Information Features Research Articles

TF-REF-RNN: Time-Frequency and Reference Signal Feature Fusion Recurrent Neural Network for Underwater Backscatter Signal Separation

Underwater wireless sensor networks play an important role in exploring the oceans as part of an integrated space–air–ground–ocean network. Because underwater energy is limited, the equipment’s efficiency is significantly impacted by the battery duration. Underwater backscatter technology does not require batteries and has significant potential in positioning, navigation, communication, and sensing due to its passive characteristics. However, underwater backscatter signals are susceptible to being swamped by the excitation signal. Additionally, the signals from different reflection signals share the same frequency and overlap, and contain fewer useful features, leading to significant challenges in detection. In order to solve the above problems, this paper proposes a recurrent neural network that introduces time-frequency and reference signal features for underwater backscatter signal separation (TF-REF-RNN). In the feature extraction part, we design an encoder that introduces time-frequency domain features to learn more about the frequency details. Additionally, to improve performance, we designed a separator that incorporates the reference signal’s pure global information features. The proposed TF-REF-RNN network model achieves metrics of 28.55 dB SI-SNRi and 19.51 dB SDRi in the dataset that includes shipsEar noise data and underwater simulated backscatter signals, outperforming similar classical methods.

A dual branch network combining detail information and color feature for remote sensing image dehazing

A dual branch network combining detail information and color feature for remote sensing image dehazing

Multi-Domain Joint Synthetic Aperture Radar Ship Detection Method Integrating Complex Information with Deep Learning

With the flourishing development of deep learning, synthetic aperture radar (SAR) ship detection based on this method has been widely applied across various domains. However, most deep-learning-based detection methods currently only use the amplitude information from SAR images. In fact, phase information and time-frequency features can also play a role in ship detection. Additionally, the background noise and the small size of ships also pose challenges to detection. Finally, satellite-based detection requires the model to be lightweight and capable of real-time processing. To address these difficulties, we propose a multi-domain joint SAR ship detection method that integrates complex information with deep learning. Based on the imaging mechanism of line-by-line scanning, we can first confirm the presence of ships within echo returns in the eigen-subspace domain, which can reduce detection time. Benefiting from the complex information of single-look complex (SLC) SAR images, we transform the echo returns containing ships into the time-frequency domain. In the time-frequency domain, ships exhibit distinctive features that are different from noise, without the limitation of size, which is highly advantageous for detection. Therefore, we constructed a time-frequency SAR image dataset (TFSID) using the images in the time-frequency domain, and utilizing the advantages of this dataset, we combined space-to-depth convolution (SPDConv) and Inception depthwise convolution (InceptionDWConv) to propose Efficient SPD-InceptionDWConv (ESIDConv). Using this module as the core, we proposed a lightweight SAR ship detector (LSDet) based on YOLOv5n. The detector achieves a detection accuracy of 99.5 with only 0.3 M parameters and 1.2 G operations on the dataset. Extensive experiments on different datasets demonstrated the superiority and effectiveness of our proposed method.

Paramps: Convolutional neural networks based on tensor decomposition for heart sound signal analysis and cardiovascular disease diagnosis

Currently, convolutional neural networks have demonstrated outstanding efficiency in heart sound detection and automatic diagnosis of cardiovascular diseases. However, due to the non-stationary nature and complex data patterns caused by environmental noise and stethoscope differences, traditional neural networks are limited in extracting discriminative features. This article proposes a convolutional neural network based on tensor decomposition to address this issue. This model uses a convolutional neural network with four parallel structures to extract audio features of heart sound signals and introduces a tensor network to use tensor decomposition to perform low-rank approximation on the convolutional kernel, compress model parameters, reduce redundancy, and improve performance. When processing feature data, the model divides large areas of features into locally unordered small areas to achieve feature compression and reorganization, ensuring that crucial information is preserved while compressing parameters. The model can accurately capture spatial structural information and critical features by refining the matrix product state layer. Experiments were conducted on the 2016 PhysioNet/CinC Challenge and the Yaseen heart sound public dataset, the experimental results show that the proposed method has an accuracy of 96.4% and 99.2% on two datasets, specificity of 99.1% and 99.8%, demonstrating its excellent generalization ability and diagnostic accuracy.

