Search Results (4,648)

With global climate change, urbanization, and agricultural resource limitations, precision agriculture and crop monitoring are crucial worldwide. Integrating multi-source remote sensing data with deep learning enables accurate crop mapping, but selecting optimal network architectures remains challenging. To improve remote sensing-based fruit planting classification and support orchard management and rural revitalization, this study explored feature selection and network optimization. We proposed an improved CF-EfficientNet model (incorporating FGMF and CGAR modules) for fruit planting classification. Multi-source remote sensing data (Sentinel-1, Sentinel-2, and SRTM) were used to extract spectral, vegetation, polarization, terrain, and texture features, thereby constructing a high-dimensional feature space. Feature selection identified 13 highly discriminative bands, forming an optimal dataset, namely the preferred bands (PBs). At the same time, two classification datasets—multi-spectral bands (MS) and preferred bands (PBs)—were constructed, and five typical deep learning models were introduced to compare performance: (1) EfficientNetB0, (2) AlexNet, (3) VGG16, (4) ResNet18, (5) RepVGG. The experimental results showed that the EfficientNetB0 model based on the preferred band performed best in terms of overall accuracy (87.1%) and Kappa coefficient (0.677). Furthermore, a Fine-Grained Multi-scale Fusion (FGMF) and a Condition-Guided Attention Refinement (CGAR) were incorporated into EfficientNetB0, and the traditional SGD optimizer was replaced with Adam to construct the CF-EfficientNet architecture. The results indicated that the improved CF-EfficientNet model achieved high performance in crop classification, with an overall accuracy of 92.6% and a Kappa coefficient of 0.830. These represent improvements of 5.5 percentage points and 0.153, compared with the baseline model, demonstrating superiority in both classification accuracy and stability. Full article

This study presents a robust and extensible hybrid classification framework for accurately detecting diseases in citrus leaves by integrating transfer learning-based deep learning models with classical machine learning techniques. Features were extracted using advanced pretrained architectures—DenseNet201, ResNet50, MobileNetV2, and EfficientNet-B0—and refined via the minimum redundancy maximum relevance (mRMR) method to reduce redundancy while maximizing discriminative power. These features were classified using support vector machines (SVMs), ensemble bagged trees, k-nearest neighbors (kNNs), and neural networks under stratified 10-fold cross-validation. On the lemon dataset, the best configuration (DenseNet201 + SVM) achieved 94.1 ± 4.9% accuracy, 93.2 ± 5.7% F1 score, and a balanced accuracy of 93.4 ± 6.0%, demonstrating strong and stable performance. To assess external generalization, the same pipeline was applied to mango and pomegranate leaves, achieving 100.0 ± 0.0% and 98.7 ± 1.5% accuracy, respectively—confirming the model’s robustness across citrus and non-citrus domains. Beyond accuracy, lightweight models such as EfficientNet-B0 and MobileNetV2 provided significantly higher throughput and lower latency, underscoring their suitability for real-time agricultural applications. These findings highlight the importance of combining deep representations with efficient classical classifiers for precision agriculture, offering both high diagnostic accuracy and practical deployability in field conditions. Full article

In resource-constrained edge agricultural environments, the accurate recognition of toxic weeds poses dual challenges related to model lightweight design and the few-shot generalization capability. To address these challenges, a multi-strategy recognition framework is proposed, which integrates a lightweight backbone network, a pseudo-labeling guidance mechanism, and a contrastive boundary enhancement module. This approach is designed to improve deployment efficiency on low-power devices while ensuring high accuracy in identifying rare toxic weed categories. The proposed model achieves a real-time inference speed of 18.9 FPS on the Jetson Nano platform, with a compact model size of 18.6 MB and power consumption maintained below 5.1 W, demonstrating its efficiency for edge deployment. In standard classification tasks, the model attains 89.64%, 87.91%, 88.76%, and 88.43% in terms of precision, recall, F1-score, and accuracy, respectively, outperforming existing mainstream lightweight models such as ResNet18, MobileNetV2, and MobileViT across all evaluation metrics. In few-shot classification tasks targeting rare toxic weed species, the complete model achieves an accuracy of 80.32%, marking an average improvement of over 13 percentage points compared to ablation variants that exclude pseudo-labeling and self-supervised modules or adopt a CNN-only architecture. The experimental results indicate that the proposed model not only delivers strong overall classification performance but also exhibits superior adaptability for deployment and robustness in low-data regimes, offering an effective solution for the precise identification and ecological control of toxic weeds within intelligent agricultural perception systems. Full article

