Uneven Distribution Of Samples Research Articles

Eres-UNet++: Liver CT image segmentation based on high-efficiency channel attention and Res-UNet++

Computerized tomography (CT) is of great significance for the localization and diagnosis of liver cancer. Many scholars have recently applied deep learning methods to segment CT images of liver and liver tumors. Unlike natural images, medical image segmentation is usually more challenging due to its nature. Aiming at the problem of blurry boundaries and complex gradients of liver tumor images, a deep supervision network based on the combination of high-efficiency channel attention and Res-UNet++ (ECA residual UNet++) is proposed for liver CT image segmentation, enabling fully automated end-to-end segmentation of the network. In this paper, the UNet++ structure is selected as the baseline. The residual block feature encoder based on context awareness enhances the feature extraction ability and solves the problem of deep network degradation. The introduction of an efficient attention module combines the depth of the feature map with spatial information to alleviate the uneven sample distribution impact; Use DiceLoss to replace the cross-entropy loss function to optimize network parameters. The liver and liver tumor segmentation accuracy on the LITS dataset was 95.8% and 89.3%, respectively. The results show that compared with other algorithms, the method proposed in this paper achieves a good segmentation performance, which has specific reference significance for computer-assisted diagnosis and treatment to attain fine segmentation of liver and liver tumors.

PV-YOLO: Lightweight YOLO for Photovoltaic Panel Fault Detection

The rapid development of the photovoltaic industry in recent years has made the efficient and accurate completion of photovoltaic operation and maintenance a major focus in recent studies. The key to photovoltaic operation and maintenance is the accurate multifault identification of photovoltaic panel images collected using drones. In this paper, PV-YOLO is proposed to replace YOLOX’s backbone network, CSPDarknet53, with a transformer-based PVTv2 network to obtain local connections between images and feature maps to extract more edge-detail features of similar faults. The CBAM attention mechanism is added to enhance the effective features and improve the detection accuracy of small objects. The label assignment mechanism is optimized, and the SIoU loss functionis used to improve the uneven distribution of samples and accelerate network convergence. Experiments on the dataset prove that this method is superior to the existing technology, as the highest mAP value is 92.56%. This value is 10.46% higher than that of YOLOX, and the mAP is optimal under the same parameter magnitude,proving the model’s effectiveness.Moreover, mAP is increased by over 10%, especially for small targets. In this paper, we implemented a lightweight design for the model, and proposes four models of different sizes to be-sized models that are suitable for different detection scenarios.

Electrochemically assisted wide area Raman with standard curved surface quantification method

Reproducibility is still a great challenge for surface-enhanced Raman scattering (SERS), because the uncontrollable fabrication of SERS substrates or the uneven distribution of samples on the substrate result in the signal fluctuation with or between the substrates. Herein, a novel SERS quantitative method with good reproducibility was proposed. It is based on the basic principle that the SERS signal intensity is not only related to electromagnetic enhancement and the concentration of sample, but also related to the specific surface area of the substrate. The surface area information of the substrate is obtained through electrochemical technology, and then introduced into the standard curve with the linear relationship of concentration of sample and SERS intensity as a new variable to obtain a 3D standard curved surface, which effectively corrects the signal difference between the substrates, and combines the wide area Raman method to reduce the difference within the substrate, thereby improving the reproducibility of SERS quantitative detection. Using malachite green (MG) as the probe molecule and using cyclic voltammetry to calculate the substrate area fitted plane model (CV-standard curved surface), the root mean square error (RMSE) of the predicted result is 0.26 and the relative error (RE) is 0.25. It shows that the detection error significantly reduces comparing with the traditional standard curve method. Also, the proposed method can be used in other SERS quantitative detection and has potential application prospects.

Learning latent local manifold embeddings for hyperspectral feature extraction

Hyperspectral images with an immense number of spectral bands provide abundant discriminant information for accurate land-cover classification in the remote sensing field. However, these narrow and adjacent bands contain a large amount of redundant information. Analyzing these images always requires a huge storage space with expensive computational costs. Furthermore, their high correlation coefficient would lead to the Hughes phenomenon, hindering the improvement of classification performance. We propose a linear semi-supervised hyperspectral feature extraction method L3ME to learn latent local manifold embeddings. Although labeled samples are beneficial to construct learning models, their number is always limited in real-world tasks. The motivation of this paper is to jointly enhance the contributions of labeled and unlabeled samples for learning local manifold structures of hyperspectral images. Features in labeled samples are extracted by two procedures, the adaptive patch alignment framework and integrated intraclass-interclass relationships, from different perspectives. The former aims to solve the problem of the uneven distribution of classes by introducing spectral angle based adaptive parameters. The latter aims to solve the problem of the uneven distribution of samples by constructing several adjacency graphs. The locality preserving projection is capable of preserving the local neighborhood structure of samples. A penalty for sparse regularization is cleverly integrated into the proposed linear discriminant objective function, which is optimized using a novel updating strategy. The convergence of L3ME is proved in detail and analyzed in this paper. Experiments on three typical hyperspectral datasets illustrate the effectiveness of the proposed method over some state-of-the-art techniques. The implementation of L3ME is available at https://github.com/biowby/L3ME.

