Search Results (104)

Major depressive disorder requires scalable, low-burden screening tools. We examined whether three-channel resting-state EEG can support reliable discrimination between major depressive disorder and healthy controls using a lightweight model compatible with portable implementations. This work makes three main contributions: (i) a compact hybrid fusion model combining raw-window Conv1D embeddings with per-channel spectral–statistical descriptors for three-channel resting-state EEG, (ii) a leakage-resistant subject-independent (cross-subject) evaluation protocol with subject-level inference via majority voting, and (iii) a preliminary external feasibility test on an independent portable three-channel cohort without fine-tuning. The proposed model fuses a Conv1D encoding of raw ≈15 s eyes-closed windows (3840 samples; 15.36 s at 250 Hz) with per-channel spectral and statistical descriptors. Training uses subject-independent splits to avoid leakage, class weighting, and data augmentation (including MixUp); hyperparameters are selected via randomized search with refinement. The model is trained on a publicly available MDD dataset and subsequently applied, without fine-tuning, on an independent acquisition of 20 subjects recorded with a portable three-channel device; we report both window-level and subject-level (majority-vote) performance. On the held-out test subjects from the public dataset, the hybrid model attains 93.43% window-level accuracy. The independent evaluation is reported as a preliminary external feasibility analysis; given the small cohort, we report subject-level performance with 95% confidence intervals to reflect uncertainty and avoid over-interpreting cross-device generalization. The model occupies approximately 40.19 MB on disk, and the architecture is compatible with post-training int8 (TFLite) quantization for resource-constrained hardware. These results, obtained on limited samples, support the feasibility of three-channel EEG for major depressive disorder detection using a lightweight hybrid architecture and motivate prospective clinical validation, on-device inference and quantization studies, and broader evaluation across centers and devices. Full article

Text-to-music generation aims to automatically produce audio content with semantic consistency and coherent musical structure based on natural language descriptions. However, existing methods still face challenges in terms of style diversity, rhythmic consistency, and long-term structural modeling. To address these issues, we propose a novel text-to-music generation model, termed MusicDiffusionNet (MDN), which integrates diffusion models with the WaveNet architecture to jointly model musical semantics and temporal structure in a continuous latent space. By decoupling high-level semantic conditioning from low-level audio generation, MDN enhances its ability to model long-range musical structure while improving semantic alignment between text and generated music with stable generation behavior. Building upon this framework, we further design two complementary mixing strategies to improve generation quality and structural coherence. Adaptive Style Mixing (ASM) performs weighted interpolation among stylistically similar music samples in the style embedding space, incorporating key and harmonic compatibility constraints to expand the style distribution while avoiding dissonance. Multi-scale Temporal Mixing (MTM) adopts beat-aware temporal decomposition, mixing, and reorganization across multiple time scales, thereby enhancing the modeling of both local and global temporal variations while preserving rhythmic periodicity and musical groove. Both strategies are integrated into the diffusion process as conditional augmentation mechanisms, contributing to improved learning stability and representational capacity under limited data conditions. Experimental results on the Audiostock dataset demonstrate that MDN and its mixing strategies achieve consistent improvements across multiple objective metrics, including generation quality, style diversity, and rhythmic coherence, validating the effectiveness of the proposed approach for text-to-music generation. Full article

Pain recognition based on multimodal physiological signals remains a challenge, not only because of the limited training data, but also due to the varying responses of individuals. In this article, we present a randomized modality mixing technique (Modmix) for multimodal data augmentation and a patchwise radial basis function (RBF) network designed to improve robustness in limited and highly heterogeneous data. Modmix generates new samples by randomly swapping modalities between existing data points, creating new data in a very simple but effective way. The RBF patch network divides the input into randomly selected, overlapping patches that capture local similarities between modalities. Each patch network is trained end-to-end using stochastic gradient descent. Moreover, the model’s performance is further improved by using multiple independently trained networks and combining them into a single decision. Experiments with the two different pain datasets X-ITE and BioVid were performed under limited training data conditions, where only approximately 30% of the original datasets were used for training. With both datasets the RBF patch network achieved significant improvements for a subset of subjects, resulting in a similar or even slightly better mean accuracy compared to competing related models such as random forest and support vector machine. Full article