Accurate and timely prediction of diseases in water-intensive crops is critical for sustainable agriculture and food security. AI-based crop disease management tools are essential for an optimized approach, as they offer significant potential for enhancing yield and sustainability. This study centers on maize, training deep learning models on UAV imagery and satellite remote-sensing data to detect and predict disease. The performance of multiple convolutional neural networks, such as ResNet-50, DenseNet-121, etc., is evaluated by their ability to classify maize diseases such as Northern Leaf Blight, Gray Leaf Spot, Common Rust, and Blight using UAV drone data. Remotely sensed MODIS satellite data was used to generate spatial severity maps over a uniform grid by implementing time-series modeling. Furthermore, reinforcement learning techniques were used to identify hotspots and prioritize the next locations for inspection by analyzing spatial and temporal patterns, identifying critical factors that affect disease progression, and enabling better decision-making. The integrated pipeline automates data ingestion and delivers farm-level condition views without manual uploads. The combination of multiple remotely sensed data sources leads to an efficient and scalable solution for early disease detection. Full article

Wearable sensors have become valuable tools for assessing gait in both laboratory and free-living environments. However, detection of walking in free-living environments remains challenging, especially in clinical populations. Machine learning models may offer more robust gait identification, but most are trained on healthy participants, limiting their generalizability to other populations. To extend a previously validated machine learning model, an updated model was trained using an open dataset (PAMAP2), before progressively including training datasets with additional healthy participants and a clinical osteoarthritis population. The performance of the model in identifying walking was also evaluated using a frequency-based gait detection algorithm. The results showed that the model trained with all three datasets performed best in terms of activity classification, ultimately achieving a high accuracy of 96% on held-out test data. The model generally performed on par with the heuristic, frequency-based method for walking bout identification. However, for patients with slower gait speeds (<0.8 m/s), the machine learning model maintained high recall (>0.89), while the heuristic method performed poorly, with recall as low as 0.38. This study demonstrates the enhancement of existing model architectures by training with diverse datasets, highlighting the importance of dataset diversity when developing more robust models for clinical applications. Full article

Tailings storage facilities (TSFs) have experienced numerous global failures, many linked to active deposition on tailings beaches. Understanding these processes is vital for effective management. As deposition alters surface elevation, developing an explainable model to predict the changes can enhance insight into deposition dynamics and support proactive TSF management. This study applies deep learning (DL) to predict surface elevation changes in tailings storage facilities (TSFs) from high-resolution digital elevation models (DEMs) generated from UAV photogrammetry. Three DL architectures, including multilayer perceptron (MLP), fully convolutional network (FCN), and residual network (ResNet), were evaluated across spatial patch sizes of 64 × 64, 128 × 128, and 256 × 256 pixels. The results show that incorporating broader spatial contexts improves predictive accuracy, with ResNet achieving an $R2$ of 0.886 at the 256 × 256 scale, explaining nearly 89% of the variance in observed deposition patterns. To enhance interpretability, SHapley Additive exPlanations (SHAP) were applied, revealing that spatial coordinates and curvature exert the strongest influence, linking deposition patterns to discharge distance and microtopographic variability. By prioritizing predictive performance while providing mechanistic insight, this framework offers a practical and quantitative tool for reliable TSF monitoring and management. Full article

This study aims to enhance the accuracy of human lower limb motion intention recognition based on surface electromyography (sEMG) signals and proposes a signal denoising method based on Sequential Variational Mode Decomposition (SVMD) optimized by the Parrot Optimization (PO) algorithm and a joint motion angle prediction model combining Residual Network (ResNet) with Gated Recurrent Unit (GRU) for the two aspects of signal processing and predictive modeling, respectively. First, for the two motion conditions of level walking and stair climbing, sEMG signals from the rectus femoris, vastus lateralis, semitendinosus, and biceps femoris, as well as the motion angles of the hip and knee joints, were simultaneously collected from five healthy subjects, yielding a total of 400 gait cycle data points. The sEMG signals were denoised using the method combining PO-SVMD with wavelet thresholding. Compared with denoising methods such as Empirical Mode Decomposition, Partial Ensemble Empirical Mode Decomposition, Independent Component Analysis, and wavelet thresholding alone, the signal-to-noise ratio (SNR) of the proposed method was increased to a maximum of 23.42 dB. Then, the gait cycle information was divided into training and testing sets at a 4:1 ratio, and five models—ResNet-GRU, Transformer-LSTM, CNN-GRU, ResNet, and GRU—were trained and tested individually using the processed sEMG signals as input and the hip and knee joint movement angles as output. Finally, the root mean square error (RMSE), mean absolute error (MAE), and coefficient of determination (R²) were used as evaluation metrics for the test results. The results show that for both motion conditions, the evaluation metrics of the ResNet-GRU model in the test results are superior to those of the other four models. The optimal evaluation metrics for level walking are 2.512 ± 0.415°, 1.863 ± 0.265°, and 0.979 ± 0.007, respectively, while the optimal evaluation metrics for stair climbing are 2.475 ± 0.442°, 2.012 ± 0.336°, and 0.98 ± 0.009, respectively. The method proposed in this study achieves improvements in both signal processing and predictive modeling, providing a new method for research on lower limb motion intention recognition. Full article

