Search Results (12,224)

The unique geographical isolation and climate sensitivity of island ecosystems make them valuable for ecological research. The Normalized Difference Vegetation Index (NDVI) is an important indicator when monitoring and evaluating these systems, and its prediction has become a key research focus. However, island NDVI prediction remains uncertain due to a limited understanding of vegetation growth and insufficient high-quality data. Deterministic models fail to capture or quantify such uncertainty, often leading to overfitting. To address this issue, this study proposes an uncertainty prediction model for the island NDVI within a coding–prediction–decoding framework, referred to as a Convolutional Autoencoder–Regularized Bayesian Neural Network (CAE-RBNN). The model integrates a convolutional autoencoder with feature regularization to extract latent NDVI features, aiming to reconcile spatial scale disparities with environmental data, while a Bayesian Neural Network (BNN) quantifies uncertainty arising from limited samples and an incomplete understanding of the process. Finally, Monte Carlo sampling and SHAP analysis evaluate model performance, quantify predictive uncertainty, and enhance interpretability. Experiments on six islands in the Xisha archipelago demonstrate that CAE-RBNN outperforms the Convolutional Neural Network–Recurrent Neural Network (CNN-RNN), the Convolutional Recurrent Neural Network (ConvRNN), Convolutional Long Short-Term Memory (ConvLSTM), and Random Forest (RF). Among them, CAE-RBNN reduces the MAE and MSE of the single-time-step prediction task by 8.40% and 10.69%, respectively, compared with the suboptimal model and decreases them by 16.31% and 22.57%, respectively, in the continuous prediction task. More importantly, it effectively quantifies the uncertainty of different driving forces, thereby improving the reliability of island NDVI predictions influenced by the environment. Full article

Full waveform inversion (FWI) iteratively improves the accuracy of the model by minimizing the discrepancies between the predicted and the observed data. However, FWI commonly suffers from cycle skipping when the initial model is poor, leading to an erroneous result. To mitigate this problem, we propose deep-learning-backed adaptive waveform inversion (DL-AWI), which introduces a deep twin neural network to precondition the waveforms and compare the ratio of two signals with a zero-lag spike, thereby enhancing the stability of the inversion process. DL-AWI can project the synthetic and observed signals into an extended latent space via several convolutional neural networks (CNNs) with shared weights, which can accelerate the data matching. Compared with classic FWI methods, the proposed DL-AWI provides a wider space for model updates, significantly decreasing the risk of being trapped in local minima. We use synthetic and field examples to validate its efficiency in subsurface model inversion, and the results show that DL-AWI is robust even when a poor initial model is provided. Full article

This paper investigates an artificial intelligence (AI)-enhanced visible light communication (VLC) system for body area networks (BANs) based on a hybrid modulation framework that jointly employs quadrature amplitude modulation (QAM) and pulse-position modulation (PPM). The dual-modulation strategy leverages the high spectral efficiency of QAM together with the robustness of PPM to light-emitting diode (LED) nonlinearity and timing distortions, enabling simultaneous high-rate and reliable communication, two essential requirements in BAN applications. To address the nonlinear response of light-emitting diodes and the variability in indoor optical channels, the system integrates classical predistortion techniques with a deep learning equalizer combining convolutional neural network (CNN)–transformer layers. This hybrid model captures both local and long-range distortion patterns, improving symbol reconstruction for both modulation branches. The study further examines pilot-assisted equalization and adaptive bit loading, showing that these strategies strengthen link robustness under diverse channel conditions while enhancing spectral efficiency. The proposed architecture demonstrates that combining dual modulation with AI-driven equalization and adaptive transmission strategies leads to a more resilient and efficient VLC system, well-suited for the dynamic constraints of wearable and body-centric communication environments. Full article

