Search Results (1,795)

Individual differences in second-language (L2) proficiency are expected to influence how listeners parse and represent continuous speech, yet their neural signatures under naturalistic conditions remain unclear. We investigated this question using task-based fMRI during continuous speech listening. A total of 43 healthy participants completed four listening runs synchronized with MRI acquisition via PsychoPy(Peirce 2007), with eyes open throughout scanning. To promote sustained attention and comprehension, participants provided a native-language oral recall after each run. Based on behavioral proficiency scores, participants were grouped into low- (LP, n = 14), moderate- (MP, n = 14), and high-proficiency (HP, n = 15) groups. We evaluated three temporal information-encoding frameworks derived from BOLD dynamics: direct temporal series, functional connectivity (FC), and self-information weighted inter-subject correlation (ISC-W). Using a 10 × 5-fold nested cross-validation scheme, we tested both categorical classification (Support Vector Machines) for discrete proficiency groups (LP, MP, HP) and continuous multivariate regression (Ridge/Lasso) for continuous proficiency scores. Furthermore, we applied ROI-based ANOVA and univariate Neural Correlation Analysis (NCA) to identify key brain regions, evaluating significance via nonparametric permutation testing (1000 permutations) and False Discovery Rate (FDR) correction. Results indicated that while categorical classification yielded numerical trends—with ISC-W performing best—it did not reach statistical significance under stringent permutation testing. However, multivariate continuous regression using ISC-W features successfully predicted continuous proficiency scores with statistical significance (p < 0.05). Exploratory ROI analysis highlighted the bilateral orbital inferior frontal gyrus (IFG_orb_bilat) as a highly sensitive region. These findings suggest that L2 proficiency is best represented as a distributed, continuous neural variable, and that self-information weighting effectively filters background noise to capture cognitive variance. Methodologically, this study provides a reproducible pipeline integrating information-theoretic feature construction with rigorous whole-brain nonparametric inference. Full article

Passive Optical Networks (PONs) play a vital role in providing high-speed broadband access in the 5G and F5G generation. However, their shared nature makes them vulnerable to physical-layer attacks like fiber bending, tapping and fiber cut. The problem is more serious in high-density PONs, where high split ratios result in high optical loss and overlapping back-scattered light, making it difficult to distinguish small attacks from background noise. Contrary to most existing works that neglect class imbalance and signal interference in high-density networks, this paper proposes a robust hierarchical two-stage attack detection scheme. First, we employ a binary classifier to distinguish eavesdropping attacks from normal traffic. Then, a second stage focuses on the specific eavesdropping categories (C1–C4). To address the small amount of attack samples, SMOTE is utilized for oversampling the minority class, and PCA-SVM is used to refine feature selection. Finally, the output of both stages is combined using probability score to obtain reliable decision. The experimental results show the effectiveness of our approach, achieving a classification accuracy of 89.07%. When evaluated on the same data, it has shown superior results in comparison to conventional machine learning algorithms, including decision tree (86.3%), k-nearest neighbors (79%), logistic regression (60%), and Naïve Bayes (52.6%). Full article

This study investigates the feasibility of acoustic signal analysis for the assessment of weld bead quality in the shielded metal arc welding (SMAW) process. The work focuses on comparing time-domain acoustic signals and time–frequency spectrogram representations for the classification of welds as accepted or rejected according to standard welding inspection criteria. Two key acoustic descriptors, the fundamental frequency (F₀) and the harmonics-to-noise ratio (HNR), were extracted and analyzed to evaluate statistical differences between the two weld quality classes. Statistical tests, including Anderson–Darling, Levene, ANOVA, and Kruskal–Wallis (α = 0.05), revealed significant differences between accepted and rejected welds. Accepted welds exhibited a bimodal HNR distribution associated with transient arc instability at the beginning and end of the bead, whereas rejected welds showed more uniform acoustic behavior throughout the process. Subsequently, the acoustic data were represented using both audio signals and spectrograms and used as inputs for ten supervised machine learning models, including Support Vector Classifier (SVC), Logistic Regression (LR), k-Nearest Neighbors (KNN), Decision Tree (DT), Random Forest (RF), Extra Trees (ET), Gradient Boosting (GB), and Naïve Bayes (NB). The results demonstrate that spectrogram-based representations significantly outperform time-domain signals, achieving accuracies of 0.95–0.96, ROC-AUC values above 0.95, and false positive and false negative rates below 6%. These findings indicate that, while scalar acoustic descriptors provide statistically significant insight into weld quality, time–frequency representations combined with machine learning enable a more robust and reliable framework for automated non-destructive evaluation, particularly in manual SMAW processes under realistic operating conditions. Full article