As oil and gas exploration and development advance into deep and ultra-deep areas, kick accidents are becoming more frequent during drilling operations, posing a serious threat to construction safety. Traditional kick monitoring methods are limited in their multivariate coupling modeling. These models rely too heavily on single-feature weights, making them prone to misjudgment. Therefore, this paper proposes a drilling kick risk prediction method based on image modality. First, a sliding window mechanism is used to slice key drilling parameters in time series to extract multivariate data for continuous time periods. Second, data processing is performed to construct joint logging curve image samples. Then, classical CNN models such as VGG16 and ResNet are used to train and classify image samples; finally, the performance of the model on a number of indicators is evaluated and compared with different CNN and temporal neural network models. Finally, the model’s performance is evaluated across multiple metrics and compared with CNN and time series neural network models of different structures. Experimental results show that the image-based VGG16 model outperforms typical convolutional neural network models such as AlexNet, ResNet, and EfficientNet in overall performance, and significantly outperforms LSTM and GRU time series models in classification accuracy and comprehensive discriminative power. Compared to LSTM, the recall rate increased by 23.8% and the precision increased by 5.8%, demonstrating that its convolutional structure possesses stronger perception and discriminative capabilities in extracting local spatiotemporal features and recognizing patterns, enabling more accurate identification of kick risks. Furthermore, the pre-trained VGG16 model achieved an 8.69% improvement in accuracy compared to the custom VGG16 model, fully demonstrating the effectiveness and generalization advantages of transfer learning in small-sample engineering problems and providing feasibility support for model deployment and engineering applications. Full article

Platycodonis radix is a commonly used traditional Chinese medicine (TCM) material. Its bioactive compounds and medicinal value are closely related to its geographical origin. The internal components of Platycodonis radix from different origins are different due to the influence of environmental factors such as soil and climate. These differences can affect the medicinal value. Therefore, accurate identification of Platycodonis radix origin is crucial for drug safety and scientific research. Traditional methods of identification of TCM materials, such as morphological identification and physicochemical analysis, cannot meet the efficiency requirements. Although emerging technologies such as computer vision and spectroscopy can achieve rapid detection, their accuracy in identifying the origin of Platycodonis radix is limited when relying solely on RGB images or spectral features. To solve this problem, we aim to develop a rapid, non-destructive, and accurate method for origin identification of Platycodonis radix using hyperspectral imaging (HSI) combined with deep learning. We captured hyperspectral images of Platycodonis radix slices in 400–1000 nm range, and proposed a deep learning classification model based on these images. Our model uses one-dimensional (1D) convolution kernels to extract spectral features and two-dimensional (2D) convolution kernels to extract spatial features, fully utilizing the hyperspectral data. The average accuracy has reached 96.2%, significantly better than that of 49.0% based on RGB images and 81.8% based on spectral features in 400–1000 nm range. Furthermore, based on hyperspectral images, our model’s accuracy is 14.6%, 8.4%, and 9.6% higher than the variants of VGG, ResNet, and GoogLeNet, respectively. These results not only demonstrate the advantages of HSI in identifying the origin of Platycodonis radix, but also demonstrate the advantages of combining 1D convolution and 2D convolution in hyperspectral image classification. Full article

