Search Results (1,890)

Gastrointestinal (GI) cancers account for a quarter of all cancer cases worldwide and are responsible for a third of cancer deaths. One of the characteristic features of GI tissue is its multilayered structure, which, in addition to multiple scattering, complicates optical spectral analysis. The use of spectroscopic diagnostics and photodynamic therapy for the detection and treatment of GI cancer is a rapidly developing field. The method proposed in this paper for layer-by-layer optical properties assessment, suitable for real-time clinical application to the walls of hollow organs, allows us to calculate the absorbed dose layer by layer. This paper proposes a method for recording spectral data in two geometries, diffuse reflectance and transmission, using light delivery from both the external and internal surfaces of the gastrointestinal tract wall. Layer-by-layer assessment of optical properties was performed using a developed algorithm based on the inverse adding–doubling method with initial optical properties values determined using the modified two-stream Kubelka–Munk model with the accuracy equal to 86 ± 13%. The method was approved in clinical conditions. Based on the results of the work, the developed method for assessing the optical properties of multilayered biological tissues exhibited sufficient speed and accuracy for in vivo application to personalize laser-induced therapy by correction of the laser dose. Full article

Roadside LiDAR is a key sensing technology for intelligent transportation systems (ITSs) due to its high-precision spatial information and reliable monitoring of traffic environments. However, extracting traffic information from LiDAR point cloud data remains challenging because measurements are produced through angular sampling, causing the spacing between adjacent points to depend on radius and beam distribution. This study proposes a geometry-aware framework that incorporates LiDAR sampling geometry into the neighborhood criterion used to determine point-to-point association. The formulation defines neighborhood tolerance as a function of radial distance and vertical angular separation, enabling clustering decisions that are consistent with the sensing mechanism. In addition, the approach integrates deployment constraints based on sensor mounting height and region-of-interest limits to maintain physically meaningful connectivity under roadside sensing conditions. A systematic calibration procedure is conducted to estimate the scaling factor and radial spacing parameters and evaluate the method using both controlled and real-world datasets. Experimental results reveal that the proposed approach improves clustering accuracy and stability by reducing false negatives in sparse regions while avoiding excessive cluster merging in dense areas. The method demonstrates robust performance across varying sensing conditions and achieves higher accuracy than baseline approaches without parameter retuning, while introducing negligible computational overhead. Full article

Despite recent advances in metamaterials, experimental studies addressing the dynamic behavior of waveguide-type fractals manufactured by means of additive manufacturing remain scarce, limiting understanding of their performance in real-world vibration control. This study investigates the dynamic behavior of fractal waveguide beams based on Sierpinski geometry through combined experimental and analytical approaches. Beams with iterations i = 0–3 were fabricated via stereolithography and tested under a doubly clamped configuration subjected to harmonic excitation. The dynamic response was captured using an accelerometer and analyzed in both time and frequency domains using Fast Fourier Transform. A single-degree-of-freedom mass–spring model was employed to estimate dynamic stiffness and validate experimental results. The findings reveal that fractal geometry significantly influences vibrational behavior, producing a nonlinear and non-monotonic evolution of stiffness and energy dissipation. The highest-order fractal beam exhibited the greatest vibration attenuation and resonance frequency (27.2 Hz), despite having the lowest effective mass, demonstrating an optimized stiffness-to-mass ratio. Spectral area analyses confirmed that energy dissipation increases with fractal complexity, enabling identification of transitions between stiffness- and inertia-dominated regimes. By identifying these regimes, this work provides a framework for engineering lightweight, adaptive structures for advanced vibration attenuation and tunable mechanical vibration control applications. Full article