Co-training based virtual sample generation for solving the small sample size problem in process industry

With the development of industrialization, the production scale and complexity of process industries are getting larger and larger. But, limited by the small amounts of samples and the uneven sample distribution in the process industry, it is difficult to establish accurate and efficient data-driven soft sensor models to predict some variables. To further develop the application of soft sensor models, generating new virtual samples based on the original sample distribution to extend the sample set is an ideal approach to solve this problem. In this paper, a novel virtual sample generation method based on the co-training of two K-Nearest Neighbor (KNN) models is proposed. First, according to the sparse parameter, sparse regions in each dimension of the feature space are identified. Second, the input features of virtual samples are generated in these sparse regions by performing interpolation operations. Third, the outputs of virtual samples are predicted by double KNN regressors based on co-training. The qualified virtual samples are screened and the model is updated using these virtual samples to improve the prediction accuracy of the double KNN models. To verify the effectiveness and superiority of the proposed virtual sample generation method based on the co-training (CTVSG), case studies are conducted using two standard functions and a Purified Terephthalic Acid (PTA) industrial dataset, where the effectiveness of CTVSG is confirmed.

Automatic detection of three cell types in a microscope image based on deep learning.

With the continuous integration of deep learning and the technique of molecular biology, target detection models must accurately detect the position of each cell in the image and classify it correctly. We present a model for the multi-scale feature fusion of the existing human cell image dataset based on Gaussian mixedly clustering. First, a novel feature extraction network for extracting preliminary features at picture multi scales was presented, which was based on a residual neural network with Instance Normalization and a Mish activation function. Second, the presented model adopts the idea of feature fusion and introduced a new type of feature fusion network to integrate feature graphs on different scales. Furthermore, a Gaussian hybrid clustering algorithm was proposed to cluster the hyperparameters. Based on the experimental results, the average accuracy of the proposed model in the human cell image dataset exceeds 0.96, which improves by 11.9% compared with the existing target detection methods in the same field. Experiments show that the proposed model had been adapted to datasets with uneven sample distribution, providing new ideas for research on medical images.

Effects of Mechanical Stress on Insulation Structure and Performance of HV Cable.

Mechanical stresses generated during manufacturing and laying process of high voltage cables can result in degradation of insulation properties, affecting the stable operation of the transmission system. Traditional test methods for testing the effect of mechanical stress on the insulation properties of polyethylene still have some shortcomings to be explored and it is able to explain the changes of the insulation properties of polyethylene under mechanical stress from a microscopic perspective. In order to further study the effect of stress on the insulation properties of polyethylene, microstructural changes, the breakdown field strength, conductivity and charge distribution of polyethylene at different elongation rates are investigated by a combination of experimental and molecular dynamics simulations. The results show that the increase in stress leads to a decrease in crystallinity and microcrystalline size of the material decrease. The untwisting and orientation of the polyethylene molecular chains during the stretching process can create cavities, resulting in an uneven sample distribution and thickness reduction, leading to a reduction in the breakdown field strength. Meanwhile, some crystal regions are transformed into amorphous regions. The loose amorphous regions facilitate the directional migration of carriers, resulting in the increase of conductivity. When the elongation ratio is smaller, the distance between the molecular chains increases and the trap depth of the specimen becomes shallower. This facilitates the migration of ions and electrons and increases the rate of decay of the surface potential. When the stretch is further increased, new traps are created by broken molecular chains to limit the movement of charges, decreasing the decay rate of the surface potential and reducing the insulation properties of the polyethylene. Meanwhile, the molecular dynamics model of semi-crystalline polyethylene was developed to observe the microstructure and energy changes during the stretching process. The conclusions in terms of tensile tests were verified from a microscopic perspective.

