Search Results (1,468)

Background & Objectives: Quantitative ultrasound (QUS) radiomics extracts microstructure-sensitive spectral features from radiofrequency data and may provide contrast-free, early indicators of neoadjuvant chemotherapy (NAC) response in breast cancer. This review synthesized open access human studies evaluating QUS radiomics for a priori prediction and early on-treatment monitoring. Methods: Following PRISMA-2020, we included English, free full-text clinical studies of biopsy-proven breast cancer receiving NAC that reported QUS spectral parameters (mid-band fit, spectral slope/intercept) ± textures/derivatives and machine learning models against clinical/pathologic response. Data on design, RF acquisition/normalization, features, validation, and performance (area under the curve (AUC), accuracy, sensitivity/specificity, balanced accuracy) were extracted. Results: Twelve cohorts were included. A priori baseline models achieved accuracies of 76–88% with AUCs 0.68–0.90; examples include 87% accuracy in a multi-institutional study, 82% accuracy/AUC 0.86 using texture-derivatives, 86% balanced accuracy with transfer learning, 88% accuracy/AUC 0.86 with deep learning, and AUC 0.90 in a hybrid QUS and molecular-subtype model. Early monitoring improved discrimination: week-1 results ranged from AUC 0.81 to 1.00 and accuracy 70 to 100%, noting that the upper bound was reported in a small cohort using combined QUS and diffuse optical spectroscopy features, while week 4 typically peaked (AUC 0.87–0.91; accuracy 80–86% in observational cohorts), and one series reported week-8 accuracy of 93%. Across reporting cohorts, mean AUC increased with a 0.05 absolute gain. A randomized feasibility study reported prospective week-4 model accuracy of 98% and demonstrated decision impact. Conclusions: QUS radiomics provides informative a priori prediction and strengthens by weeks 1–4 of NAC, supporting adaptive treatment windows without contrast or radiation. Standardized radiofrequency (RF) access, normalization, region of interest (ROI)/margin definitions, and external validation are priorities for clinical translation. Full article

An important use case of speech bandwidth extension (BWE) is generating high-frequency components from band-limited speech processed by a speech codec. Recent works on BWE have demonstrated remarkable capabilities in generating high-quality, high-band components using deep learning techniques. Among them, Streaming SEANet (StrmSEANet) has also been shown to be effective for BWE with reduced delay and computational complexity, making it suitable for real-time speech processing. However, the effect of the coding artifact in the lower band of the input signal has not been sufficiently considered in many deep learning-based BWE methods. In this work, we propose Parallel Enhancement and Bandwidth Extension of coded speech (PEBE), where two lightweight networks, referred to as Compact Streaming SEANet (CompSEANet), for coded speech enhancement (CSE) and BWE are configured in parallel. The CSE and BWE models are separately trained with the task-specific training settings, thereby effectively improving the reconstruction quality of the band-limited speech signals degraded by coding artifacts. Experimental results demonstrate that the proposed PEBE significantly outperforms the baseline AP-BWE, StrmSEANet, and standalone CompSEANet in reconstructing wideband (WB) and fullband speech from Opus-coded narrowband and WB signals. The proposed method achieves the highest scores in the subjective MUSHRA test while providing the fastest inference among all compared methods, with real-time factors (RTF) of 33.95× and 18.38× measured on a Samsung SM-F711 mobile device under single-thread execution. Full article

To address the technical challenges in exploring concealed high-grade iron deposits in China, this study focuses on Banded Iron Formation, BIF, which represents the largest reserves and hosts the greatest number of large-scale deposits in the country. The Gongchangling iron deposit, a typical high-grade iron deposit in the Anben region, was selected as the main study area. In situ measurements and statistical analysis of the geophysical parameters of rocks and ores were conducted, with an emphasis on evaluating their sensitivity to high-grade magnetite mineralization. Based on this analysis, an integrated gravity, magnetic, and electrical survey method was identified as the optimal exploration approach. Building on this foundation, high-precision gravity and magnetic surveys were performed to investigate the geophysical anomaly response mechanisms of the Gongchangling-type high-grade ores. Forward and inverse modeling were applied to identify deep-seated concealed iron ore bodies, with results further validated by audio-frequency magnetotellurics. This study enhances the methodological framework for mineral exploration, improves prospecting efficiency, and provides practical insights to support new breakthroughs in exploration initiatives. Full article

