Search Results (6,971)

Arbuscular mycorrhizal (AM) fungi form mutualistic symbioses with about 80% of land plants and play a key role in improving host inorganic phosphate (Pi), nitrogen, and water acquisition. Traditional AM fungi research relies on field trials, compartmented cultivation, and pot cultures—methods that are time-consuming (taking months to years) and unable to monitor dynamic transport, thus limiting efficient strain screening. We developed a real-time fluorescence imaging platform integrating sterile symbiotic microchambers with photodiode array detection. This system enables the non-invasive, quantitative tracking of hyphal cytoplasmic streaming and transport kinetics at the plant–fungal interface. Distinct AM fungi strains exhibit significant differences in fluorescence kinetics—such as accumulation rate and peak intensity—providing measurable indicators of transport efficiency. Our method overcomes the temporal and technical limitations of conventional AM fungi screening approaches. By enabling simultaneous real-time monitoring, it shortens screening cycles and provides new insights for the (1) precise screening of AM fungi strains for efficient nutrient transport; (2) investigation of nutrient exchange mechanisms; (3) development of sustainable microbial inoculants. Full article

Monocular 3D multi-object tracking (3D MOT) remains challenging because it is hard to model how objects move over time and to keep correct identities without explicit depth information. In this context, we introduce D3SSTrack, a novel tracking-by-detection framework that integrates Mamba state-space modeling into the 3D tracking pipeline. At its core is the Solid State Track (SST) block, which extends the original Mamba block with dropout regularization and an additional projection layer to improve feature integration before temporal fusion. This design enables efficient modeling of long-range temporal dependencies while maintaining real-time performance at 38 FPS on a single GPU. The proposed tracker combines structured sequence modeling with effective temporal association, improving robustness against occlusions and abrupt motion changes. On the KITTI benchmark, D3SSTrack achieves the best sAMOTA (97.12%) and AMOTA (49.95%) among recent monocular 3D MOT methods, outperforming the best model S3MOT by 0.16% and 0.22%, respectively. Our results highlight the potential of state space-based architectures for real-world monocular 3D MOT applications. Full article

Background/Objectives: Functional near-infrared spectroscopy (fNIRS) has emerged as a non-invasive, implant-compatible imaging modality capable of capturing cortical hemodynamics during ecologically valid auditory and linguistic tasks. Its silent operation and tolerance to electrical artifacts make it particularly well suited to the study of hearing-impaired individuals, including cochlear implant (CI) users. However, evidence on the application of fNIRS to investigate speech perception, cognitive performance, and proxy of cortical activation patterns in patients with hearing loss (HL) remains fragmented. This systematic review aims to provide a structured, population-stratified description of current fNIRS literature on auditory and cognitive processing in adults with age-related hearing loss (ARHL) and CI users. Methods: A systematic search on PubMed Central, Web of Science and Scopus, based on PRISMA (2020) guidelines, was conducted to identify original studies that evaluate speech perception by means of fNIRS to assess auditory and cognitive process in hearing-impaired populations. Results: Across studies, fNIRS consistently detected activation of superior temporal and frontal cortices during speech-related tasks. In ARHL, increased dorsolateral prefrontal cortex (DLPFC) recruitment during speech-in-noise indicated compensatory yet inefficient processing. Longitudinal auditory training led to reduced prefrontal overactivation and enhanced temporal–frontal connectivity. In CI users, cortical responses to phonological and comprehension tasks show partially overlapping activation patterns with normal hearing (NH) peers, although arising within different neurobiological contexts, and are modulated by device experience and residual hearing (AV) speech, and stimulus-level effects further shape cortical responses. When interpreted in light of developmental evidence, these findings may be contextualized as reflecting distinct trajectories of cortical reorganization, rather than a common mechanism. Conclusions: fNIRS provides a tool to investigate auditory and cognitive responses in distinct hearing-impaired populations under ecologically valid conditions. It detects maladaptive frontal inefficiency in ARHL, tracks neuroplastic changes after rehabilitation, and captures population-specific cortical recruitment patterns in CI users. These findings are descriptive and context-dependent, and do not support cross-population mechanistic generalizations. Standardized protocols and longitudinal pediatric studies are needed to clarify the potential clinical relevance of fNIRS-derived cortical measures. Full article

