Search Results (412)

Avocado (Persea americana Mill.) is one of the most widely consumed fruits worldwide. The tree species is traditionally classified into three botanical races: Mexican, Guatemalan, and West Indian (with a potentially distinct Colombian genepool). However, previous studies using molecular markers, such as AFLPs, microsatellites (SSRs), and GBS-derived SNP markers, have only partially resolved this racial divergence, especially in the hyper agrobiodiverse region of northwest South America. Therefore, in order to confirm genetic identity and origin of “criollo” avocado cultivars in the region, as well as to improve their traceability as rootstocks for the Hass variety, we performed low-coverage whole genome resequencing (lcWGS) on 205 ex situ conserved tree samples, comprising 42 commercial varieties and 163 “criollo” trees from various provinces in Colombia. This characterization yielded a total of 64,310,961 SNPs at an average coverage of 4.69×. Population structure analysis using principal component analysis (PCA) and ADMIXTURE retrieved at least five genetic clusters (K = 5), partly confirmed by Bayesian phylogenetic inference. Three clusters matched the recognized Mesoamerican botanical races (Mexican, Guatemalan, and West Indian), and two clusters reinforced the distinctness of two novel Andean and Caribbean Colombian genetic groups. Finally, in order to retrieve high-quality SNP markers for racial screening, a second genomic dataset was filtered, consisting of 68 avocado tree samples exhibiting more than 80% ancestry to a given racial cluster, and 9826 SNPs with a minimum allele frequency (maf) of 5%, a minimum sequencing depth (SD) of 10× per position, and missing data per variant not exceeding 20% (i.e., variants with genotypes present in at least 80% of the samples). This racially segregating high-quality subset was analyzed against the racial substructure using linear mixed models (LMMs), enabling the identification of 254 SNP markers associated with the five avocado genetic races. The previous candidate SNPs may be leveraged by nurseries and producers through a high-throughput SNP screening system for the racial traceability of seedling donor trees, saplings, and rootstocks. These genomic resources will support the selection of regionally adapted elite rootstocks and represent a landmark in Colombian horticulture as the first large-scale lcWGS-based characterization of a local avocado germplasm collection. Full article

Parental adverse childhood experiences (ACEs) are linked to negative outcomes in children, including emotional and behavioral problems, developmental delays, and higher risk for psychopathology. Most research focuses on school-aged children or community samples, with few studies examining preschool-aged children in child psychiatric care. Understanding parental ACEs in this population is crucial, as early childhood is a sensitive developmental period, and intergenerational effects may be particularly pronounced in children already presenting with psychiatric symptoms. Background/Objectives: The goal of this study was to analyze how parents of patients in an early childhood (0–5.9 yrs) mental health outpatient clinic differ from the general population in terms of the frequency of ACEs. In addition, we investigated the connection between mental health disorders in young children and the specific ACE scores of their parents. Methods: A total of 116 caregivers (34.45 years (SD = 5.28)) and their children (71.6% boys, 28.4% girls) at an average age of 3.99 years (SD = 1.35, range = 0.31–5.95) were included in the analysis. The legal guardians completed the 10-item ACE questionnaire. The young children were diagnosed as part of outpatient treatment using the DC:0–5 classification system. We analyzed the ACE scores and diagnoses descriptively and in comparison to a community sample. Results: An average value of 2.38 parental ACEs was reported by our sample, and 68.1% (n = 79) reported at least one ACE. The high-risk group with four or more ACEs comprised 30.2% (n = 35). The most common diagnosis in young children was the Disorder of Dysregulated Anger and Aggression of Early Childhood, followed by global developmental delay. Adjustment disorder was third in terms of frequency. Among the examined child psychiatric diagnoses, adjustment disorder showed a significant correlation with parents being affected by the ACE category of neglect (OR = 2.54; 95% CI: 1.012–6.369; p = 0.047). Conclusions: Parents who presented their children at an early childhood mental health outpatient clinic reported significantly more ACEs as compared to representative data on ACEs in adulthood. These results highlight the need for further studies with larger samples to enable a more in-depth analysis of the general intergenerational transmission processes and the differential transmission of specific ACEs to specific diagnoses in preschool-aged children. Full article

