Search Results (415)

Change detection (CD) is an important research direction in the field of remote sensing, which aims to analyze the changes in the same area over different periods and is widely used in urban planning and environmental protection. While supervised learning methods in change detection have demonstrated substantial efficacy, they are often hindered by the rising costs associated with data annotation. Semi-supervised methods have attracted increasing interest, offering promising results with limited data labeling. These approaches typically employ strategies such as consistency regularization, pseudo-labeling, and generative adversarial networks. However, they usually face the problems of insufficient data augmentation and unbalanced quality and quantity of pseudo-labeling. To address the above problems, we propose a semi-supervised change detection method with data augmentation and adaptive threshold updating (DA-AT) for high-resolution remote sensing images. Firstly, a channel-level data augmentation (CLDA) technique is designed to enhance the strong augmentation effect and improve consistency regularization so as to address the problem of insufficient feature representation. Secondly, an adaptive threshold (AT) is proposed to dynamically adjust the threshold during the training process to balance the quality and quantity of pseudo-labeling so as to optimize the self-training process. Finally, an adaptive class weight (ACW) mechanism is proposed to alleviate the impact of the imbalance between the changed classes and the unchanged classes, which effectively enhances the learning ability of the model for the changed classes. We verify the effectiveness and robustness of the proposed method on two high-resolution remote sensing image datasets, WHU-CD and LEVIR-CD. We compare our method to five state-of-the-art change detection methods and show that it achieves better or comparable results. Full article

Online learning is a framework for processing and learning from sequential data in real time, offering benefits such as promptness and low memory usage. However, it faces critical challenges, including concept drift, where data distributions evolve over time, and class imbalance, which significantly hinders the accurate classification of minority classes. Addressing these issues simultaneously remains a challenging research problem. This study introduces a novel algorithm that integrates adaptive weighted kernel density estimation (awKDE) and a conscious biasing mechanism to efficiently manage memory, while enhancing the classification performance. The proposed method dynamically detects the minority class and employs a biasing strategy to prioritize its representation during training. By generating synthetic minority samples using awKDE, the algorithm adaptively balances class distributions, ensuring robustness in evolving environments. Experimental evaluations across synthetic and real-world datasets demonstrated that the proposed method achieved up to a 13.3 times improvement in classification performance over established oversampling methods and up to a 1.66 times better performance over adaptive rebalancing approaches, while requiring significantly less memory. These results underscore the method’s scalability and practicality for real-time online learning applications. Full article

In order to solve the problems of high planting density, similar color, and serious occlusion between spikes in sorghum fields, such as difficult identification and detection of sorghum spikes, low accuracy and high false detection, and missed detection rates, this study proposes an improved sorghum spike detection method based on YOLOv8s. The method involves augmenting the information fusion capability of the YOLOv8 model’s neck module by integrating the Gold feature pyramid module. Additionally, the SPPF module is refined with the LSKA attention mechanism to heighten focus on critical features. To tackle class imbalance in sorghum detection and expedite model convergence, a loss function incorporating Focal-EIOU is employed. Consequently, the YOLOv8s-Gold-LSKA model, based on the Gold module and LSKA attention mechanism, is developed. Experimental results demonstrate that this improved method significantly enhances sorghum spike detection accuracy in natural field settings. The improved model achieved a precision of 90.72%, recall of 76.81%, mean average precision (mAP) of 85.86%, and an F1-score of 81.19%. Comparing the improved model of this study with the three target detection models of YOLOv5s, SSD, and YOLOv8, respectively, the improved model of this study has better detection performance. This advancement provides technical support for the rapid and accurate recognition of multiple sorghum spike targets in natural field backgrounds, thereby improving sorghum yield estimation accuracy. It also contributes to increased sorghum production and harvest, as well as the enhancement of intelligent harvesting equipment for agricultural machinery. Full article

The ever-growing number of cyber attacks in today’s digitally interconnected world requires highly efficient intrusion detection systems (IDSs), which accurately identify both frequent and rare network intrusions. One of the most important challenges in IDSs is the class imbalance problem of network traffic flow data, where benign traffic flow significantly outweighs attack instances. This directly affects the ability of machine learning models to identify minority class threats. This paper is intended to evaluate various machine learning algorithms under different levels of class imbalances, using resampling as a strategy for this problem. The paper will provide an experimental comparison by combining various algorithms for classification and class imbalance learning, assessing the performance through the F1-score and geometric mean (G-mean). The work will contribute to creating robust and adaptive IDS through the judicious integration of resampling with machine learning models, thus helping the domain of cybersecurity to become resilient. Full article

