Kernel Structure Research Articles

A novel intelligent fault diagnosis method of rotating machinery based on signal-to-image mapping and deep Gabor convolutional adaptive pooling network

To address the limitations of insufficient feature representation and easy to be overwhelmed by strong noise in the grayscale images of vibration signals, the random generation and single structure of convolutional kernels of the convolutional neural network leading to insufficient extracted features, and the max pooling and average pooling leading to model overfitting and suppression of critical fault features, this paper proposes a novel diagnosis method based on signal-to-image mapping and deep Gabor convolutional adaptive pooling network. Firstly, this paper designs a vibration signal-to-image mapping strategy to highlight the fault information of vibration signal. Then Gabor convolutional filter is proposed instead of convolutional kernels to guide the model to extract multi-scale and multi-directional fault features. Next, the dynamic adaptive pooling is designed to facilitate the retention of local features and suppress the decay of critical features. Finally, a deep Gabor convolutional adaptive pooling network model is constructed to improve the robustness of the fault feature extraction process and the generalization of the model. The results of the bearing and gear datasets indicate that the proposed method enhances the feature extraction ability, improves the robustness and generalization of the model, and realizes highly accurate fault diagnosis.

Research on Dynamic Characteristics of the RBBH System Based on Dynamics Model and Vibration Data Fusion.

The roll-bearing-bearing housing (RBBH) system is one of the most common kernel structures used to determine strip mill stability and product surface quality in modern metallurgical machinery. To better understand dynamic characteristics of the RBBH system, this paper provides a nonlinear dynamic model and designs an engineering test platform on the RBBH system in the whole rolling process. First, a nonlinear dynamic model of the RBBH system supported by four-row rolling bearings under high speed and heavy load is established. Then, the method of combining Riccati transfer matrix and Newmark-β numerical integration is employed to solve nonlinear dynamic equations. After that, the engineering test platform is designed and assembled to capture and analyze the vibration signals of weathering steel (SPA-H) with finished thicknesses of 1.6 and 3.2 mm. Finally, the dynamic characteristics of the RBBH system are studied with the method of the dynamic model and vibration data fusion. The results show that the SPA-H with a finished thickness of 1.6 mm is rolled, the RBBH system fluctuates violently in both horizontal and vertical directions, and numerical results are highly consistent with experimental results in acceleration response, velocity response, and displacement response. In addition, the dynamic performance parameters of the four-row rolling bearing will also fluctuate greatly. Finally, there is significant interest to gain the benefits for the RBBH system design and mill stable rolling purposes.

Trainable segmentation for transmission electron microscope images of inorganic nanoparticles.

We present a trainable segmentation method implemented within the python package ParticleSpy. The method takes user labelled pixels, which are used to train a classifier and segment images of inorganic nanoparticles from transmission electron microscope images. This implementation is based on the trainable Waikato Environment for Knowledge Analysis (WEKA) segmentation, but is written in python, allowing a large degree of flexibility and meaning it can be easily expanded using other python packages. We find that trainable segmentation offers better accuracy than global or local thresholding methods and requires as few as 100 user-labelled pixels to produce an accurate segmentation. Trainable segmentation presents a balance of accuracy and training time between global/local thresholding and neural networks, when used on transmission electron microscope images of nanoparticles. We also quantitatively investigate the effectiveness of the components of trainable segmentation, its filter kernels and classifiers, in order to demonstrate the use cases for the different filter kernels in ParticleSpy and the most accurate classifiers for different data types. A set of filter kernels is identified that are effective in distinguishing particles from background but that retain dissimilar features. In terms of classifiers, we find that different classifiers perform optimally for different image contrast; specifically, a random forest classifier performs best for high-contrast ADF images, but that QDA and Gaussian Naïve Bayes classifiers perform better for low-contrast TEM images.

Modeling of the microwave heating-toasting time-related variables and characterization of non-isothermal rheological properties of floury and sweet specialty maize kernels

The three primary floury and sweet maize types, with specialty kernels to make entire ready-to-eat maize, and packed in sealable paper envelopes, were the experimental units (150 g of raw kernels) to model the effect of the microwave heating-toasting (2450 MHz microwave oven, 492 W, times 0, 78, 156, 234, 312, and 390 s) on time-related variables and characterize the non-isothermal rheological properties. Pauses every 60 s for a rapid manual shaking compensated for non-uniformity of microwave volumetric heating. Surface color difference (ΔE*), internal porosity, milling average particle size, and flour hydration properties displayed curves adequately described by simple and nonlinear regression models. The milling particle size, hydration properties, and rheological parameters illustrated floury and sweet kernel differences ascribed to their proximal composition. Onset and peak temperatures depended on maize types and showed a little variation attributed to microwave heating-toasting times. The elastic/viscous modulus ratio increased in floury maize. It decreased in sweet maize, unveiling rheological differences associated with microwave heating-toasting time effect on the contrasting structure of floury and sweet specialty Andean maize kernels used for toasting.