Background/Objectives: Cytochrome P450 3A4 (CYP3A4) metabolizes approximately 30–50% of clinically used drugs; thus, accurate prediction of CYP3A4 inhibition is essential for early assessment of drug–drug interaction (DDI) risk and toxicity. This study evaluated an integrated artificial intelligence framework for predicting CYP3A4 inhibition (%) using a large, curated chemical dataset. Methods: A dataset of 23,713 compounds was compiled from the Korea Chemical Bank and multiple commercial and public databases. Vector-based machine learning (ML) models (LightGBM, XGBoost, CatBoost, and a weighted ML ensemble) and graph neural network (GNN) models (O-GNN with contrastive learning and manifold mixup (O-GNN + CL + Mixup), D-MPNN, GINE, and GATv2) were evaluated. Manifold mixup was applied during GNN training, and SMILES enumeration-based test-time augmentation was used at inference. The best-performing ML and GNN models were integrated using a weighted ensemble strategy. Model interpretability was examined using SHAP analysis for ML models and occlusion sensitivity analysis for O-GNN + CL + Mixup. Results: The weighted ML ensemble achieved the best performance among ML models (RMSE = 19.1031, Pearson correlation coefficient (PCC) = 0.7566); the O-GNN + CL + Mixup model performed the best among GNN models (RMSE = 20.1002, PCC = 0.7265). The hybrid model achieved improved predictive accuracy (RMSE = 19.0784, PCC = 0.7570). External validation on 100 newly generated experimental data points confirmed generalizability (Custom Metric = 0.8035). Conclusions: This study demonstrated that integrating ML and GNN models with data augmentation strategies improves the robustness and interpretability of CYP3A4 inhibition prediction and established a practical framework for metabolic screening and DDI risk assessment. Full article

The growing global reliance on solar photovoltaic (PV) systems requires robust, automated inspection techniques to ensure reliability and efficiency. Thermal infrared (IR) imaging is widely used for detecting PV faults; however, accurate classification remains challenging due to severe class imbalance, low thermal contrast, and high inter-class visual similarity among fault types. This study proposes a hierarchical deep learning framework for thermal PV fault classification, integrating a multi-class dataset-balancing strategy to enhance representational efficiency. The proposed framework consists of two major components: (i) a hierarchical two-stage classification scheme that mitigates data imbalance and leverages limited labeled data for improved fault discrimination; and (ii) a contrast-preserving MixUp augmentation technique designed explicitly for low-contrast thermal imagery, improving minority fault class recognition and overall robustness. Comprehensive experiments were conducted on benchmark 8-class thermal PV datasets using nine deep network architectures. Dataset refactoring decisions are validated through quantitative inter-class distance analysis using multiple complementary metrics. Results demonstrate that the proposed hierarchical SlantNet model achieves the best trade-off between accuracy and computational efficiency, achieving an F1-Efficiency Index of 337.6 and processing 42,072 images per second on a GPU, over twice the efficiency of conventional approaches. Comparatively, the Swin-T Transformer attained the highest classification accuracy of 89.48% and F1 score of 80.50%, while SlantNet achieved 86.15% accuracy and 73.03% F1 score with substantially higher inference speed, highlighting its real-time potential. Ablation studies on augmentation and regularization strategies confirm that the proposed techniques significantly improve minority class detection without compromising overall performance, with detailed per-class precision, recall, and F1 analysis. The proposed framework delivers a high-accuracy, low-latency, and edge-deployable solution for automated PV inspection, facilitating seamless integration into operational PV plants for real-time fault diagnosis. Full article

Plant disease recognition is a critical technology for ensuring food security and advancing precision agriculture. However, challenges such as class imbalance, heterogeneous image quality, and limited model interpretability remain unresolved. In this study, we propose a Synergistic Dual-Augmentation and Class-Aware Hybrid (SDA-CAH) model designed to achieve robust and interpretable recognition of plant diseases. Our approach introduces two innovative augmentation strategies: (1) an optimized MixUp method that dynamically integrates class-specific features to enhance the representation of minority classes; and (2) a customized augmentation pipeline that combines geometric transformations with photometric perturbations to strengthen the model’s resilience against image variability. To address class imbalance, we further design a class-aware hybrid sampling mechanism that incorporates weighted random sampling, effectively improving the learning of underrepresented categories and optimizing feature distribution. Additionally, a Grad-CAM–based visualization module is integrated to explicitly localize lesion regions, thereby enhancing the transparency and trustworthiness of the predictions. We evaluate SDA-CAH on the PlantVillage dataset using a pretrained EfficientNet-B0 as the backbone network. Systematic experiments demonstrate that our model achieves 99.95% accuracy, 99.89% F1-score, and 99.89% recall, outperforming several strong baselines, including an optimized Xception (99.42% accuracy, 99.39% F1-score, 99.41% recall), standard EfficientNet-B0 (99.35%, 99.32%, 99.33%), and MobileNetV2 (95.77%, 94.52%, 94.77%). For practical deployment, we developed a web-based diagnostic system that integrates automated recognition with treatment recommendations, offering user-friendly access for farmers. Experimental evaluations indicate that SDA-CAH outperforms existing approaches in predictive accuracy and simultaneously defines a new paradigm for interpretable and scalable plant disease recognition, paving the way for next-generation precision agriculture. Full article