The overload problem in semi-autogenous grinding (SAG) mills is critical in the mining industry, impacting the extraction of valuable metals and overall productivity. Overloads can lead to severe operational issues, including increased wear, reduced grinding efficiency, and unscheduled shutdowns, which result in financial losses. Various strategies have been employed to address SAG mill overload, from real-time monitoring to predictive modeling and machine learning techniques. However, existing methods often lack the integration of domain-specific knowledge, particularly in handling class imbalance within operational data, leading to limitations in predictive accuracy. This paper presents a novel approach that integrates convolutional neural networks (CNNs) with physics-informed neural networks (PINNs), embedding physical laws directly into the model’s loss function. This hybrid methodology captures the complex interactions and nonlinearities inherent in SAG mill operations and leverages domain expertise to enforce physical consistency, ensuring more robust predictions. Incorporating physics-based constraints allows the model to remain sensitive to critical overload conditions while addressing the challenge of imbalanced data. Our method demonstrates a significant enhancement in prediction accuracy through extensive experiments on real-world SAG mill operational data, achieving an F1-score of 94.5%. The results confirm the importance of integrating physics-based knowledge into machine learning models, improving predictive performance, and offering a more interpretable and reliable tool for mill operators. This work sets a new benchmark in the predictive modeling of SAG mill overloads, paving the way for more advanced, physically informed predictive maintenance strategies in the mining industry. Full article

Surrounding rock squeezing is a common geological disaster in underground excavation projects (e.g., TBM tunneling and deep mining), which has adverse effects on construction safety, schedule, and property. To predict the squeezing of the surrounding rock accurately and quickly, this study proposes a hybrid machine learning paradigm that integrates generative artificial intelligence and deep ensemble learning. Specifically, conditional tabular generative adversarial network is devised to solve the problems of data shortage and class imbalance for data augmentation at the data level, and the deep random forest is built based on the augmented data for subsequent squeezing classification. A total of 139 historical squeezing cases are collected worldwide to validate the efficacy of the proposed modeling paradigm. The results reveal that this paradigm achieves a prediction accuracy of 92.86% and a macro F₁-score of 0.9292. In particular, the individual F₁-scores on strong squeezing and extremely strong squeezing are more than 0.9, with excellent prediction reliability for high-intensity squeezing. Finally, a comparative analysis with traditional machine learning techniques is conducted and the superiority of this paradigm is further verified. This study provides a valuable reference for surrounding rock squeezing classification under a limited data environment. Full article

Background and Objective: Diabetes Mellitus is a long-term, multifaceted metabolic condition that necessitates ongoing medical management. Hypogonadism is a syndrome that is a clinical and/or biochemical indicator of testosterone deficiency. Cross-sectional studies have reported that 20–80.4% of all men with Type 2 diabetes have hypogonadism, and Type 2 diabetes is related to low testosterone. This study presents an analysis of the use of ML and EL classifiers in predicting testosterone deficiency. In our study, we compared optimized traditional ML classifiers and three EL classifiers using grid search and stratified k-fold cross-validation. We used the SMOTE method for the class imbalance problem. Methods: This database contains 3397 patients for the assessment of testosterone deficiency. Among these patients, 1886 patients with Type 2 diabetes were included in the study. In the data preprocessing stage, firstly, outlier/excessive observation analyses were performed with LOF and missing value analyses were performed with random forest. The SMOTE is a method for generating synthetic samples of the minority class. Four basic classifiers, namely MLP, RF, ELM and LR, were used as first-level classifiers. Tree ensemble classifiers, namely ADA, XGBoost and SGB, were used as second-level classifiers. Results: After the SMOTE, while the diagnostic accuracy decreased in all base classifiers except ELM, sensitivity values increased in all classifiers. Similarly, while the specificity values decreased in all classifiers, F1 score increased. The RF classifier gave more successful results on the base-training dataset. The most successful ensemble classifier in the training dataset was the ADA classifier in the original data and in the SMOTE data. In terms of the testing data, XGBoost is the most suitable model for your intended use in evaluating model performance. XGBoost, which exhibits a balanced performance especially when the SMOTE is used, can be preferred to correct class imbalance. Conclusions: The SMOTE is used to correct the class imbalance in the original data. However, as seen in this study, when the SMOTE was applied, the diagnostic accuracy decreased in some models but the sensitivity increased significantly. This shows the positive effects of the SMOTE in terms of better predicting the minority class. Full article