Agriculture is a major economic industry that sustains life. Moreover, plant health is a crucial aspect of a highly functional agricultural system. Because stress agents can damage crops and plants, it is important to understand what effect these agents can have and be able to detect this negative impact early in the process. Machine learning technology can help to prevent these undesirable consequences. This research investigates machine learning applications for plant health analysis and classification. Specifically, Residual Networks (ResNet) and Long Short-Term Memory (LSTM) models are utilized to detect and classify plants response to abiotic external stressors. Two types of plants, azalea (shrub) and Chinese tallow (tree), were used in this research study and different concentrations of sodium chloride (NaCL) and acetic acid were used to treat the plants. Data from cameras and soil sensors were analyzed by the machine learning algorithms. The ResNet34 and LSTM models achieved accuracies of 96% and 97.8%, respectively, in classifying plants with good, medium, or bad health status on test data sets. These results demonstrate that machine learning algorithms can be used to accurately detect plant health status as well as healthy and unhealthy plant conditions and thus potentially prevent negative long-term effects in agriculture. Full article

Background: Alzheimer’s disease (AD) is a progressive neurodegenerative condition marked by cognitive decline and memory loss. Despite advancements in AI-driven neuroimaging analysis for AD detection, clinical deployment remains limited due to challenges in model interpretability and usability. Explainable AI (XAI) frameworks such as XRAI offer potential to bridge this gap by providing clinically meaningful visualizations of model decision-making. Methods: This study developed a comprehensive, clinically deployable AI system for AD severity classification using 2D brain MRI data. Three deep learning architectures MobileNet-V3 Large, EfficientNet-B4, and ResNet-50 were trained on an augmented Kaggle dataset (33,984 images across four AD severity classes). The models were evaluated on both augmented and original datasets, with integrated XRAI explainability providing region-based attribution maps. A web-based clinical interface was built using Gradio to deliver real-time predictions and visual explanations. Results: MobileNet-V3 achieved the highest accuracy (99.18% on the augmented test set; 99.47% on the original dataset), while using the fewest parameters (4.2 M), confirming its efficiency and suitability for clinical use. XRAI visualizations aligned with known neuroanatomical patterns of AD progression, enhancing clinical interpretability. The web interface delivered sub-20 s inference with high classification confidence across all AD severity levels, successfully supporting real-world diagnostic workflows. Conclusions: This research presents the first systematic integration of XRAI into AD severity classification using MRI and deep learning. The MobileNet-V3-based system offers high accuracy, computational efficiency, and interpretability through a user-friendly clinical interface. These contributions demonstrate a practical pathway toward real-world adoption of explainable AI for early and accurate Alzheimer’s disease detection. Full article

Coastal zones, as critical intersections of ecosystems, resource utilization, and socioeconomic activities, exhibit complex and diverse land cover types with frequent changes. Acquiring large-scale, high-quality annotated data in these areas is costly and time-consuming, which makes rule-based segmentation methods reliant on extensive annotations impractical. Few-shot semantic segmentation, which enables effective generalization from limited labeled samples, thus becomes essential for coastal region analysis. In this work, we propose an optimized few-shot segmentation method based on the Segment Anything Model (SAM) with a frozen-parameter segmentation backbone to improve generalization. To address the high visual similarity among coastal vegetation classes, we design a cross-matching module integrated with a hyper-correlation pyramid to enhance fine-grained visual correspondence. Additionally, a self-matching module is introduced to mitigate scale variations caused by UAV altitude changes. Furthermore, we construct a novel few-shot segmentation dataset, OUC-UAV-SEG-$2^{\mathrm{i}}$, based on the OUC-UAV-SEG dataset, to alleviate data scarcity. In quantitative experiments, the suggested approach outperforms existing models in mIoU and FB-IoU under ResNet50/101 (e.g., ResNet50’s 1-shot/5-shot mIoU rises by 4.69% and 4.50% vs. SOTA), and an ablation study shows adding CMM, SMM, and SAM boosts Mean mIoU by 4.69% over the original HSNet, significantly improving few-shot semantic segmentation performance. Full article

Classifying low-concentration Gas Sensor Array (GSA) data is hard due to low SNR, sensor heterogeneity, drift, and small samples. We benchmark time-series-to-image (TS2I) CNNs against time-series classifiers, after reproducing a strong FE-ELM baseline under a shared fold manifest. Using the GSA-LC and GSA-FM datasets, we compare FE-ELM, vector baselines, time-series methods, and TS2I-CNNs with 20 × 5 repeated stratified cross-validation (n = 100). ROCKET delivers the best accuracy on both datasets and is significantly better than TCN and MiniROCKET (paired tests with Holm–Bonferroni, p < 0.05): on GSA-FM, accuracy 0.9721 ± 0.0480 (95% CI [0.9627, 0.9815]) with Macro-F1 0.9757; on GSA-LC, 0.9578 ± 0.0433 (95% CI [0.9493, 0.9663]) with Macro-F1 0.9555. Among image-based models, CNN-RP is the most robust, whereas CNN-GASF lags, especially on GSA-LC. RGB fusion strategies (e.g., with MTF) are dataset-dependent and often inconsistent, and transfer learning with ResNet-18 offers no consistent advantage. Overall, ROCKET ranks first across folds, while CNN-RP is the most reliable TS2I alternative under low-concentration conditions. These results provide a reproducible, fair benchmark for e-nose applications and practical guidance for model selection, while clarifying both the potential and limitations of TS2I. Full article

