Accurate Feature Extraction Research Articles

Advanced Sparse Filtering-Based Domain Adaptation for Fault Diagnosis in Variable Working Conditions

Traditional domain adaptation (DA) methods often encounter challenges with cross-domain feature extraction and the precise assessment of domain differences. To overcome these limitations, we introduce the Enhanced Sparse Filtering-Based Domain Adaptation (ESFBDA) method. This method distinguishes itself by enhancing sparse filtering (SF) with the integration of row-column normalization and a cosine penalty, specifically designed to minimize feature loss—a critical issue in existing DA techniques. Additionally, we employ Bootstrap resampling to refine domain distribution alignment, a novel step that boosts feature similarity and effectiveness in DA. This integrated approach ensures more accurate feature extraction, which is crucial for the classifier's fault detection capability. In our study, through two distinct experiments on WT-planetary gearbox fault diagnosis and bearing fault diagnosis, the ESFBDA method demonstrated remarkable accuracy, significantly surpassing traditional approaches and showcasing its robust applicability across varied diagnostic scenarios.

ESR Essentials: radiomics-practice recommendations by the European Society of Medical Imaging Informatics.

Radiomics is a method to extract detailed information from diagnostic images that cannot be perceived by the naked eye. Although radiomics research carries great potential to improve clinical decision-making, its inherent methodological complexities make it difficult to comprehend every step of the analysis, often causing reproducibility and generalizability issues that hinder clinical adoption. Critical steps in the radiomics analysis and model development pipeline-such as image, application of image filters, and selection of feature extraction parameters-can greatly affect the values of radiomic features. Moreover, common errors in data partitioning, model comparison, fine-tuning, assessment, and calibration can reduce reproducibility and impede clinical translation. Clinical adoption of radiomics also requires a deep understanding of model explainability and the development of intuitive interpretations of radiomic features. To address these challenges, it is essential for radiomics model developers and clinicians to be well-versed in current best practices. Proper knowledge and application of these practices is crucial for accurate radiomics feature extraction, robust model development, and thorough assessment, ultimately increasing reproducibility, generalizability, and the likelihood of successful clinical translation. In this article, we have provided researchers with our recommendations along with practical examples to facilitate good research practices in radiomics. KEY POINTS: Radiomics' inherent methodological complexity should be understood to ensure rigorous radiomic model development to improve clinical decision-making. Adherence to radiomics-specific checklists and quality assessment tools ensures methodological rigor. Use of standardized radiomics tools and best practices enhances clinical translation of radiomics models.

Edge segmentation method for Si3N4 bearing rolling elements microcracks with profile-distortion

For the profile-distortion of Si3N4 bearing rolling elements microcracks image. A coupling method of variable-scale truncated median filtering and detection-driven active contour model is proposed. Details are as follows. The sigmoid activation function is constructed to dynamically adjust the circular window. The local threshold truncation is designed to adapt to the characteristics of different regions in the image. The area threshold is defined to eliminate non-target features. The mean peak signal-to-noise ratio (PSNR) of filtered images is about 40.263. The edge overlap rate is as low as 0.1027. The mean accuracy of feature extraction is about 94.33 %. To sum up, the influence result from profile-distortion on the accuracy of feature extraction of Si3N4 bearing rolling elements microcracks is effectively solved.