ScMGATGRN: a multiview graph attention network-based method for inferring gene regulatory networks from single-cell transcriptomic data.

The gene regulatory network (GRN) plays a vital role in understanding the structure and dynamics of cellular systems, revealing complex regulatory relationships, and exploring disease mechanisms. Recently, deep learning (DL)-based methods have been proposed to infer GRNs from single-cell transcriptomic data and achieved impressive performance. However, these methods do not fully utilize graph topological information and high-order neighbor information from multiple receptive fields. To overcome those limitations, we propose a novel model based on multiview graph attention network, namely, scMGATGRN, to infer GRNs. scMGATGRN mainly consists of GAT, multiview, and view-level attention mechanism. GAT can extract essential features of the gene regulatory network. The multiview model can simultaneously utilize local feature information and high-order neighbor feature information of nodes in the gene regulatory network. The view-level attention mechanism dynamically adjusts the relative importance of node embedding representations and efficiently aggregates node embedding representations from two views. To verify the effectiveness of scMGATGRN, we compared its performance with 10 methods (five shallow learning algorithms and five state-of-the-art DL-based methods) on seven benchmark single-cell RNA sequencing (scRNA-seq) datasets from five cell lines (two in human and three in mouse) with four different kinds of ground-truth networks. The experimental results not only show that scMGATGRN outperforms competing methods but also demonstrate the potential of this model in inferring GRNs. The code and data of scMGATGRN are made freely available on GitHub (https://github.com/nathanyl/scMGATGRN).

A two-task predictor for discovering phase separation proteins and their undergoing mechanism.

Liquid-liquid phase separation (LLPS) is one of the mechanisms mediating the compartmentalization of macromolecules (proteins and nucleic acids) in cells, forming biomolecular condensates or membraneless organelles. Consequently, the systematic identification of potential LLPS proteins is crucial for understanding the phase separation process and its biological mechanisms. A two-task predictor, Opt_PredLLPS, was developed to discover potential phase separation proteins and further evaluate their mechanism. The first task model of Opt_PredLLPS combines a convolutional neural network (CNN) and bidirectional long short-term memory (BiLSTM) through a fully connected layer, where the CNN utilizes evolutionary information features as input, and BiLSTM utilizes multimodal features as input. If a protein is predicted to be an LLPS protein, it is input into the second task model to predict whether this protein needs to interact with its partners to undergo LLPS. The second task model employs the XGBoost classification algorithm and 37 physicochemical properties following a three-step feature selection. The effectiveness of the model was validated on multiple benchmark datasets, and in silico saturation mutagenesis was used to identify regions that play a key role in phase separation. These findings may assist future research on the LLPS mechanism and the discovery of potential phase separation proteins.

Progressively global–local fusion with explicit guidance for accurate and robust 3d hand pose reconstruction

Parametric and non-parametric methods are two commonly used strategies in current 3D hand pose reconstruction. Parametric methods predict low-dimensional parameters to fit a predefined hand model to the input image. Benefiting from the prior knowledge of hand models, parametric methods guarantee plausible hand poses, whereas the pose estimation accuracy is limited due to nonlinear regression and spatial information loss. Differently, non-parametric methods directly estimate the coordinates of keypoints or mesh vertices from the input image. The reconstructed 3D hand poses show high precision but may be less robust. In this paper, we integrate the advantages of two methods for accurate and robust hand pose reconstruction. Specifically, we disentangle the hand pose reconstruction into global modeling and local refinement, which is performed in a coarse-to-fine manner. Firstly, we utilize global features from the encoder to generate the initial estimation by a parametric method, which aims to provide the prior knowledge of the human hand for subsequent processes. Then, we gradually fuse multi-scale contextual features for local refinement by explicitly integrating global prior information and local visual features. In particular, we introduce a consecutive pixel-aligned feature retrieval module to extract fine-grained information from visual features, thereby achieving pixel-level alignment. Furthermore, we demonstrate that our method can be extended to weakly-supervised learning where only sparse pose annotations are needed, potentially alleviating the burden of meticulous mesh annotation. The effectiveness and robustness of our method are substantiated through both fully- and weakly-supervised experiments, demonstrating superior performance compared to state-of-the-art methods. We plan to release our code at https://github.com/Kun-Gao/P_GLFnet.