Accurate identification and quantitative assessment of fish feeding intensity are pivotal for enhancing aquaculture production efficiency. Currently, feeding intensity is mainly assessed based on fish school feeding images with a single feature, overlooking the interdependencies between individual fish and the fish school’s behavior. Therefore, this paper presents a method based on detecting individual fish heads to characterize the feeding aggregation speed and the average swimming speed of the fish school, thereby quantifying the fish school’s feeding intensity. First, the improved YOLOv11n-ALL model was employed to detect individual fish heads, resulting in improved detection performance, increasing inference speed, and reducing computational complexity. Additionally, feeding aggregation speed and average swimming speed indices for fish schools were constructed by combining the YOLOv11n-ALL model with the ByteTrack algorithm to track and extract the centers of individual fish heads’ detection boxes. Finally, the fish school feeding kinetic energy was assessed using the feeding aggregation speed and average swimming speed dual indices, and the fish school feeding intensity levels were classified according to the feeding kinetic energy. Experimental results reveal that the improved YOLOv11n-ALL model achieved an average detection precision (mAP50) of 94.13% for detecting fish heads, reduced the parameter count by 22.09%, and exhibited a computational complexity of 6.4 GFLOPs. Furthermore, the classification model of fish school feeding intensity, quantified by the dual indices of average swimming speed and feeding aggregation speed, achieved a detection accuracy of 97.41%. This method digitizes detection results, enabling rapid classification of fish school feeding intensity and demonstrating its effectiveness for feeding intensity assessment and the development of scientific feeding strategies. Full article

Background/Objectives: The use of artificial intelligence (AI) in imaging departments is increasing in Europe. This study assesses the clinical value of an AI fracture algorithm by assessing ease of use, clinicians’ trust, and perceived barriers and benefits of this decision support tool in daily practice across two emergency departments (EDs) in Denmark. Methods: An online survey was distributed over four weeks (June–July 2025) to healthcare professionals interpreting radiographs in the ED at Lillebaelt Hospital. The survey included open-ended, closed-ended, and free-text questions addressing AI use. Additionally, an observational study was conducted, including workflow observations and time tracking of patient progression through the ED. Historical injury conference records from February 2023 to 2025 were reviewed to assess changes in patient management before and after AI implementation. Results: A total of 56 responses were obtained (24 male, 32 female). Most respondents reported a positive attitude toward the algorithm. Ease of use was rated satisfactory by 51 out of 56 participants, and 48 were satisfied with AI as a clinical decision support tool. Overall trust was high, with more than two thirds (n = 38) “agreeing” or “strongly agreeing” that the algorithm reliably detects fractures. However, an asymmetry in clinical trust was observed, whereby clinicians expressed greater confidence in their own assessments when the algorithm indicated the presence of a fracture than when it did not. Value stream analyses showed a delay of 6–23 min between radiograph acquisition and availability of the AI report. No differences were observed in the number of patients with treatment changes before, during, or after full implementation of the algorithm. Conclusions: In our limited study population, the AI fracture detection tool was overall well received by clinicians, although some observations indicate that implementation and workflow integration still require improvement. Larger studies are needed to validate the reported barriers and benefits of the AI fracture detection tool. Full article

This study proposes an intelligent spraying vehicle speed control system integrating real-time canopy density detection with a fuzzy PID control algorithm. Utilizing LiDAR-acquired 3D point cloud data for canopy density calculation, the system dynamically adjusts PID parameters through fuzzy logic to achieve coordinated optimization of vehicle speed and spray volume. Based on the designed canopy density prediction model, a MATLAB/Simulink co-simulation framework integrating canopy perception with vehicle dynamics was established. Simulation results based on the MATLAB/Simulink platform demonstrate that the fuzzy PID controller achieves superior performance compared to conventional PID control. While maintaining a tracking accuracy of ±0.15 m/s, the proposed controller reduces speed overshoot by 5.8 percentage points. The developed control system ensures optimal speed tracking under varying canopy conditions, providing an extensible technical framework for intelligent sprayer vehicles. Full article

