task scenarios such as navigation, obstacle avoidance, and tracking in a variety of environments. Visual perception plays a critical role in enabling autonomous behavior, offering a cost-effective alternative to multi-sensor systems. This paper proposes an image segmentation-guided visual tracking framework to enhance both perception and motion control in quadruped robots. On the perception side, a cascaded convolutional neural network is introduced, integrating a global information guidance module to fuse low-level textures and high-level semantic features. This architecture effectively addresses limitations in single-scale feature extraction and improves segmentation accuracy under visually degraded conditions. On the control side, segmentation outputs are embedded into a biologically inspired central pattern generator (CPG), enabling coordinated generation of limb and spinal trajectories. This integration facilitates a closed-loop visual-motor system that adapts dynamically to environmental changes. Experimental evaluations on benchmark image segmentation datasets and robotic locomotion tasks demonstrate that the proposed framework achieves enhanced segmentation precision and motion flexibility, outperforming existing methods. The results highlight the effectiveness of vision-guided control strategies and their potential for deployment in real-time robotic navigation. Full article

Background: Artificial intelligence-based computer-aided detection (AI-CAD) systems are increasingly being used in endovascular practice to support time-sensitive detection, triage and prioritization tasks in imaging and procedural workflows. Despite rapid technological advancements and expanding regulatory clearances, the translation to lasting clinical benefit varies. Objective: This narrative review synthesizes AI-CAD applications in endovascular interventions and proposes an evaluation-oriented framework to support responsible clinical translation; this framework emphasizes detection-specific metrics, external validation, bias-aware assessment, and workflow integration. Methods: A structured narrative review was conducted using targeted searches in PubMed, Google Scholar, and IEEE Xplore (2020–2026); this review was supported by an examination of US FDA device databases and citation tracking. Evidence was assessed using a pragmatic hierarchical classification framework based on regulatory status and validation rigor. Results: AI-CAD applications were mapped across four main endovascular domains: neurovascular interventions (e.g., large vessel occlusion triage), coronary interventions (CCTA-based stenosis detection and intravascular imaging support), aortic interventions/EVAR (endoleak detection and sac monitoring), and peripheral interventions (lesion detection and angiographic decision support). Across the domains, performance reporting was heterogeneous and often relied on retrospective, single-center assessments. Key barriers to clinical readiness included acquisition variability and dataset shift due to artifacts, limited multicenter validation, annotation variability, and human–AI workflow factors. Evaluation priorities included whether to assess at the lesion level or case level, false positive burden and calibration, external validation under real-world heterogeneity, and clinical impact measures such as treatment timing and procedural decision-making. Conclusions: AI-CAD systems hold significant potential for improving endovascular care; however, clinical readiness depends on rigorous, endovascular feature-specific assessment and transparent reporting, beyond retrospective accuracy. The proposed evidence level framework and assessment checklist provide practical tools for distinguishing mature technologies from research prototypes and guiding future validation, implementation, and post-market monitoring. Full article

Compared with single-radar systems, multi-radar systems generally achieve superior detection performance due to their spatial and frequency diversity. To further enhance multi-target tracking, this paper proposes a multi-radar distributed fusion algorithm aided by multi-feature information. Each radar computes its measurement-updated Labeled Multi-Bernoulli (LMB) posterior, and track association is performed using multi-feature information extracted from radar echoes, including Doppler frequency and signal-to-noise ratio (SNR), improving robustness in complex scenarios. Distributed fusion is then carried out via the Generalized Covariance Intersection (GCI) algorithm. Simulation results show that, compared with other fusion methods, the proposed approach achieves superior multi-target tracking accuracy while maintaining lower computational cost. Full article

On heavy-haul railways, ballast fouling progressively reduces ballast resistance, which in turn degrades the electrical performance of track circuits. To address this cascading issue, we propose a ground-penetrating radar (GPR)-based method for assessing ballast bed conditions and inverting ballast resistance $R_b$ continuously along the track. First, by integrating transmission line theory with Archie’s law, this paper establishes the mechanistic link between microscale dielectric deterioration of the fouled ballast and the macroscale electrical parameters of the track circuit. Next, we build a full-wave electromagnetic simulation model to extract two key GPR signal features: time-domain relative energy attenuation and frequency-domain spectral redshift. Recognizing the limitations of single-feature analysis, we introduce an adaptive weight-based multi-feature fusion algorithm to construct a comprehensive fouling index that quantifies the physical state of the ballast. Based on this index, we develop a quantitative mapping model between the fouling index (FI) and $R_b$, enabling continuous inversion of ballast resistance over the entire line. Our results show excellent agreement between the inverted $R_b$ profile and the theoretical ground truth, with the FI alarm threshold precisely corresponding to the critical safety limit of $R_b$ = 0.5 Ω km. This approach effectively overcomes the limitations of traditional discrete monitoring and provides a practical tool for predictive maintenance of track circuits. Full article