Self-Supervised Learning across the Spectrum

Satellite image time series (SITS) segmentation is crucial for many applications, like environmental monitoring, land cover mapping, and agricultural crop type classification. However, training models for SITS segmentation remains a challenging task due to the lack of abundant training data, which requires fine-grained annotation. We propose S4, a new self-supervised pretraining approach that significantly reduces the requirement for labeled training data by utilizing two key insights of satellite imagery: (a) Satellites capture images in different parts of the spectrum, such as radio frequencies and visible frequencies. (b) Satellite imagery is geo-registered, allowing for fine-grained spatial alignment. We use these insights to formulate pretraining tasks in S4. To the best of our knowledge, S4 is the first multimodal and temporal approach for SITS segmentation. S4’s novelty stems from leveraging multiple properties required for SITS self-supervision: (1) multiple modalities, (2) temporal information, and (3) pixel-level feature extraction. We also curate m2s2-SITS, a large-scale dataset of unlabeled, spatially aligned, multimodal, and geographic-specific SITS that serves as representative pretraining data for S4. Finally, we evaluate S4 on multiple SITS segmentation datasets and demonstrate its efficacy against competing baselines while using limited labeled data. Through a series of extensive comparisons and ablation studies, we demonstrate S4’s ability as an effective feature extractor for downstream semantic segmentation.

Efficient and accurate semi-supervised semantic segmentation for industrial surface defects

Deep learning-based defect detection methods have gained widespread application in industrial quality inspection. However, limitations such as insufficient sample sizes, low data utilization, and issues with accuracy and speed persist. This paper proposes a semi-supervised semantic segmentation framework that addresses these challenges through perturbation invariance at both the image and feature space. The framework employs diverse perturbation cross-pseudo-supervision to reduce dependency on extensive labeled datasets. Our lightweight method incorporates edge pixel-level semantic information and shallow feature fusion to enhance real-time performance and improve the accuracy of defect edge detection and small target segmentation in industrial inspection. Experimental results demonstrate that the proposed method outperforms the current state-of-the-art (SOTA) semi-supervised semantic segmentation methods across various industrial scenarios. Specifically, our method achieves a mean Intersection over Union (mIoU) 3.11% higher than the SOTA method on our dataset and 4.39% higher on the public KolektorSDD dataset. Additionally, our semantic segmentation network matches the speed of the fastest network, U-net, while achieving a mIoU 2.99% higher than DeepLabv3Plus.

The Use of Design Thinking Methods in the Development of Telkomedika Mobile Applications for Patients with Conscientiousness Personality Types

This research aims to improve the quality of Telkomedika Telkom University Clinic services by developing a mobile application that is tailored to the personality type of patients with conscientiousness. This Mobile Application is designed to fulfill the patient's need for service information through the service information feature and streamline the queuing process through the online reservation feature. Through the use of the DISC personality type approach, this study focuses on the preferences and characteristics of patients to increase satisfaction. Users or patients with this conscientious personality type tend to be meticulous, systematic, and structured. Therefore, a structured interface design and also an easy-to-understand task flow will help users in using the application efficiently. The results of the study show the importance of understanding user preferences in designing applications. Usability Testing on the Telmed 2.0 application prototype resulted in a Single Ease Question (SEQ) score of 6.88, indicating ease of use. In addition, User Acceptance Testing showed that all features worked well, with a score of 91.5 on the System Usability Scale (SUS), indicating an excellent level of ease of use of the application.