Long-tailed data distribution (i.e., minority classes occupy most of the data, while most classes have very few samples) is a common problem in image classification. In this paper, we propose a novel multimodal framework for long-tailed data recognition. In the first stage, long-tailed data are used for visual-semantic contrastive learning to obtain good features, while in the second stage, class-balanced data are used for classifier training. The proposed framework leverages the advantages of multimodal models and mitigates the problem of class imbalance in long-tailed data recognition. Experimental results demonstrate that the proposed framework achieves competitive performance on the CIFAR-10-LT, CIFAR-100-LT, ImageNet-LT, and iNaturalist2018 datasets for image classification. Full article

Although imbalanced data have been studied for many years, the problem of data imbalance is still a major problem in the development of machine learning and artificial intelligence. The development of deep learning and artificial intelligence has further expanded the impact of imbalanced data, so studying imbalanced data classification is of practical significance. We propose an image oversampling algorithm based on the influence function and sample weights. Our scheme not only synthesizes high-quality minority class samples but also preserves the original features and information of minority class images. To address the lack of visually reasonable features in SMOTE when synthesizing images, we improve the pre-training model by removing the pooling layer and the fully connected layer in the model, extracting the important features of the image by convolving the image, executing SMOTE interpolation operation on the extracted important features to derive the synthesized image features, and inputting the features into a DCGAN network generator, which maps these features into the high-dimensional image space to generate a realistic image. To verify that our scheme can synthesize high-quality images and thus improve classification accuracy, we conduct experiments on the processed CIFAR10, CIFAR100, and ImageNet-LT datasets. Full article

In botany and agriculture, classifying leaves is a crucial process that yields vital information for studies on biodiversity, ecological studies, and the identification of plant species. The Cope Leaf Dataset offers a comprehensive collection of leaf images from various plant species, enabling the development and evaluation of advanced classification algorithms. This study presents a robust methodology for classifying leaf images within the Cope Leaf Dataset by enhancing the feature extraction and selection process. Cope Leaf Dataset has 99 classes and 64 features with 1584 records. Features are extracted based on the margin, texture, and shape of the leaves. It is challenging to classify a large number of labels because of class imbalance, feature complexity, overfitting, and label noise. Our approach combines advanced feature selection techniques with robust preprocessing methods, including normalization, imputation, and noise reduction. By systematically integrating these techniques, we aim to reduce dimensionality, eliminate irrelevant or redundant features, and improve data quality. Increasing accuracy in classification, especially when dealing with large datasets and many classes, involves a combination of data preprocessing, model selection, regularization techniques, and fine-tuning. The results indicate that the Multilayer Perception algorithm gives 89.48%, the Naïve Bayes Classifier gives 89.63%, Convolutional Neural Networks has 88.72%, and the Hoeffding Tree algorithm gives 89.92% accuracy for the classification of 99 label plant leaf classification problems. Full article

The Police Robot for Inspection and Mapping of Underwater Evidence (PRIME) is an uncrewed surface vehicle (USV) currently being developed for underwater search and recovery teams to assist in crime scene investigation. The USV maps underwater scenes using sidescan sonar (SSS). Test exercises use a clothed mannequin lying on the seafloor as a target object to evaluate system performance. A robust, automated method for detecting human body-shaped objects is required to maximise operational functionality. The use of a convolutional neural network (CNN) for automatic target recognition (ATR) is proposed. SSS image data acquired from four different locations during previous missions were used to build a dataset consisting of two classes, i.e., a binary classification problem. The target object class consisted of 166 196 × 196 pixel image snippets of the underwater mannequin, whereas the non-target class consisted of 13,054 examples. Due to the large class imbalance in the dataset, CNN models were trained with six different imbalance ratios. Two different pre-trained models (ResNet-50 and Xception) were compared, and trained via transfer learning. This paper presents results from the CNNs and details the training methods used. Larger datasets are shown to improve CNN performance despite class imbalance, achieving average F1 scores of 97% in image classification. Average F1 scores for target vs background classification with unseen data are only 47% but the end result is enhanced by combining multiple weak classification results in an ensemble average. The combined output, represented as a georeferenced heatmap, accurately indicates the target object location with a high detection confidence and one false positive of low confidence. The CNN approach shows improved object detection performance when compared to the currently used ATR method. Full article