Single-object tracking in complex scenes faces challenges such as drastic target scale variation and strong background interference. To address these issues, an object tracking algorithm based on multi-scale attention and adaptive fusion is proposed. The method integrates a multi-scale attention module and an adaptive gated fusion module, enabling the adaptive mining of key features and dynamic adjustment of fusion weights across multi-level features. This effectively highlights target regions, suppresses redundant information, and enhances the model’s discriminative capability and robustness under complex backgrounds and occlusion. Experiments are conducted on the OTB100 and UAV123 datasets. Results show that, compared with the baseline model, the proposed algorithm improves the success rate and precision by 1.9% and 3.3%, respectively, on OTB100, and by 2.9% and 3.5%, respectively, on UAV123. Moreover, it achieves superior performance when facing typical challenging attributes such as occlusion, scale variation, and background clutter. In summary, the proposed algorithm enhances both tracking accuracy and robustness, offering a viable approach for object tracking under complex conditions. Full article

High-speed solid particles ejected during battery thermal runaway pose severe safety threats, yet their velocity measurement is hindered by high density, microscopic size, and intense glare. This study proposes a non-intrusive velocimetry framework that integrates an enhanced single-stage object detector with a structural similarity matching algorithm. The detector incorporates specialized feature extraction modules and a high-resolution layer to identify microscopic targets in extreme environments, while the matching algorithm employs adaptive direction constraints to ensure precise trajectory tracking. Experimental validation demonstrates that the framework achieves a mean average precision of 92.7% and supports real-time processing. The method successfully quantifies a three-stage velocity evolution in battery failure events, identifying a peak particle speed exceeding 120 m/s. These findings provide critical kinematic data for optimizing battery safety structures and modeling fire propagation mechanisms. Full article

Accurate temperature control in ceramic roller kilns is critical for ensuring product quality; however, it remains challenging due to nonlinear thermal dynamics and the spatial lag inherent in traditional contact-based sensors. To address the limitations of sparse wall-mounted thermocouples and optical interference in kiln images, this paper presents a multimodal spatiotemporal fusion network (MST-FusionNet) for noncontact temperature detection of ceramic bodies on roller tracks. The proposed network integrates in-furnace combustion image sequences with distributed thermocouple measurements. First, a physics-informed pseudo-heatmap generation strategy based on Gaussian distributions is introduced to align discrete thermocouple readings with visual features, enabling effective early-stage multimodal fusion. Second, a residual compensation mechanism uses thermocouple data as a stable reference to learn local temperature deviations from visual and temporal features. In addition, an attention-enhanced LSTM module is employed to model combustion dynamics and suppress unreliable frames caused by smoke and flame fluctuations. Experimental results on a real industrial dataset show that the proposed method achieves a mean absolute error of 0.9164 °C and a root mean squared error of 1.2422 °C, demonstrating better performance than single-modal methods and simple fusion baselines. The proposed framework exhibits stable spatial characteristics across different roller positions and helps bridge the spatial discrepancy between boundary measurements and the actual thermal state of ceramic products, providing an effective solution for temperature detection in roller kilns. Full article

A capsule endoscope (CE) provides noninvasive access to the gastrointestinal tract, offering diagnostic information that cannot be obtained through external imaging alone. However, during the examination inside the stomach, the CE’s posture may change rapidly as it moves within a dynamically deforming organ, making it difficult to determine its orientation using only the onboard camera feedback. To address this problem, this study proposes a method that employs an external array of Hall Effect Sensors (HES) to estimate the capsule’s position and orientation in real time, based on the magnetic field generated by a permanent magnet (PM) embedded inside the capsule, without the need for any additional internal sensors. This approach introduces a unified magnetic actuation and localization framework that enables real-time 5-degree-of-freedom posture estimation using only the internal PM of the capsule. Furthermore, the proposed system features an integrated architecture capable of simultaneous actuation and localization. To enhance system practicality, the sensor module and communication board were combined into a single unit that employs a digital serial communication scheme, eliminating the need for analog to digital conversion of sensing signals. By avoiding additional onboard sensors and employing a PM-based actuation system, the proposed system simplifies hardware configuration by preserving capsule miniaturization and by eliminating the high power consumption and thermal issues associated with electromagnet-based actuation, while maintaining accurate real-time tracking performance. Through an optimization process, the system achieved a position error of less than 2 mm and an angular error within 2° over a sensing range of up to 60 mm. Repeated experiments further validated the system’s effectiveness and reliability under realistic operating conditions, demonstrating its feasibility for compact and clinically applicable active capsule endoscopy systems. Full article

