Anti-noise Ability Research Articles

Metallogenic Prediction of Magnetite in the Pandian Area at the Northwest Margin of Luxi Uplift, China: Constraints of Wide-Field Electromagnetic Data

The Pandian deposit is a newly discovered contact metasomatic skarn magnetite deposit found in the Cainozoic super-thick overburden on the northwest margin of Luxi Uplift (LXU). Presently, the horizontal scale of the deposit delineated by the potential field (gravity and magnetic method) has shown giant potential for ore deposits, and mapping the ore-controlling structures in the vertical scale becomes a primary task for metallogenic prediction. In our study, the wide-field electromagnetic method (WFEM), with a strong anti-noise ability in recording electromagnetic signals on the surface at multiple frequencies, is applied to characterize the deep conductivity distribution of the Pandian area. Based on the inversion results from two parallel WFEM profiles, which consist of 105 sites and previous geological and geophysical results, the 2D geoelectric models are established. The low-resistivity regions (with a typical range of 25~32 Ω·m) in the electrical models are proven to be ore bodies of Pandian deposit, which are developed along the contact zone between Yanshanian intrusive rocks and Paleozoic Ordovician strata. The scattered bodies (typically >32 Ω·m) in Ordovician limestone strata are probably caused by intrusive diorite pluton closely related to magnetite mineralization. Due to contact metasomatism, bedded limestone near magnetite was metamorphosed into marble and accompanied by low-resistivity skarn alteration, with resistivity much different from its high-resistivity protolith. The inverted geoelectrical models visually reflect the spatial distribution features of intrusive rocks and lithologic alteration/fracture zones.

MIMO Multi-Frequency Active Vibration Control for Aircraft Panel Structure Using Piezoelectric Actuators

Undesirable vibration of aircraft panel structures has a significant impact on the safety of their occupants and the operational reliability of various systems. The traditional time-domain controller based on the parallel multi-frequency filtered-x least mean square (FxLMS) control algorithm is simple and effective. However, the mutual influence of convergence steps and the induced harmonic components will limit its performance. An improved parallel multi-input multi-output multi-frequency FxLMS (MIMOMF-FxLMS) algorithm is proposed, considering the multi-input multi-output (MIMO) control requirement of the aircraft panel structure active vibration control (AVC) system and its inevitable channel coupling phenomenon. The feedback error signal and the control channel model are processed by frequency division in the MIMOMF-FxLMS algorithm, so that the FxLMS algorithm of each control channel runs independently, effectively avoiding mutual interference between convergence steps and the generation of induced harmonic components. Simulation and experimental research on multi-frequency AVC of the panel structure model is performed using a new type of piezoelectric stack actuator. The test results show that the proposed controller reduces the vibration level of each observation point by more than 98%, and the vibration responses of the first two-order frequency component are significantly suppressed, which also has strong adaptability and anti-noise ability.

Damage Diagnosis of Frame Structure Based on Convolutional Neural Network with SE-Res2Net Module

The complex application environments of frame structures and the similar vibration signals between different locations make it difficult to accurately diagnose damage using traditional methods. Based on modifying the parameters and configuration of the convolution neural network with training interference (TICNN), this paper proposes a new model for damage diagnosis of frame structures by implanting a squeeze-and-excitation neural network (SENet) and Res2Net modules. Taking the frame structure model from the University of British Columbia as the research object, the proposed damage diagnosis model was used to diagnose its damage type. The proposed new model was compared with other models in terms of accuracy and anti-noise ability. The experimental results show that the accuracy of the proposed model was 99.44% when the training epoch was 30 and 99.78% when training epoch was 100. It is superior to other similar models in terms of convergence speed and accuracy. At the same time, the proposed model also has an excellent advantage in anti-noise ability. Therefore, the proposed damage diagnosis model has the advantages of fast convergence and higher damage diagnosis accuracy under a strong noise environment. It can realize the accurate damage diagnosis of structural frames.