Epilepsy affects over 50 million people worldwide, yet automated seizure detection systems either achieve moderate sensitivity with excessive false alarms or rely on uninterpretable deep networks. This study presents a patient-independent EEG-based seizure detection framework that achieved zero false alarms in 24 h with 95% sensitivity in a retrospective evaluation on a CHB–MIT pediatric cohort (n = 6 seizure-positive patients). The pipeline extracts 27 time-, frequency-, and nonlinear-domain features from 5 s windows and trains five ensemble classifiers (XGBoost, CatBoost, LightGBM, Extra Trees, Random Forest) using strict leave-one-subject-out cross-validation. All models achieved segment-level AUC ≥ 0.99. Under zero-false-alarm constraints, XGBoost attained perfect specificity with 0.922 sensitivity. SHAP and LIME analyses suggested candidate EEG biomarkers that appear consistent with known ictal signatures, including temporo-parietal theta-band power, amplitude variability (IQR, RMS), and Hjorth activity. External validation on the Siena Scalp EEG Database (12 adult patients, 37 seizures) demonstrated cross-dataset generalization with 95% event-level sensitivity (Extra Trees) and AUC of 0.86 (Random Forest). Temporal lobe channels dominated feature importance in both datasets, confirming consistent biomarker identification across pediatric and adult populations. These findings demonstrate that calibrated gradient-boosted ensembles using interpretable EEG features achieve clinically safe seizure detection with cross-dataset generalizability. Full article

We present a study of the linear polarization properties of radio sources within the 10 deg². Wide Chandra Deep Field South (W-CDFS) in S-band (2–4 GHz). Our W-CDFS image has an angular resolution of 15 arcsec and a 1$\sigma$ RMS in Stokes I of ≈50 $\mathsf{\mu }$Jy/beam. We detect 1920 distinct source components in Stokes I and 175 in linear polarization. We examine the polarized source counts, Faraday Rotation measures, and fractional polarization of the sources in the survey. We show that sources with a total intensity above ≈10 mJy have a mean fractional polarization value of ≈3% from modeling the polarized counts. We also calculate an estimate for the limit on the fractional polarization level of sources with a total intensity below 1 mJy (mostly star-forming galaxies) of ≲3% using stacking. The mean Faraday Rotation we measure is consistent with that due to the Milky Way. We also show that fractional polarization is correlated with in-band spectral index, consistent with a lower mean fractional polarization for the flat-spectrum population. In addition to characterizing the S-band polarization properties of sources in the W-CDFS, this study will be used to validate the shallower, but higher angular resolution S-band polarimetric information that the VLA Sky Survey will provide for the whole sky above Declination −40 degrees over the next few years. Full article

An efficient deep-learning-based framework for optimization-based inverse design of electromagnetic metasurface design is proposed in this paper. A novel unit-cell parameterization strategy generates 16-element structures via symmetry operations governed by ten geometric parameters, overcoming the inefficiencies of pixel-based representations. A dataset of 16,000 parameter–reflection phase pairs is constructed, and a hybrid model combining Convolutional Neural Network (CNN), attention mechanisms, and the Kolmogorov–Arnold Network (KAN) is developed for broadband response prediction. The coefficient of determination (R²) of the proposed model is 0.8837 in the 2–18 GHz band, which is 44.87% higher than the R² without KAN. The proposed chessboard metasurface achieves a 10 dB monostatic radar cross-section (RCS) reduction under normal incidence over a wide frequency band from 7.4 to 15.2 GHz, corresponding to a relative bandwidth of 69%. This approach provides a generalizable, data-efficient solution for intelligent metasurface design. Full article