Rice seed variety classification is crucial for seed quality control and breeding, yet practical deployment is often limited by the computational and memory demands of modern deep models. We propose SimpleEfficientCNN (SimpleEfficient: simple & efficient; CNN: convolutional neural network), an ultra-lightweight convolutional network built on depthwise separable convolutions for efficient fine-grained seed classification. Experiments were conducted on three datasets with distinct imaging characteristics: a self-constructed Guangdong dataset (7 varieties; 10,500 seeds imaged once and expanded to 112 K images via post-split augmentation), the public M600 rice subset (7 varieties; 9100 original images expanded to 112 K images using the same post-split augmentation pipeline for scale-matched comparison), and the International dataset (75 K images; official train/validation/test split provided by the original release and used as-is without any preprocessing or augmentation, 5 varieties). SimpleEfficientCNN achieved 98.52%, 88.07%, and 99.37% accuracy on the Guangdong, M600, and International test sets, respectively. With only 0.231 M parameters (≈92× fewer than ResNet34), it required 20.5 MB peak GPU memory and delivered 2.0 ms GPU latency (RTX 4090D, batch = 1, FP32) and 1.8 ms single-thread CPU median latency (Ryzen 9 7950X3D, batch = 1, FP32). These results indicate that competitive accuracy can be achieved with substantially reduced model size and inference cost, supporting deployment in resource-constrained agricultural settings. Full article

Adaptive optics (AO) aims to counteract wavefront distortions caused by atmospheric turbulence and inherent system errors. Aberration recovery accuracy and computational speed play crucial roles in its correction capability. To address the issues of slow wavefront aberration detection speed and low measurement accuracy in current wavefront sensorless adaptive optics, this paper proposes a wavefront correction method based on the EfficientNetV2-S model. The method utilizes paired focal plane and defocused plane intensity images to directly extract intensity features and reconstruct phase information in a non-iterative manner. This approach enables the direct prediction of wavefront Zernike coefficients from the measured intensity images, specifically for orders 3 to 35, significantly enhancing the real-time correction capability of the AO system. Simulation results show that the root mean square error (RMSE) of the predicted Zernike coefficients for D/r₀ values of 5, 10, and 15 are 0.038λ, 0.071λ, and 0.111λ, respectively, outperforming conventional convolutional neural network (CNN), ResNet50/101 and ConvNeXt-T models. The experimental results demonstrate that the EfficientNetV2-S model maintains good wavefront reconstruction and prediction capabilities at D/r₀ = 5 and 10, highlighting its high precision and robust wavefront prediction ability. Compared to traditional iterative algorithms, the proposed method offers advantages such as high precision, fast computation, no need for iteration, and avoidance of local minima in processing wavefront aberrations. Full article

Reinforcement Learning (RL) enables learning optimal decision-making strategies by maximizing cumulative rewards. Deep reinforcement learning (DRL) enhances this process by integrating deep neural networks (DNNs) for effective feature extraction from high-dimensional input data. Unlike prior studies focusing on algorithm design, we investigated the impact of different feature extractors, DNNs, on DRL performance. We propose an enhanced feature extraction model to improve control effectiveness based on the proximal policy optimization (PPO) framework in autonomous driving scenarios. Through a comparative analysis of well-known convolutional neural networks (CNNs), MobileNet, SqueezeNet, and ResNet, the experimental results demonstrate that our model achieves higher cumulative rewards and better control stability, providing valuable insights for DRL applications in autonomous systems. Full article