A Novel Intrusion Detection Method Based on Lightweight Neural Network for Internet of Things

The purpose of a network intrusion detection (NID) is to detect intrusions in the network, which plays a critical role in ensuring the security of the Internet of Things (IoT). Recently, deep learning (DL) has achieved a great success in the field of intrusion detection. However, the limited computing capabilities and storage of IoT devices hinder the actual deployment of DL-based high-complexity models. In this article, we propose a novel NID method for IoT based on the lightweight deep neural network (LNN). In the data preprocessing stage, to avoid high-dimensional raw traffic features leading to high model complexity, we use the principal component analysis (PCA) algorithm to achieve feature dimensionality reduction. Besides, our classifier uses the expansion and compression structure, the inverse residual structure, and the channel shuffle operation to achieve effective feature extraction with low computational cost. For the multiclassification task, we adopt the NID loss that acts as a better loss function to replace the standard cross-entropy loss for dealing with the problem of uneven distribution of samples. The results of experiments on two real-world NID data sets demonstrate that our method has excellent classification performance with low model complexity and small model size, and it is suitable for classifying the IoT traffic of normal and attack scenarios.

Eclipse Attack Detection for Blockchain Network Layer Based on Deep Feature Extraction

An eclipse attack is a common method used to attack the blockchain network layer; however, detecting eclipse attacks is challenging, and the performance of existing methods is inadequate due to uneven sample distribution, incomplete definition of discriminating features, and weak feature perception. Thus, this paper proposes an eclipse attack traffic detection method based in a custom combination of features and deep learning. To describe the behavior characteristics of attack traffic more accurately, traffic attribute features in there levels are defined in combination with the eclipse attack method. Here, the downstream traffic behavior feature of the eclipse attack is described from the conventional traffic feature, and the frequency distribution characteristics of eclipse attack traffic is by introducing the φ-entropy divergence algorithm. In addition, the structural characteristics of eclipse attack traffic are mapped from the rate of changes in traffic communication and load features. Then, the improved synthetic minority oversampling technique (ISMOTE) up-sampling algorithm is employed to eliminate interference caused by the uneven distribution of eclipse attack traffic samples on the detection results. In addition, the ISMOTE algorithm adjusts the sampling weight of minority class samples, supports automatic clustering and efficient up-sampling of samples, and improves the detection accuracy performance of eclipse attack samples by calculating the local cluster density. Then, deep feature mining is performed on the eclipse attack traffic from the distribution characteristics of space and time series using a CNN and Bi-LSTM. Simultaneously, mining features are fully integrated into mixed feature using the multihead attention mechanism such that the relevance and complementarity of the two feature distributions can be utilized to enhance the model’s ability to perceive the spatiotemporal relationship of the eclipse attack traffic. Finally, the generated multihead attention items are detected for binary classification, and the results are output. Experimental results demonstrate that the proposed method can comprehensively enhance detection performance and sufficiently detect and classify eclipse attack traffic in the blockchain network layer.

Bayesian Calibration of Traffic Flow Fundamental Diagrams Using Gaussian Processes

Modeling the relationship between vehicle speed and density on the road is a fundamental problem in traffic flow theory. Recent research found that using the least-squares (LS) method to calibrate single-regime speed-density models is biased because of the uneven distribution of samples. This paper explains the issue of the LS method from a statistical perspective: the biased calibration is caused by the correlations/dependencies in regression residuals. Based on this explanation, we propose a new calibration method for single-regime speed-density models by modeling the covariance of residuals via a zero-mean Gaussian Process (GP). Our approach can be viewed as a generalized least-squares (GLS) method with a specific covariance structure (i.e., kernel function) and is a generalization of the existing LS and the weighted least-squares (WLS) methods. Next, we use a sparse approximation to address the scalability issue of GPs and apply a Markov chain Monte Carlo (MCMC) sampling scheme to obtain the posterior distributions of the parameters for speed-density models and the hyperparameters (i.e., length scale and variance) of the GP kernel. Finally, we calibrate six well-known single-regime speed-density models with the proposed method. Results show that the proposed GP-based methods (1) significantly reduce the biases in the LS calibration, (2) achieve a similar effect as the WLS method, (3) can be used as a non-parametric speed-density model, and (4) provide a Bayesian solution to estimate posterior distributions of parameters and speed-density functions.

FFSSD: Feature Fusion SSD algorithm with SE on Traffic Sign Detection

Traffic sign detection is of great importance to the development of intelligent vehicles. In this paper, we propose a modified SSD algorithm called FFSSD to the traffic environment. Firstly,we integrate low and high level features together in order to enhance the accuracy of tiny instances. Besides, we insert a feature enhancement module into it and the original SSD loss was altered by focal loss, which is designed to solve the problem of uneven sample distribution. We evaluate the algorithm on GTSDB (The German Traffic Sign Detection Benchmark dataset). The experimental result demonstrates that our algorithm has a great achievement. Compared with some up-of-date methods, it also achieves higher correctness in the traffic field.