Chemical monitoring of pollutants and hazardous materials in water supply systems traditionally depends on centralized laboratories, advanced instrumentation, and trained personnel, limiting accessibility and preventing real-time, on-site analysis. This work presents an alternative cost-effective, field-deployable approach that uses genetically engineered bioluminescent bioreporters, encapsulated in self-sufficient alginate capsules and integrated with an optoelectronic detection circuit, to detect and quantify target materials in water. We have developed a scalable single-channel prototype featuring four sensing tracks—two for sample measurement, one for clean water, and one for a standard reference solution. The latter employs the standard ratio (SR) method to ensure robust quantification, compensating for batch variability and environmental effects. System characterization showed high uniformity across tracks. Validation with nalidixic acid (NA) demonstrated reliable quantitative performance, with a blind test estimation of 5.6 mg/L for a true concentration of 5 mg/L, well within the calibration error range. Additional sensitivity testing confirmed detection of mitomycin C (MMC) at concentrations as low as 50 µg/L. Overall, the results highlight the potential of bacterial chemical sensing as a practical and scalable tool for real-time, in situ water quality monitoring networks. Full article

A primary bottleneck in deploying Fiber Bragg Grating (FBG) sensors lies in their inherent dual sensitivity to thermal and mechanical variations, which mandates robust decoupling mechanisms for precise parameter extraction. To address this persistent cross-sensitivity issue, this study introduces a novel interrogation scheme that integrates a Convolutional Neural Network with a Bidirectional Long Short-Term Memory (CNN-BiLSTM) architecture. Instead of relying on conventional peak-tracking algorithms or isolated central wavelengths, our proposed data-driven strategy directly mines structural features from the full reflection spectra, thereby substantially mitigating cross-interference errors. The experimental results reveal that the coefficients of determination (R²) for strain and temperature prediction reach 99.37% and 99.75% each, while the root mean square errors (RMSEs) are 13.51 µε and 1.42 °C, respectively. The proposed method requires only a single FBG sensor, which reduces the sensor requirements, showing great potential in sensing applications requiring low costs and high adaptability. In addition, in some special environments, temperature information cannot be obtained, so we utilize another reference FBG to realize the temperature compensation. Meanwhile, we proposed a spectral differencing method (SDM) by differencing the spectra of the two FBGs to obtain the spectra containing only strain information and sent them as a dataset for model training, with a 4-times improvement in accuracy over traditional compensation methods. Finally, we also explored the application of the system for distributed FBGs, achieving an absolute peak wavelength interrogation precision of approximately ±0.02 nm. The system is expected to be applied in the field of structural health monitoring, which is promising even in harsh environments. Full article

Spaceborne infrared small-target detection plays a critical role in space-sky early warning, disaster rescue, and reconnaissance tracking, benefiting from all-time, all-weather, and wide-area monitoring capabilities. The deployment of high-spatial-resolution infrared payloads (ground sampling distance, GSD < 10 m) has introduced pronounced scale diversity among targets, leading to size-sensitive performance degradation in existing detectors and heightened risks of missed detections or false alarms in mixed-size scenarios. Furthermore, multi-frame infrared small-target detection methods often face challenges in maintaining consistent temporal coherence during feature propagation across sequences. To overcome these limitations in high-resolution spaceborne infrared videos, we propose DTRFR, an end-to-end unified detection framework built on an enhanced recurrent feature refinement architecture. This approach incorporates a realistic SITP-QLSD dataset derived from QLSAT-2 infrared backgrounds, featuring diverse scenes, multi-size small targets, and a dedicated generalization sub-test set with extremely small targets partially unseen in training; a multi-scale IRFeatureExtractor leveraging parallel convolutions and dilated receptive fields for improved cross-scale discrimination and clutter suppression; and an adaptive gating pyramid deformable alignment module to optimize sequence alignment and enhance temporal consistency, enabling robust performance across various clutter levels and dynamic backgrounds. Extensive evaluations on SITP-QLSD demonstrate that DTRFR attains competitive performance, achieving mIoU of 74.32% and Pd of 94.51% on the main set, with strong robustness on the generalization sub-test set (Pd = 92.37%). Compared to single-frame and multi-frame baselines, the proposed method achieves higher detection accuracy with significantly reduced false alarms, benefiting from multi-scale feature extraction that enables robust detection of small targets of different sizes in infrared videos. Full article