Simultaneous Determination of Non-Uniform Soot Temperature and Volume Fraction from Flame Images

This paper presents a method to invert the two-dimensional distribution of temperature and volume fraction of soot particles from flame images. The temperature field and particle volume concentration field of the non-uniform soot flame are simultaneously reconstructed using the wide response spectrum of the color CCD camera without adding monochromatic filters. The influences of the number of cameras, error of cameras position angle, measurement noise and different reconstruction algorithms on the measurement accuracy, are analyzed. The numerical simulation results demonstrate that the error of cameras position angle plays a crucial role in the reconstruction accuracy. In addition, increasing the number of cameras can improve the reconstruction results accuracy. Compared with the least squares algorithm, the Tikhonov regularization algorithm has a stronger anti-noise ability, which can resist 39 dB of noise. The conclusions obtained in this paper are helpful to guide the following experimental studies.

A Multichannel MN-GCN for Wheelset-Bearing System Fault Diagnosis

The working condition of high-speed train wheelset bearings is complex and bad, which makes its vibration signal contain strong noise. To obtain more information of samples, signals are constructed into graphs and fit by graph convolution network (GCN). The existing GCN-based models still have some problems, such as insufficient theoretical basis of graph and the unstable and overfitting during training of models, which significantly limits the diagnosis accuracy. To address these issues, first, a weighted <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\varepsilon $ </tex-math></inline-formula> -recurrence network is proposed to construct the recurrence graph (RG). The recurrence relationship between samples is analyzed by the recursive nature of vibration signals. Maximum mean discrepancy (MMD) is used to obtain the regenerated Hilbert spatial distribution distance between two samples to reduce the weight gap between different recursive pairs. Also, the proposed method has better ex ante interpretability. Second, a vertex mean normalization (MN) layer is proposed to normalize individual vertex features to introduce some spatial perturbations and reduce the variance of vertex features, which can improve training stability and reduce overfitting. In addition, multichannel MN-GCN is proposed to fit multiscale graph features. Analyze recurrence nature of samples at different scales through RGs with varying densities of connection to improve the antinoise ability. Experimental results show that the proposed model can obtain spatial topology information accurately and improve the wheelset-bearing system fault diagnosis performance.

Fault diagnosis of gearbox based on adaptive wavelet de-noising and convolution neural network

In this paper, in order to solve the problem that it is difficult to carry out accurate fault diagnosis for gearbox under noise environment, complete ensemble imperial mode decomposition with adaptive noise analysis (CEEMDAN) is used to solve the sample entropy of the original signal and each intrinsic mode function (IMF) component, adaptive wavelet is adopted to decompose and reconstruct IMF with large sample entropy for noise reduction, and first layer wide convolution kernel deep convolution neural network (WDCNN) and long short term memory (LSTM) are used to extract the basic digital features of the reconstructed signal and the correlation features between the features. Therefore, a new fault diagnosis method for gearbox under noise environment is proposed. Taking the public data set of Jiangsu Qiangpeng Diagnostic Engineering Co., Ltd as the research object, the experiments were carried out with the method proposed in this paper. The experimental results show that the proposed method has high accuracy and strong anti-noise ability. Under the environment of no noise and low noise, the fault diagnosis accuracy of the gearbox is 100%; even if the signal to noise ratio is −4 dB, the fault diagnosis accuracy of the gearbox can still reach 99.97%. Therefore, this paper provides a method support for gearbox fault diagnosis under noise environment.

ICSI: an improved contrast source inversion method for electromagnetic inverse scattering problems.

An improved contrast source inversion method (ICSI) is proposed to solve the problem of electromagnetic inverse scattering. Specifically, we first resort Fourier bases to represent contrast source, so that we can solve contrast source in the frequency domain, which can accelerate the solution of contrast source. Then, a spatial-frequency domain constraint is designed to ensure that the spanned-domain calculation is synchronous optimal. Afterwards, a multi-round optimization combined with SVD (the singular value decomposition) is developed to alleviate the reliance on initial guesses. Finally, we utilize a frequency-domain filter to eliminate redundant inversion information and narrow the search scope of the solution. Extensive experiments on the synthetic and real data show that ICSI holds a faster computing speed, a better inversion ability of relative permittivities, and a stronger anti-noise ability.