The cutterhead torque of a full-face tunnel boring machine (TBM) is a pivotal parameter that characterises the rock-machine interaction. Its dynamic prediction is of considerable significance to achieve intelligent regulation of the boring parameters and enhance the construction efficiency and safety. In order to achieve high-precision time series prediction of cutterhead torque under complex geological conditions, this study proposes an intelligent prediction method (VBGAP) that integrates signal decomposition mechanism and physical constraints. At the data preprocessing level, a multi-step data cleaning process is designed. This process comprises the following steps: the processing of invalid values, the detection of outliers, and normalisation. The non-smooth torque time-series signal is decomposed by variational mode decomposition (VMD) into narrow-band sub-signals that serve as a data-driven, frequency-specific input for subsequent modelling, and a hybrid deep learning model based on Bi-GRU and self-attention mechanism is built for each sub-signal. Finally, the prediction results of each component are linearly superimposed to achieve signal reconstruction. Concurrently, a novel modal energy conservation loss function is proposed, with the objective of effectively constraining the information entropy decay in the decomposition-reconstruction process. The validity of the proposed method is supported by empirical evidence from a real tunnel project dataset in Northeast China, which demonstrates an average accuracy of over 90% in a multi-step prediction task with a time step of 30 s. This suggests that the proposed method exhibits superior adaptability and prediction accuracy in comparison to existing mainstream deep learning models. The findings of the research provide novel concepts and methodologies for the intelligent regulation of TBM boring parameters. Full article

Biomimetic pectoral fin propulsion offers a low-noise, highly maneuverable alternative to conventional propellers for next-generation underwater robotic systems. This study develops a manta ray-inspired dual-servo pectoral fin module with a CPG-based controller and employs it as a single-fin test article in a recirculating water tunnel to quantify its hydrodynamic performance. Controlled experiments demonstrate that the fin generates stable thrust over a range of flapping amplitudes, with mean thrust increasing markedly as the amplitude rises, while also revealing an optimal frequency band in which thrust and thrust work are maximized and beyond which efficiency saturates. To interpret these trends, a quasi-steady CFD analysis using the k–ω SST turbulence model is conducted for a series of static angles of attack representative of the instantaneous effective angles experienced during flapping. The simulations show a transition from attached flow with favorable lift-to-drag ratios at moderate angles of attack to massive separation, deep stall, and high drag at extreme angles, corresponding to high-amplitude fin motion. By linking the experimentally observed thrust saturation to the onset of deep stall in the numerical flow fields, this work establishes a unified experimental–numerical framework that clarifies the hydrodynamic limits of pectoral fin propulsion and provides guidance for the design and operation of low-noise, highly maneuverable biomimetic underwater robots. Full article

This study presents a multiscale, uncertainty-aware hybrid deep learning approach addressing the short-term wind speed prediction problem, which is critical for the reliable planning and operation of wind energy systems. Wind signals are decomposed using adaptive variational mode decomposition (VMD), and the resulting wind components are processed together with meteorological data through a dual-stream CNN–BiLSTM architecture. Based on this multiscale representation, probabilistic forecasts are generated using quantile regression to capture best- and worst-case scenarios for decision-making purposes. Unlike fixed prediction intervals, the proposed approach produces adaptive prediction bands that expand during unstable wind conditions and contract during calm periods. The developed model is evaluated using four years of meteorological data from the Afyonkarahisar region of Türkiye. While the proposed model achieves competitive point forecasting performance (RMSE = 0.700 m/s and MAE = 0.54 m/s), its main contribution lies in providing reliable probabilistic forecasts through well-calibrated uncertainty quantification, offering decision-relevant information beyond single-point predictions. The proposed method is compared with a classical CNN–LSTM and several structural variants. Furthermore, SHAP-based explainability analysis indicates that seasonal and solar-related variables play a dominant role in the forecasting process. Full article