Background/Objectives: Orthodontically induced root resorption (OIRR) is a well-documented but undesired consequence of orthodontic treatment. This systematic review and meta-analysis aimed to assess the diagnostic performance of artificial intelligence (AI) models applied to cone-beam computed tomography (CBCT) for detecting and quantifying OIRR while evaluating their agreement with manual reference standards and the impact of model architecture, validation design, and quantification strategy. Methods: Comprehensive searches were conducted across PubMed/MEDLINE, Scopus, Web of Science, and EMBASE up to November 2025. Studies were included if they employed AI for OIRR diagnosis using CBCT and reported relevant performance metrics. Following PRISMA guidelines, data were extracted and a random-effect meta-analysis was performed. Subgroup analyses explored the influence of model design and validation. Results: Seven studies were included. Pooled sensitivity from three eligible studies was 0.903 (95% CI: 0.818–0.989), suggesting excellent true positive rates. Specificity ranged from 82% to 98%, and area under the receiver operating characteristic curve values reached up to 0.96 across studies using EfficientNet, U-Net, and other convolutional neural network (CNN)-based architectures. The pooled intraclass correlation coefficient for agreement with manual quantification was 1.000, reflecting near-perfect concordance. Subgroup analyzes showed slightly superior performance in CNN-only models compared to hybrid approaches, and better diagnostic metrics with internal validation. Linear assessments appeared more sensitive to early apical shortening than volumetric methods. Conclusions: AI models applied to CBCT demonstrate excellent diagnostic accuracy and high concordance with expert assessments for OIRR detection. These findings support their potential integration into clinical orthodontic workflows. Full article

Foreground segmentation and background subtraction are critical components in many computer vision applications, such as intelligent video surveillance, urban security systems, and obstacle detection for autonomous vehicles. Although extensively studied over the past decades, these tasks remain challenging, particularly due to rapid illumination changes, dynamic backgrounds, cast shadows, and camera movements. The emergence of supervised deep learning-based methods has significantly enhanced performance, surpassing traditional approaches on the benchmark dataset CDnet2014. In this context, this paper provides a comprehensive review of recent supervised deep learning techniques applied to background subtraction, along with an in-depth comparative analysis of state-of-the-art approaches available on the official CDnet2014 results platform. Specifically, we examine several key architecture families, including convolutional neural networks (CNN and FCN), encoder–decoder models such as FgSegNet and Motion U-Net, adversarial frameworks (GAN), Transformer-based architectures, and hybrid methods combining intermittent semantic segmentation with rapid detection algorithms such as RT-SBS-v2. Beyond summarizing existing works, this review contributes a structured cross-family comparison under a unified benchmark, a focused analysis of performance behavior across challenging CDnet2014 scenarios, and a critical discussion of the trade-offs between segmentation accuracy, robustness, and computational efficiency for practical deployment. Full article

Osteoarthritis (OA) is a prevalent joint disorder characterized by symptoms such as pain and stiffness, often leading to loss of function and disability. Knee osteoarthritis (KOA) represents the most prevalent type of osteoarthritis. KOA is usually detected using X-ray radiographs of the knee; however, the classification of disease severity remains subjective and varies among clinicians, motivating the need for automated assessment methods. In recent years, deep learning–based approaches have shown promising performance for KOA classification tasks, particularly when applied to structured imaging datasets. This review analyzes convolution neural network (CNN)-based approaches reported in the literature and compares their performance across multiple criteria. Studies were identified through systematic searches of IEEE Xplore, SpringerLink, Elsevier (ScienceDirect), Wiley Online Library, ACM Digital Library, and other sources such as PubMed and arXiv, with the last search conducted in March 2025. The review examines datasets used (primarily X-ray and MRI), preprocessing strategies, segmentation techniques, and deep learning architectures. Reported classification accuracies range from 61% to 98%, depending on the dataset, imaging modality, and task formulation. Finally, this paper highlights key methodological limitations in existing studies and outlines future research directions to improve the robustness and clinical applicability of deep learning–based KOA classification systems. Full article