Semantic segmentation often suffers from class imbalance, where the label ratio for each class in the dataset is not uniform. Recent studies have addressed the issue of class imbalance in semantic segmentation by leveraging the neural collapse phenomenon in conjunction with an Equiangular Tight Frame (ETF). While the use of ETF aids in enhancing the discriminability of minor classes, class correlation is another crucial factor that must be taken into account. However, managing the balance between class correlation and discrimination through neural collapse remains challenging, as these properties inherently conflict with one another. Moreover, this control is established during the training stage, resulting in a fixed classifier. There is no guarantee that this classifier will consistently perform well with different input images. To address this problem, we propose an Equiangular Tight Frame Transformer (ETFT), a transformer-based model that jointly processes the features and classifier using ETF structure, and dynamically generates the classifier as a function of the input for imbalanced semantic segmentation. Specifically, the classifier initialized with the ETF structure is jointly processed with the input patch tokens during the attention process. As a result, the transformed patch tokens, aided by the ETF structure, achieve discriminability between classes while preserving contextual correlation. The classifier, initially structured as an ETF, is adjusted to incorporate the correlation information, benefiting from the attention mechanism. Furthermore, the learned classifier is combined with the fixed ETF classifier, leveraging the advantages of both. Extensive experiments demonstrate that the proposed method outperforms state-of-the-art methods for imbalanced semantic segmentation on both the ADE20K and Cityscapes datasets. Full article

Most online action detection methods focus on solving a (K + 1) classification problem, where the additional category represents the ‘background’ class. However, training on the ‘background’ class and managing data imbalance are common challenges in online action detection. To address these issues, we propose a framework for online action detection by incorporating an additional pathway between the feature extractor and online action detection model. Specifically, we present one configuration that retains feature distinctions for fusion with the final decision from the Long Short-Term Transformer (LSTR), enhancing its performance in the (K + 1) classification. Experimental results show that the proposed method achieves an accuracy of 71.2% in mean Average Precision (mAP) on the Thumos14 dataset, outperforming the 69.5% achieved by the original LSTR method. Full article

Researchers using machine learning methods for classification can face challenges due to class imbalance, where a certain class is underrepresented. Over or under-sampling of minority or majority class observations, or solely relying on model selection for ensemble methods, may prove ineffective when the class imbalance ratio is extremely high. To address this issue, this paper proposes a method called enhance tree ensemble (ETE), based on generating synthetic data for minority class observations in conjunction with tree selection based on their performance on the training data. The proposed method first generates minority class instances to balance the training data and then uses the idea of tree selection by leveraging out-of-bag (${\mathrm{E}\mathrm{T}\mathrm{E}}_{\mathrm{O}\mathrm{O}\mathrm{B}}$) and sub-samples (${\mathrm{E}\mathrm{T}\mathrm{E}}_{\mathrm{S}\mathrm{S}}$) observations, respectively. The efficacy of the proposed method is assessed using twenty benchmark problems for binary classification with moderate to extreme class imbalance, comparing it against other well-known methods such as optimal tree ensemble (OTE), SMOTE random forest (${RF}_{SMOTE}$), oversampling random forest (${\mathrm{R}\mathrm{F}}_{\mathrm{O}\mathrm{S}}$), under-sampling random forest (${\mathrm{R}\mathrm{F}}_{\mathrm{U}\mathrm{S}}$), k-nearest neighbor (k-NN), support vector machine (SVM), tree, and artificial neural network (ANN). Performance metrics such as classification error rate and precision are used for evaluation purposes. The analyses of the study revealed that the proposed method, based on data balancing and model selection, yielded better results than the other methods. Full article

In response to the COVID-19 pandemic, governments worldwide have implemented mandatory face mask regulations in crowded public spaces, making the development of automatic face mask detection systems critical. To achieve robust face mask detection performance, a high-quality and comprehensive face mask dataset is required. However, due to the difficulty in obtaining face samples with masks in the real-world, public face mask datasets are often imbalanced, leading to the data imbalance problem in model training and negatively impacting detection performance. To address this problem, this paper proposes a novel recursive model-training technique designed to improve detection accuracy on imbalanced datasets. The proposed method recursively splits and merges the dataset based on the attribute characteristics of different classes, enabling more balanced and effective model training. Our approach demonstrates that the carefully designed splitting and merging of datasets can significantly enhance model-training performance. This method was evaluated using two imbalanced datasets. The experimental results show that the proposed recursive learning technique achieves a percentage increase (PI) of 84.5% in mean average precision ([email protected]) on the Kaggle dataset and of 186.3% on the Eden dataset compared to traditional supervised learning. Additionally, when combined with existing oversampling techniques, the PI on the Kaggle dataset further increases to 88.9%, highlighting the potential of the proposed method for improving detection accuracy in highly imbalanced datasets. Full article