PsyneuroNet architecture for multi-class prediction of neurological disorders

Early detection and diagnosis of psychiatric disorders are crucial for timely intervention, improved treatment outcomes, and preventing complications. The purpose of this study is to use artificial intelligence methods to diagnose symptoms of psychiatric conditions such as depression, schizophrenia, sleep disorder, and Alzheimer’s disease in epileptic patients using EEG data. The research uses a cross-validation procedure with ten iterations and looks at three data sets: the CHB-MIT dataset with EEG recordings from neonatal subjects, the DEAP dataset containing physiological signals and emotional ratings, and the OpenNeuro dataset containing multichannel EEG. Preprocessing involves dividing the EEG signals into five brain wave frequency components and applying filtering techniques for further analysis. We introduce a novel architecture called PsyneuroNet, which aims to improve feature extraction and prediction accuracy for real-time psychiatric disorder recognition and integrates three key components: cross-normalization across convolution, a bidirectional long-short-term memory network (Bi-LSTM), and an enhanced intuition-based convolutional neural network (ICNN). The proposed methodology is evaluated based on the 99.65% prediction accuracy achieved on the CHB-MIT dataset, the 97.27% prediction accuracy achieved on the DEAP dataset, and the 98.08% prediction accuracy achieved on the OpenNeuro dataset for prediction problems. The proposed method outperforms the state-of-the-art approaches in terms of accuracy by 3.64%, with a sensitivity of 99.65%, a specificity of 99.75%, and a very low false positive rate per hour (FPR/h) of 0.3%, all achieved by using ten folds cross-validation. The PsyneuroNet’s capability to classify a diverse range of neurological disorders within a single architecture is noteworthy. This versatility makes the model suitable for addressing a broad spectrum of clinical scenarios. The model’s ability to generalize effectively to unseen data, as demonstrated by testing its performance on the DEAP and OpenNeuro datasets after training on CHB-MIT data, is a significant aspect of novelty.

Extraction method for characterizing microcracks on Si3N4 ceramic bearings rolling element with contour segmentation

AbstractAiming at the fuzzy diffusion characteristics of microcrack regions in Si3N4 ceramic bearing rolling elements, an adaptive region segmentation method is proposed to achieve precise extraction of microcrack features. The fuzzy diffusion effect of the microcrack region is analyzed, and a structural complexity matrix is defined to represent the degree of structural variation in the image. A threshold point is determined through histogram analysis, and the matrix dispersion rate is calculated using a box plot to update the correction factor, optimizing the overlap of noise in the microcrack image. The causes of distortion in the microcrack region are analyzed, and pixel points are assigned based on spatial metrics and LAB color features. The fuzzy boundaries and overlapping regions are segmented using the fuzzy C‐means clustering algorithm. A grid search algorithm is embedded to quantitatively evaluate the optimal combination of hyperparameters, enabling comprehensive extraction of microcrack features in Si3N4 ceramic bearing rolling elements. The optimized image achieves an average peak signal‐to‐noise ratio of 39.3, an information fidelity criterion of 7.9328, and an average extraction accuracy of approximately 0.92, effectively overcoming the impact of the fuzzy diffusion effect on the accuracy of microcrack feature extraction in Si3N4 ceramic bearing rolling elements.

A novel intelligent fault diagnosis method for gearbox based on multi-dimensional attention denoising convolution.

In the field of intelligent fault diagnosis, particularly concerning rotating machinery, convolutional neural networks (CNNs) face significant challenges when applied to real industrial vibration data. These data are not only contaminated by various types of noise but also exhibit fault features that vary across different scales. Consequently, the effective suppression of extraneous noise and accurate extraction of multi-scale fault features are crucial issues. To address these challenges, this study proposes a novel deep neural network framework, termed the Multidimensional Fusion Residual Attention Network (MFRANet), for gearbox fault diagnosis. The MFRANet employs a multi-scale deep separable convolution module to thoroughly investigate the fundamental characteristics of the original vibration signals in both the time and time-frequency domains. To enhance the detailed analysis of diagnostic data and mitigate the risks of overfitting and noise interference, an efficient residual channel attention module is incorporated to weight and denoise the feature maps. Additionally, an external attention module is introduced to create implicit connections between the denoised multi-scale feature maps and to highlight potential correlations within the sample data, thereby improving the accuracy of fault diagnosis. Experimental evaluations on a gearbox fault dataset demonstrate that the proposed method surpasses several benchmark and state-of-the-art techniques in terms of diagnostic performance, exhibiting robust noise resilience across various noise levels. This indicates enhanced reliability and accuracy in gearbox fault diagnosis, providing an innovative and efficient solution for fault diagnosis in rotating machinery. The study underscores the contributions of artificial intelligence through the innovative structure of the method and the integration of advanced deep learning modules, while its engineering application is evidenced by addressing practical challenges in rotating machinery fault diagnosis. This work meets the urgent need for reliable diagnostic methods in industrial environments.

