Search Results (15)

This paper investigates a five-level active neutral-point-clamped (5L-ANPC) converter operating in rectifier mode with unbalanced DC-side loads, where neutral-point (NP) deviation may deteriorate grid-current quality. Conventional space-vector pulsewidth modulation (SVPWM) is typically derived under the split-capacitor-voltage symmetry assumption; when NP deviation occurs, fixed sector boundaries and ideal volt–second balance calculations can lead to sector misclassification and synthesis errors. To address this issue, an NP-aware SVPWM scheme is proposed by reconstructing sector criteria using real-time capacitor voltages and correcting the vector dwelling-time computation to improve modulation accuracy under imbalance. Based on the power-transfer mechanism, an average-power boundary condition is further derived to quantify the admissible upper/lower load power ratio that allows NP regulation without additional hardware, and its validity is examined under resistive-load cases. Moreover, for battery-type loads exhibiting voltage-source characteristics, the control objective is extended from voltage symmetry to controllable power/charge allocation by establishing a mapping between the small-vector duty ratio and the branch average-power ratio, with constrained online solution and smoothing to mitigate coefficient jitter. Experimental validation is conducted on an OPAL-RT OP5707-based hardware-in-the-loop platform, where both single-phase and three-phase 5L-ANPC systems are implemented according to different verification objectives. The derived boundary condition for resistive loads is examined in the single-phase system, while the proposed modulation and battery-load power-allocation strategy are verified in the three-phase system. The three-phase arrangement is adopted for the battery-load case in order to avoid the second-order power ripple inherent to single-phase operation. Full article

Traditional domain adaptation methods often assume balanced data distributions. However, this assumption is frequently violated in real-world industrial scenarios, where normal samples predominate while fault samples are inherently scarce. Under severe class imbalance, conventional decision boundaries tend to shift toward minority fault regions. This shift leads to persistently high misclassification rates for rare fault samples. To overcome this limitation, we propose the Dynamic Maximum Triple-View Classifier Discrepancy (DMTVCD) network, which integrates a Triple-View Classifier (TVC) Architecture and a Primary–Auxiliary Fused Cooperative Loss (PAFL). Specifically, the TVC employs auxiliary binary classifiers to aggregate fine-grained fault sub-classes into a unified “Fault Super-class.” This constructs a robust “normal-fault” binary boundary that effectively counteracts class imbalance. Driven by the PAFL, this boundary acts as a hierarchical geometric constraint to suppress the primary classifier’s tendency to misclassify faults as normal samples, thereby enhancing feature discriminability. Furthermore, a dynamic weighting strategy is introduced to assign large initial weights. This forces the model to bypass simple decision logic dominated by the majority class, ensuring a smooth transition from global exploration to fine-grained alignment. Extensive evaluations on the CWRU and JNU datasets demonstrate that DMTVCD consistently outperforms state-of-the-art approaches under high imbalance ratios (e.g., 20:1). Full article

To establish a rapid traceability method for tea varieties and address the limitations of traditional identification techniques, this study focused on four types of tea—Longjing, Maofeng, Zhuyeqing, and Biluochun—using near-infrared (NIR) spectroscopy. A total of 84 sets of NIR spectra were collected and preprocessed using Savitzky–Golay smoothing (S-G), multiplicative scatter correction (MSC), standard normal variate transformation (SNV), and first derivative (1stDer) methods. Dimensionality reduction and feature selection were then performed using principal component analysis (PCA), linear discriminant analysis (LDA), their combination (PCA-LDA), and the successive projections algorithm (SPA). Classification models based on multiple linear regression (MLR) and support vector machine (SVM) were constructed and evaluated via five-fold cross-validation to assess generalization ability and stability. The results indicated that the SVM model significantly outperformed the MLR model in overall classification and generalization. The PCA-LDA combined approach proved to be the most effective feature selection method. The optimal classification model for tea variety traceability was achieved using MSC or SNV preprocessing combined with PCA-LDA-SVM, yielding a mean five-fold cross-validation accuracy of 96.67%. The confusion matrix revealed that misclassifications mainly occurred between Longjing and Biluochun and between Maofeng and Zhuyeqing, which can be attributed to similarities in processing techniques and chemical composition among these tea varieties. This study provides a rapid, non-destructive, and accurate spectroscopic detection method for tea quality control and traceability, offering a valuable reference for the rapid identification of agricultural products. Full article