A fault diagnosis of nuclear power plant rotating machinery based on multi-sensor and deep residual neural network

Rotating machinery is a key component of nuclear power plants (NPPs). The integrity of rotating machine is related to the safety and economy of the entire NPPs. In order to achieve better and more robust diagnostic performance, this work proposes an intelligent fault diagnosis method based on multi-sensor and deep residual neural network. This method gives full play to the value of multi-sensor information, and utilizes the powerful learning ability of deep learning model to realize the identification of rotating machinery fault types. The effectiveness of the method is evaluated by using the motor dataset and the bearing dataset from fault simulation experiment bench. In addition, the anti-noise ability of the method is tested and compared with other methods. The results show that the proposed method has higher diagnosis accuracy and stronger robustness, demonstrating the potential application value in rotating machinery of NPPs.

Studies on modified limited-memory BFGS method in full waveform inversion

Full waveform inversion (FWI) is a non-linear optimization problem based on full-wavefield modeling to obtain quantitative information of subsurface structure by minimizing the difference between the observed seismic data and the predicted wavefield. The limited-memory Broyden-Fletcher-Goldfarb-Shanno (L-BFGS) method is an effective quasi-Newton method in FWI due to its high inversion efficiency with low calculation and storage requirements. Like other conventional quasi-Newton methods, the approximation of the Hessian matrix in the L-BFGS method satisfies the quasi-Newton equation, which only exploits the gradient and model information while the available objective function value is neglected. The modified quasi-Newton equation considers the gradient, model, and objective function information together. Theoretical analysis reveals that the modified quasi-Newton equation is superior to the conventional quasi-Newton equation as it achieves higher-order accuracy in approximating the Hessian matrix. The modified L-BFGS method can be obtained by using the modified quasi-Newton equation to modify the L-BFGS method. This modification improves the accuracy of the Hessian matrix approximation with little increase of calculation for each iteration. We incorporate the modified L-BFGS method into FWI, numerical results show that the modified L-BFGS method has a higher convergence rate, achieves better inversion results, and has stronger anti-noise ability than the conventional L-BFGS method.

Energy consumption prediction using the GRU-MMattention-LightGBM model with features of Prophet decomposition.

The prediction of energy consumption is of great significance to the stability of the regional energy supply. In previous research on energy consumption forecasting, researchers have constantly proposed improved neural network prediction models or improved machine learning models to predict time series data. Combining the well-performing machine learning model and neural network model in energy consumption prediction, we propose a hybrid model architecture of GRU-MMattention-LightGBM with feature selection based on Prophet decomposition. During the prediction process, first, the prophet features are extracted from the original time series. We select the best LightGBM model in the training set and save the best parameters. Then, the Prophet feature is input to GRU-MMattention for training. Finally, MLP is used to learn the final prediction weight between LightGBM and GRU-MMattention. After the prediction weights are learned, the final prediction result is determined. The innovation of this paper lies in that we propose a structure to learn the internal correlation between features based on Prophet feature extraction combined with the gating and attention mechanism. The structure also has the characteristics of a strong anti-noise ability of the LightGBM method, which can reduce the impact of the energy consumption mutation point on the overall prediction effect of the model. In addition, we propose a simple method to select the hyperparameters of the time window length using ACF and PACF diagrams. The MAPE of the GRU-MMattention-LightGBM model is 1.69%, and the relative error is 8.66% less than that of the GRU structure and 2.02% less than that of the LightGBM prediction. Compared with a single method, the prediction accuracy and stability of this hybrid architecture are significantly improved.