This paper presents an electromagnetic levitation system that stabilizes a magnetic body using an array of electromagnets controlled by a Hall-effect sensor array and TinyML-based position detection. Departing from conventional optical tracking methods, the proposed design combines finite-element-optimized electromagnets with a microcontroller-optimized neural network that processes sensor data to predict the levitated object’s position with 0.0263–0.0381 mm mean absolute error. The system employs both quantized and full-precision implementations of a supervised multi-output regression model trained on spatially sampled data (40 × 40 × 15 mm volume at 5 mm intervals). Comprehensive benchmarking demonstrates stable operation at 850–1000 Hz control frequencies, matching optical systems’ performance while eliminating their cost and complexity. The integrated solution performs real-time position detection and current calculation entirely on-board, requiring no external tracking devices or high-performance computing. By achieving sub 30 μm accuracy with standard microcontrollers and minimal hardware, this work validates machine learning as a viable alternative to optical position detection in magnetic levitation systems, reducing implementation barriers for research and industrial applications. The complete system design, including electromagnetic array characterization, neural network architecture selection, and real-time implementation challenges, is presented alongside performance comparisons with conventional approaches. Full article

Background/Objectives: We provide a framework for determining how far into the future the spatiotemporal dynamics of tumor growth can be accurately predicted using routinely available magnetic resonance imaging (MRI) data. Our analysis is applied to a coupled set of reaction-diffusion equations describing the spatiotemporal development of tumor cellularity and vascularity, initialized and constrained with diffusion-weighted (DW) and dynamic contrast-enhanced (DCE) MRI data, respectively. Methods: Motivated by experimentally acquired murine glioma data, the rat brain serves as the computational domain within which we seed an in silico tumor. We generate a set of 13 virtual tumors defined by different combinations of model parameters. The first parameter combination was selected as it generated a tumor with a necrotic core during our simulated ten-day experiment. We then tested 12 additional parameter combinations to study a range of high and low tumor cell proliferation and diffusion values. Each tumor is grown for ten days via our model system to establish “ground truth” spatiotemporal tumor dynamics with an infinite signal-to-noise ratio (SNR). We then systematically reduce the quality of the imaging data by decreasing the SNR, downsampling the spatial resolution (SR), and decreasing the sampling frequency, our proxy for reduced temporal resolution (TR). With each decrement in image quality, we assess the accuracy of the calibration and subsequent prediction by comparing it to the corresponding ground truth data using the concordance correlation coefficient (CCC) for both tumor and vasculature volume fractions, as well as the Dice similarity coefficient for tumor volume fraction. Results: All tumor CCC and Dice scores for each of the 13 virtual tumors are >0.9 regardless of the SNR/SR/TR combination. Vasculature CCC scores with any SR/TR combination are >0.9 provided the SNR ≥ 80 for all virtual tumors; for the special case of high-proliferating tumors (i.e., proliferation > 0.0263 day⁻¹), any SR/TR combination yields CCC and Dice scores > 0.9 provided the SNR ≥ 40. Conclusions: Our systematic evaluation demonstrates that reaction-diffusion models can maintain acceptable longitudinal prediction accuracy—especially for tumor predictions—despite limitations in the quality and quantity of experimental data. Full article