Forging is a key manufacturing route for high-performance structural components, but its process design, quality prediction, and adaptive control still rely heavily on empirical rules, offline simulations, and fragmented production data. This review examines intelligent forging from the perspective of mechanism–data–knowledge fusion, with emphasis on forging-specific process chains, real alloy systems, model validation, and industrial maturity. To improve methodological traceability, a structured literature search was conducted using Web of Science Core Collection, Scopus, ScienceDirect, SpringerLink, and Google Scholar, covering studies published from 1996 to 2026. The screened literature was organized around process perception, mechanism-based modeling, data-driven learning, hybrid modeling, knowledge representation, digital twins, online prediction, and adaptive regulation. Representative cases are discussed for closed-die forging, open-die/large forging, multistage forging, radial forging, and forging of aluminum alloys, titanium alloys, steels, and Ni-based superalloys. Particular attention is given to how specific models are validated, including independent experiments, finite-element benchmarks, industrial datasets, new geometries, sensor noise, and cross-material or cross-equipment transfer. The review further distinguishes consolidated technologies, such as FEM-based process simulation and die/preform optimization, from methods still under validation, including hybrid digital twins, sensor-updated models, and adaptive control. Large-model-assisted forging is considered a prospective direction mainly for information retrieval, case recovery, diagnostic support, and engineer-supervised recommendation rather than unsupervised real-time control. This review provides a more process-specific and critically assessed reference for developing explainable, validated, and deployable intelligent forging systems. Full article

Urban environments are saturated with imaging sensors deployed for purposes unrelated to vehicle identification, from ATM and dashboard cameras to pole-mounted CCTV and smartphones. We term the use of such non-purpose-built sensors for secondary inference “opportunistic sensing”; its central question is where, under uncontrolled capture conditions, AI-enabled restoration remains reliable. This paper introduces recoverability maps, a task-agnostic methodology for quantifying that boundary, and applies it to oblique-view license plate recognition (LPR). It pairs a full-grid synthetic sweep of the degradation space with two summary measures: a boundary area-under-curve for coverage and a reliability score $F$ for the frequency and depth of interior unrecovered pockets. For LPR, the space is the oblique-angle grid $[0°,89°{]}^2$ sampled by Scrambled Sobol sequences, and the utility is plate-level optical character recognition (OCR) accuracy. Within this synthetic benchmark, approximately $90$–$92\%$ of the angle grid is recoverable (best single model to union of restoration arms), recovery degrades sharply beyond roughly $80°$ in both axes, and lateral rotations are harder to reconstruct than elevational ones. Five restoration architectures cluster within a narrow AUC band of $0.89$–$0.93$, and share the same $\alpha /\beta$ asymmetry, so the recoverable region is set primarily by sensing geometry, with architecture affecting efficiency and interior consistency; discriminative architectures outperform generative models. The methodology is validated on real plates: on CCPD and the Brazilian legacy and Mercosur layouts of RodoSol-ALPR, restoration raises held-out extreme-angle recognition by $+15$ to $+38$ exact-match points under plate-specialized recognizers, and the discriminative-over-generative ordering reproduces on real data. Full article

Automated mapping of vertical traffic signs and horizontal road markings is essential for road safety and Intelligent Transportation Systems (ITS). Traditional methods are labor-intensive, while existing automated solutions often lack a unified approach or are proprietary, limiting research accessibility and reproducibility. This paper presents a comprehensive framework for identifying these assets using a low-cost, vehicle-mounted action camera. A distance-aware frame extraction strategy is introduced to minimize data redundancy and ensure high spatial diversity. Specific strategies address the class imbalance inherent in real-world driving, ensuring robust detection for infrequent sign categories. Deep learning models handle the distinct geometries of vertical and horizontal assets, employing segmentation-based annotation for irregular road markings. Experimental results show high performance, with leading YOLO-based architectures achieving an F1-score of 0.92 for vertical signage and 0.96 for horizontal markings. By transforming raw visual data into structured georeferenced information, this framework facilitates the generation of High-Definition (HD) maps and digital inventories, supporting road authorities in proactive maintenance planning and regional road safety assessments. Full article