Cooperative coevolutionary differential evolution with linkage measurement minimization for large-scale optimization problems in noisy environments

Many optimization problems suffer from noise, and the noise combined with the large-scale attributes makes the problem complexity explode. Cooperative coevolution (CC) based on divide and conquer decomposes the problems and solves the sub-problems alternately, which is a popular framework for solving large-scale optimization problems (LSOPs). Many studies show that the CC framework is sensitive to decomposition, and the high-accuracy decomposition methods such as differential grouping (DG), DG2, and recursive DG (RDG) are extremely sensitive to sampling accuracy, which will fail to detect the interactions in noisy environments. Therefore, solving LSOPs in noisy environments based on the CC framework faces unprecedented challenges. In this paper, we propose a novel decomposition method named linkage measurement minimization (LMM). We regard the decomposition problem as a combinatorial optimization problem and design the linkage measurement function (LMF) based on Linkage Identification by non-linearity check for real-coded GA (LINC-R). A detailed theoretical analysis explains why our proposal can determine the interactions in noisy environments. In the optimization, we introduce an advanced optimizer named modified differential evolution with distance-based selection (MDE-DS), and the various mutation strategy and distance-based selection endow MDE-DS with strong anti-noise ability. Numerical experiments show that our proposal is competitive with the state-of-the-art decomposition methods in noisy environments, and the introduction of MDE-DS can accelerate the optimization in noisy environments significantly.

Robust feature selection using label enhancement and β-precision fuzzy rough sets for multilabel fuzzy decision system

High-dimensionality is the most noticeable characteristic of multilabel data. In practice, multilabel data typically contain complex noises. Ignoring these noises in the feature selection process tends to cause an inaccurate prediction. Besides, many existing multilabel feature selection methods assume that the relation between samples and relevant labels is crisp, and the difference information hiding in the label space is lost. Given all these, in this paper, soft labels are investigated by label enhancement in multilabel feature selection. A robust feature selection algorithm is proposed using label enhancement and multilabel β-precision fuzzy rough sets. With the perspective of data distribution from samples in the same and different class, the margin-based robust fuzzy neighborhood is first defined to construct the robust fuzzy granular space. Second, label enhancement strategy is given in the robust fuzzy granular space considering multilabel data distribution. To investigate the noise-tolerant model, the underlying structure of label space after label enhancement is employed to encode the score vector of samples, which is used to search the pseudo-different class's samples of target sample. Then, the multilabel β-precision fuzzy rough set model is built to deal with multilabel data. Moreover, the fuzzy approximation degree of knowledge and the fuzzy dependency of decision classes with respect to conditional features are fused to measure the significance of features. Finally, a robust heuristic multilabel feature selection algorithm is proposed. Extensive experiments on classification performance and anti-noise ability are conducted, which verify that the proposed algorithm is effective and robust.

Error Model and Two-Phase Correction Method for Indirect Illumination

Phase shifting profilometry (PSP) has the advantages of high accuracy, spatial resolution, and anti-noise ability. However, in addition to random noise, indirect illumination, such as subsurface scattering, inter-reflection, and volume scattering, often occurs in the actual measurement environment, seriously affecting the system accuracy. In this paper, a sine series model (SSM) is proposed to simulate the error, which significantly simplifies the computational work. Based on the sine series model, a two-phase correction method (TPC) is proposed, where two phases with different frequencies are adopted to suppress the interference caused by indirect illumination and random noise. Moreover, by combining the multi-wavelength method to unwrap phase, TPC does not need to project additional patterns. Contrast experiments demonstrate that the proposed TPC method has the performance of reducing the error by 40.8%.