Testing Virulence of Different Species of Insect Associated Fungi against Yellow Mealworm (Coleoptera: Tenebrionidae) and Their Potential Growth Stimulation to Maize.

This paper investigates 71 isolates of two genera of entomopathogens, Metarhizium and Beauveria, and a biostimulative genus Trichoderma, for their ability to infect yellow mealworms (Tenebrio molitor) and to stimulate maize (Zea mays) growth. Fungal origin, host, and isolation methods were taken into account in virulence analysis as well. Isolates Metarhizium brunneum (1154) and Beauveria bassiana (2121) showed the highest mortality (100%) against T. molitor. High virulence seems to be associated with fungi isolated from wild adult mycosed insects, meadow habitats, and Lepidopteran hosts, but due to uneven sample distribution, we cannot draw firm conclusions. Trichoderma atroviride (2882) and Trichoderma gamsii (2883) increased shoot length, three Metarhizium robertsii isolates (2691, 2693, and 2688) increased root length and two M. robertsii isolates (2146 and 2794) increased plant dry weight. Considering both criteria, the isolate M. robertsii (2693) was the best as it caused the death of 73% T. molitor larvae and also significantly increased maize root length by 24.4%. The results warrant further studies with this isolate in a tri-trophic system.

Network Intrusion Detection Model Based on Improved BYOL Self-Supervised Learning

The combination of deep learning and intrusion detection has become a hot topic in today’s network security. In the face of massive, high-dimensional network traffic with uneven sample distribution, how to be able to accurately detect anomalous traffic is the primary task of intrusion detection. Most research on intrusion detection systems based on network anomalous traffic detection has focused on supervised learning; however, the process of obtaining labeled data often requires a lot of time and effort, as well as the support of network experts. Therefore, it is worthwhile investigating the development of label-free self-supervised learning-based approaches called BYOL which is a simple and elegant framework with sufficiently powerful feature extraction capabilities for intrusion detection systems. In this paper, we propose a new data augmentation strategy for intrusion detection data and an intrusion detection model based on label-free self-supervised learning, using a new data augmentation strategy to introduce a perturbation enhancement model to learn invariant feature representation capability and an improved BYOL self-supervised learning method to train the UNSW-NB15 intrusion detection dataset without labels to extract network traffic feature representations. Linear evaluation on UNSW-NB15 and transfer learning on NSK-KDD, KDD CUP99, CIC IDS2017, and CIDDS_001 achieve excellent performance in all metrics.

Foreign Object Detection Algorithm Based on Multi-scale Convolutional Network

In order to detect foreign matter invading the track and prevent the intrusion of foreign matter from causing railway safety accidents, the detection algorithm of foreign matter intrusion on the track is studied. Aiming at the problem that the rail transit scene is complex and the obstacle scale changes in the acquired image information, this research proposes a multi-scale target detection algorithm based on the YOLO (you only look once) algorithm. First, an adaptive feature fusion module is designed to make the feature maps used for detection have strong semantic information at various scales; then, a new loss function is designed to alleviate the problem of uneven sample distribution and optimize the training process. Experiments show that the algorithm has obvious advantages in multi-scale detection, which not only improves the accuracy of target detection, especially the accuracy of small targets, but also does not significantly increase the inference time and the amount of parameters, and has high real-time performance.

Approach for 3D Cultural Relic Classification Based on a Low-Dimensional Descriptor and Unsupervised Learning

Computer-aided classification serves as the basis of virtual cultural relic management and display. The majority of the existing cultural relic classification methods require labelling of the samples of the dataset; however, in practical applications, there is often a lack of category labels of samples or an uneven distribution of samples of different categories. To solve this problem, we propose a 3D cultural relic classification method based on a low dimensional descriptor and unsupervised learning. First, the scale-invariant heat kernel signature (Si-HKS) was computed. The heat kernel signature denotes the heat flow of any two vertices across a 3D shape and the heat diffusion propagation is governed by the heat equation. Secondly, the Bag-of-Words (BoW) mechanism was utilized to transform the Si-HKS descriptor into a low-dimensional feature tensor, named a SiHKS-BoW descriptor that is related to entropy. Finally, we applied an unsupervised learning algorithm, called MKDSIF-FCM, to conduct the classification task. A dataset consisting of 3D models from 41 Tang tri-color Hu terracotta Eures was utilized to validate the effectiveness of the proposed method. A series of experiments demonstrated that the SiHKS-BoW descriptor along with the MKDSIF-FCM algorithm showed the best classification accuracy, up to 99.41%, which is a solution for an actual case with the absence of category labels and an uneven distribution of different categories of data. The present work promotes the application of virtual reality in digital projects and enriches the content of digital archaeology.