This paper presents the structural characterization of zinc coatings on S235JR steel elements. The study offers a novel and comprehensive assessment of zinc coatings applied to profiled steel elements through hot-dip galvanizing. It examines coatings formed under real industrial production conditions, providing practical insight into their behavior on complex geometries. The characterization includes metallographic, mechanical, diffraction, and tribological tests. Metallographic observations revealed the layered structure of zinc coatings, consisting of the η, ζ, δ, and Γ phases, each with varying chemical compositions and microhardness. All coatings exhibited similar resistance to damage initiation; however, microscopic analysis revealed differences in their subsequent degradation. The thickest coating showed earlier formation of adhesive cracks, indicating increased stress concentration and a faster progression of damage. Full article

This paper presents a three-dimensional generalization of the M-integral, formulated as an interaction integral based on a bilinear strain energy density, for the mixed-mode decoupling of crack front energies in finite structural components. The proposed $M_{\theta }^{3D}$ integral combines real and virtual mechanical fields within a local spherical reference frame, enabling the separate evaluation of mode I (opening), mode II (in-plane shear) and mode III (out-of-plane shear) energy release rates along arbitrary crack front lines. The theoretical framework, derived from Noether’s theorem and the virtual work principle, is implemented in the Cast3M finite element code using a toroidal integration domain with a local theta weighting function. Numerical validations are conducted on the Mixed-Mode Crack Growth (MMCG) specimen, a geometry representative of structural components subjected to combined tension and shear. Three key findings are demonstrated: (i) practical domain independence is achieved for all three fracture modes; (ii) the three-dimensional approach converges to the plane-stress solution for thin specimens and reveals significant deviations from plane-strain assumptions; (iii) even under nominally mode I + II loading, a non-negligible mode III component emerges due to Poisson-induced out-of-plane effects, with magnitude increasing at free surfaces and for thicker geometries. These results indicate that finite-thickness and out-of-plane effects can significantly affect the partition of fracture energy between modes. For the MMCG configuration investigated here, the three-dimensional formulation shows the limitations of two-dimensional assumptions and provides an energetic basis for the analysis of mixed-mode fracture in finite-thickness components. Full article

Stereo matching has become an increasingly important component of modern autonomous systems. Developing deep learning-based stereo-matching models that deliver high accuracy while operating in real time continues to be a major challenge in computer vision. In the domain of cost volume-based stereo matching, accurate disparity estimation depends heavily on large-scale cost volumes. However, such large volumes store substantial redundant information and also require computationally intensive aggregation units for processing and regression, making real-time performance unattainable. Conversely, small-scale cost volumes followed by lightweight aggregation units provide a promising route for real-time performance, but lack sufficient information to ensure highly accurate disparity estimation. To address this challenge, we propose the Enhanced Shuffle Mixer (ESM) to mitigate information loss associated with small-scale cost volumes. ESM restores critical details by integrating primary features into the disparity upsampling unit. It quickly extracts features from the initial disparity estimation and fuses them with image features. These features are mixed by shuffling and layer splitting, then refined through a compact feature-guided hourglass network to recover more detailed scene geometry. The ESM focuses on local contextual connectivity with a large receptive field and low computational cost, leading to improved disparity estimation accuracy while maintaining real-time performance under the evaluated settings. The compact version of ESMStereo achieves an inference speed of 116 FPS on RTX 4070S and 91 FPS on the AGX Orin. Full article

Routine monitoring of ortho-phthalaldehyde (OPA) disinfectants is critical for endoscope reprocessing, yet commercial test strips suffer from subjective visual ambiguity, strict manual timing, and susceptibility to sample matrix dilution. This study proposes a portable multi-spectral colorimetric sensing platform paired with structurally engineered microfluidic plastic strips for quantitative OPA monitoring. The strips utilize a confined microfluidic geometry to achieve capillary-driven volumetric self-metering (5.4 μL), while cross-hatched micro-structures eliminate edge pooling, yielding uniform colorimetric responses. Analytically, the system integrates a matrix-matched reagent formulation, an interference-free indicator, and an automated steady-state ratiometric readout algorithm to counteract physical dilution and spectral interference. Cross-validation against a capillary electrophoresis benchmark confirmed quantitative accuracy (R² = 0.9684) under physical dilution of real-world CIDEX OPA solutions. This correlation facilitated a matrix-compensated 0.32% diagnostic threshold for unambiguous, automated “[PASS]” or “[FAIL]” alerts. Ultimately, this scalable, cost-effective microfluidic architecture provides an objective point-of-care diagnostic solution, demonstrating translational potential for broad dry chemistry optical detection. Full article