The accurate and timely identification of urban building footprints is critical for sustainable urban planning and disaster management. Traditional remote sensing methods for this task often face limitations in scalability, accuracy, and adaptability to complex urban morphologies. This paper addresses these challenges by developing and evaluating a novel data-centric framework that synergistically integrates Graph Neural Networks (GNNs) with zero-shot superpixel segmentation derived from the Segment Anything Model (SAM) applied to Sentinel-2 imagery. A cornerstone of our methodology is a rigorous assessment of OpenStreetMap (OSM) data, refined through temporal NDVI stability analysis to generate high-quality ground truth. We propose an optimized UrbanGraphSAGE model, enhanced with spectral data augmentation and trained using a robust loss function with label smoothing to mitigate label noise. In the complex urban landscape of Algiers, Algeria, our approach achieves a Test F1-Score of 0.7131, demonstrating highly competitive performance with standard pixel-based baselines like U-Net while offering significant topological and computational advantages. Specifically, our model operates with merely 19,585 parameters—orders of magnitude fewer than pixel-based CNNs. A rigorous Gold Standard evaluation against manually labeled imagery confirms the model’s high recall (0.8484) and reliability for automated urban monitoring. Full article

With the explosive growth of the Internet of Things (IoT) and cloud-computing traffic, Intrusion Detection Systems (IDSs) have become a cornerstone of network security. However, modern traffic data often exhibits extreme class imbalance and long-tailed distributions, leading to persistently high miss rates for minority attack categories in Machine Learning (ML)-based IDSs. Conventional oversampling may introduce decision noise, whereas standard Generative Adversarial Networks (GANs) can suffer from training instability and mode collapse when modeling high-dimensional tabular traffic features. To address these challenges, we propose a high-fidelity traffic augmentation framework based on an Adaptive Hybrid-loss Conditional GAN (AH-CGAN). Specifically, AH-CGAN introduces an iteration-dependent adaptive gradient penalty (AGP) schedule to enforce the Lipschitz continuity constraint more effectively during training and incorporates a feature-matching objective to align intermediate critic representations between real and synthetic traffic. Experiments on the CIC-IDS2017 benchmark show that AH-CGAN generates distribution-consistent synthetic samples and that augmentation improves downstream detection across multiple classifiers. In particular, the weighted F1-score of Logistic Regression increases from 0.8237 to 0.8697 (Δ = +0.0460, i.e., +4.6%). Overall, the proposed approach enhances minority coverage in the feature space and can improve class separability, providing a practical solution for long-tailed IDS. Full article

Reliable sensor fault detection is critical for the safe and efficient operation of complex industrial systems, such as thermal power plants. However, traditional data-driven methods and standard deep learning models often struggle to detect incipient gradual drift faults under severe environmental noise, primarily because they ignore the inherent physical correlations among multivariate sensor signals. To address this challenge, this paper proposes a novel Physics-Coupled Deep Long Short-Term Memory Autoencoder (PC-Deep-LSTM-AE). Specifically, we integrate a deep LSTM architecture with an explicit non-linear information compression bottleneck and layer normalization to enhance robust feature extraction in high-noise environments. Furthermore, we innovatively introduce a Physics-Coupling Loss (PCC Loss) that jointly optimizes the mean squared reconstruction error and the Pearson correlation coefficient, forcing the model to strictly preserve the dynamic physical relationships among multivariable signals. Extensive experiments were conducted on a real-world thermal power plant dataset with severe noise injection. The results demonstrate that the proposed PC-Deep-LSTM-AE achieves an outstanding F1-score of over 0.98, significantly outperforming mainstream baseline models, including Vanilla LSTM-AE, GRU-AE, Bi-LSTM-AE, and CNN-AE. The proposed method exhibits exceptional robustness and high interpretability for root-cause analysis, highlighting its immense potential for real-world industrial deployment. Full article