The increasing frequency and intensity of wildfires pose severe risks to ecosystems, infrastructure, and human safety. In wildland–urban interface (WUI) areas, nearby vegetation strongly influences building ignition risk through flame contact and radiant heat exposure. However, limited research has leveraged Unmanned Aerial Systems (UAS) remote sensing (RS) to capture species-specific vegetation geometry and predict thermal responses during ignition events This study proposes a two-stage framework integrating UAS-based multispectral (MS) imagery, LiDAR data, and Fire Dynamics Simulator (FDS) modeling to estimate the maximum temperature (T) and heat flux (HF) of outdoor vegetation, focusing on Syzygium smithii (Lilly Pilly). The study data was collected at a plant nursery at Queensland, Australia. A total of 72 commercially available outdoor vegetation samples were classified into 11 classes based on pixel counts. In the first stage, ensemble learning and watershed segmentation were employed to segment target vegetation patches. Vegetation UAS-LiDAR point cloud delineation was performed using Raycloudtools, then projected onto a 2D raster to generate instance ID maps. The delineated point clouds associated with the target vegetation were filtered using georeferenced vegetation patches. In the second stage, cone-shaped synthetic models of Lilly Pilly were simulated in FDS, and the resulting data from the sensor grid placed near the vegetation in the simulation environment were used to train an XGBoost model to predict T and HF based on vegetation height (H) and crown diameter (D). The point cloud delineation successfully extracted all Lilly Pilly vegetation within the test region. The thermal response prediction model demonstrated high accuracy, achieving an RMSE of 0.0547 °C and R² of 0.9971 for T, and an RMSE of 0.1372 kW/m² with an R² of 0.9933 for HF. This study demonstrates the framework’s feasibility using a single vegetation species under controlled ignition simulation conditions and establishes a scalable foundation for extending its applicability to diverse vegetation types and environmental conditions. Full article

Accurate diagnosis of myocardial infarction (MI) holds significant clinical importance for public health systems. Deep learning-based ECG, classification and localization methods can automatically extract features, thereby overcoming the dependence on manual feature extraction in traditional methods. However, these methods still face challenges such as insufficient utilization of dynamic information in cardiac cycles, inadequate ability to capture both global and local features, and data imbalance. To address these issues, this paper proposes a ResNet-Transformer cascaded network (RTCN) to process time frequency features of ECG signals generated by the S-transform. First, the S-transform is applied to adaptively extract global time frequency features from the time frequency domain of ECG signals. Its scalable Gaussian window and high phase resolution can effectively capture the dynamic changes in cardiac cycles that traditional methods often fail to extract. Then, we develop an architecture that combines the Transformer attention mechanism with ResNet to extract multi-scale local features and global temporal dependencies collaboratively. This compensates for the existing deep learning models’ insufficient ability to capture both global and local features simultaneously. To address the data imbalance problem, the Denoising Diffusion Probabilistic Model (DDPM) is applied to synthesize high-quality ECG samples for minority classes, increasing the inter-patient accuracy from 61.66% to 68.39%. Gradient-weighted Class Activation Mapping (Grad-CAM) visualization confirms that the model’s attention areas are highly consistent with pathological features, verifying its clinical interpretability. Full article

Frequency-modulated continuous-wave (FMCW) LiDAR systems are extensively utilized in industrial metrology, autonomous navigation, and geospatial sensing due to their high precision and resilience to interference. However, the intrinsic nonlinear dynamics of laser systems introduce significant distortion, adversely affecting measurement accuracy. Although conventional iterative pre-distortion correction methods can effectively mitigate nonlinearities, their long-term reliability is compromised by factors such as temperature-induced drift and component aging, necessitating periodic recalibration. In light of recent advances in artificial intelligence, deep reinforcement learning (DRL) has emerged as a promising approach to adaptive nonlinear compensation. By continuously interacting with the environment, DRL agents can dynamically modify correction strategies to accommodate evolving system behaviors. Nonetheless, existing DRL-based methods often exhibit limited adaptability in rapidly changing nonlinear contexts and are constrained by inefficient uniform experience replay mechanisms that fail to emphasize critical learning samples. To address these limitations, this study proposes an enhanced Soft Actor-Critic (SAC) algorithm incorporating a hybrid prioritized experience replay framework. The prioritization mechanism integrates modulation frequency (MF) error and temporal difference (TD) error, enabling the algorithm to dynamically reconcile short-term nonlinear perturbations with long-term optimization goals. Furthermore, a time-varying delayed experience (TDE) injection strategy is introduced, which adaptively modulates data storage intervals based on the rate of change in modulation frequency error, thereby improving data relevance, enhancing sample diversity, and increasing training efficiency. Experimental validation demonstrates that the proposed method achieves superior convergence speed and stability in nonlinear correction tasks for FMCW LiDAR systems. The residual nonlinearity of the upward and downward frequency sweeps was reduced to $1.869\times {10}^{-5}$ and $1.9411\times {10}^{-5}$, respectively, with a spatial resolution of 0.0203m. These results underscore the effectiveness of the proposed approach in advancing intelligent calibration methodologies for LiDAR systems and highlight its potential for broad application in high-precision measurement domains. Full article