This study develops a machine-learning-based framework for multiclass soil classification using Cone Penetration Test (CPT) data, aiming to overcome the limitations of traditional empirical Soil Behavior Type (SBT) charts and improve the automation, continuity, robustness, and reliability of stratigraphic interpretation. A dataset of 340 CPT soundings from 26 sites in Shanghai is compiled, and a sliding-window feature engineering strategy is introduced to transform point measurements into local pattern descriptors. An XGBoost-based multiclass classifier is then constructed using fifteen engineered features, integrating second-order optimization, regularized tree structures, and probability-based decision functions. Results demonstrate that the proposed method achieves strong classification performance across nine soil categories, with an overall classification accuracy of approximately 92.6%, an average F1-score exceeding 0.905, and a mean Average Precision (mAP) of 0.954. The confusion matrix, P–R curves, and prediction probabilities show that soil types with distinctive CPT signatures are classified with near-perfect confidence, whereas transitional clay–silt facies exhibit moderate but geologically consistent misclassification. To evaluate depth-wise prediction reliability, an Accuracy Coverage Rate (ACR) metric is proposed. Analysis of all CPTs reveals a mean ACR of 0.924, and the ACR follows a Weibull distribution. Feature importance analysis indicates that depth-dependent variables and smoothed p_s statistics are the dominant predictors governing soil behavior differentiation. The proposed XGBoost-based framework effectively captures nonlinear CPT–soil relationships, offering a practical and interpretable tool for high-resolution soil classification in subsurface investigations. Full article

In the wild, snow is not merely additive noise; it is a non-stationary, semi-transparent veil whose spatial statistics vary with depth, illumination, and wind. Because conventional two-stage pipelines first detect a binary mask and then inpaint the occluded regions, any early mis-classification is irreversibly baked into the final result, leading to over-smoothed textures or ghosting artifacts. We propose BAT-Net, a Bidirectional Attention Transformer Network that frames desnowing as a coupled representation learning problem, jointly disentangling snow appearance and scene radiance in a single forward pass. Our core contributions are as follows: (1) A novel dual-decoder architecture where a background decoder and a snow decoder are coupled via a Bidirectional Attention Module (BAM). The BAM implements a continuous predict–verify–correct mechanism, allowing the background branch to dynamically accept, reject, or refine the snow branch’s occlusion hypotheses, dramatically reducing error accumulation. (2) A lightweight yet effective multi-scale feature fusion scheme comprising a Scale Conversion Module (SCM) and a Feature Aggregation Module (FAM), enabling the model to handle the large scale variance among snowflakes without a prohibitive computational cost. (3) The introduction of the FallingSnow dataset, curated to eliminate the label noise caused by irremovable ground snow in existing benchmarks, providing a cleaner benchmark for evaluating dynamic snow removal. Extensive experiments on synthetic and real-world datasets demonstrate that BAT-Net sets a new state of the art. It achieves a PSNR of 35.78 dB on the CSD dataset, outperforming the best prior model by 1.37 dB, and also achieves top results on SRRS (32.13 dB) and Snow100K (34.62 dB) datasets. The proposed method has significant practical applications in autonomous driving and surveillance systems, where accurate snow removal is crucial for maintaining visual clarity. Full article

Road extraction from remote sensing imagery plays a critical role in applications such as autonomous driving, urban planning, and infrastructure development. Although deep learning methods have achieved notable progress, current approaches still struggle with complex backgrounds, varying road widths, and strong texture interference, often leading to fragmented road predictions or the misclassification of background regions. Given that roads typically exhibit smooth low-frequency characteristics while background clutter tends to manifest in mid- and high-frequency ranges, incorporating frequency-domain information can enhance the model’s structural perception and discrimination capabilities. To address these challenges, we propose a novel frequency-aware road extraction network, termed PWFNet, which combines frequency-domain modeling with multi-scale feature enhancement. PWFNet comprises two key modules. First, the Pyramidal Wavelet Convolution (PWC) module employs multi-scale wavelet decomposition fused with localized convolution to accurately capture road structures across various spatial resolutions. Second, the Frequency-aware Adjustment Module (FAM) partitions the Fourier spectrum into multiple frequency bands and incorporates a spatial attention mechanism to strengthen low-frequency road responses while suppressing mid- and high-frequency background noise. By integrating complementary modeling from both spatial and frequency domains, PWFNet significantly improves road continuity, edge clarity, and robustness under complex conditions. Experiments on the DeepGlobe and CHN6-CUG road datasets demonstrate that PWFNet achieves IoU improvements of 3.8% and 1.25% over the best-performing baseline methods, respectively. In addition, we conducted cross-region transfer experiments by directly applying the trained model to remote sensing images from different geographic regions and at varying resolutions to assess its generalization capability. The results demonstrate that PWFNet maintains the continuity of main and branch roads and preserves edge details in these transfer scenarios, effectively reducing false positives and missed detections. This further validates its practicality and robustness in diverse real-world environments. Full article