Clinical diagnostic model for predicting indolent or aggressive lymphoma based on clinical information and ultrasound features of superficial lymph nodes

PurposeThe aim of this study was to develop a diagnostic model for predicting indolent lymphoma or aggressive lymphoma using clinical information and ultrasound characteristics of superficial lymph nodes. MethodPatients with confirmed pathological lymphoma subtypes who had undergone ultrasound and contrast-enhanced ultrasound examinations were enrolled. Clinical and ultrasound imaging features were retrospectively analysed and compared to the pathological results, which were considered the gold standard for diagnosis. Two diagnostic models were developed: a clinical model (Model-C) using clinical data only, and a combined model (Model-US) integrating ultrasound features into the clinical model. The efficacy of these models in differentiating between indolent and aggressive lymphoma was compared. ResultsIn total, 236 consecutive patients were enrolled, including 78 patients with indolent lymphomas and 158 patients with aggressive lymphomas. Receiver operating characteristic (ROC) curve analysis revealed that the areas under the curves of Model-C and Model-US were 0.78 (95 % confidence interval: 0.72–0.84) and 0.87 (95 % confidence interval: 0.82–0.92), respectively (p < 0.001). Model-US was further evaluated for calibration and is presented as a nomogram. ConclusionsThe diagnostic model incorporated clinical and ultrasound characteristics and offered a noninvasive method for assessing lymphoma with good discrimination and calibration.

Method for enhanced gesture recognition under low light conditions based on wearable mechanoluminescence sensors

Gestures, as one of the key modes of human–computer interaction, are currently identified and processed mainly through two methods: machine vision imaging and wearable stress/strain sensing.However, the former has high requirements for lighting and background.This paper innovatively proposes a feature fusion algorithm that combines mechanoluminescent sensors for gesture recognition under low-light conditions. Unlike existing methods, this algorithm creates a system that integrates mechanoluminescent sensors for visual gesture recognition. By triggering the sensor’s luminescence through mechanical stress, it provides additional light source information to enhance image quality in low-light environments.For this purpose, this study employed the fluorescent emission properties of ZnS:Cu to fabricate a mechanoluminescence sensor. Its mechanoluminescence response characteristics were measured. Based on these findings, an algorithm for the fusion of gesture information features was developed for low illumination backgrounds. This algorithm decomposes the gesture visual images through YCbCr, extracting the HOG features of the Cr channel (Cr-HOG). Simultaneously, feature fusion is performed using the pooling layer (VGG16-Conv5-pool) following the convolutional layer (Conv5-3) in the VGG16 model. A one-to-one composite SVM classifier is constructed to complete the training and testing of the gesture recognition model. Ultimately, the feasibility of this enhanced gesture recognition method was validated through unmanned vehicle control experiment. Experimental results demonstrated that in environments with an illuminance level below 10 LUX measured by a light meter, the average recognition rate of the wearable mechanoluminescence sensor feature fusion algorithm reached 95.82 %. This is 32.24 % higher than the recognition rate of the single Cr-HOG feature classification and 28.27 % higher than the single VGG16-Conv5-pool feature classification. Compared with feature extraction using ResNet-50 and DenseNet-121 networks, the recognition rate for classifying gestures under low-light conditions is approximately 30 % higher.Compared with other image enhancement recognition methods, the recognition can be increased by up to 30.88 %.