Satellite communication systems experience significant signal degradation during rain events, a phenomenon that can be leveraged for meteorological applications. This study introduces a novel hybrid machine learning framework combining unsupervised clustering with cluster-specific supervised deep learning models to transform satellite signal attenuation into a predictive tool for rainfall prediction. Unlike conventional single-model approaches treating all atmospheric conditions uniformly, our methodology employs K-Means Clustering with the Elbow Method to identify four distinct atmospheric regimes based on Signal-to-Noise Ratio (SNR) patterns from a 12-m Ku-band satellite ground station at King Mongkut’s Institute of Technology Ladkrabang (KMITL), Bangkok, Thailand, combined with absolute pressure and hourly rainfall measurements. The dataset comprises 98,483 observations collected with 30-s temporal resolutions, providing comprehensive coverage of diverse tropical atmospheric conditions. The experimental platform integrates three subsystems: a receiver chain featuring a Low-Noise Block (LNB) converter and Software-Defined Radio (SDR) platform for real-time data acquisition; a control system with two-axis motorized pointing incorporating dual-encoder feedback; and a preprocessing workflow implementing data cleaning, K-Means Clustering (k = 4), Synthetic Minority Over-Sampling Technique (SMOTE) for balanced representation, and standardization. Specialized Long Short-Term Memory (LSTM) networks trained for each identified cluster enable capture of regime-specific temporal dynamics. Experimental validation demonstrates substantial performance improvements, with cluster-specific LSTM models achieving R² values exceeding 0.92 across all atmospheric regimes. Comparative analysis confirms LSTM superiority over RNN and GRU. Classification performance evaluation reveals exceptional detection capabilities with Probability of Detection ranging from 0.75 to 0.99 and False Alarm Ratios below 0.23. This work presents a scalable approach to weather radar systems for tropical regions with limited ground-based infrastructure, particularly during rapid meteorological transitions characteristic of tropical climates. Full article

Accurate delineation of inland waterbodies is critical for applications such as hydrological monitoring, disaster response preparedness and response, and environmental management. While optical satellite imagery is hindered by cloud cover or low-light conditions, Synthetic Aperture Radar (SAR) provides consistent surface observations regardless of weather or illumination. This study introduces a deep learning-based ensemble framework for precise inland waterbody detection using high-resolution X-band Capella SAR imagery. To improve the discrimination of water from spectrally similar non-water surfaces (e.g., roads and urban structures), an 8-channel input configuration was developed by incorporating auxiliary geospatial features such as height above nearest drainage (HAND), slope, and land cover classification. Four advanced deep learning segmentation models—Proportional–Integral–Derivative Network (PIDNet), Mask2Former, Swin Transformer, and Kernel Network (K-Net)—were systematically evaluated via cross-validation. Their outputs were combined using a weighted average ensemble strategy. The proposed ensemble model achieved an Intersection over Union (IoU) of 0.9422 and an F1-score of 0.9703 in blind testing, indicating high accuracy. While the ensemble gains over the best single model (IoU: 0.9371) were moderate, the enhanced operational reliability through balanced Precision–Recall performance provides significant practical value for flood and water resource monitoring with high-resolution SAR imagery, particularly under data-constrained commercial satellite platforms. Full article

A growing challenge in mobile robotics is the reliance on complex graphical interfaces and rigid control pipelines, which limit accessibility for non-expert users. This work introduces a latency-aware benchmarking framework that enables natural-language robot navigation by integrating multiple Large Language Models (LLMs) with the Robot Operating System 2 (ROS 2) Navigation 2 (Nav2) stack. The system allows robots to interpret and act upon free-form text instructions, replacing traditional Human–Machine Interfaces (HMIs) with conversational interaction. Using a simulated TurtleBot4 platform in Gazebo Fortress, we benchmarked a diverse set of contemporary LLMs, including GPT-3.5, GPT-4, GPT-5, Claude 3.7, Gemini 2.5, Mistral-7B Instruct, DeepSeek-R1, and LLaMA-3.3-70B, across three local planners, namely Dynamic Window Approach (DWB), Timed Elastic Band (TEB), and Regulated Pure Pursuit (RPP). The framework measures end-to-end response latency, instruction-parsing accuracy, path quality, and task success rate in standardised indoor scenarios. The results show that there are clear trade-offs between latency and accuracy, where smaller models respond quickly but have less spatial reasoning, while larger models have more consistent navigation intent but take longer to respond. The proposed framework is the first reproducible multi-LLM system with multi-planner evaluations within ROS 2, supporting the development of intuitive and latency-efficient natural-language interfaces for robot navigation. Full article