Online Active Learning Framework for Data Stream Classification With Density-Peaks Recognition

This paper considers a practical scenario—data stream classification, and uses online active learning to assist the classifier. Most active learning methods are proposed based on label uncertainty, but the methods based on representativeness are faced with difficulties in stream scenarios. The sampling criteria based on representativeness are usually fixed, which makes it difficult for them to work effectively in dynamic sample spaces, especially for data streams with concept drift. This paper proposes a novel online active learning framework based on sample representativeness. The framework uses local nearest-neighbor information to measure the representativeness of unlabeled samples and divides the maximum influence space of the representative sample. We also develop an independent mechanism to identify and store short-term cluster fragments to ensure the integrity of information. The framework is deployed to the online environment and adapts to any incremental learner. Simulation experiments on multiple datasets and classifiers show that our algorithm can improve the performance of the primary classifier. Compared with other online active learning, the proposed method can achieve more stable accuracy and better anti-noise ability under fewer labeled samples.

Plug-and-Play Typed Polarization Direction Indicator by Azimuthal Polarizer

This work is on polarization direction visualization of linearly-polarized light. Different from using conventional rotation or multiple beam-path approaches, a more direct and popular solution is to generate the so-called “Malus pattern” and visualize the polarization direction directly by an azimuthal polarizer (AP). Several experimental configurations on the basic principle have been reported. However, there has been no proper solution to plug-and-play the AP for the measurement directly since their high-performance hardware suffered from complex coupling relations, and their algorithms relied on filtering and manual operations. The present work is for the first time to: 1) point out the problems and propose the integration of the AP as a “plug-and-play” module; 2) propose a high-performance hardware configuration without coupling relation; and 3) propose a frequency-domain algorithm with high anti-noise ability and automatic identification. All the involved issues are experimentally verified. Besides, detailed discussions on the strong anti-noise ability and the factors which might influence the measurement accuracy are also elaborated.

A Robust Hierarchical Domain Constraint Strategy for Multiscale Contrast Objects Reconstruction

A robust hierarchical domain constraint (HDC) strategy is proposed for the multi-scale contrast objects reconstruction in this letter. The Monte Carlo method and point evaluation are adopted and modified for the classification of background and scatterers cells, the parameters of the background cells are set as the same as the actual background and removed from the inversion. The major work of the HDC strategy is to divide the inversion process into several stages, and the classification of cells is evaluated separately at each stage, making the classification reversible. And the HDC can effectively classify the inversion domain of low-contrast objects without negligence in the multi-scale contrast objects case, as well as the continuously varying inhomogeneous objects’ low-contrast parts. Another advantage of HDC is the threshold determining the classification of cells can be flexibly chosen. This robust constraint of the inversion domain compresses the solution space so that the ill-posedness of the inverse problem is mitigated, and better accuracy thus is achieved. In this letter, the HDC strategy is applied to the Variational Born Iterative Method (VBIM), numerical results validate the accuracy, robustness, and antinoise ability of the proposed VBIM-HDC.

Semi-supervised dual-task cross-consistency constraint network for 3D cardiac MRI segmentation