The New Ag-S Cluster [Ag50S13(StBu)20][CF3COO]4 with a Unique hcp Ag14 Kernel and Ag36 Keplerian-Shell-Based Structural Architecture and Its Photoresponsivity.

In metal nanoclusters (NCs), the kernel geometry and the nature of the surface protecting ligands are very crucial for their structural stability and properties. The synthesis and structural elucidation of Ag NCs is challenging because the zerovalent oxidation state of Ag is very reactive and prone to oxidization. Here, we report the NC [Ag50S13(StBu)20][CF3COO]4 with a hexagonal close-packed (hcp) cagelike Ag14 kernel. A truncated cubic shell and an octahedral shell encapsulate the hcp-layered kernel via an interstitial S2- anionic shell to form an Ag36 Keplerian outer shell of the NC. A theoretical study indicates the stability of this NC in its 4+ charge state and the charge distribution between the kernel and Keplerian shell. The unprecedented electronic structure facilitates its application toward sustainable photoresponse properties. The new insights into this novel Ag NC kernel and Keplerian shell structure may pave the way to understanding the unique structure and developing electronic structure-based applications.

High-dimensional expensive multi-objective optimization via additive structure

• A high-dimensional expensive multi-objective optimization method is proposed. • A multi-point sampling strategy to recommend multiple candidate solutions is introduced. • Additive Gaussian Structure in expensive multi-objective optimization in highdimensional cases is addressed. Expensive multi-objective problems (MOPs) are extremely challenging due to the high evaluation cost to find satisfying solutions with adequate precision, especially in high-dimensional cases. However, most of the current EGO-based algorithms for expensive MOPs are limited to low decision dimensions because of the exponential difficulty in high dimensional circumstances. This paper presents High-Dimensional Expensive Multi-objective Optimization with Additive structure (ADD-HDEMO) to solve high-dimensional expensive MOPs via additive structural kernel and identifies two key challenges in this endeavor. First, we integrate multiple sub-objectives in high-dimensional expensive MOPs into a single objective with the decision space unchanged. Then, we infer the dependence correlation between the decision and objective space of the augmented EMOP via an additive GP kernel structure where Gibbs sampling is used to learn the latent additive structure. Furthermore, we parallel the proposed algorithm by introducing a multi-point sampling mechanism when recommending infill points. The effectiveness of the proposed method is evaluated on ZDT and DTLZ benchmarks compared with three other EGO-based multi-objective optimization approaches, ParEGO, SMS-EGO and MOEA/D-EGO. Our analyses demonstrate that ADD-HDEMO is effective in solving high-dimensional expensive MOPs.

Efficient convolutional networks learning through irregular convolutional kernels

As deep neural networks are increasingly used in applications suited for low-power devices, a fundamental dilemma emerges: the trend is to develop models to use the increasing amount of data, resulting in memory-intensive models; however, low-power devices have very limited memory and cannot store large models. Parameters pruning is critical for deep model deployment on low-power devices. Existing efforts mainly focus on designing highly efficient structures or pruning redundant connections in networks. They are typically sensitive to the tasks or rely on dedicated and expensive hashing storage strategies. In this work, we introduce a novel approach to achieve a lightweight model from the perspective of reconstructing the structure of convolution kernels for efficient storage. Our approach transforms a traditional square convolution kernel into line segments, and automatically learns a proper strategy for equipping these line segments to model diverse features. Experimental results show that our approach can significantly reduce the number of parameters (pruned 69% on DenseNet-40) and calculation costs (pruned 59% on DenseNet-40) while maintaining acceptable performance (only lose less than 2% accuracy).

Bayesian spatiotemporal modeling on complex-valued fMRI signals via kernel convolutions.