Virtual reality can support the preparation and rehearsal of assembly tasks by providing a safe and repeatable digital representation of workstations. This study presents the development and laboratory feasibility validation of a geometry- and procedure-oriented VR simulation model for the assembly and disassembly of end-effectors on an industrial robot. The workflow was implemented using the Almega AX-V6 robotic workstation as a case study and included geometric acquisition of the real robot, CAD modelling in SolidWorks, redesign of the original end-effector connection using a quick-change flange concept, creation of two alternative end-effector models, modelling of the laboratory workspace in SketchUp, and scene enhancement in Twinmotion. The resulting robot and environment models were integrated in Pixyz Review and deployed through an Oculus Rift-based VR setup. Compared with the original flange concept, which required twelve screws, the redesigned training concept used two screws and two nuts, reducing the number of fastening elements by 66.7% and the number of screw positions by 83.3%. The VR implementation supported visual inspection, controller-based placement and alignment, and symbolic confirmation of fastening steps; it did not include force feedback, threaded fastening physics, automatic error scoring, or quantified transfer-of-training evaluation. Laboratory feasibility validation confirmed correct asset integration, spatial correspondence with the physical workplace, and functional executability of the target exchange sequence. The results show that the workflow is useful as a case-study pipeline for CAD-to-VR modelling and assembly rehearsal, while controlled user studies are still required before claims about training effectiveness can be made. Full article

Infrared cameras used in radio telescopes often suffer image degradation in complex optical and thermal environments. Solar radiation, convergent reflected light, and thermal emission from support structures can substantially impair imaging performance. To address this problem, this paper proposes a split reflective ellipsoidal baffle for suppressing infrared imaging degradation. Unlike conventional baffles, which mainly rely on structural occlusion and surface absorption, the proposed design functions as an upstream stray light regulation unit. It also establishes a computational framework integrating ellipsoidal vane geometry, realistic edge microtopography modelling, ray-tracing simulation, and detector plane irradiance response analysis. First, the reflective properties of the ellipsoidal surface are used to construct an off-axis stray light propagation constraint model. Under this model, incident stray radiation is redirected away from the effective imaging path or guided into light-trapping regions between adjacent vanes. Second, a laser confocal microscope is used to capture the true three-dimensional edge morphology of vanes with different materials and machining angles. This strategy addresses the limitations of the conventional 0.02 mm rounded edge approximation, which cannot accurately represent real scattering behaviour. The measured morphologies are then converted into high-fidelity computational models compatible with ray-tracing analysis. Furthermore, stray light suppression performance is evaluated using point source transmittance, detector plane irradiance distribution, and grey scale response in experimental images. Simulation and darkroom experiments show that the proposed baffle suppresses residual stray light more effectively than conventional absorptive baffles. The results demonstrate a computable, manufacturable, and experimentally verifiable strategy for front-end stray light control and baffle optimisation. This strategy can also support image quality enhancement in infrared imaging systems operating under complex optical and thermal environments. Full article