The classification of submarine topography and geomorphology is essential for marine resource exploitation and ocean engineering, with wide-ranging implications in marine geology, disaster assessment, resource exploration, and autonomous underwater navigation. Submarine landscapes are highly complex and diverse. Traditional visual interpretation methods are not only inefficient and subjective but also lack the precision required for high-accuracy classification. While many machine learning and deep learning models have achieved promising results in image classification, limited work has been performed on integrating backscatter and bathymetric data for multi-source processing. Existing approaches often suffer from high computational costs and excessive hyperparameter demands. In this study, we propose a novel approach that integrates pruning-enhanced ConDenseNet with label smoothing regularization to reduce misclassification, strengthen the cross-entropy loss function, and significantly lower model complexity. Our method improves classification accuracy by 2% to 10%, reduces the number of hyperparameters by 50% to 96%, and cuts computation time by 50% to 85.5% compared to state-of-the-art models, including AlexNet, VGG, ResNet, and Vision Transformer. These results demonstrate the effectiveness and efficiency of our model for multi-source submarine topography classification. Full article

Machine learning (ML) promises advances in automation and threat detection for the future generations of communication networks. However, new threats are introduced, as adversaries target ML systems with malicious data. Adversarial attacks on tree-based ML models involve crafting input perturbations that exploit non-smooth decision boundaries, causing misclassifications. These so-called evasion attacks are imperceptible, as they do not significantly alter the input data distribution and have been shown to degrade the performance of tree-based models across various tasks. Adversarial training and genetic algorithms have been proposed as potential defenses against these attacks. In this paper, we explore the robustness of tree-based models for network intrusion detection systems. This study evaluates an optimization approach inspired by genetic algorithms to generate adversarial samples and studies the impact of adversarial training on the accuracy of attack detection. This paper exposed random forest and extreme gradient boosting classifiers to various adversarial samples generated from communication network-related CIC-IDS2019 and 5G-NIDD datasets. The results indicate that the improvements of robustness to adversarial attacks come with a cost to the accuracy of the network intrusion detection models. These costs can be optimized with intelligent, use case-specific feature engineering. Full article

Terrestrial laser scanning (TLS) technology characterizes standing trees with millimetric precision. An important step to accurately quantify tree volume and above-ground biomass using TLS point clouds is the discrimination between timber and leaf components. This study evaluates the performance of machine learning (ML)-derived models aimed at discriminating timber and leaf TLS point clouds, focusing on eight Mediterranean tree species datasets. The results show the best accuracies for random forests, gradient boosting machine, stacked ensemble model, and deep learning models with an average F1 score equal to 0.92. The top-performing ML-derived models showed well-balanced average precision and recall rates, ranging from 0.86 to 0.91 and 0.92 to 0.96 for precision and recall, respectively. Our findings show that Italian maple, European beech, hazel, and small-leaf lime tree species have more accurate F1 scores, with the best average F1 score of 0.96. The factors influencing the timber–leaf discrimination include phenotypic factors, such as bark surface (i.e., roughness and smoothness), technical issues (i.e., noise points and misclassification of points), and secondary factors (i.e., bark defects, lianas, and microhabitats). The top-performing ML-derived models report a time computation ranging from 8 to 37 s for processing 2 million points. Future studies are encouraged to calibrate, configure, and validate the potential of top-performing ML-derived models on other tree species and at the plot level. Full article