An Improved Nonnegative Matrix Factorization Algorithm Combined with K-Means for Audio Noise Reduction

Clustering algorithms have the characteristics of being simple and efficient and can complete calculations without a large number of datasets, making them suitable for application in noise reduction processing for audio module mass production testing. In order to solve the problems of the NMF algorithm easily getting stuck in local optimal solutions and difficult feature signal extraction, an improved NMF audio denoising algorithm combined with K-means initialization was designed. Firstly, the Euclidean distance formula of K-means has been improved to extract audio signal features from multiple dimensions. Combined with the initialization strategy of K-means decomposition, the initialization dictionary matrix of the NMF algorithm has been optimized to avoid getting stuck in local optimal solutions and effectively improve the robustness of the algorithm. Secondly, in the sparse coding part of the NMF algorithm, feature extraction expressions are added to solve the problem of noise residue and partial spectral signal loss in audio signals during the operation process. At the same time, the size of the coefficient matrix is limited to reduce operation time and improve the accuracy of feature extraction in high-precision audio signals. Then, comparative experiments were conducted using the NOIZEUS and NOISEX-92 datasets, as well as random noise audio signals. This algorithm improved the signal-to-noise ratio by 10–20 dB and reduced harmonic distortion by approximately −10 dB. Finally, a high-precision audio acquisition unit based on FPGA was designed, and practical applications have shown that it can effectively improve the signal-to-noise ratio of audio signals and reduce harmonic distortion.

Research on a Photovoltaic Panel Dust Detection Algorithm Based on 3D Data Generation

With the rapid advancements in AI technology, UAV-based inspection has become a mainstream method for intelligent maintenance of PV power stations. To address limitations in accuracy and data acquisition, this paper presents a defect detection algorithm for PV panels based on an enhanced YOLOv8 model. The PV panel dust dataset is manually extended using 3D modeling technology, which significantly improves the model’s ability to generalize and detect fine dust particles in complex environments. SENetV2 is introduced to improve the model’s perception of dust features in cluttered backgrounds. AKConv replaces traditional convolution in the neck network, allowing for more flexible and accurate feature extraction through arbitrary kernel parameters and sampling shapes. Additionally, a DySample dynamic upsampler accelerates processing by 8.73%, improving the frame rate from 87.58 FPS to 95.23 FPS while maintaining efficiency. Experimental results show that the 3D image expansion method contributes to a 4.6% increase in detection accuracy, an 8.4% improvement in recall, a 5.7% increase in mAP@50, and a 15.1% improvement in mAP@50-95 compared to the original YOLOv8. The expanded dataset and enhanced model demonstrate the effectiveness and practicality of the proposed approach.

RU-Net, Multi-Scale Feature Fusion and Transfer Learning: Unlocking the Potential of Cuffless Blood Pressure Monitoring with PPG and ECG.

This study introduces an innovative deep-learning model for cuffless blood pressure estimation using PPG and ECG signals, demonstrating state-of-the-art performance on the largest clean dataset, PulseDB. The rU-Net architecture, a fusion of U-Net and ResNet, enhances both generalization and feature extraction accuracy. Accurate multi-scale feature capture is facilitated by short-time Fourier transform (STFT) time-frequency distributions and multi-head attention mechanisms, allowing data-driven feature selection. The inclusion of demographic parameters as supervisory information further elevates performance. On the calibration-based dataset, our model excels, achieving outstanding accuracy (SBP MAE ± std: 4.49 ± 4.86 mmHg, DBP MAE ± std: 2.69 ± 3.10 mmHg), surpassing AAMI standards and earning a BHS Grade A rating. Addressing the challenge of calibration-free data, we propose a fine-tuning-based transfer learning approach. Remarkably, with only 10% data transfer, our model attains exceptional accuracy (SBP MAE ± std: 4.14 ± 5.01 mmHg, DBP MAE ± std: 2.48 ± 2.93 mmHg). This study sets the stage for the development of highly accurate and reliable wearable cuffless blood pressure monitoring devices.