Accurate recognition of estrus behavior in sows is of great importance for achieving scientific breeding management, improving reproductive efficiency, and reducing labor costs in modern pig farms. However, due to the evident spatiotemporal continuity, stage-specific changes, and ambiguous category boundaries of estrus behaviors, traditional methods based on static images or manual observation suffer from low efficiency and high misjudgment rates in practical applications. To address these issues, this study follows a video-based behavior recognition approach and designs three deep learning model structures: (Convolutional Neural Network combined with Long Short-Term Memory) CNN + LSTM, (Three-Dimensional Convolutional Neural Network) 3D-CNN, and (Convolutional Neural Network combined with Temporal Convolutional Network) CNN + TCN, aiming to achieve high-precision recognition and classification of four key behaviors (SOB, SOC, SOS, SOW) during the estrus process in sows. In terms of data processing, a sliding window strategy was adopted to slice the annotated video sequences, constructing image sequence samples with uniform length. The training, validation, and test sets were divided in a 6:2:2 ratio, ensuring balanced distribution of behavior categories. During model training and evaluation, a systematic comparative analysis was conducted from multiple aspects, including loss function variation (Loss), accuracy, precision, recall, F1-score, confusion matrix, and ROC-AUC curves. Experimental results show that the CNN + TCN model performed best overall, with validation accuracy exceeding 0.98, F1-score approaching 1.0, and an average AUC value of 0.9988, demonstrating excellent recognition accuracy and generalization ability. The 3D-CNN model performed well in recognizing short-term dynamic behaviors (such as SOC), achieving a validation F1-score of 0.91 and an AUC of 0.770, making it suitable for high-frequency, short-duration behavior recognition. The CNN + LSTM model exhibited good robustness in handling long-duration static behaviors (such as SOB and SOS), with a validation accuracy of 0.99 and an AUC of 0.9965. In addition, this study further developed an intelligent recognition system with front-end visualization, result feedback, and user interaction functions, enabling local deployment and real-time application of the model in farming environments, thus providing practical technical support for the digitalization and intelligentization of reproductive management in large-scale pig farms. Full article

Lithium-ion batteries (LIBs) are critical components in safety-critical systems such as electric vehicles, aerospace, and grid-scale energy storage. Their degradation over time can lead to catastrophic failures, including thermal runaway and uncontrolled combustion, posing severe threats to human safety and infrastructure. Developing a robust AI framework for degradation prognostics in safety-critical systems is essential to mitigate these risks and ensure operational safety. However, sensor noise, dynamic operating conditions, and the multi-scale nature of degradation processes complicate this task. Traditional denoising and modeling approaches often fail to preserve informative temporal features or capture both abrupt fluctuations and long-term trends simultaneously. To address these limitations, this paper proposes a hybrid data-driven framework that combines Sample Entropy-guided Variational Mode Decomposition (SE-VMD) with K-means clustering for adaptive signal preprocessing. The SE-VMD algorithm automatically determines the optimal number of decomposition modes, while K-means separates high- and low-frequency components, enabling robust feature extraction. A dual-branch architecture is designed, where Gated Recurrent Units (GRUs) extract short-term dynamics from high-frequency signals, and Transformers model long-term trends from low-frequency signals. This dual-branch approach ensures comprehensive multi-scale degradation feature learning. Additionally, experiments with varying sliding window sizes are conducted to optimize temporal modeling and enhance the framework’s robustness and generalization. Benchmark dataset evaluations demonstrate that the proposed method outperforms traditional approaches in prediction accuracy and stability under diverse conditions. The framework directly contributes to Artificial Intelligence for Security by providing a reliable solution for battery health monitoring in safety-critical applications, enabling early risk mitigation and ensuring operational safety in real-world scenarios. Full article