An efficient detector for detecting surface defects on cold-rolled steel strips

Surface-defect inspection is vital in cold-rolled steel-strip manufacturing, given the complexities of production environments and the high speeds involved. Further, the defects on cold-rolled steel strips are often characterized by their small size, diversity of types, and similarities among different types, posing significant challenges in balancing detection accuracy and efficiency. To address the challenges, we designed a detector based on You Only Look Once version 5 (YOLOv5) to achieve precise detection of surface defects on cold-rolled steel strips. First, a dataset containing seven types of defects was curated, named the Cold-Rolled Steel Defect Dataset (CR7-DET). Next, a feature-extraction network based on residual-like connections within a single residual block (Res2net) was developed to enhance the model’s feature-extraction capability, alongside introducing a multi-head attention module to focus on key information features. To reduce the information loss during feature fusion, we established an adaptive feature-fusion Path Aggregation Network (aff-PAN), which was optimized by designing a lightweight adaptive down-sampling module (LAD) to increase the sensory-field implementation of feature fusion. The ghost convolution effectively reduced the number of parameters and increased the speed without affecting the model’s performance. Finally, experiments were conducted on our CR7-DET and a public dataset (GC10-DET). With a reduced parameter count of 6.85 million, our model achieved a mean average precision(mAP) of 87.6% on CR7-DET and 79.7% on GC10-DET. The experimental results demonstrated that our model achieved a balance between detection accuracy and inference efficiency. The model has the potential to reduce scrap rates caused by defects and improve the overall surface quality of cold-rolled steel strips.

Histologic Features of Liver Injury Associated With SARS-CoV-2 Messenger RNA Vaccines.

Many drugs can induce liver injury; however, vaccine-induced liver injury is a rare phenomenon. SARS-CoV-2 messenger RNA (mRNA) vaccines are now widely administered, and clinical evidence of liver injury has been reported. To characterize the histologic features of SARS-CoV-2 mRNA vaccine-associated liver injury. Thirteen liver biopsies from 12 patients with elevated liver enzymes clinically favored to be secondary to SARS-CoV-2 mRNA vaccine were identified between 2021 and 2022. Demographics, clinical information, and histologic features of liver biopsies were reviewed. All patients (median age, 58 years; M:F = 4:8) received at least 1 dose of SARS-CoV-2 mRNA vaccines (7 Pfizer and 5 Moderna). Four patients had a history of liver disease. Nine patients developed symptoms between 1 day and 2 months after receiving the vaccine dose. Viral serologies were negative. Drug-induced liver injury was thought to be less likely clinically in the 3 patients who had started new medications. Autoimmune antibodies were detected in 9 patients. Moderate to severe active hepatitis was the dominant histologic pattern of injury (9 of 13 biopsies; 69%). Resolving hepatitis, cholestatic hepatitic injury, and bile duct injury were identified in 1 biopsy each. All patients recovered spontaneously or with steroid therapy except one patient who developed autoimmune hepatitis. Moderate to severe active hepatitis is commonly observed in SARS-CoV-2 mRNA vaccine-associated liver injury, and female patients may be more susceptible to injury. Liver injury resolves spontaneously or with steroid treatment. In rare cases, these vaccines may trigger an underlying immune condition.

Integration of multiscale fusion of residual neural network with 2-D gramian angular fields for lower limb movement recognition based on multi-channel sEMG signals

The human lower limb movements recognition (LLMR) plays a pivotal role in active lower limb exoskeleton robots. Employing surface electromyography (sEMG) signals for LLMR allows for the convenient, rapid and stable capture of signal variations, facilitating efficient identification of lower limb motion patterns. However, current sEMG-based LLMR methods face challenges such as incomplete feature extraction, limited contextual information and restricted feature extraction scales during feature extraction. This paper proposed a LLMR method based on Gramian Angular Fields (GAF) and multiscale fusion of Residual Neural Network (MS-ResNet). The denoised sEMG time series was transformed into Gramian Angular Difference Field (GADF) matrix based on GAF. The MS-ResNet model, incorporating ResNet and multiscale feature fusion concepts, was proposed to comprehensively capture global and local information through different-scale feature extraction and fusion, so as to improve recognition performance. sEMG signals from 11 muscles of the preferred leg of 15 healthy subjects were recorded during six common lower limb movements. Experimental analysis investigated the impact of the convolutional kernel size (k × k) in Stream 2 of MS-ResNet and the number of muscles involved on recognition performance. The study revealed that selecting k as 13, coupled with 11 muscles, yielded optimal model performance with the average cross-individual recognition accuracy reaching 97.62 %, demonstrating the model’s efficiency in LLMR. This method could provide a viable solution for developing more efficient and reliable LLMR systems, applicable to lower limb exoskeleton robots and intelligent prosthetics.