Electroencephalography-based motor imagery (EEG-MI) classification is a cornerstone of Brain–Computer Interface (BCI) systems, enabling the identification of motor intentions by decoding neural patterns within EEG signals. However, conventional methods, predominantly reliant on convolutional neural networks (CNNs), are proficient at extracting local temporal features but struggle to capture long-range dependencies and global contextual information. To address this limitation, we propose a Triple-path Heterogeneous Feature Collaboration Network (TPHFC-Net), which synergistically integrates three distinct temporal modeling pathways: a multi-scale Temporal Convolutional Network (TCN) to capture fine-grained local dynamics, a Transformer branch to model global dependencies via multi-head self-attention, and a Long Short-Term Memory (LSTM) network to track sequential state evolution. These heterogeneous features are subsequently fused adaptively by a dynamic gating mechanism. In addition, the model’s robustness and discriminative power are further augmented by a lightweight front-end denoising diffusion model for enhanced noisy feature representation and a back-end prototype attention mechanism to bolster the inter-class separability of non-stationary EEG features. Extensive experiments on the BCI Competition IV-2a and IV-2b datasets validate the superiority of the proposed model, achieving mean classification accuracies of 82.45% and 89.49%, respectively, on the subject-dependent MI task and significantly outperforming existing mainstream baselines. Full article

Emotions are classified into the valence dimension (positive and negative) and the arousal dimension (low and high). Using electrocardiogram (ECG) phase space diagrams and a deep learning approach, emotional states were identified in this study. The DREAMER database was utilized for training and testing the classification model developed. We examined different ECG phase space parameters and compared different deep learning models, including the Visual Geometry Group and Residual networks, and a simple convolutional neural network (CNN) with attention modules. Among the models, a simple four-layer CNN integrated with a convolutional block attention module showed the best performance. Experimental results indicate that the model achieved an accuracy of 87.89% for the valence dimension and 91.79% for the arousal dimension. Compared with existing models, the developed model demonstrates superior performance in emotion recognition. Emotional changes produce noticeable variations in the trajectory patterns of ECG phase space diagrams, which enhance the model’s ability to recognize emotions, even when using relatively simple networks. Full article

This work investigates the effect of ambient humidity on the Electromechanical Impedance (EMI) signatures of steel-reinforced concrete (RC) for structural health monitoring (SHM). The influence of varying relative humidity (%RH) is quantified using three RC blocks containing piezoelectric sensors bonded to the steel reinforcements of the RC blocks. We show that the the Root Mean Squared Deviation (RMSD) score is strongly affected by humidity, highlighting the need to address humidity effects to achieve robust damage detection using EMI. Using the reactive component of the EMI (X) in the range of 20 kHz and 120 kHz, a three-layer one-dimensional convolution neural network (1D-CNN) was able to estimate ambient %RH between 20% and 80%, with a Mean Absolute Error (MAE) of 2.14%RH. The results highlight the significant impact of humidity on EMI-based SHM and suggests that the imaginary part of the EMI signature can be used to detect the effect of humidity. This work provides a foundation for more robust SHM systems in humidity-varying environments applicable to a wide range of concrete infrastructure. Full article

Resource-limited settings continue to face challenges in the identification of COVID-19, bacterial pneumonia, viral pneumonia, and normal lung conditions because of the overlap of CT appearance and inter-observer variability. We justify a hybrid architecture of deep learning which combines hand-designed descriptors (Histogram of Oriented Gradients, Local Binary Patterns) and a 20-layer Convolutional Neural Network with dual self-attention. Handcrafted features were then trained with Support Vector Machines, and ensemble averaging was used to integrate the results with the CNN. The confidence level of 0.7 was used to mark suspicious cases to be reviewed manually. On a balanced dataset of 14,000 chest CT scans (3500 per class), the model was trained and cross-validated five-fold on a patient-wise basis. It had 97.43% test accuracy and a macro F1-score of 0.97, which was statistically significant compared to standalone CNN (92.0%), ResNet-50 (90.0%), multiscale CNN (94.5%), and ensemble CNN (96.0%). A further 2–3% enhancement was added by the self-attention module that targets the diagnostically salient lung regions. The predictions that were below the confidence limit amounted to only 5 percent, which indicated reliability and clinical usefulness. The framework provides an interpretable and scalable method of diagnosing multiclass lung disease, especially applicable to be deployed in healthcare settings with limited resources. The further development of the work will involve the multi-center validation, optimization of the model, and greater interpretability to be used in the real world. Full article