Harmful algal blooms (HABs) are an escalating global concern due to their increasing frequency, duration, intensity, and geographic spread. These events threaten public health by contaminating drinking water sources, recreational areas, and food production systems with cyanotoxins. Effective monitoring is critical but remains limited by the spatial and temporal variability of blooms. Unmanned aerial vehicles (UAVs) have recently emerged as a flexible, high-resolution tool for HAB monitoring that can complement satellite and in situ methods. This review synthesizes recent applications of UAVs in HAB detection, mapping, and sampling, with a focus on how these approaches can support public health interventions. Key UAV platforms, sensor types, and data processing workflows are summarized, along with considerations related to flight regulations. Studies linking UAV data to indicators like chlorophyll-a and phycocyanin are discussed, highlighting their relevance for early warning systems and water treatment responses. Finally, the review identifies persistent challenges—including validation, regulatory gaps, and integration with health risk frameworks—and provides recommendations to advance UAV-based monitoring. These insights support the continued development of UAV systems as part of comprehensive strategies to mitigate HAB-related health risks. Full article

Power converters play an important role in incorporating renewable energy sources into power systems. Among different converter designs, Buck and Boost converters are popular, as they use fewer components and deliver cost savings and high efficiency. However, Boost converters are known as non–minimum phase systems, imposing harder constraints for designing a robust converter. Developing an efficient controller for these topologies can be difficult since they exhibit nonlinearity and distortion in high frequency modes. The Lyapunov-based Adaptive Backstepping Control (ABSC) technology is used to regulate suitable outputs for these structures. This approach is an updated version of the technique that uses the stability Lyapunov function to produce increased stability and resistance to fluctuations in real-world circumstances. However, in real-time situations, disturbances with larger ranges such as supply voltage changes, parameter variations, and noise may have a negative impact on the operation of this strategy. To increase the controller’s flexibility under more difficult working settings, the most appropriate first gains must be established. To solve these concerns, the ABSC’s performance is optimized using the Reinforcement Learning (RL) adaptive technique. RL has several advantages, including lower susceptibility to error, more trustworthy findings obtained from data gathering from the environment, perfect model behavior within a certain context, and better frequency matching in real-time applications. Random exploration, on the other hand, can have disastrous effects and produce unexpected results in real-world situations. As a result, we choose the Deep Deterministic Policy Gradient (DDPG) approach, which uses a deterministic action function rather than a stochastic one. Its key advantages include effective handling of continuous action spaces, improved sample efficiency through off-policy learning, and faster convergence via its actor–critic architecture that balances value estimation and policy optimization. Furthermore, this technique uses the Grey Wolf Optimization (GWO) algorithm to improve the initial set of gains, resulting in more reliable outcomes and quicker dynamics. The GWO technique is notable for its disciplined and nature-inspired approach, which leads to faster decision-making and greater accuracy than other optimization methods. This method considers the system as a black box without its exact mathematical modeling, leading to lower complexity and computational burden. The effectiveness of this strategy is tested in both modeling and experimental scenarios utilizing the Hardware-In-Loop (HIL) framework, with considerable results and decreased error sensitivity. Full article

Divers’ navigation heavily depends on their experience and physical condition, and accidents caused by failure to return occur every year. To address this issue, we developed a navigation system for divers. This navigation system leverages Raspberry Pi and low-cost sensors, including an accelerometer, gyro sensor, geomagnetic sensor, and pressure gauge, to guide divers along predefined routes back to their starting point. The system employs a 20 Hz sampling frequency and applies high-pass filtering (HPF) to acceleration signals to eliminate gravitational interference. Velocity integration errors are corrected using the rate of pressure change, while impulse noise in accelerometer and geomagnetic sensors is removed via the Robust Kalman Filter (RKF). A time-varying system noise covariance matrix enhances accuracy during rotational states. Quaternion-based attitude avoids gimbal lock, with the Kalman Filter (KF) fusion of accelerometer/geomagnetic data mitigating gyro sensor drift. Forced oscillator trials achieved pitch/roll RMS errors of ±1.23° and ±0.26°. In Kanagawa, Japan, divers successfully navigated 44 waypoints (<5 m spacing) along a route with obstacles (30 m rope, Authors, reefs), with a start/end GNSS positioning error of 6.67 m. Full article