We propose a model-based approach that combines Bayesian variable selection tools, a novel spatial kernel convolution structure, and autoregressive processes for detecting a subject's brain activation at the voxel level in complex-valued functional magnetic resonance imaging (CV-fMRI) data. A computationally efficient Markov chain Monte Carlo algorithm for posterior inference is developed by taking advantage of the dimension reduction of the kernel-based structure. The proposed spatiotemporal model leads to more accurate posterior probability activation maps and less false positives than alternative spatial approaches based on Gaussian process models, and other complex-valued models that do not incorporate spatial and/or temporal structure. This is illustrated in the analysis of simulated data and human task-related CV-fMRI data. In addition, we show that complex-valued approaches dominate magnitude-only approaches and that the kernel structure in our proposed model considerably improves sensitivity rates when detecting activation at the voxellevel.

An evaluation of selected engineering properties of polish durum wheat grain

The physical properties of durum wheat grain have to be evaluated due to the growing diversity of durum wheat cultivars in the food processing industry and increasing qualitative requirements. The size, texture and mechanical properties of wheat grain play an important role in grain processing. In the present study, the morphological and mechanical properties of grain and the correlations between these traits were investigated in seven Polish genotypes of durum wheat. The kernels of the studied cultivars were relatively similar in shape, and their dimensions and weight approximated the average for durum wheat, which indicates that this wheat species can be processed in standard production lines. Hardness index (HI) values (81–89) were relatively similar, whereas grain vitreousness differed across the tested genotypes. The highest HI values were noted in kernels with a thickness of 2.90–2.95 mm. Kernel structure was damaged within a deformation range of around 18–21%. Rupture force, rupture energy and HI values increased with a rise in grain vitreousness. Rupture force was lowest in kernels with vitreousness of 70–75%.

Effect of drying on the physical and chemical properties of palm kernel oil.

Palm kernel is the edible seed of the oil palm fruit obtained during the palm oil milling process. For efficient processing and storage, the moisture content of palm kernel must be reduced to an optimal level by drying. This study aimed to see how drying influenced the physical structure and physicochemical properties of palm kernel and oil. Before and after drying, the free fatty acid (FFA), color, fatty acid composition, Fourier transform infrared, thermal properties and structure of palm kernel were investigated. Results show that drying significantly (P < 0.05) reduced FFA and color of palm kernel oil. Drying also significantly affected (P < 0.05) composition of some fatty acids in palm kernel oil such as capric acid, lauric acid, myristic acid, palmitic acid and oleic acid. However, drying did not affect palm kernel and palm kernel oil functional groups and thermal properties. After drying, structural damage of palm kernel was observed. Based on these findings, the quality of kernel oil may be maintained after drying, and it can even be improved based on lower FFA content. © 2022 Society of Chemical Industry.

Operator-valued positive definite kernels and differentiable universality

We present a characterization for a positive definite operator-valued kernel to be universal or [Formula: see text]-universal, and apply these characterizations to a family of operator-valued kernels that are shown to be well behaved. Later, we obtain a characterization for an operator-valued differentiable kernel to be [Formula: see text]-universal and [Formula: see text]-universal. In order to obtain such characterization and examples, we generalize some well-known results concerning the structure of differentiable kernels to the operator-valued context. On the examples is given an emphasis on the radial kernels on Euclidean spaces.

Colon tissue image segmentation with MWSI-NET.

Developments in deep learning have resulted in computer-aided diagnosis for many types of cancer. Previously, pathologists manually performed the labeling work in the analysis of colon tissues, which is both time-consuming and labor-intensive. Results are easily affected by subjective conditions. Therefore, it is beneficial to identify the cancerous regions of colon cancer with the assistance of computer-aided technology. Pathological images are often difficult to process due to their irregularity, similarity between cancerous and non-cancerous tissues and large size. We propose a multi-scale perceptual field fusion structure based on a dilated convolutional network. Using this model, a structure of dilated convolution kernels with different aspect ratios is inserted, which can process cancerous regions of different sizes and generate larger receptive fields. Thus, the model can fuse detailed information at different scales for better semantic segmentation. Two different attention mechanisms are adopted to highlight the cancerous areas. A large, open-source dataset was used to verify improved efficacy when compared to previously disclosed methods.