Pre-trained quantum convolutional neural network for COVID-19 disease classification using computed tomography images

Background The COVID-19 pandemic has had a significant influence on economies and healthcare systems around the globe. One of the most important strategies that has proven to be effective in limiting the disease and reducing its rapid spread is early detection and quick isolation of infections. Several diagnostic tools are currently being used for COVID-19 detection using computed tomography (CT) scan and chest X-ray (CXR) images. Methods In this study, a novel deep learning-based model is proposed for rapid detection of COVID-19 using CT-scan images. The model, called pre-trained quantum convolutional neural network (QCNN), seamlessly combines the strength of quantum computing with the feature extraction capabilities of a pre-trained convolutional neural network (CNN), particularly VGG16. By combining the robust feature learning of classical models with the complex data handling of quantum computing, the combination of QCNN and the pre-trained VGG16 model improves the accuracy of feature extraction and classification, which is the significance of the proposed model compared to classical and quantum-based models in previous works. Results The QCNN model was tested on a SARS-CoV-2 CT dataset, initially without any pre-trained models and then with a variety of pre-trained models, such as ResNet50, ResNet18, VGG16, VGG19, and EfficientNetV2L. The results showed the VGG16 model performs the best. The proposed model achieved 96.78% accuracy, 0.9837 precision, 0.9528 recall, 0.9835 specificity, 0.9678 F1-Score and 0.1373 loss. Conclusion Our study presents pre-trained QCNN models as a viable technique for COVID-19 disease detection, showcasing their effectiveness in reaching higher accuracy and specificity. The current paper adds to the continuous efforts to utilize artificial intelligence to aid healthcare professionals in the diagnosis of COVID-19 patients.

Image segmentation of tunnel water leakage defects in complex environments using an improved Unet model

Computer vision technology provides an intelligent means for detecting tunnel water leakage areas. However, the accuracy of defect feature extraction and segmentation is limited by factors such as insufficient lighting and environmental interference inside tunnels. To address the problem, this paper proposes a tunnel water leakage area segmentation network model called Customized Side Guided-Unet (CSG-Unet), using Unet as the baseline model. The main contributions are: (1) To improve the accuracy of water leakage area extraction, a customized side guided term is introduced to direct the net’s attention to the changes in light and shade within the image. A parallel attention network module is designed to extract internal information from the guided term. Subsequently, a strengthened channel attention module aggregates the guided term and the original information to achieve accurate segmentation of water leakage areas; (2) To address the scarcity of tunnel water leakage area datasets, a basic dataset is constructed by collecting data from open-source datasets and manually gathered data in tunnels. On this basis, perspective transformation is used to change the camera viewpoint, gaussian noise is randomly added to the images in the dataset to simulate images taken in dimly lit scenes, thereby expanding the dataset and enhancing the network’s generalization. The CSG-Unet network was trained using the constructed training set, achieving a mean Intersection over Union (mi IoU) of 85.54%, a mean Dice coefficient (mi Dice) of 85.26%, and a mean Pixel Accuracy (mi PA) of 90.85%. Compared to its baseline network, U-Net (tiny), these metrics show an improvement of over 3.2% in each indicator. Finally, a visual comparison between the improved network and the baseline network further confirms that the proposed model can effectively adapt to the segmentation of water leakage areas in complex environments.

Infrared target detection algorithm based on multipath coordinate attention mechanism

Abstract The current generation of infrared target detection algorithms frequently exhibits a high degree of dependency on parameter configurations within complex operational environments. This often results in a reduction in detection accuracy, an increase in the number of model parameters, and a slowing of the detection process. To address these limitations, a new algorithm, CGhostNet-Attention-YOLO (CAY), is proposed in this paper. Firstly, we designed a lightweight backbone network, CGhostNet, with the objective of improving feature extraction efficiency, thereby enabling accurate and real-time feature extraction. Furthermore, we proposed a Multipath Coordinate Attention (MPCA) mechanism, which incorporates both channel and positional information, thereby facilitating enhanced context awareness and the comprehension of relationships between different positions. This effectively enhances the model's ability to comprehend the overall meaning and addresses the issue of missed detections in infrared targets, significantly improving detection accuracy. Moreover, we employed the Inner-SIoU loss function to accelerate model convergence, reduce loss, and enhance the robustness of the model. Finally, comparative experiments were conducted on our dataset (IFD) as well as publicly available datasets, including FLIR, Pascal VOC, and NEU-DET. The results demonstrate that the CAY algorithm achieved a mean Average Precision (mAP@0.5) of 81.3% on the IFD dataset, 86.1% on the FLIR dataset, 79.2% on the Pascal VOC dataset, and 79.9% on the NEU-DET dataset, with a 27% reduction in the number of parameters. These findings validate the feasibility of the proposed algorithm.