Reliable detection of small agricultural targets is fundamental to precision crop protection, phenotyping, yield estimation, and robotic intervention. Typical examples include detecting aphids such as Aphis gossypii, whiteflies such as Bemisia tabaci, planthoppers such as Nilaparvata lugens, and other tiny pests on sticky traps or crop canopies for early warning, identifying crop-like weed seedlings for site-specific herbicide spraying, locating early disease lesions for targeted treatment, and detecting young fruits, flowers, or wheat heads for yield estimation and robotic manipulation. Agricultural small-object detection differs from generic small-object detection because target visibility is jointly determined by pixel area, physical size, imaging distance, ground sampling distance, canopy structure, biological similarity, and task-specific intervention requirements. Existing reviews have summarized agricultural object detection or general small-object detection, but they rarely connect agricultural failure modes with detector-level mechanisms and reproducible evaluation practices. This review addresses this gap through a mechanism-oriented synthesis of agricultural small-object detection. First, we revisit the limitations of the COCO-style 32²-pixel threshold and propose an agricultural scale-reporting framework that combines pixel area, physical scale, relative image occupancy, and acquisition geometry. Second, we organize recent methods according to the mechanisms by which they address detail loss, scale shift, occlusion, dense distributions, foreground–background confusion, localization uncertainty, and edge-deployment constraints. Third, we summarize public datasets, quantitative evaluation metrics, reporting checklists, and real-device deployment evidence to support fair and field-oriented comparison. Finally, we identify future directions in multimodal sensing, foundation-model adaptation, label-efficient learning, and hardware-aware optimization. By linking agricultural scene characteristics, detector mechanisms, and evaluation requirements, this review aims to provide a more actionable framework for developing robust small-object detection systems in precision agriculture. Full article

Object detection in unstructured agricultural environments remains challenging due to large scale variations, complex backgrounds, irregular obstacle shapes, and limited computational resources. To address these challenges, this paper proposes Agri-DETR, an efficient end-to-end detection framework based on the Real-Time Detection Transformer (RT-DETR), with coordinated improvements in feature perception, multi-scale representation, spatial reconstruction, and bounding box regression. Specifically, a lightweight backbone with a high-resolution feature branch is introduced to enhance the representation of small and fine-grained targets. A large selective feature fusion module is designed to strengthen multi-scale contextual modeling and improve feature discrimination under complex backgrounds. In addition, an attention-enhanced dynamic upsampling module refines high-resolution feature reconstruction, while a scale–shape–geometry-aware Intersection over Union (SSGIoU) loss improves localization stability for irregular and elongated objects. Experimental results show that Agri-DETR achieves 66.0% Average Precision (AP) on the self-constructed Agricultural Obstacle Dataset (AO-Dataset), outperforming representative detectors while reducing the parameter count by approximately 25% compared with RT-DETR-R18 baseline. In particular, small-object AP increases by 1.4%, demonstrating improved detection capability for small obstacles. Cross-dataset evaluation on COCO2017 further shows that Agri-DETR achieves 48.3% AP, demonstrating favorable generalization capability beyond the agricultural domain. These results indicate that Agri-DETR achieves an effective balance among detection accuracy, model complexity, and practical efficiency, making it a promising solution for real-world agricultural obstacle detection. Full article

Recently, there has been great interest in AI-based approaches for de novo design of novel drug candidates. However, the generation of useful lead drug candidate compounds requires more than predicting engagement with the desired protein target. Candidate molecules must also be anchored in the real world of medicinal chemistry for their synthesis and modification as well as satisfying multiple drug development-related criteria. Here, we present Nevermore, an AI target-conditioned, database-grounded workflow for prioritizing candidate ligands from large compound libraries. Nevermore uses a geometry-aware protein–ligand affinity oracle to score target-specific binding and perform sparse integer edits in count-based Morgan fingerprint space. Nevermore then retrieves the most structurally similar molecules from public chemical databases. This design enables multi-objective search over predicted affinity and absorption, distribution, metabolism, excretion, and toxicity (ADMET) proxies while keeping all candidates anchored to valid database compounds. We evaluated Nevermore’s performance across three biologically distinct targets: Menin, a protein-interaction target relevant to leukemia; SARS-CoV-2 M^pro, a viral cysteine protease relevant to antiviral discovery; and epidermal growth factor receptor (EGFR), a kinase-superfamily oncology target with extensive experimentally tested compounds. Nevermore retrieved candidate sets with favorable predicted affinity–property trade-offs. These results support database-grounded fingerprint steering as a practical computational strategy for lead prioritization and for generating testable molecular hypotheses, although the prioritized candidates remain predictions, requiring follow-up experimental validation. Full article