Stroke is a leading cause of long-term disability worldwide, necessitating efficient motor function assessment to guide personalized rehabilitation. The Fugl–Meyer Assessment for the Upper Extremity (FMA-UE) is a clinical gold-standard tool, but it is time consuming and requires trained clinicians, which limits its frequency of use and accessibility. While wearable sensors and deep learning offer promising avenues for remote assessment, accurately estimating detailed sub-scores of specific motor functions remains a significant challenge. This work introduces a deep learning framework for automated estimation of FMA-UE total and subdivision scores. Data was collected from 15 participants using four inertial measurement units (IMUs) positioned on the arm and trunk. Each participant performed seven specialized functional motions designed for comprehensive joint synergy involvement within ten minutes. A therapist-rated FMA-UE provided true scores. The proposed model leverages the integration of an LSTM-based autoencoder and mixup augmentation to enhance generalization and robustness. Evaluated through a leave-one-subject-out cross-validation (LOSOCV), the estimator demonstrated strong performance, achieving R² values exceeding 0.82. Pearson’s correlation coefficient r was more than 0.90, and the normalized root-mean-square errors (NRMSE) were below 0.14 for all subparts (A–D). Crucially, the total FMA-UE score was estimated with an NRMSE of 0.0678. These results show that a concise, sensor-based assessment can reliably predict detailed motor function scores. Full article

Aero-engine ablation detection is a critical task in aircraft health management, yet existing rotation-based object detection methods often face challenges of high computational complexity and insufficient local feature extraction. This paper proposes an improved YOLOv11 algorithm incorporating Context-guided Large-kernel attention and Rotated detection head, called CLR-YOLOv11. The model achieves synergistic improvement in both detection efficiency and accuracy through dual structural optimization, with its innovations primarily embodied in the following three tightly coupled strategies: (1) Targeted Data Preprocessing Pipeline Design: To address challenges such as limited sample size, low overall image brightness, and noise interference, we designed an ordered data augmentation and normalization pipeline. This pipeline is not a mere stacking of techniques but strategically enhances sample diversity through geometric transformations (random flipping, rotation), hybrid augmentations (Mixup, Mosaic), and pixel-value transformations (histogram equalization, Gaussian filtering). All processed images subsequently undergo Z-Score normalization. This order-aware pipeline design effectively improves the quality, diversity, and consistency of the input data. (2) Context-Guided Feature Fusion Mechanism: To overcome the limitations of traditional Convolutional Neural Networks in modeling long-range contextual dependencies between ablation areas and surrounding structures, we replaced the original C3k2 layer with the C3K2CG module. This module adaptively fuses local textural details with global semantic information through a context-guided mechanism, enabling the model to more accurately understand the gradual boundaries and spatial context of ablation regions. (3) Efficiency-Oriented Large-Kernel Attention Optimization: To expand the receptive field while strictly controlling the additional computational overhead introduced by rotated detection, we replaced the C2PSA module with the C2PSLA module. By employing large-kernel decomposition and a spatial selective focusing strategy, this module significantly reduces computational load while maintaining multi-scale feature perception capability, ensuring the model meets the demands of high real-time applications. Experiments on a self-built aero-engine ablation dataset demonstrate that the improved model achieves 78.5% mAP@0.5:0.95, representing a 4.2% improvement over the YOLOv11-obb which model without the specialized data augmentation. This study provides an effective solution for high-precision real-time aviation inspection tasks. Full article