The export of Hass avocado (Persea americana Mill.) from Colombia requires accurate determination of harvest maturity, currently assessed through destructive dry matter (DM) measurements that are wasteful and limited in throughput. The objective of the article is to propose a low-cost, non-destructive approach to determine the maturity of the Hass avocado crop based on machine learning techniques. The approach consists of a low-cost, non-invasive bioimpedance spectroscopy system operating in the 1–10 kHz range, featuring a custom Analog Front End (AFE) and a tetrapolar surface probe to mitigate skin contact resistance, which collects data for predictive models of avocado maturity. To evaluate the quality of the approach, a longitudinal field study (n = 100) was conducted in a commercial orchard in Cundinamarca, Colombia, tracking complex impedance features—Magnitude, Phase Angle, Resistance, and Reactance—of tagged fruits over 8 weeks across four measurement timepoints. The predictive performance of a classical chemometric model (PLS-DA), non-linear classifiers (SVM, Random Forest), and a temporal Deep Learning (LSTM) architecture was compared using a Stratified Group K-Fold Cross-Validation scheme to prevent data leakage across fruits from the same tree. The 4-electrode configuration successfully isolated mesocarp impedance, identifying the 5–7.2 kHz band as the most sensitive to physiological maturation. In turn, the LSTM model achieved a mean accuracy of 92.0% and an AUC of 0.94, outperforming the other models by 4.0% in mean accuracy. The results demonstrate that modeling the temporal trajectory of impedance, rather than single-point measurements, improves harvest maturity classification in Hass avocados, providing a scalable, low-cost alternative to destructive testing. Full article

Face recognition is increasingly being adopted in industries such as education, security, and personalized services. This research introduces a face recognition system that leverages the embedding capabilities of the CLIP model. The model is trained on multimodal data, such as images and text and it generates high-dimensional features, which are then stored in a vector index for further queries. The system is designed to facilitate accurate real-time identification, with potential applications in areas such as attendance tracking and security screening. Specific use cases include event check-ins, implementation of advanced security systems, and more. The process involves encoding known faces into high-dimensional vectors, indexing them using a vector index FAISS, and comparing them to unknown images based on L2 (euclidean) distance. Experimental results demonstrate a high accuracy that exceeds 90% and prove efficient scalability and good performance efficiency even in datasets with a high volume of entries. Notably, the system exhibits superior computational efficiency compared to traditional deep convolutional neural networks (CNNs), significantly reducing CPU load and memory consumption while maintaining competitive inference speeds. In the first iteration of experiments, the system achieved over 90% accuracy on live video feeds where each identity had a single reference video for both training and validation; however, when tested on a more challenging dataset with many low-quality classes, accuracy dropped to approximately 73%, highlighting the impact of dataset quality and variability on performance. Full article

In metal additive manufacturing, the molten pool directly influences the performance of the fabricated components. Therefore, a comprehensive understanding of the molten pool behavior is essential for improving the quality of the parts and mitigating the formation of defects. Selective arc melting (SAM) is a promising additive manufacturing method for fabricating metal matrix composites. However, the melting and solidification process of the powder layer under the arc heat source remains unrevealed. This study aims to elucidate the formation mechanisms of surface morphology during SAM processing and the influence of carbide addition on the melting and solidification behavior of Inconel 718 powder. In this study, thin-walled parts of Inconel 718 and TiC/Inconel 718 composite were fabricated and their microstructures were studied. The melting and solidification behavior of Inconel 718 and TiC/Inconel 718 composite during single-track single-layer deposition was investigated using high-speed photography. Focusing on the differences in the sidewall surface morphology of the Inconel 718 and TiC/Inconel 718 composite parts, the edge feature formation of the deposition track of both materials was studied. Furthermore, the formation mechanism of the differences in forming height at different positions of the deposition track was explored. The results indicate that the melted material in the molten pool of Inconel 718 mainly comes from the mass transport of the beads generated around the molten pool, while the liquid material in the molten pool of TiC/Inconel 718 composite mainly comes from the in situ powder melted under the arc center. During the melting process of Inconel 718 powder, beads at the edge of the heating area come into contact with the boundary of the molten pool and solidify in situ, forming protrusion features. The randomness in the bead size leads to different volumes of molten material at different positions within the same time, thereby causing variations in building height. Full article