目的 针对人体组织器官及病灶区域的3维图像分割是计算机辅助医疗诊断的重要前提，是医学影像3维可视化的重要技术基础。深度学习方法在医学图像分割任务中的成功通常取决于大量有标注数据。半监督学习利用未标注数据容易获取的优点，在模型训练过程中使用少量标注数据和大量未标注数据进行学习，缓解了数据标注昂贵耗时的问题，在医学图像分割中受到了广泛关注。为更好地利用无标注数据，提升医学图像分割效果，提出一种新的一致性正则方法用于半监督3维医学图像分割。方法 模型以V-Net为基础架构，通过扩展网络结构，在均带有分割任务及回归任务属性的双任务主副解码器之间添加了用于正则化约束的交叉损失，构建了具有形状感知的基于双任务的交叉一致性正则网络SACC-Net （shape-aware cross-consistency regular network based on dual tasks），实现将数据层面和模型层面的扰动融合进多任务机制的一致性正则方法，使模型能够更好地利用未标注数据的有效先验信息，并且具有更好的泛化性能。结果 在MICCAI 2018（Medical Image Computing and Computer Assisted Intervention Society）心房分割挑战赛公布的数据集中的3维左心房核磁共振成像上验证本文算法，在仅使用训练集中10%的有标注数据的实验组中，Dice系数、Jaccard指数、HD（Hausdorff distance）距离和平均对称表面距离分别为88.01%、78.89%、8.19和2.09。在另一组仅使用20%的有标注数据的实验中Dice系数、Jaccard指数、HD距离和平均对称表面距离分别达到90.11%、82.11%、6.57和1.78。结论 本文提出的半监督分割模型性能显著，综合了数据、模型和任务层面的一致性正则约束，与其他半监督方法相比分割效果更好且具有更佳的泛化性能。;Objective Three-dimensional（3D）image segmentation of human tissues，organs and lesion areas is projected for computer-aided diagnosis and medical images-related 3D visualization. Thanks to the emerging deep learning technique，fully-supervised network models have been developing intensively in relevant to medical image segmentation tasks. However，it is challenged for a large amount of annotated data and 3D image segmentation data-labeled is costly and inefficient. Semi-supervised learning is focused on a small size of data-labeled and sufficient data-unlabeled in terms of easy acquisition of unlabeled data，which can alleviate the cost and time-consuming problem of data labeling. Our research is focused on new consistency regular method for semi-supervised 3D medical image segmentation model. To improve the medical image segmentation effect，our model can use unlabeled data through the fusion of different consistency methods. Method The network model is demonstrated on the V-Net，which can remove the residual structure of encoding and decoding. To get efficient features of unlabeled data，the proposed shape-aware cross-consistency regular network is introduced via the V-Net network structure extension on the basis of an encoder and two independent decoders-involved dual tasks （shape-aware cross-consistency regular network based on dual tasks（SACC-Net）），which are divided into a main decoder a and an auxiliary decoder b. The output of encoder-shared is transmitted to the two decoders after noise disturbance. At the same time，the two decoders can output the prediction results after each iteration. To increase the generalization and anti-noise ability of the model，it can minimize the difference between the two parts of the results during the training process. Additionally，the proportion of labeled samples in the training samples is extremely small because the feature distributions between the pre-processed medical image samples are relatively similar. To improve the learning ability of the model to segmented samples further，geometric prior information constraints are melted into the segmentation target. A shape-aware regression layer is added at the end of each decoder as well. During the training phase，each decoder can output two parts of the prediction results at the same time. That is，the total output of each iteration-after network consists of four parts. It can be used to decode the segmentation map SA and the signed distance map output by the decoder A，and the segmentation map SB and the signed distance map output by the decoder B through the dual-task consistency of each decoding part. To enhance the model’s ability and learn the effective features of segmentation targets to a greater extent， constraints and cross constraints can be used to realize a consistent regular method that combines data-level and modellevel disturbances with multi-task mechanisms，and make better use of unlabeled data. Result Our algorithm is validated on the MRI data set published in Atrium Segmentation Challenge held by MICCAI（Medical Image Computing and Computer Assisted Intervention Society）in 2018. The experiment is divided into two test groups based on the amounts proportion of labeled data. In the training set，10% annotated data is used only in the experimental group，the Dice coefficient， Jaccard index，HD （Hausdorff distance） distance，and average symmetric surface distance is reached to 88. 01%， 78. 89%，8. 19，and 2. 09 of each. In the other group，20% annotated data of the experiments are used only. The median Dice coefficient，Jaccard index，HD distance and average symmetric surface distance can be reached to 90. 14%， 82. 11%，6. 57，and 1. 78 each as well. Furthermore，In respect of the shape perception method using the level set function for regression tasks，the Dice evaluation index can be improved by 0. 69 and 0. 60 in comparison with shape-aware semi-supervised net（SASS Net）in 10% and 20% of the marked training results. Each improvement is reached to 1. 44% and 0. 72% in terms of comparative results of dual-task consistency（DTC）trained with 10% and 20% labeled data. Conclusion The semi-supervised segmentation model（SACC-Net）is illustrated for the criteria optimization for both of the region and boundary-based segmentation，which can incorporate the level-consistency of its data，model and task. The constrained method has its potential segmentation effect and generalization performance for semi-supervised methods.

