Explore the vast range of titles available.

Rockburst is a prevalent geological hazard in deep geotechnical engineering, and its accurate prognostication is vital for prevention measures. Consequently, this research proffers a pioneering classification prediction methodology, namely Cross Reconstruction Learning (CR), underpinned by conventional machine learning algorithms and metric learning strategies. Initially, this technique partitions and restructures the original dataset, where each sample feature intersects and reconfigures with features from other samples within the set. During this amalgamation, new samples are assigned labels based on the degree of divergence or congruity between two sets of sample labels, thereby forming a new set of samples. Subsequently, an array of machine learning algorithms is utilized to train and test this new dataset. Ultimately, employing a universal class voting mechanism and decoding test set results through probability assignment, the predicted labels are converted back into rock burst outcomes, thereby determining the final prediction classification. The proposed model was trained on a database encompassing 239 instance samples, and its performance was validated against the currently proficient models (KNN, XGBoost, and Random Forest algorithms) employed in rock burst prediction. The outcome revealed a decline in the performance metrics of all three machine learning algorithms when interfaced with the Cross Reconstruction learning method, particularly the KNN algorithm, owing to the doubled feature dimensions in the combined dataset. However, the metrics of ensemble models, XGBoost and Random Forest, exhibited a notable improvement compared to the original classification models. On comparing multiple performance metrics, it was discovered that the CR-XGBoost model outperformed others across all evaluations, thereby offering significant guidance for practical engineering applications.

Many practical applications suffer from imbalanced data classification, in which case the minority class has degraded recognition rate. The primary causes are the sample scarcity of the minority class and the intrinsic complex distribution characteristics of imbalanced datasets. The imbalanced classification problem is more serious on small sample datasets. To solve the problems of small sample and class imbalance, a hybrid resampling method is proposed. The proposed method combines an oversampling approach (synthetic minority oversampling technique, SMOTE) and a novel data cleaning approach (weighted edited nearest neighbor rule, WENN). First, SMOTE generates synthetic minority class examples using linear interpolation. Then, WENN detects and deletes unsafe majority and minority class examples using weighted distance function and k-nearest neighbor (kNN) rule. The weighted distance function scales up a commonly used distance by considering local imbalance and spacial sparsity. Extensive experiments over synthetic and real datasets validate the superiority of the proposed SMOTE-WENN compared with three state-of-the-art resampling methods.

The fault diagnosis of rolling bearings is faced with the problem of a lack of fault data. Currently, fault diagnosis based on traditional convolutional neural networks decreases the diagnosis rate. In this paper, the developed adaptive residual shrinkage network model is combined with transfer learning to solve the above problems. The model is trained on the Case Western Reserve dataset, and then the trained model is migrated to a small-sample dataset with a scaled-down sample size and the Jiangnan University bearing dataset to conduct the experiments. The experimental results show that the proposed method can efficiently learn from small-sample datasets, improving the accuracy of the fault diagnosis of bearings under variable loads and variable speeds. The adaptive parameter-rectified linear unit is utilized to adapt the nonlinear transformation. When rolling bearings are in operation, noise production is inevitable. In this paper, soft thresholding and an attention mechanism are added to the model, which can effectively process vibration signals with strong noise. In this paper, the real noise is simulated by adding Gaussian white noise in migration task experiments on small-sample datasets. The experimental results show that the algorithm has noise resistance.

In the field of data mining, the performance of clustering is largely affected by the number of samples. However, obtaining enough data samples in some applications is difficult and expensive. To solve this problem, data augmentation like the oversampling methods have been adopted, but these methods mainly focus more on the local information of the data, without considering its potential distribution. In this paper, a new data augmentation method is proposed, which is the Wasserstein Generation Adversarial Network based on the Gaussian Mixture Model (GMM_WGAN) to generate datasets for small samples, to solve the problem of insufficient dataset size in clustering. It includes two steps, in the first step we use the Gaussian Mixture Model to capture the potential distribution of the real dataset, and in the second step, we use Wasserstein generative adversarial network to generate data samples to expand the small size dataset. We utilize five clustering algorithms to evaluate GMM_WGAN performance and compare it with the other seven data enhancement methods. Experiments on 10 small size datasets demonstrate that the proposed approach achieves greater result than others based on five evaluation metrics.