Algorithms combining CNN (Convolutional Neural Network) and super-pixel based smoothing have been proposed in recent years for Synthetic Aperture Radar (SAR) image classification. However, the smoothing may lead to the damage of details. To solve this problem the feature fusion strategy is utilized, and a novel adaptive fusion module named Gated Channel Attention (GCA) is designed in this paper. In this module, the relevance between channels is embedded into the conventional gated attention module to emphasize the variation in contribution on classification results between channels of feature-maps, which is not well considered by the conventional gated attention module. A GCA-CNN network is then constructed for SAR image classification. In this network, feature-maps corresponding to the original image and the smoothed image are extracted, respectively, by feature-extraction layers and adaptively fused. The fused features are used to obtain the results. Classification can be performed by the GCA-CNN in an end-to-end way. By the adaptive feature fusion in GCA-CNN, the smoothing of misclassification and the detail keeping can be realized at the same time. Experiments have been performed on one elaborately designed synthetic image and three real world SAR images. The superiority of the GCA-CNN is demonstrated by comparing with the conventional algorithms and the relative state-of-the-art algorithms. Full article

The semantic segmentation model usually provides pixel-wise category prediction for images. However, a massive amount of pixel-wise annotation images is required for model training, which is time-consuming and labor-intensive. An image-level categorical annotation is recently popular and attempted to overcome the above issue in this work. This is also termed weakly supervised semantic segmentation, and the general framework aims to generate pseudo masks with class activation mapping. This can be learned through classification tasks that focus on explicit features. Some major issues in these approaches are as follows: (1) Excessive attention on the specific area; (2) for some objects, the detected range is beyond the boundary, and (3) the smooth areas or minor color gradients along the object are difficult to categorize. All these problems are comprehensively addressed in this work, mainly to overcome the importance of overly focusing on significant features. The suppression expansion module is used to diminish the centralized features and to expand the attention view. Moreover, to tackle the misclassification problem, the saliency-guided module is adopted to assist in learning regional information. It limits the object area effectively while simultaneously resolving the challenge of internal color smoothing. Experimental results show that the pseudo masks generated by the proposed network can achieve 76.0%, 73.3%, and 73.5% in mIoU with the PASCAL VOC 2012 train, validation, and test set, respectively, and outperform the state-of-the-art methods. Full article

High-precision habitat mapping can contribute to the identification and quantification of the human footprint on the seafloor. As a representative of seafloor habitats, seabed sediment classification is crucial for marine geological research, marine environment monitoring, marine engineering construction, and seabed biotic and abiotic resource assessment. Multibeam echo-sounding systems (MBES) have become the most popular tool in terms of acoustic equipment for seabed sediment classification. However, sonar images tend to consist of obvious noise and stripe interference. Furthermore, the low efficiency and high cost of seafloor field sampling leads to limited field samples. The factors above restrict high accuracy classification by a single classifier. To further investigate the classification techniques for seabed sediments, we developed a decision fusion algorithm based on voting strategies and fuzzy membership rules to integrate the merits of deep learning and shallow learning methods. First, in order to overcome the influence of obvious noise and the lack of training samples, we employed an effective deep learning framework, namely random patches network (RPNet), for classification. Then, to alleviate the over-smoothness and misclassifications of RPNet, the misclassified pixels with a lower fuzzy membership degree were rectified by other shallow learning classifiers, using the proposed decision fusion algorithm. The effectiveness of the proposed method was tested in two areas of Europe. The results show that RPNet outperforms other traditional classification methods, and the decision fusion framework further improves the accuracy compared with the results of a single classifier. Our experiments predict a promising prospect for efficiently mapping seafloor habitats through deep learning and multi-classifier combinations, even with few field samples. Full article