IKPCA-ELM-based Intrusion Detection Method

An IKPCA-ELM-based intrusion detection method is developed to address the problem of the low accuracy and slow speed of intrusion detection caused by redundancies and high dimensions of data in the network. First, in order to reduce the effects of uneven sample distribution and sample attribute differences on the extraction of KPCA features, the sample attribute mean and mean square error are introduced into the Gaussian radial basis function and polynomial kernel function respectively, and the two improved kernel functions are combined to construct a hybrid kernel function. Second, an improved particle swarm optimization (IPSO) algorithm is proposed to determine the optimal hybrid kernel function for improved kernel principal component analysis (IKPCA). Finally, IKPCA is conducted to complete feature extraction, and an extreme learning machine (ELM) is applied to classify common attack type detection. The experimental results demonstrate the effectiveness of the constructed hybrid kernel function. Compared with other intrusion detection methods, IKPCA-ELM not only ensures high accuracy rates, but also reduces the detection time and false alarm rate, especially reducing the false alarm rate of small sample attacks.

Study on the Method of Fundus Image Generation Based on Improved GAN

With the continuous development of deep learning, the performance of the intelligent diagnosis system for ocular fundus diseases has been significantly improved, but during the system training process, problems like lack of fundus samples and uneven sample distribution (the number of disease samples is much smaller than the number of normal samples) have become increasingly prominent. In view of the previous issues, this paper proposes a method for generating fundus images based on “Combined GAN” (Com-GAN), which can generate both normal fundus images and fundus images with hard exudates, so that the sample distribution can be more even, while the fundus data are expanded. First, this paper uses existing images to train a Com-GAN, which consists of two subnetworks: im-WGAN and im-CGAN; then, it uses the trained model to generate fundus images, then performs qualitative and quantitative evaluation on the generated images, and adds the images to the original image set to expand the datasets; finally, based on this expanded training set, it trains the hard exudate detection system. The expanded datasets effectively improve the generalization ability of the system on the public datasets DIARETDB1 and e-ophtha EX, thereby verifying the effectiveness of the proposed method.

Ensembles of feature selectors for dealing with class-imbalanced datasets: A proposal and comparative study

Feature selection is an important task in many machine learning and data mining problems. Due to the increasing size of datasets, the removal of redundant, erroneous or noisy features is frequently an initial step. In many common applications, datasets have imbalanced class distribution. Although feature selection suffers in the presence of an uneven distribution of samples among the classes, there are few methods specifically designed for this situation. We propose a new approach based on the use of feature selection boosting to address this problem. Ensembles of feature selectors using both, standard and specifically designed for class-imbalanced datasets methods, are constructed using boosting algorithms,. These ensembles are used to perform feature selection in class-imbalanced datasets. The combination of different rounds of feature selectors over different samples with an adaptive distribution of the instances achieves an improved performance when compared with standard feature selection methods in class-imbalanced datasets. A comprehensive set of experiments that employ 18 different ensemble methods, 7 different feature selection methods and 140 class-imbalanced datasets demonstrates the efficiency of the ensemble approach in terms of reduction ability and classification performance. Further study of the proposed method shows its robustness in the presence of class label noise.

Surface Blemishes of Aluminum Material Image Recognition Based on Transfer Learning

Image datasets in the field of industrial manufacturing usually have the problem of uneven distribution of samples. To solve this problem, this paper utilizes transfer learning to recognize surface blemishes of Aluminum material image. In order to get rid of the disadvantage of VGGNet too many parameters, this paper combines VGGNet with Network-in-Network to generate a new model. The results of experiments is shown that it has achieved significant improvement by using transfer learning. Additionally, the new model also achieves a better performance and the number of parameters of the new model is much smaller than that of the original VGGNet.

Fault diagnosis of transformer based on fuzzy clustering and the optimized wavelet neural network

ABSTRACTIn order to solve the disadvantages of the traditional wavelet neural network (WNN) algorithm applied in transformer fault diagnosis, such as uneven sample distribution of training samples and high diagnostic error rate and long training time, an improved fault diagnosis method is proposed based on fuzzy clustering and the flower pollination algorithm. Firstly, fuzzy clustering is applied to deal with transformer fault sample data so as to remove the bad data; secondly, the flower pollination algorithm is applied to obtain the optimal parameters of the WNN. The example analysis results show that WNN based on the flower pollination algorithm (FPA-WNN) has better convergence, lower diagnosis error rate and shorter training time compared with WNN based on the particle swarm algorithm (PWA-WNN) and it is more suitable for transformer fault diagnosis.