Traffic classification remains a critical challenge in the Internet of Things (IoT), particularly for enhancing security and ensuring Quality of Service (QoS). Although deep learning methods have shown strong performance in traffic classification, learning diverse and complementary representations across heterogeneous network traffic patterns remains difficult. To address this issue, this study proposes a novel Mixture of Experts (MoE) architecture for multiclass traffic classification in IoT environments. The proposed model integrates five specialized expert networks, each targeting a distinct feature category in network traffic. Specifically, it employs a Dense Neural Network for general features, a Convolutional Neural Network (CNN) for spatial patterns, a Gated Recurrent Unit (GRU)-based model for statistical variations, a Convolutional Autoencoder (CAE) for frequency-domain representations, and a Long Short-Term Memory (LSTM) for temporal dependencies. A dynamic gating mechanism, coupled with an Attention-based Learnable Fusion (ALF) module, adaptively aggregates the experts’ outputs to produce the final classification decision. The proposed ALF-MoE model was evaluated on three public benchmark datasets, such as ISCX VPN-nonVPN, Unicauca, and UNSW-IoTraffic, achieving accuracies of 98.43%, 98.96%, and 97.93%, respectively. These results confirm its effectiveness and reliability across diverse scenarios. It also outperforms baseline methods in terms of its accuracy and the F1-score. Full article

Accurate prediction, forecasting and interpretability of air pollutant concentrations are important for sustainable environmental management and protecting public health. An integrated artificial intelligence (AI) framework is proposed to predict, forecast and analyse six major air pollutants, such as particulate matter concentrations (PM_2.5 and PM₁₀), ground-level ozone (O₃), carbon monoxide (CO), nitrogen dioxide (NO₂), and sulphur dioxide (SO₂), using a combination of ensemble and deep learning models. Five years of hourly air quality and meteorological data are analysed through correlation and Granger causality tests to uncover pollutant interdependencies and driving factors. The results of the Pearson correlation analysis reveal strong positive associations among primary pollutants (PM_2.5–PM₁₀, CO–nitrogen oxides NO_x and VOCs) and inverse correlations between O₃ and NO_x (NO and NO₂), confirming typical photochemical behaviour. Granger causality analysis further identified NO₂ and NO as key causal drivers influencing other pollutants, particularly O₃ formation. Among the 23 tested AI models for prediction, XGBoost, Random Forest, and Convolutional Neural Networks (CNNs) achieve the best performance for different pollutants. NO₂ prediction using CNNs displays the highest accuracy in testing (R² = 0.999, RMSE = 0.66 µg/m³), followed by PM_2.5 and PM₁₀ with XGBoost (R² = 0.90 and 0.79 during testing, respectively). The Air Quality Index (AQI) analysis shows that SO₂ and PM₁₀ are the dominant contributors to poor air quality episodes, while ozone peaks occur during warm, high-radiation periods. The interpretability analysis based on Shapley Additive exPlanations (SHAP) highlights the key influence of relative humidity, temperature, solar brightness, and NO_x species on pollutant concentrations, confirming their meteorological and chemical relevance. Finally, a deep-NARMAX model was applied to forecast the next horizons for the six air pollutants studied. Six formulas were elaborated using input data at times (t, t − 1, t − 2, …, t − n) to forecast a horizon of (t + 1) hours for single-step forecasting. For multi-step forecasting, the forecast is extended iteratively to (t + 2) hours and beyond. A recursive strategy is adopted for this purpose, whereby the forecast at (t + 1) is fed back as an input to generate the forecasts at (t + 2), and so forth. Overall, this integrated framework combines predictive accuracy with physical interpretability, offering a powerful data-driven tool for air quality assessment and policy support. This approach can be extended to real-time applications for sustainable environmental monitoring and decision-making systems. Full article