People walk on different types of terrain daily; for instance, level-ground walking, ramp and stair ascent and descent, and stepping over obstacles are common activities in daily life. Movement patterns change as people move from one terrain to another. The prediction of transitions between locomotion modes is important for developing assistive devices, such as exoskeletons, as the optimal assistive strategies may differ for different locomotion modes. The prediction of locomotion mode transitions is often accompanied by gait-event detection that provides important information during locomotion about critical events, such as foot contact (FC) and toe off (TO). In this study, we introduce a method to integrate locomotion mode prediction and gait-event identification into one machine learning framework, comprised of two multilayer perceptrons (MLP). Input features to the framework were from fused data from wearable sensors—specifically, electromyography sensors and inertial measurement units. The first MLP successfully identified FC and TO, FC events were identified accurately, and a small number of misclassifications only occurred near TO events. A small time difference (2.5 ms and −5.3 ms for FC and TO, respectively) was found between predicted and true gait events. The second MLP correctly identified walking, ramp ascent, and ramp descent transitions with the best aggregate accuracy of 96.3%, 90.1%, and 90.6%, respectively, with sufficient prediction time prior to the critical events. The models in this study demonstrate high accuracy in predicting transitions between different locomotion modes in the same side’s mid- to late stance of the stride prior to the step into the new mode using data from EMG and IMU sensors. Our results may help assistive devices achieve smooth and seamless transitions in different locomotion modes for those with motor disorders. Full article

This paper addresses the lack of robustness of feature selection algorithms for fuzzy clustering segmentation with the Gaussian mixture model. Assuming that the neighbourhood pixels and the centre pixels obey the same distribution, a Markov method is introduced to construct the prior probability distribution and achieve the membership degree regularisation constraint for clustering sample points. Then, a noise smoothing factor is introduced to optimise the prior probability constraint. Second, a power index is constructed by combining the classification membership degree and prior probability since the Kullback–Leibler (KL) divergence of the noise smoothing factor is used to supervise the prior probability; this probability is embedded into Fuzzy Superpixels Fuzzy C-means (FSFCM) as a regular factor. This paper proposes a fuzzy clustering image segmentation algorithm based on an adaptive feature selection Gaussian mixture model with neighbourhood information constraints. To verify the segmentation performance and anti-noise robustness of the improved algorithm, the fuzzy C-means clustering algorithm Fuzzy C-means (FCM), FSFCM, Spatially Variant Finite Mixture Model (SVFMM), EGFMM, extended Gaussian mixture model (EGMM), adaptive feature selection robust fuzzy clustering segmentation algorithm (AFSFCM), fast and robust spatially constrained Gaussian mixture model (GMM) for image segmentation (FRSCGMM), and improve method are used to segment grey images containing Gaussian noise, salt-and-pepper noise, multiplicative noise and mixed noise. The peak signal-to-noise ratio (PSNR) and the error rate (MCR) are used as the theoretical basis for assessing the segmentation results. The improved algorithm indicators proposed in this paper are optimised. The improved algorithm yields increases of 0.1272–12.9803 dB, 1.5501–13.4396 dB, 1.9113–11.2613 dB and 1.0233–10.2804 dB over the other methods, and the Misclassification rate (MSR) decreases by 0.32–37.32%, 5.02–41.05%, 0.3–21.79% and 0.9–30.95% compared to that with the other algorithms. It is verified that the segmentation results of the improved algorithm have good regional consistency and strong anti-noise robustness, and they meet the needs of noisy image segmentation. Full article

Traditional and convolutional neural network (CNN)-based geographic object-based image analysis (GeOBIA) land-cover classification methods prosper in remote sensing and generate numerous distinguished achievements. However, a bottleneck emerges and hinders further improvements in classification results, due to the insufficiency of information provided by very high-spatial resolution images (VHSRIs). To be specific, the phenomenon of different objects with similar spectrum and the lack of topographic information (heights) are natural drawbacks of VHSRIs. Thus, multisource data steps into people’s sight and shows a promising future. Firstly, for data fusion, this paper proposed a standard normalized digital surface model (StdnDSM) method which was actually a digital elevation model derived from a digital terrain model (DTM) and digital surface model (DSM) to break through the bottleneck by fusing VHSRI and cloud points. It smoothed and improved the fusion of point cloud and VHSRIs and thus performed well in follow-up classification. The fusion data then were utilized to perform multiresolution segmentation (MRS) and worked as training data for the CNN. Moreover, the grey-level co-occurrence matrix (GLCM) was introduced for a stratified MRS. Secondly, for data processing, the stratified MRS was more efficient than unstratified MRS, and its outcome result was theoretically more rational and explainable than traditional global segmentation. Eventually, classes of segmented polygons were determined by majority voting. Compared to pixel-based and traditional object-based classification methods, majority voting strategy has stronger robustness and avoids misclassifications caused by minor misclassified centre points. Experimental analysis results suggested that the proposed method was promising for object-based classification. Full article