Cyber-physical systems (CPSs) represent sophisticated intelligent architectures that tightly couple computational elements, communication networks, and physical processes. Their deployments now span virtually every industrial and civilian domain—from power grids and manufacturing plants to autonomous transportation networks. Ensuring the secure operation of CPSs relies fundamentally on effective time series anomaly detection, which remains a challenging task due to the complex, often unknown system dynamics and non-negligible sensor noise present in real-world environments. To address these challenges, we introduce a Neural Network-Enhanced Kalman Filter (NNEKF), a novel anomaly detection framework that combines model-based filtering with data-driven learning. The NNEKF employs a two-stage trained neural network with a specialized architecture: the first stage learns the underlying dynamics of the CPS, while the second stage optimizes the computation of the Kalman gain during the update step. At inference time, the enhanced Kalman filter recursively estimates the likelihood of observed sensor measurements to identify anomalies, supported by a batched parallel inference scheme that delivers substantial speedups. Extensive experiments on benchmark datasets demonstrate that the NNEKF attains an average F1-score of 0.935, coupled with rapid inference and minimal model footprint—surpassing all competitive baselines and facilitating dependable real-time anomaly detection for CPS environments. Full article

Against the background of highly interconnected global capital markets and rapidly propagating cross-lingual information streams, traditional anomaly detection paradigms based solely on single-modality numerical time-series sensors are insufficient for forward-looking risk sensing. From the perspective of artificial intelligence-driven sensing, this study proposes a multilingual semantic–numerical collaborative Transformer framework to construct a unified multimodal financial sensing architecture for intelligent anomaly sensing and risk perception. Within the proposed sensing paradigm, multilingual texts are conceptualized as semantic sensors that continuously emit event-driven sensing signals, while market prices, trading volumes, and order book dynamics are modeled as heterogeneous numerical sensor streams reflecting behavioral market sensing responses. These heterogeneous sensors are jointly integrated through a cross-modal sensor fusion architecture. A cross-modal temporal alignment attention mechanism is designed to explicitly model dynamic lag structures between semantic sensing signals and numerical sensor responses, enabling temporally adaptive sensor-level alignment and fusion. To enhance sensing robustness, a multilingual semantic noise-robust encoding module is introduced to suppress unreliable textual sensor noise and stabilize cross-lingual semantic sensing representations. Furthermore, a semantic–numerical collaborative risk fusion module is constructed within a shared latent sensing space to achieve adaptive sensor contribution weighting and cross-sensor feature coupling, thereby improving anomaly sensing accuracy and robustness under complex multimodal sensing environments. Extensive experiments conducted on real-world multi-market financial sensing datasets demonstrate that the proposed artificial intelligence-driven sensing framework significantly outperforms representative statistical and deep learning baselines. The framework achieves a Precision of $0.852$, Recall of $0.781$, F1-score of $0.815$, and an AUC of $0.892$, while substantially improving early warning time in practical risk sensing scenarios. In cross-market transfer settings, the proposed sensing architecture maintains stable anomaly sensing performance under bidirectional domain shifts, with AUC consistently exceeding $0.86$, indicating strong structural generalization across heterogeneous sensing environments. Ablation analysis further verifies that temporal sensor alignment, semantic sensor denoising, and collaborative cross-sensor risk coupling contribute independently and synergistically to the overall sensing performance. Overall, this study establishes a scalable multimodal intelligent sensing framework for dynamic financial anomaly sensing, providing an effective artificial intelligence-driven sensing solution for cross-market risk surveillance and adaptive financial signal sensing. Full article

This study proposes a unified multimodal temporal motion state perception framework for optical imaging-oriented biomedical applications, integrating visual skeleton sequences, inertial measurement unit (IMU) signals, and surface electromyography (EMG) signals. The framework utilizes modality-specific encoders and a cross-modal temporal alignment attention mechanism to explicitly model temporal offsets from heterogeneous sensing streams. A multimodal temporal Transformer backbone is introduced to capture long-range motion dependencies and cross-modal interactions, while an uncertainty-aware fusion module dynamically allocates weights based on modality confidence. Experimental results demonstrate that the proposed approach achieves an accuracy of 94.37%, an F1-score of 93.95%, and a mean average precision of 96.02%, outperforming mainstream baseline models. Robustness evaluations further confirm stable performance under visual occlusion and sensor noise. These results indicate that the framework provides a highly accurate and robust solution for rehabilitation assessment, sports training monitoring, and wearable intelligent interaction systems. Full article