Background: Automatic adventitious lung sound classification using deep learning is a promising strategy for objective respiratory disease screening. Evaluating model performance is challenging, particularly with imbalanced clinical datasets. This study compares CNN architectures and proposes a dual-stream classification approach. Methods: Using the public ICBHI 2017 dataset, we compared five pre-trained architectures: VGG16, VGG19, InceptionV3, MobileNetV2, and ResNet152V2. To mitigate class imbalance, we implemented pitch shifting, random shifting, and mixup data augmentation. We also developed and evaluated a novel VGGish-dual-stream network. The primary endpoint was the Average Score (AS), the arithmetic mean of Sensitivity and Specificity. Results: Among benchmarked models, ResNet152V2 achieved the highest AS ($0.541$), approaching the state-of-the-art range (0.56–0.58). This performance was characterised by a high Specificity ($0.67$) but low Sensitivity ($0.41$). Our proposed dual-stream network yielded a more balanced, albeit slightly lower, performance with an AS of $0.508$. Conclusions: Standard CNN architectures like ResNet152V2 can achieve competitive classification performance but may exhibit a clinically significant bias towards high specificity at the expense of sensitivity. This trade-off poses a risk of missing pathological events (false negatives). To ensure clinical safety and utility, future work must prioritise strategies that explicitly improve model sensitivity. Full article

Rotating machinery is a core component of modern industry, and its operational state directly affects system safety and reliability. In order to achieve intelligent fault diagnosis of bearings under complex working conditions, the health management of bearings has become an important issue. Although deep learning has shown remarkable advantages, its performance still relies on the assumption that the training and testing data share the same distribution, which often deteriorates in real applications due to variations in load and rotational speed. This study focused on the scenario of domain generalization (DG) and proposed a Meta-Learning with Gradient Alignment and Data Augmentation (MGADA) method for cross-domain bearing fault diagnosis. Within the meta-learning framework, Mixup-based data augmentation was performed on the support set in the inner loop to alleviate overfitting under small-sample conditions and enhanced task-level data diversity. In the outer loop optimization stage, an arithmetic gradient alignment constraint was introduced to ensure consistent update directions across different source domains, thereby reducing cross-domain optimization conflicts. Meanwhile, a centroid convergence constraint was incorporated to enforce samples of the same class from different domains to converge to a shared centroid in the feature space, thus enhancing intra-class compactness and semantic consistency. Cross-working-condition experiments conducted on the Case Western Reserve University (CWRU) bearing dataset demonstrate that the proposed method achieves high classification accuracy across different target domains, with an average accuracy of 98.89%. Furthermore, ablation studies confirm the necessity of each module (Mixup, gradient alignment, and centroid convergence), while t-SNE and confusion matrix visualizations further illustrate that the proposed approach effectively achieves cross-domain feature alignment and intra-class aggregation. The proposed method provides an efficient and robust solution for bearing fault diagnosis under complex working conditions and offers new insights and theoretical references for promoting domain generalization in practical industrial applications. Full article

In order to ensure the earthquake safety of existing buildings, retrofitting applications come to the fore in terms of being fast and cost-effective. Among these applications, fiber-reinforced polymer (FRP) composites are widely preferred thanks to their advantages such as high strength, corrosion resistance, applicability without changing the cross-section and easy assembly. This study presents a data augmentation, modeling, and comparison-based approach to predict the fire resistance (FR) of FRP-strengthened reinforced concrete beams. The aim of this study was to explore the role of data augmentation in enhancing prediction accuracy and to find out which augmentation method provides the best prediction performance. The study utilizes an experimental dataset taken from the existing literature. The dataset contains inputs such as varying geometric dimensions and FRP-strengthening levels. Since the original dataset used in the study consisted of 49 rows, the data size was increased using augmentation methods to enhance accuracy in model training. In this study, Gaussian noise, Regression Mixup, SMOGN, Residual-based, Polynomial + Noise, PCA-based, Adversarial-like, Quantile-based, Feature Mixup, and Conditional Sampling data augmentation methods were applied to the original dataset. Using each of them, individual augmented datasets were generated. Each augmented dataset was firstly trained using eXtreme Gradient Boosting (XGBoost) with 10-fold cross-validation. After selecting the best-performing augmentation method (Adversarial-like) based on XGBoost results, the best-performing augmented dataset was later evaluated in HyperNetExplorer, a more advanced NAS tool that can find the best performing hyperparameter optimized ANN for the dataset. ANNs achieving R² = 0.99, MSE = 22.6 on the holdout set were discovered in this stage. This whole process is unique for the FR prediction of structural elements in terms of the data augmentation and training pipeline introduced in this study. Full article