The complex seabed topography and mechanical properties of deep-sea sediments impose stringent requirements on the traction performance and locomotion stability of tracked mining vehicles. Experimental investigations on the coupled effects of grouser geometry and operating conditions on traction remain limited. To address this, rheological tests and multi-parameter traction experiments were conducted. Deep-sea sediments were modeled as a power-law fluid to capture their non-Newtonian behavior, considering particle size distribution, water content, and compaction state. Using a self-designed traction test apparatus, the influences of grouser geometry and operating parameters on traction force were systematically analyzed. Results indicate that both grouser configuration and operating conditions significantly affect traction force magnitude and stability. Rectangular grousers, exhibiting more uniform stress distribution and pronounced shear bands, demonstrated enhanced traction efficiency and locomotion stability under high-load, low-speed conditions. When the grouser length was 30 mm and the traveling speed was maintained at 7–12 mm/s, sediment fluidization was significantly mitigated, improving traction performance. Furthermore, a spacing of at least 20 mm between adjacent grousers produced a synergistic effect, increasing sediment shear strength by approximately 30–40%. These findings provide quantitative guidance for grouser design and operational optimization of tracked deep-sea mining vehicles. Full article

Timely and accurate crop yield estimation is vital for food security and management decision-making. Integrating remote sensing with machine learning provides an effective solution. In this study, based on canopy hyperspectral data collected by an ASD FieldSpec 3 handheld spectrometer during the critical growth stages of winter wheat, 18 vegetation indices (VIs) were systematically calculated, and their correlation with yield was analyzed. At the same time, a continuous projection algorithm, Successive Projections Algorithm (SPA), was used to screen the characteristic bands. Recursive Feature Elimination (RFE) was employed to select optimal features from VIs and characteristic spectral bands, facilitating the construction of a multi-temporal fusion feature set. To identify the superior yield estimation approach, a comparative analysis was conducted among four machine learning models: Deep Forest (DF), Support Vector Regression (SVR), Random Forest (RF), and Gaussian Process Regression (GPR). Performance was evaluated using the coefficient of determination (R²), root mean square error (RMSE), and relative root mean square error (rRMSE). Results indicate that the highest correlations between VIs and grain yield were observed during the flowering and grain-filling stages. Independent analysis showed that VIs reached absolute correlations of 0.713 and 0.730 with winter wheat yield during the flowering and grain-filling stages, respectively, while the SPA further identified key bands primarily in the near-infrared and short-wave infrared regions. On this basis, integrating multi-temporal features through RFE significantly improved the accuracy of yield estimation. Among them, the DF model with the fusion of flowering and filling stage features performed best (R² = 0.786, RMSE = 641.470 kg·hm⁻², rRMSE = 15.67%). This study demonstrates that combining hyperspectral data and VIs from different growth stages provides complementary information. These findings provide an effective method for crop yield estimation in precision agriculture. Full article

High rock slopes are extensively distributed in areas of major engineering constructions, such as transportation infrastructure, hydraulic projects, and mining operations. The stability and failure evolution mechanism during their multi-stage excavation process have consistently been a crucial research topic in geotechnical engineering. In this paper, a series of two-dimensional rock slope models, incorporating various combinations of slope height and slope angle, were established utilizing the Discrete Element Method (DEM) software PFC2D. This systematic investigation delves into the meso-mechanical response of the slopes during multi-stage excavation. The Parallel Bond Model (PBM) was employed to simulate the contact and fracture behavior between particles. Parameter calibration was performed to ensure that the simulation results align with the actual mechanical properties of the rock mass. The research primarily focuses on analyzing the evolution of displacement, the failure modes, and the changing characteristics of the force chain structure under different geometric conditions. The results indicate that as both the slope height and slope angle increase, the inter-particle deformation of the slope intensifies significantly, and the shear band progressively extends deeper into the slope mass. The failure mode transitions from shallow localized sliding to deep-seated overall failure. Prior to instability, the force chain system exhibits an evolutionary pattern characterized by “bundling–reconfiguration–fracturing,” serving as a critical indicator for characterizing the micro-scale failure mechanism of the slope body. Full article