Background: Papilledema, an ophthalmic finding associated with increased intracranial pressure, is often induced by dermatological medications, including corticosteroids, isotretinoin, and tetracyclines. Early detection is crucial for preventing irreversible optic nerve damage, but access to ophthalmologic expertise is often limited in rural settings. Artificial intelligence (AI) may enable the automated and accurate detection of papilledema from fundus images, thereby supporting timely diagnosis and management. Objective: The primary objective of this study was to explore the diagnostic capability of ChatGPT-4o, a general large language model with multimodal input, in identifying papilledema from fundus photographs. For context, its performance was compared with a ResNet-based convolutional neural network (CNN) specifically fine-tuned for ophthalmic imaging, as well as with the assessments of two human ophthalmologists. The focus was on applications relevant to dermatological care in resource-limited environments. Methods: A dataset of 1094 fundus images (295 papilledema, 799 normal) was preprocessed and partitioned into a training set and a test set. The ResNet model was fine-tuned using discriminative learning rates and a one-cycle learning rate policy. GPT-4o and two human evaluators (a senior ophthalmologist and an ophthalmology resident) independently assessed the test images. Diagnostic metrics including sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), accuracy, and Cohen’s Kappa, were calculated for each evaluator. Results: GPT-4o, when applied to papilledema detection, achieved an overall accuracy of 85.9% with substantial agreement beyond chance (Cohen’s Kappa = 0.72), but lower specificity (78.9%) and positive predictive value (73.7%) compared to benchmark models. For context, the ResNet model, fine-tuned for ophthalmic imaging, reached near-perfect accuracy (99.5%, Kappa = 0.99), while two human ophthalmologists achieved accuracies of 96.0% (Kappa ≈ 0.92). Conclusions: This study explored the capability of GPT-4o, a large language model with multimodal input, for detecting papilledema from fundus photographs. GPT-4o achieved moderate diagnostic accuracy and substantial agreement with the ground truth, but it underperformed compared to both a domain-specific ResNet model and human ophthalmologists. These findings underscore the distinction between generalist large language models and specialized diagnostic AI: while GPT-4o is not optimized for ophthalmic imaging, its accessibility, adaptability, and rapid evolution highlight its potential as a future adjunct in clinical screening, particularly in underserved settings. These findings also underscore the need for validation on external datasets and real-world clinical environments before such tools can be broadly implemented. Full article

Ensuring secure and reliable communication in Vehicular Ad hoc Networks (VANETs) is critical for safe transportation systems. This paper presents Vehicular Misbehavior Network (VeMisNet), a deep learning framework for detecting misbehaving vehicles, with primary contributions in systematic feature engineering and scalability analysis. VeMisNet introduces domain-informed spatiotemporal features—including DSRC neighborhood density, inter-message timing patterns, and communication frequency analysis—derived from the publicly available VeReMi Extension Dataset. The framework evaluates Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), and Bidirectional LSTM architectures across dataset scales from 100 K to 2 M samples, encompassing all 20 attack categories. To address severe class imbalance (59.6% legitimate vehicles), VeMisNet applies SMOTE post train–test split, preventing data leakage while enabling balanced evaluation. Bidirectional LSTM with engineered features achieves 99.81% accuracy and F1-score on 500 K samples, with remarkable scalability maintaining >99.5% accuracy at 2 M samples. Critical metrics include 0.19% missed attack rates, under 0.05% false alarms, and 41.76 ms inference latency. The study acknowledges important limitations, including reliance on simulated data, single-split evaluation, and potential adversarial vulnerability. Domain-informed feature engineering provides 27.5% relative improvement over dimensionality reduction and 22-fold better scalability than basic features. These results establish new VANET misbehavior detection benchmarks while providing honest assessment of deployment readiness and research constraints. Full article