Dark current represents a fundamental limiting factor in photodiode performance, establishing the noise floor and constraining detectivity in low-light applications. This comprehensive literature review examines publications covering the physical mechanisms underlying dark current generation and diverse techniques employed for its reduction. Covered mechanisms include diffusion current, Shockley–Read–Hall (SRH) generation–recombination, trap-assisted tunneling, band-to-band tunneling, and surface leakage, each examined with respect to its physical origin and characteristic signatures. Reduction strategies are categorized into thermal management approaches, surface passivation techniques including atomic-layer-deposited aluminum oxide (ALD Al₂O₃), guard ring architectures (attached, floating, and combined configurations), gettering and defect engineering methods, doping profile optimization, bias voltage management, and advanced device architectures such as pinned photodiodes and black silicon structures. A classification table organizes all the reviewed literature by material system, reduction technique, and key findings. Special emphasis is placed on silicon, germanium, III–V compounds, and emerging material photodiodes relevant to near-infrared detection, CMOS imaging, single-photon avalanche diodes (SPADs), and Time-of-Flight (ToF) applications. Full article

To address the issues of uneven grayscale distribution, weak defect features, and small target scales on the coating surface of LCD polarizers during manufacturing, an improved YOLOv10-N-based method is proposed for surface defect detection. First, a polarizer coating defect dataset is constructed based on the LCD polarizer coating process and the characteristics of coating defects. Adaptive median filtering is then employed for image denoising, while a particle-swarm-optimization-based improved histogram equalization method is adopted for image enhancement. Next, the Scale-aware Pyramid Pooling (SCPP) module is introduced into the C2f module of the backbone network to construct the C2f_SCPP feature extraction module, thereby improving the model’s ability to detect coating defects with different morphologies through multi-scale semantic feature fusion. In addition, rotation-equivariant convolution PreCM is incorporated into the SPPF module of the backbone network to build the SPPF_PreCM module, which effectively suppresses feature redundancy and scale conflicts while strengthening the representation of tiny defects. Finally, while retaining the original Distribution Focal Loss (DFL) branch of YOLOv10, WIoU is used to replace CIoU as the IoU loss term in bounding box regression, thereby improving localization accuracy and accelerating model convergence during training. Experimental results show that, compared with YOLOv10-N, the proposed method improves mAP@0.5 and mAP@0.5:0.95 by 1.8 and 2.8 percentage points, respectively, demonstrating its effectiveness for polarizer coating defect detection. However, its generalization capability under diverse production environments, varying illumination conditions, and complex noise scenarios still requires further investigation. Full article

Citrus trees exhibit severe alternate bearing, resulting in significant annual yield fluctuations and posing substantial challenges to orchard management planning. Accurate citrus bud counting provides an effective solution by supplying essential data for tree-level and orchard-level yield prediction. However, citrus buds are extremely small (5–10 mm in diameter) and are frequently occluded by leaves during the flowering stage, which makes precise detection highly challenging in complex orchard environments. To address these challenges, this paper proposes a Contextual and Frequency-Aware Detector (CFADet) for robust citrus bud detection. Specifically, an Enhanced Feature Fusion (EFF) module is introduced in the neck to refine multi-scale feature aggregation and strengthen information flow for small targets. A Contextual Boundary Enhancement Module (CBEM) is designed to capture surrounding contextual cues and enhance boundary representation through dimensional interaction and max-pooling operations. To suppress background interference, a Frequency-Aware Module (FAM) is developed to adaptively recalibrate frequency components in the amplitude spectrum, thereby enhancing target features while reducing background noise. In addition, Spatial-to-Depth Convolution (SPDConv) is employed to reconstruct the backbone to preserve fine-grained bud features while reducing model parameters. Experimental results show that CFADet achieves 81.1% precision, 80.9% recall, 81.0% F1-score, and 87.8% mAP, with stable real-time performance on mobile devices in practical orchard scenarios. This study presents a preliminary investigation into robust citrus bud detection in real-world orchard environments and provides a promising technical foundation for intelligent orchard monitoring and early yield estimation, while further validation on larger and more diverse datasets is still required. Full article