Understanding cell migration is essential not only for fundamental biology but also for the development of targeted disease therapies. Traditional in vitro cell migration assays typically rely on optical microscopy to capture cell movements and subsequent image-based tracking to quantify cell migration characteristics, which often involve substantial experimental workload and analytical complexity. Therefore, there is a need for an automated and streamlined approach to monitor and analyze cell movements. In this work, a microfabricated impedance sensor integrating electrode pairs and selectively protein-coated channels was developed for real-time monitoring of single-cell migration. The optimized electrode dimensions with 10 μm width and 10 μm gap enabled sensitive detection of impedance magnitude increase induced by individual cells. The impedance magnitude changes were correlated with the cell coverage area on electrodes, allowing continuous tracking of single-mouse osteoblast MC3T3 cell movement across the electrode pair. Distinct impedance responses of signal duration and magnitude were observed under different surface coatings, revealing the influence of microenvironmental chemistry on cell motility and adhesion. Furthermore, comparative impedance profiling of MC3T3 and nasopharyngeal epithelial NP460 cells demonstrated that MC3T3 cells produced larger changes in impedance real part and phase due to larger spreading area and larger number of focal adhesions, whereas NP460 cells showed shorter impedance signal change durations, consistent with faster cell migration. These electrical signatures collectively captured intrinsic differences in cell morphology, adhesion, and motility. The developed impedance sensor provides a label-free approach for single-cell migration characterization and can be potentially applied to cell identification. Full article

Real-time tracking of high-speed targets in autonomous systems requires detection and decision-making pipelines that can operate within sub-millisecond time budgets. Single Photon Avalanche Diode (SPAD) sensors are well suited for this task, offering 10 kHz Time-of-Flight (ToF) measurements with picosecond timing precision. However, processing such high-frequency time-series data with conventional deep learning models introduces computational bottlenecks that are difficult to handle on resource-constrained embedded hardware. This paper presents an ultra-lightweight, dual-head architecture built on the MiniRocket transformation algorithm, where a single shared feature extractor simultaneously feeds two independent decision pathways: one for multi-class target classification and one for 3-parameter kinematic regression covering velocity, pitch, and yaw. As a single-pixel sensor, the device provides only 1D range information; lateral 3D spatial localization is outside the scope of this work. To the best of the authors’ knowledge, this is the first application of MiniRocket to continuous kinematic estimation from high-frequency sensor data. Since collecting labeled physical flight data at these speeds is largely infeasible, a physics-based ray-casting simulation was developed to generate a 55,440-sample dataset across four 3D CAD target models under varying speed (100–450 m/s), orientation, and noise conditions. The proposed architecture achieves 98.6% classification accuracy and a velocity Mean Absolute Error (MAE) of 0.26 m/s, with orientation estimation yielding a pitch MAE of 3.47° and a yaw MAE of 2.46°—values consistent across all five cross-validation folds, indicating that the orientation performance floor is governed by the sensor’s physical angular resolution rather than by model capacity. With approximately 27,000 trainable parameters, the system completes full dual-task inference in 0.56 ms on a 16-core CPU (1785 Frames Per Second-FPS), satisfying the 1 ms real-time constraint of a 10 kHz sensor without GPU acceleration. It should be noted that the single-pixel SPAD architecture provides only 1D range-along-beam information; full 3D spatial localization is physically not extractable from a single sensor and is not addressed in this study. Full article