Image super-resolution reconstruction of vast-receptive-field pixel attention for precision measurement

Abstract Compared with traditional contact precision measurement, vision-based non-contact precision measurement has the features of low cost and flexible multi-point information extraction, but how to ensure the measurement accuracy of vision-based non-contact precision measurement is an urgent problem. Traditional thinking often focuses on hardware upgrades to improve image resolution, but this brings high costs and is limited by the physical characteristics of the hardware itself. In this paper, we start from the software aspect to improve the image resolution by using the super-resolution reconstruction algorithm and propose an image super-resolution reconstruction algorithm—Swin Transformer with a Vast-receptive-field Pixel Attention, which combines the vast-receptive-field pixel attention mechanism with the Swin Transformer self-attention mechanism, focuses on the learning of the high-frequency information features of the image. Experiments are conducted both in public datasets and real measurement images. Extensive experimental validation shows that the model can obtain more edge and high-frequency detail features in public datasets, and the objective evaluation index on Set5, Set14, B100, Urban100, and Manga109 datasets is improved by 0.06 dB on average compared with the existing algorithms. In actual measurements, the algorithm in this paper for USAF1951 resolution tablet, image super-resolution reconstruction image in the horizontal and vertical direction of the measurement accuracy increased by an average of 6.97%, the horizontal and vertical direction of the relative measurement accuracy of an average of 30.20% improvement. This study provides a potential development direction for vision-based non-contact precision measurement.

Side-Scan Sonar Image Augmentation Method Based on CC-WGAN

The utilization of deep learning algorithms for side-scan sonar target detection is impeded by the restricted quantity and representativeness of side-scan sonar (SSS) samples. To address this issue, this paper proposes a method for image augmentation using a CC-WGAN network. First, the generator incorporates the Convolutional Block Attention Module (CBAM) to enhance the assimilation of global information and local features in the input images. This integration also improves stability and avoids mode collapse problems associated with the original Generative Adversarial Network. Subsequently, the CBAM is incorporated into the discriminator to facilitate a better understanding of the relevance and significance of input data, thereby enhancing the model’s generalization ability. Finally, based on this model, existing few-sample SSS images are augmented, and we utilize the augmented images for discrimination and detection with YOLOv5. The experimental results show that following training with the SSS dataset that is augmented by this network, the accuracy of target detection increased by 7.6%, validating the feasibility of our proposed method. This method presents a novel solution to the problem of low model accuracy in underwater target detection with side-scan sonar due to limited samples.

Phasor-Based Myoelectric Synergy Features: A Fast Hand-Crafted Feature Extraction Scheme for Boosting Performance in Gait Phase Recognition.