Existing fault diagnosis methods assume the identical distribution of training and test data, failing to adapt to source–target domain differences in industrial scenarios and limiting generalization. They also struggle to explore inter-domain correlations with scarce labeled target samples, leading to poor convergence and generalization. To address this, our paper proposes a cross-domain few-shot intelligent fault diagnosis method based on Mixup data augmentation. Firstly, a Mixup data augmentation method is used to linearly combine source domain and target domain data in a specific proportion to generate mixed-domain data, enabling the model to learn correlations and features between data from different domains and improving its generalization ability in cross-domain few-shot learning tasks. Secondly, a feature decoupling module based on the self-attention mechanism is proposed to extract domain-independent features and domain-related features, allowing the model to further reduce the domain distribution gap and effectively generalize source domain knowledge to the target domain. Then, the model parameters are optimized through a multi-task learning mechanism consisting of sample classification tasks and domain classification tasks. Finally, applications in classification tasks on multiple sets of equipment fault datasets show that the proposed method can significantly improve the fault recognition ability of the diagnosis model under the conditions of large distribution differences in the target domain and scarce labeled samples. Full article

To tackle phenotypic variability and detection accuracy issues of tea shoots in open-air gardens due to lighting and varietal differences, this study proposes Tea CycleGAN and a data augmentation method. It combines multi-scale image style transfer with spatial consistency dataset generation. Using Longjing 43 and Zhongcha 108 as cross-domain objects, the generator integrates SKConv and a dynamic multi-branch residual structure for multi-scale feature fusion, optimized by an attention mechanism. A deep discriminator with more conv layers and batch norm enhances detail discrimination. A global–local framework trains on 600 × 600 background and 64 × 64 tea shoots regions, with a restoration-paste strategy to preserve spatial consistency. Experiments show Tea CycleGAN achieves FID scores of 42.26 and 26.75, outperforming CycleGAN. Detection using YOLOv7 sees mAP rise from 73.94% to 83.54%, surpassing Mosaic and Mixup. The method effectively mitigates lighting/scale impacts, offering a reliable data augmentation solution for tea picking. Full article

Semi-supervised object detection (SSOD) has emerged as a promising technique to boost the performance of the detectors, utilizing both labeled and unlabeled data. However, in marine environments, SSOD faces formidable challenges posed by complex conditions like shore-based landscapes, varying ship scales, and diverse weather, which complicate data acquisition and thus the generation of accurate pseudo-labels. To tackle these issues, we propose two novel strategies, depth-aware pseudo-label filtering (DAPF) and dynamic region mixup (DRMix) augmentation, from a data-centric perspective. Specifically, the DAPF strategy incorporates depth information as a prior to refine pseudo-labels by filtering out unreliable ones, thereby improving the quality of pseudo-label–data pairs used for training. Meanwhile, DRMix augmentation dynamically mixes images at the regional level, generating diverse and representative data suitable for maritime object detection tasks. Extensive experiments on maritime datasets validate the effectiveness of our approach, achieving mAP improvements of 2.2% on the SeaShips dataset and 0.9% on the Singapore Maritime dataset compared to other state-of-the-art (SOTA) methods. Our code will be made publicly available. Full article

Increasing road congestion is the main constraint that may influence the economic development of cities and urban freight transport efficiency because it generates additional costs related to delay, influences social life, increases environmental emissions, and decreases service quality. This may result from several factors, including an increase in logistics activities in the urban core. Therefore, this paper aims to define the relationship between the logistics sprawl phenomenon and congestion level. In this sense, we explored the literature to summarize the phenomenon of logistics sprawl in different cities and defined the dependent and independent variables. Congestion level was defined as the dependent variable, while the increasing distance resulting from logistics sprawl, along with city and operational flow characteristics, was treated as independent variables. We compared the performance of several models, including decision tree, support vector machine, gradient boosting, k-nearest neighbor, logistic regression and random forest. Among all the models tested, we found that the random forest algorithm delivered the best performance in terms of prediction. We combined both logistic regression—for its interpretability—and random forest—for its predictive strength—to define, explain, and interpret the relationship between the studied variables. Subsequently, we collected data from the literature and various databases, including transit city sources. The resulting dataset, composed of secondary and open-source data, was then enhanced through standard augmentation techniques—SMOTE, mixup, Gaussian noise, and linear interpolation—to improve class balance and data quality and ensure the robustness of the analysis. Then, we developed a Python code and executed it in Colab. As a result, we deduced an equation that describes the relationship between the congestion level and the defined independent variables. Full article