Extratropical cyclones (ETCs) are primary drivers of mid-latitude weather variability, yet most climatologies rely on single-level tracking, leaving their vertical structure poorly characterised. Because the vertical extent of a cyclone reflects its degree of baroclinic coupling and the tropospheric layer in which it resides is closely linked to the dominant physical processes governing its formation and impacts, a multi-level perspective is essential. Using the STACKER 4D tracking algorithm and ERA5 reanalysis (2000–2023), this study provides a comprehensive climatology of shallow ETCs (2–3 pressure levels) across 12 levels (925–100 hPa) over the Southern Hemisphere (14° S–78° S). A total of 21,701 shallow systems were detected, representing 42% of all multi-level ETCs. Classification into three subfamilies, shallow low (SL, 925–600 hPa; 43%), shallow mid (SM, 500–250 hPa; 35%), and shallow upper (SU, 200–100 hPa; 22%), suggests a possible linkage with different physical mechanisms: surface baroclinic instability for SL, upper-level potential vorticity forcing for SM, and tropopause-level dynamics for SU. SM and SU systems, jointly accounting for 57% of shallow events, are unlikely to be detected by conventional single-level-based tracking methods. Three-level systems (S3) exhibit higher vorticity, longer lifetimes, and greater interaction with the UTLS region than two-level systems (S2), with implications for stratosphere–troposphere exchange. Maximum cyclone density is concentrated between 30–40° S and 50–60° S. Full article

With the rapid expansion of high-speed railways, maintaining track structural health is vital for modern railway systems. Although deep learning has improved defect detection, models still face problems such as varying defect scales, severe background noise (e.g., lubricant residues and ferruginous oxidation), and irregular defect boundaries. To solve these problems, we introduce a new network named Rail-Adaptive-RCNN (RA-RCNN). It uses a Large Selective Kernel (LSK) backbone to dynamically adjust the Effective Receptive Field (ERF) for capturing periodic corrugation. We also added an Efficient Multi-Scale Attention (EMA) module that purifies features by suppressing noise without lowering dimensions. Finally, combining Scylla-IoU (SIoU) Loss with K-means clustering optimizes the regression of odd-shaped defects. Our experiments indicate that RA-RCNN reaches a mean Average Precision (mAP_0.5) of 86.2%, outperforming the baseline Faster R-CNN by 8.8%. Corrugation detection specifically reached 91.4%. With a processing speed of 26 FPS, this method effectively meets the practical needs of real-time automated railway maintenance. Full article

Persistent traffic congestion and the need for efficient traffic monitoring have increased the demand for automated vehicle-analysis systems based on CCTV footage. This study presents a CCTV-based vehicle monitoring system that integrates vehicle detection, tracking, counting, public/private vehicle class prediction, seven-category vehicle-type prediction, vehicle-color recognition, and traffic-state estimation using YOLOv12 and DeepSORT. To reduce manual annotation effort during the initial training stage, a semi-automated method for generating synthetic composite road scenes was developed by combining cropped vehicle images and road-background images. The detector was first trained on 10,000 synthetic images and then sequentially fine-tuned on real CCTV data. Four real-world traffic video clips from Metro Manila were used in the study. Three 5 min clips were used within the staged refinement workflow: the first two for iterative refinement and the third for final post-refinement evaluation of the adapted model. A separate fourth CCTV clip was reserved exclusively for blind evaluation without on-the-fly retraining. The final system achieved average accuracies of 97% for public/private vehicle class prediction, 90% for seven-category vehicle-type prediction, 82% for vehicle-color recognition, and 96.67% for vehicle counting on the final evaluation video. The results show that synthetic pretraining combined with limited real-world fine-tuning can improve performance in CCTV-based vehicle monitoring while reducing the amount of manually labeled real-world data required. The study also discusses the limitations of the current evaluation protocol and the need for broader multi-location testing. Full article

Efficient path planning and trajectory tracking are central to the safe and autonomous navigation of autonomous underwater vehicles (AUVs) in complex and unknown environments. In this paper, we propose an integrated framework that couples enhanced path planning, curvature-adaptive trajectory tracking, and sonar-constrained 3D exploration. First, the path planner is improved by incorporating safety margin-based collision detection, 3D obstacle avoidance weights, and online replanning. Second, the tracking module is enhanced with B-spline optimization and curvature-adaptive speed control to ensure smooth and dynamically feasible trajectories. Third, the exploration strategy is augmented with frontier clustering, multi-dimensional information gain evaluation, and TSP path optimization. Our framework jointly addresses practical constraints including forward-looking sonar field-of-view limitations, safety clearance margins, and the coupling of dynamic replanning with low-level tracking feasibility, while supporting both modular decoupling and integrated collaborative operation. Simulations using ArduSub SITL and Gazebo demonstrate that our integrated approach achieves a superior performance in path safety and tracking accuracy, along with an exploration coverage of 79.08%, validating its effectiveness for robust AUV autonomy in unknown 3D underwater scenarios. Full article