Non-equilibrium plasma generation via nano-second multi-mode laser pulses

The formation and growth of plasma kernels generated via nano-second mode-beating laser pulses is investigated here via a non-equilibrium self-consistent computational model. Chemically reactive Navier–Stokes equations are used to describe the hydrodynamics, and non-equilibrium effects are taken into account with a two-temperature model. Inverse Bremsstrahlung and multiphoton ionization are included self-consistently in the model via a coupled solution of the plasma governing equations and the radiative transfer equation (that describes the laser beam propagation and attenuation). A self-consistent approach (despite carrying additional challenges) minimizes the empiricism and it allows for a more accurate description since it prevents both the utilization of artificial plasma seeds to trigger the breakdown and the implementation of tuning parameters to simulate the laser-energy deposition. The advantages of this approach are confirmed by the good agreement between the numerically predicted and the experimentally measured plasma boundary evolution and absorbed energy. This also holds true for the periodic plasma kernel structures that, as suggested by the experiments and confirmed by the simulations presented here, are connected to the modulating frequency.

Sensor-based human activity recognition using fuzzified deep CNN architecture with λmax method

PurposeThis work aims to develop a novel fuzzy associator rule-based fuzzified deep convolutional neural network (FDCNN) architecture for the classification of smartphone sensor-based human activity recognition. This work mainly focuses on fusing the λmax method for weight initialization, as a data normalization technique, to achieve high accuracy of classification.Design/methodology/approachThe major contributions of this work are modeled as FDCNN architecture, which is initially fused with a fuzzy logic based data aggregator. This work significantly focuses on normalizing the University of California, Irvine data set’s statistical parameters before feeding that to convolutional neural network layers. This FDCNN model with λmax method is instrumental in ensuring the faster convergence with improved performance accuracy in sensor based human activity recognition. Impact analysis is carried out to validate the appropriateness of the results with hyper-parameter tuning on the proposed FDCNN model with λmax method.FindingsThe effectiveness of the proposed FDCNN model with λmax method was outperformed than state-of-the-art models and attained with overall accuracy of 97.89% with overall F1 score as 0.9795.Practical implicationsThe proposed fuzzy associate rule layer (FAL) layer is responsible for feature association based on fuzzy rules and regulates the uncertainty in the sensor data because of signal inferences and noises. Also, the normalized data is subjectively grouped based on the FAL kernel structure weights assigned with the λmax method.Social implicationsContributed a novel FDCNN architecture that can support those who are keen in advancing human activity recognition (HAR) recognition.Originality/valueA novel FDCNN architecture is implemented with appropriate FAL kernel structures.

Svojstva zrna hibrida kukuruza za primenu u mokrom mlevenju

A grain of eight selected hybrids from the Maize Research Institute Zemun Polje was used as the subject of this study. The kernel structure, physical properties and chemical composition of the grain and starch (amylose content) were analyzed before the laboratory wet milling process for starch extraction. The in vitro enzymatic digestibility of the isolated starch was also determined. The wet milling properties were later correlated to the physicochemical characteristics of the grain. The results showed that hybrid ZP 677 had the highest starch yield, followed by hybrid ZP 704wx, while the highest starch recovery was observed for hybrid ZP 341. The highest bran yield (10.52%) was obtained by hybrid ZP 434, and the highest germ yield (8.86%) by hybrid ZP 172/8. The correlation analysis showed that starch yield was positively correlated to 1000-kernel weight and crude fiber content, while oil content negatively influenced starch extraction and yield. The starch digestibility was negatively correlated to the amylose content. These findings can be useful for the starch processing industry as well as in the production of ethanol and alcoholic drinks.

Structure Parameter Optimized Kernel Based Online Prediction With a Generalized Optimization Strategy for Nonstationary Time Series

In this paper, sparsification techniques aided online prediction algorithms in a reproducing kernel Hilbert space are studied for nonstationary time series. The online prediction algorithms as usual consist of the selection of kernel structure parameters and the kernel weight vector updating. For structure parameters, the kernel dictionary is selected by some sparsification techniques with online selective modeling criteria, and moreover the kernel covariance matrix is intermittently optimized in the light of the covariance matrix adaptation evolution strategy (CMA-ES). Optimizing the real symmetric covariance matrix can not only improve the kernel structure's flexibility by the cross relatedness of the input variables, but also partly alleviate the prediction uncertainty caused by the kernel dictionary selection for nonstationary time series. In order to sufficiently capture the underlying dynamic characteristics in prediction-error time series, a generalized optimization strategy is designed to construct the kernel dictionary sequentially in multiple kernel connection modes. The generalized optimization strategy provides a more self-contained way to construct the entire kernel connections, which enhances the ability to adaptively track the changing dynamic characteristics. Numerical simulations have demonstrated that the proposed approach has superior prediction performance for nonstationary time series.