SAR Image Change Detection in Spatial-Frequency Domain Based on Attention Mechanism and Gated Linear Unit

Change detection based on synthetic aperture radar (SAR) images is an important application in the remote sensing technology field. However, the lack of labeled data has been a difficult problem in SAR image detection, especially for pixel-level change detection. In this letter, we propose a novel unsupervised change detection algorithm, which improves the detection accuracy by exploring features from both spatial and frequency domains of SAR images. In particular, firstly clustering is used as pre-classification to obtain pseudo-labels, and then by incorporating classifiers and pseudo-labels in terms of feature learning, a novel unsupervised detection algorithm is proposed. In order to improve the sensitivity of the algorithm to changed details and enhance the anti-noise ability of the change detection network, the attention mechanism (AM) is integrated into the network to fully extract important spatial structure information. Moreover, a multi-domain fusion module is proposed to integrate spatial and frequency domain features into complementary feature representations. This module contains multi-region features weighted by the channel-spatial AM and deep features filtered out by the gated linear units (GLU) in the frequency domain. To verify the effectiveness of the proposed algorithm, it is compared against the other four SAR image change detection algorithms using three real datasets. The experimental results show that the proposed method outperforms the other four algorithms in terms of percent correct classification (PCC) and Kappa coefficient (KC).

Noise-Against Skeleton Extraction Framework and Application on Hand Gesture Recognition

Extracting stable skeletons from noisy images is a challenging problem since the skeletonization method is prone to be affected by inner and border noise. Although many methods have been proposed in the past for increasing the antinoise ability of skeletonization methods, most of them either only overcome border noise or, at the cost of lost topology, degrade the effects of two noises. In this paper, we propose a skeleton extraction framework to enhance the robustness of the existing skeletonization method against both inner and border noise. In our approach, we first use the different scales of Gaussian filters to smooth the input image and obtain multiple representations. Then, binarization and skeletonization were performed to produce a series of binary images and a series of skeletal images. Next, we use our measure on these binary and skeletal images to find the most suitable skeleton. Since our measure considers both the skeleton image changes and binary image changes caused by using a filter, the selected skeleton is sufficiently robust and has all the necessary skeletal branches. The inner noise experiment and border noise experiment are conducted for comparison. From the perspective of the measure of the rate of variation in the skeleton, the proposed framework can reduce the inner noise by approximately 92% and the border noise by approximately 40%. In addition, the experiment on static hand gesture recognition has demonstrated that the introduction of our framework can increase up to 11% mean recognition accuracy.

Feature Grouping and Selection With Graph Theory in Robust Fuzzy Rough Approximation Space

Most extant feature selection works neglect interactive features in the form of groups, leading to the omission of some important discriminative information. Moreover, the prevalence of data with uncertainty, fuzziness, and noise poses a certain obstacle to feature selection. Driven by these two issues, a Feature Grouping and Selection approach in Robust Fuzzy Rough Approximation Space using graph theory (FGS-RFRAS) is proposed in this study. First, a robust fuzzy rough approximation space is constructed by a neighborhood adaptive <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\beta$</tex-math></inline-formula> -precision fuzzy rough set model to enhance the robustness and antinoise ability of the fuzzy rough set model. Second, uncertainty measures in robust fuzzy rough approximation space are defined to analyze the interactivity and redundancy of pairwise features on graph structure. Then, a strategy of <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Interactive Retainment, Weakly Correlated Removal, and Max-Dependent Selection</i> is devised to guide feature grouping and selection. Experiments are performed on 21 datasets to evaluate the performance of FGS-RFRAS and demonstrate its significance. The robustness test indicates that it is antinoise for mislabeling.