Dental panoramic X-ray imaging, due to its high cost-effectiveness and low radiation dose, has become a widely used diagnostic tool in dentistry. Accurate tooth segmentation is crucial for lesion analysis and treatment planning, helping dentists to quickly and precisely assess the condition of teeth. However, dental X-ray images often suffer from noise, low contrast, and overlapping anatomical structures, coupled with limited available datasets, leading traditional deep learning models to experience overfitting, which affects generalization ability. In addition, high-precision deep models typically require significant computational resources for inference, making deployment in real-world applications challenging. To address these challenges, this paper proposes a tooth segmentation method based on the pre-trained SAM2 model. We employ adapter modules to fine-tune the SAM2 model and introduce ScConv modules and gated attention mechanisms to enhance the model’s semantic understanding and multi-scale feature extraction capabilities for medical images. In terms of efficiency, we utilize knowledge distillation, using the fine-tuned SAM2 model as the teacher model for distilling knowledge to a smaller model named LightUNet. Experimental results on the UFBA-UESC dataset show that, in terms of performance, our model significantly outperforms the traditional UNet model in multiple metrics such as IoU, effectively improving segmentation accuracy and model robustness, particularly with limited sample datasets. In terms of efficiency, LightUNet achieves comparable performance to UNet, but with only 1.6% of its parameters and 24.0% of the inference time, demonstrating its feasibility for deployment on edge devices.

Special scene classification and identification tasks are not easily fulfilled to obtain samples, which results in a shortage of samples. The focus of current researches lies in how to use source domain data (or auxiliary domain data) to build domain adaption transfer learning models and to improve the classification accuracy and performance of small sample machine learning in these special and difficult scenes. In this paper, a model of deep convolution and Grassmann manifold embedded selective pseudo-labeling algorithm (DC-GMESPL) is proposed to enable transfer learning classifications among multiple small sample datasets. Firstly, DC-GMESPL algorithm uses satellite remote sensing image sample data as the source domain to extract the smoke features simultaneously from both the source domain and the target domain based on the Resnet50 deep transfer network. This is done for such special scene of the target domain as the lack of local sample data for forest fire smoke video images. Secondly, DC-GMESPL algorithm makes the source domain feature distribution aligned with the target domain feature distribution. The distance between the source domain and the target domain feature distribution is minimized by removing the correlation between the source domain features and re-correlation with the target domain. And then the target domain data is pseudo-labeled by selective pseudo-labeling algorithm in Grassmann manifold space. Finally, a trainable model is constructed to complete the transfer classification between small sample datasets. The model of this paper is evaluated by transfer learning between satellite remote sensing image and video image datasets. Experiments show that DC-GMESPL transfer accuracy is higher than DC-CMEDA, Easy TL, CMMS and SPL respectively. Compared with our former DC-CMEDA, the transfer accuracy of our new DC-GMESPL algorithm has been further improved. The transfer accuracy of DC-GMESPL from satellite remote sensing image to video image has been improved by 0.50%, the transfer accuracy from video image to satellite remote sensing image has been improved by 8.50% and then, the performance has been greatly improved. 特殊场景分类和识别任务面临样本不易获得而造成样本缺乏，利用源域（或称辅助域）数据构建领域自适应迁移学习模型，提高小样本机器学习在这些困难场景中的分类准确度与性能是当前研究的热点与难点。提出深度卷积与格拉斯曼流形嵌入的选择性伪标记算法（deep convolution and Grassmann manifold embedded selective pseudo-labeling，DC-GMESPL）模型，以实现在多种小样本数据集间迁移学习分类。针对目标域特殊场景，如森林火灾烟雾视频图像的本地样本数据缺乏情景，使用卫星遥感图像异地样本数据作为源域，基于Resnet50深度迁移网络，同时提取源域与目标域的烟雾特征；通过去除源域特征间的相关性，并与目标域重新关联，最小化源域与目标域特征分布距离，使源域与目标域特征分布对齐；在格拉斯曼流形空间中，用选择性伪标记算法对目标域数据作伪标记；构建一种可训练模型完成小样本数据间迁移分类。通过卫星遥感图像与视频影像数据集间迁移学习，对文中模型进行评估。实验表明，DC-GMESPL迁移准确率均高于DC-CMEDA、Easy TL、CMMS和SPL等方法。与作者先期研究的DC-CMEDA算法相比，新算法DC-GMESPL的准确率得到进一步提升；DC-GMESPL从卫星遥感图像到视频图像迁移准确率提高了0.50%，而从视频图像到卫星遥感图像迁移准确率提高了8.50%，且在性能上有了很大改善。