This study introduces a novel, low-cost, and non-invasive method for characterizing the surface profile of transparent objects using double digital fringe projection (DDFP). By projecting dual sinusoidal patterns that generate a Moiré effect and applying a frequency-domain Gaussian filter, the system isolates relevant data for accurate phase recovery through the isotropic quadrature transform (IQT). Experimental validation with plastic and acrylic samples confirms the method’s high spatial resolution and robustness against ambient noise. Unlike traditional systems, this technique avoids coherent light sources and complex hardware, improving its accessibility for academic and industrial use in transparent surface metrology. Full article

Accurate and non-invasive assessment of fat and muscle composition is crucial for biomedical monitoring to track health conditions in humans and pets, as well as for classifying meats in the meat industry. This study introduces a cost-effective, multifunctional ultra-wideband microwave system operating from 2.4 to 4.4 GHz, designed for rapid and non-destructive quantification of fat thickness, muscle thickness, and fat-to-muscle ratio in diverse ex vivo samples, including pork, beef, and oil–water mixtures. The compact handheld device integrates essential RF components such as a frequency synthesizer, directional coupler, logarithmic power detector, and a dual-polarized Vivaldi antenna. Bluetooth telemetry enables seamless real-time data transmission to mobile- or PC-based platforms, with each measurement completed in a few seconds. To enhance signal quality, a two-stage denoising pipeline combining low-pass filtering and Savitzky–Golay smoothing was applied, effectively suppressing noise while preserving key spectral features. Using a random forest regression model trained on resonance frequency and signal-loss features, the system demonstrates high predictive performance even under limited sample conditions. Correlation coefficients for fat thickness, muscle thickness, and fat-to-muscle ratio consistently exceeded 0.90 across all sample types, while mean absolute errors remained below 3.5 mm. The highest prediction accuracy was achieved in homogeneous oil–water samples, whereas biologically complex tissues like pork and beef introduced greater variability, particularly in muscle-related measurements. The proposed microwave system is highlighted as a highly portable and time-efficient solution, with measurements completed within seconds. Its low cost, ability to analyze multiple tissue types using a single device, and non-invasive nature without the need for sample pre-treatment or anesthesia make it well suited for applications in agri-food quality control, point-of-care diagnostics, and broader biomedical fields. Full article

Cerebrovascular reactivity, cerebral autoregulation (CA), and oxygen delivery can be measured continuously and in a non-invasive fashion using cerebral near-infrared spectroscopy (NIRS). Although the literature is limited surrounding the difference between signals acquired and derived from low (<100 Hz) and high sampling rates (≥100 Hz). As part of a prospective observational study, we preliminarily explored and assessed the difference in the information provided by two NIRS systems using regional cerebral oxygen saturation and cerebral oximetry index signals at low and high sampling rates. The raw data in two frequencies (down-sampled to 1 Hz using the mean and up-sampled to 250 Hz) were decimated to focus on slow-wave vasogenic fluctuations associated with CA. Then, the data were analyzed using various statistical methods such as the absolute signal difference, Pearson correlation, Bland–Altman agreement, Cross-correlation function, optimal time-series autocorrelative structure, time-series impulse response function, and Granger causality relationships. The results of the various statistical analyses indicated that the signals obtained using high-frequency NIRS were different from signals obtained from low-frequency NIRS of the same cerebral region. Hence, high-frequency NIRS systems may possibly contain better signal features compared to NIRS systems with low sampling rates, but further work is required to assess high-frequency NIRS in other healthy and cranial trauma populations. Full article