Gait phase recognition systems based on surface electromyographic signals (EMGs) are crucial for developing advanced myoelectric control schemes that enhance the interaction between humans and lower limb assistive devices. However, machine learning models used in this context, such as Linear Discriminant Analysis (LDA) and Support Vector Machine (SVM), typically experience performance degradation when modeling the gait cycle with more than just stance and swing phases. This study introduces a generalized phasor-based feature extraction approach (PHASOR) that captures spatial myoelectric features to improve the performance of LDA and SVM in gait phase recognition. A publicly available dataset of 40 subjects was used to evaluate PHASOR against state-of-the-art feature sets in a five-phase gait recognition problem. Additionally, fully data-driven deep learning architectures, such as Rocket and Mini-Rocket, were included for comparison. The separability index (SI) and mean semi-principal axis (MSA) analyses showed mean SI and MSA metrics of 7.7 and 0.5, respectively, indicating the proposed approach's ability to effectively decode gait phases through EMG activity. The SVM classifier demonstrated the highest accuracy of 82% using a five-fold leave-one-trial-out testing approach, outperforming Rocket and Mini-Rocket. This study confirms that in gait phase recognition based on EMG signals, novel and efficient muscle synergy information feature extraction schemes, such as PHASOR, can compete with deep learning approaches that require greater processing time for feature extraction and classification.

The distribution of biomarkers for Behcet syndrome and their clinical relevance in real-world studies

Objective: To explore the distribution of different biomarkers for Behcet's syndrome (BS) and their correlation with distinct clinical phenotypes of BS patients in real-world studies. Methods: This study was a retrospective cross-sectional study. A total of 483 patients diagnosed with BS in the Department of Rheumatology and Immunology, Peking University People's Hospital from 2019 to 2022 were enrolled. The baseline information and clinical features of the patients were recorded at their first diagnosis and tested the level of HLA-B51, several auto-antibodies, antistreptolysin-O(ASO), immune globulin, complement in blood serum and interleukin-6 (IL-6). Logistic regression was used to analyze the correlation of biomarkers and phenotypes. Results: Among BS patients, the number of positive cases for HLA-B51, anti-endothelial cell antibody (AECA), antinuclear antibodies (ANA) and ASO was 129, 115, 79 and 54, respectively. The positive rate of other biomarkers was less than 5.0%. About 12.6% of patients with BS had an increased level of IgA (n=61), and 10.8% of patients had an increased level of IgG (n=52). About 41.0% of patients had increased levels of IL-6 (n=198), and 6.4% of patients had decreased levels of IgM (n=31). About 11.2% of patients had decreased levels of C3 (n=54), and 6.0% of patients had decreased levels of C4 (n=29). Elevated IgA was a risk factor for the articular phenotype of BS (OR=2.652, P=0.011). Decreased complement C4 was a risk factor for the neurological phenotype of BS (OR=3.594, P=0.039). Positive ASO was a risk factor for the gastrointestinal phenotype of BS (OR=2.578, P=0.041). Elevated IL-6 was a risk factor for the ocular phenotype of BS (OR=7.560, P=0.016). Conclusion: HLA-B51 and AECA are common biomarkers in BS. Elevated IgA, decreased complement C4, positive ASO, and elevated IL-6 are risk factors for different phenotypes of BS.

Fault diagnosis method of rotating machinery based on MSResNet feature fusion and CAM

To solve the problem of noise interference, it is difficult to extract multi-scale information from complex vibration signals in fault diagnosis with the single-scale convolution kernel of classical deep learning model convolutional neural network (CNN). Therefore, a fault diagnosis method of rotating machinery based on MSResNet feature fusion and CAM is proposed. The residual network (ResNet) and multi-scale convolutional neural network (MSCNN) are combined to extract multi-scale feature information according to convolution kernels with different sizes, so as to avoid the loss of single-scale feature extraction. Make full use of the advantages of the residual network to skip the connection and prevent the feature information extracted by the multi-scale convolution kernel from being lost when the convolution layer propagates forward. In addition, in order to avoid the interference of invalid features after multi-scale information feature fusion, a channel attention mechanism module (CAM) is introduced to screen important features adaptively. The effectiveness of MSResNet-CAM is verified by the bearing data set of Western Reserve University (CWRU) and the data set of QPZZ-II gearbox, and the anti-noise ability is verified by adding noise to the two data sets. The experimental results show that MSResNet-CAM has the characteristics of high fault classification accuracy, good robustness and strong anti-noise ability.