In the fields of coal dust control and coalbed methane (CBM) development, wettability is a crucial parameter of coal, often determined by the coal–water contact angle (CA). In order to construct an accurate CA prediction model, extensive data on industrial components, element content, and coal CAs were collected. Two sets of data were utilized: a large sample comprising 98 data groups gathered from various sources, and a small sample consisting of 16 data groups collected from a single source. These datasets were employed to develop models using three machine learning (ML) methods: K-nearest neighbor, support vector regression, and back-propagation neural network. The results revealed a significant underfitting phenomenon in all three ML methods when applied to the training and testing datasets of the large sample. This underfitting can be attributed primarily to the variations in coal sample handling by different scholars. Conversely, the three ML methods exhibited pronounced overfitting on the training dataset of the small sample, resulting in limited generalization ability on the testing dataset. This limitation arises from the small amount of data in the small sample. To address this, the synthetic minority oversampling technique was employed to generate augmented samples for the small sample. The correlation of determination of the augmented samples ranges from 0.82 to 0.92, indicating an excellent fit. Additionally, the fit superiority ratios of the training and testing datasets fell between 0.92 and 1. This approach effectively avoids the risk of underfitting in large-sample datasets and overfitting in small-sample training datasets. In the final stage, the developed model was used to predict the wettability of coal samples from three coal mines in the Qinshui Basin, China. The predicted CA values demonstrated a high level of agreement with the CA values measured in the laboratory. This comprehensive study thoroughly analyzed the underlying reasons behind the failure of ML models to effectively handle large- and small-sample data for CAs. It also provides a valuable solution to the above problems by data augmentation with small samples, which holds great significance in enabling quick and accurate prediction of CAs using limited coal parameter data.

The accurate segmentation of apple leaf disease spots is the key to identifying the classification of apple leaf diseases and disease severity. Therefore, a DeepLabV3+ semantic segmentation network model with an actors spatial pyramid pool module (ASPP) was proposed to achieve effective extraction of apple leaf lesion features and to improve the apple leaf disease recognition and disease severity diagnosis compared with the classical semantic segmentation network models PSPNet and GCNet. In addition, the effects of the learning rate, optimizer, and backbone network on the performance of the DeepLabV3+ network model with the best performance were analyzed. The experimental results show that the mean pixel accuracy (MPA) and mean intersection over union (MIoU) of the model reached 97.26% and 83.85%, respectively. After being deployed into the smartphone platform, the detection time of the detection system was 9s per image for the portable and intelligent diagnostics of apple leaf diseases. The transfer learning method provided the possibility of quickly acquiring a high-performance model under the condition of small datasets. The research results can provide a precise guide for the prevention and precise control of apple diseases in fields.

Highlight removal is a critical and challenging problem. In view of the complex highlight phenomenon on the surface of smooth liquor bottles in natural scenes, the traditional highlight removal algorithms cannot semantically disambiguate between all-white or near-white materials and highlights, and the recent highlight removal algorithms based on deep learning lack flexibility in network architecture, have network training difficulties and have insufficient object applicability. As a result, they cannot accurately locate and remove highlights in the face of some small sample highlight datasets with strong pertinence, which reduces the performance of some tasks. Therefore, this paper proposes a fast highlight removal method combining U[sup.2]-Net and LaMa. The method consists of two stages. In the first stage, the U[sup.2]-Net network is used to detect the specular reflection component in the liquor bottle input image and generate the mask map for the highlight area in batches. In the second stage, the liquor bottle input image and the mask map generated by the U[sup.2]-Net are input to the LaMa network, and the surface highlights of the smooth liquor bottle are removed by relying on the powerful image inpainting performance of LaMa. Experiments on our self-made liquor bottle surface highlight dataset showed that this method outperformed other advanced methods in highlight detection and removal.

Highlight removal is a critical and challenging problem. In view of the complex highlight phenomenon on the surface of smooth liquor bottles in natural scenes, the traditional highlight removal algorithms cannot semantically disambiguate between all-white or near-white materials and highlights, and the recent highlight removal algorithms based on deep learning lack flexibility in network architecture, have network training difficulties and have insufficient object applicability. As a result, they cannot accurately locate and remove highlights in the face of some small sample highlight datasets with strong pertinence, which reduces the performance of some tasks. Therefore, this paper proposes a fast highlight removal method combining U2-Net and LaMa. The method consists of two stages. In the first stage, the U2-Net network is used to detect the specular reflection component in the liquor bottle input image and generate the mask map for the highlight area in batches. In the second stage, the liquor bottle input image and the mask map generated by the U2-Net are input to the LaMa network, and the surface highlights of the smooth liquor bottle are removed by relying on the powerful image inpainting performance of LaMa. Experiments on our self-made liquor bottle surface highlight dataset showed that this method outperformed other advanced methods in highlight detection and removal.