Accurate and rapid transient voltage stability assessment is crucial for the safe and stable operation of new energy bases in desert and grassland regions. Existing deep learning methods fail to adequately capture the high-dimensional dynamic coupling features of transient voltage signals in large-scale renewable energy bases with UHVDC transmission, and suffer from poor performance under class-imbalanced sample conditions. This paper proposes a transient voltage stability assessment method utilizing continuous wavelet transform (CWT) time–frequency images and a deep residual network (ResNet-50). CWT with the Morlet wavelet basis converts voltage time-series signals into multi-scale time–frequency images to simultaneously capture temporal and frequency-domain transient features. An improved focal loss (FL) function is introduced to dynamically adjust category weights based on actual sample distribution, enhancing model robustness under extreme class imbalance. The proposed method is validated on a modified IEEE 39-bus system incorporating the Qishao UHVDC line and wind/photovoltaic integration in Northwest China, using 1490 simulation samples under diverse fault scenarios. Results demonstrate that the proposed CWT-ResNet achieves 98.88% accuracy, 94.74% precision, 100% recall, and 97.29% F1-score, outperforming SVM, 1D-CNN, and 1D-ResNet baselines. Under 5 dB noise conditions, the method maintains over 90% accuracy, demonstrating strong noise robustness. Full article

Adverse drug reaction (ADR) detection is essential for ensuring drug safety and effective pharmacovigilance. The rapid growth of users’ medication reviews posted on social media has introduced a valuable new data source for ADR detection. However, the large scale and high noise inherent in social media text pose substantial challenges to existing detection methods. Although large language models (LLMs) exhibit strong robustness to noisy and interfering information, they are often limited by issues such as stochastic outputs and hallucinations. To address these challenges, this paper proposes two generative detection frameworks based on Chain of Thought (CoT), namely LLaMA-DetectionADR for Supervised Fine-Tuning (SFT) and DetectionADRGPT for low-resource in-context learning. LLaMA-DetectionADR automatically generates CoT reasoning sequences to construct an instruction tuning dataset, which is then used to fine-tune the LLaMA3-8B model via Quantized Low-Rank Adaptation (QLoRA). In contrast, DetectionADRGPT leverages clustering algorithms to select representative unlabeled samples and enhances in-context learning by incorporating CoT reasoning paths together with their corresponding labels. Experimental results on the Twitter and CADEC social media datasets show that LLaMA-DetectionADR achieves excellent performance, with F1 scores of 92.67% and 86.13%, respectively. Meanwhile, DetectionADRGPT obtains competitive F1 scores of 87.29% and 82.80% with only a few labeled examples, approaching the performance of fully supervised advanced models. The overall results demonstrate the effectiveness and practical value of the proposed CoT-based generative frameworks for ADR detection from social media. Full article

Accurate monitoring of crop phenology is essential for precision agriculture and yield forecasting. However, satellite-derived time series often suffer from inherent noise, such as residual atmospheric effects and mixed pixels, as well as a frequent lack of ground-truth data in agriculture. In response, this study proposes an algorithm to define the type of spectral signatures for the principal phenological stages of crops, using them as the foundation for training supervised machine learning classification models. The algorithm was developed using Fuzzy C-Means (FCM) clustering to identify the spectral signature reference groups in winter wheat across the Burgos region (Spain) during the 2020 and 2021 growing seasons. To enhance cluster independence and biological coherence, a multi-step filtering process was implemented, including spectral purity (membership degree, SAM, and SAMder) and temporal coherence filters. The filtered and labeled dataset (80% original Burgos dataset) was used to train supervised classification models (KNN and XGBoost). The models’ reliability was verified through three wheat tests (remaining 20%), labeled using other clustering techniques, and an independent barley dataset from diverse geographic locations (Valladolid and Soria). The filtering process significantly improved cluster stability by removing outliers and transition spectral signatures. The supervised models demonstrated exceptional performance; the KNN model slightly outperformed XGB, achieving a mean Accuracy of 0.977, a Kappa of 0.967, and an F1-score of 0.977 in the wheat external test. Furthermore, the model showed, when applied to barley, that its phenological spectral signatures are equivalent in shape to those of wheat, with an Accuracy of 0.965 and an F1-score of 0.974. In addition, it was verified that the type spectral signatures remain the same regardless of the location. This study presents a robust classification tool capable of labeling four key phenological stages (tillering, stem elongation, ripening, and senescence) without ground truth. By effectively removing inherent satellite noise, the proposed methodology produces organized, cleaned datasets. This structured foundation is critical for future research integrating spectral signatures with harvester data to develop high-precision yield prediction models. Full article