Intensive pig farming presents substantial challenges for individual health monitoring due to high stocking densities, complex occlusion scenarios, and the need for continuous real-time surveillance. Existing monitoring approaches rely heavily on manual inspection, which is labor-intensive and prone to delayed detection of abnormal behaviors and disease symptoms. This study proposes an embedded intelligent monitoring system integrating a pan-tilt gimbal platform with an improved multi-object tracking and anomaly detection framework for automated pig health surveillance. The system employs a modified Periodfill_DeepSORT algorithm that incorporates a ReID network with appearance features and motion prediction trajectories to maintain identity consistency under occlusion and re-entry scenarios. For anomaly detection, a lightweight YOLOv8-based network was trained on 772 abnormal samples across three behavioral categories: movement abnormalities, postural abnormalities, and disease-related abnormalities. Experimental results demonstrate that the Periodfill_DeepSORT algorithm achieves a Multiple Object Tracking Accuracy (MOTA) of 95.34%, a Multiple Object Tracking Precision (MOTP) of 94.77%, and an IDF1 score of 96.88%, with only 12 identity switches across 2000 frames involving 12 targets—27 fewer than the standard DeepSORT algorithm. In occlusion scenarios, MOTA improved from 61.1% to 78.3%. The anomaly detection network achieves an overall detection accuracy of 94.5%, representing an 8.8 percentage point improvement over the baseline model, with recognition accuracies of 96.2% for movement abnormalities, 94.1% for postural abnormalities, and 92.8% for disease-related abnormalities. The system operates at 90 frames per second on embedded hardware with a power consumption of 3.2 watts and a startup time of approximately 1 s, with gimbal angle errors maintained within 3°. These results demonstrate the system’s effectiveness and practical feasibility for real-time intelligent health monitoring in intensive livestock farming environments. Full article

This study investigates the formation mechanism of non-doped cubic lithium lanthanum zirconium oxide (c-LLZO) nanofibers using in situ synchrotron X-ray scattering techniques. Electrospun polymer precursor nanofibers were annealed at temperatures up to 800 °C, enabling real-time tracking of phase transitions via simultaneous small-angle X-ray scattering (SAXS), wide-angle X-ray scattering (WAXS), and evolved CO₂ gas analysis. The results reveal a three-step transformation pathway: polymer decomposition, formation of La₂Zr₂O₇ (LZO), and direct conversion of LZO to c-LLZO without intermediate tetragonal phases detected within the sensitivity of our in situ WAXS measurement. Cryo-electron energy loss spectroscopy (EELS) further elucidates the role of lithium diffusion, showing Li enrichment at fiber surfaces and Li deficiency in the interior, which stabilizes the cubic phase. This Li segregation effect in nanostructured LLZO materials extends beyond the previously reported size effect. This work advances the understanding of c-LLZO formation mechanisms and provides practical insights for optimizing synthesis routes to achieve phase-pure c-LLZO for solid-state battery applications. Full article

Cropland abandonment is increasing in the upper and middle Yangtze River Basin due to complex terrain, urbanization, and labor migration. This threatens regional food security. To address the challenge of monitoring abandonment in fragmented hilly areas, we developed a framework. We integrated machine learning with time-series analysis. We mapped cropland probability using multi-source remote sensing data, random forest, and kernel density estimation, then applied LandTrendr to detect land-use changes and track the spatiotemporal evolution of abandonment from 2000 to 2022. Next, we combined Geodetector and linear regression to identify driving factors. The results show that abandoned cropland exhibited an increasing trend from 2000 to 2010, with an average annual growth rate of 20.4%. From 2010 to 2013, the area of abandoned cropland declined rapidly, decreasing by 44.6%. Between 2013 and 2022, abandoned cropland decreased steadily, with an average annual reduction rate of 24.7%. Spatially, abandonment was clustered in the central mountains and southern hills. Key drivers included distance to towns (DtT), total grain output (GTO), and GDP. Our approach supports cropland management and rural revitalization in regions with complex terrain. Full article