Spectral–Spatial Transformer Network for Hyperspectral Image Classification: A Factorized Architecture Search Framework

Neural networks have dominated the research of hyperspectral image classification, attributing to the feature learning capacity of convolution operations. However, the fixed geometric structure of convolution kernels hinders long-range interaction between features from distant locations. In this article, we propose a novel spectral–spatial transformer network (SSTN), which consists of spatial attention and spectral association modules, to overcome the constraints of convolution kernels. Also, we design a factorized architecture search (FAS) framework that involves two independent subprocedures to determine the layer-level operation choices and block-level orders of SSTN. Unlike conventional neural architecture search (NAS) that requires a bilevel optimization of both network parameters and architecture settings, the FAS focuses only on finding out optimal architecture settings to enable a stable and fast architecture search. Extensive experiments conducted on five popular HSI benchmarks demonstrate the versatility of SSTNs over other state-of-the-art (SOTA) methods and justify the FAS strategy. On the University of Houston dataset, SSTN obtains comparable overall accuracy to SOTA methods with a small fraction (1.2%) of multiply-and-accumulate operations compared to a strong baseline spectral–spatial residual network (SSRN). Most importantly, SSTNs outperform other SOTA networks using only 1.2% or fewer MACs of SSRNs on the Indian Pines, the Kennedy Space Center, the University of Pavia, and the Pavia Center datasets.

DRN-SEAM: A deep residual network based on squeeze-and-excitation attention mechanism for motion recognition in education

In order to solve the shortcomings of the traditional motion recognition methods and obtain better motion recognition effect in education, this paper proposes a residual network based on Squeeze-and-Excitation attention mechanism. Deep residual network is widely used in various fields due to the high recognition accuracy. In this paper, the convolution layer, adjustment batch normalization layer and activation function layer in the deep residual network model are modified. Squeeze-and-Excitation (SE) attention mechanism is introduced to adjust the structure of network convolution kernel. This operation enhances the feature extraction ability of the new network model. Finally, the expansibility experiments are conducted on WISDM(Wireless Sensor Data Mining), and UCI(UC Irvine) data sets. In terms of F1, the value exceeds 90%. The results show that the proposed model is more accurate than other state-of-the-art posture recognition models. The proposed method can obtain the ideal motion recognition results.

CANet: Centerness-Aware Network for Object Detection in Remote Sensing Images

Recently, feature pyramid has been widely exploited in remote sensing detectors, which greatly alleviates the problem arising from scale variation across objects in remote sensing images. However, these object detectors with feature pyramid give insufficient consideration that objects in remote sensing images usually maintain symmetrical shape. To address this issue, we propose an anchor-free-based detector called Centerness-Aware Network (CANet), which could capture the symmetrical shape of objects in remote sensing images. The kernel structure of CANet is a new Centerness-Aware Model (CAM) that contains three components: Multiscale Centerness Descriptor (MSCD), Centerness Detection Head (CDH), and Feature Selective Module (FSM). Considering that symmetrical objects will maintain a rigid appearance around their center region, three components are integrated into the feature pyramid to extract and utilize the features around the center region. More precisely, the MSCD is embedded into the feature pyramid and highlights the center of current objects through the attention mechanism. Guided by the MSCD, the CDH could accurately capture the center of objects by per-pixel prediction. Furthermore, the FSM is connected to the CDH, which guides the CDH to adaptively select the optimal feature level from the pyramidal features. The selected feature level could describe the best semantic information around the center region, which helps the network progressively fit the symmetrical shape of remote sensing objects. Besides, we also design the hybrid loss function to effectively train CAM in the end-to-end way. The experiments show that our network is competitive with some state-of-the-art detection networks.

Damage boundary of piezoresistive pressure sensor under shock environment

The piezoresistive pressure sensor is a widely used electronic component whose accuracy and function are strongly affected by the external mechanical environment. This paper studies the failure mode and damage boundary of piezoresistive pressure sensors under shock load. The failure mode of the pressure-sensitive elastic plate (the kernel structure of the pressure sensor) is derived based on the thin-plate theory. The damage boundary of the piezoresistive pressure sensor is obtained by analyzing the experiment and numerical simulation results, which agree well with the theoretical analysis. Results prove that the damage boundary of the piezoresistive pressure sensor is governed by the pseudo-velocity shock response spectrum (PVSRS) of the shock environment, which is about 7 m/s for the specimen in this paper. This study can provide guidelines for the adaptability design of electronic components.