Advanced Wind Power Forecasting

The popularity of LSTM networks in wind prediction is due to their inherent capabilities in handling the long-term dependencies of sequential data. This normally outperforms traditional methods like ARIMA. However, current work has illustrated that EMD-based approaches outperform LSTM models in many critical performance metrics. Although it is very powerful in gathering historical patterns due to the enhanced gating mechanisms, LSTM has a lot of challenges regarding computational efficiency and flexibility. EMD models overwhelmingly outperformed the LSTM model in computational time by probably about 20-25%, thereby solving a weakness that may be one of the intrinsic weaknesses of the LSTM model. In addition, the EMD models improved by about 2-4% in accuracy as compared to LSTM, thus evidencing better ability in the prediction of the wind data. On feature extraction, EMD did better, improving by 7% over LSTM. Moreover, EMD has better robustness and adaptability, with improvements of 6% and 4%, respectively. This introduction of EMD does bring a bit of an increase in model complexity, this disadvantage is rather insignificant when compared with the huge advantages it brings in efficiency and accuracy. While an LSTM network is very good at modeling a long-term relationship, it suffers from some problems in handling nonlinear interactions and continuous series data, thus its effectiveness may be limited in some cases of forecasting. In contrast, EMD has a clear advantage in real-time applications owing to enhanced efficiency and precision. From the results obtained in this study, it becomes easy to envision that the EMD methodology is un-equivocally better than LSTM in all the critical aspects, such as computational efficiency, accuracy in prediction, feature extraction, resilience, and adaptability when used individually. Results indicate that EMD has a more constructive methodology toward wind pattern predictions, beating LSTM on many measures of performance. The advantages presented should be maximized in future studies aimed at further improving and optimizing a wind-forecasting system, with special attention toward EMD's benefits in gaining more accurate and efficient forecasts.

Point cloud-based feature extraction and surface reconstruction for parts paring in high-precision assembly

Abstract Assembly plays a crucial role in industrial manufacturing in industrial manufacturing, but the efficiency of conventional manual methods for parts pairing is limited. Previous research has demonstrated the feasibility of deep learning for point cloud feature extraction and 3D reconstruction. An innovative method utilizing deep learning for high-precision feature extraction and surface reconstruction is introduced to optimize parts pairing in this paper. Geometric dimensions and surface topography data are obtained by defining key assembly features and utilizing the Random Sample Consensus method. Deep learning is then used to directly regress the Surface Distance Function from point samples, facilitating comprehensive part surface modeling and supporting assembly simulation in the digital twin. To validate this approach, a case study demonstrates successful matching of 30 shaft parts and 30 hole parts after optimization, with an increase in average uniformity by 0.024. This highlights the proposed method’s superior effectiveness and accuracy in feature extraction and surface reconstruction.

Few-shot bearing fault diagnosis method based on an EEMD parallel neural network and a relation network

Bearing fault diagnosis presents challenges, such as insufficient fault samples and significant fault data distribution variation in different bearing operating conditions. These problems cause traditional deep learning models to show poor generality and accuracy during bearing fault diagnosis. To address these challenges, this paper proposed a few-shot bearing fault diagnosis method based on an Ensemble Empirical Mode Decomposition (EEMD) parallel neural network and a relation network (RN). First, the original bearing fault vibration signal was decomposed by EEMD, while the decomposed signal components were processed via Short Time Fourier Transfor (STFT) to obtain a two-dimensional time-frequency feature map. Then, a parallel neural network was used for initial fault feature extraction, after which the extracted features were fused to construct a more accurate multi-dimensional fault feature map. A more precise fault feature vector was generated via the feature embedding module of the RN, and the fault features of the support and query sets were stitched to create a fault feature vector set. Finally, the relation module of the RN was used for the nonlinear distance determination of the fault feature vector set and to generate the relation score for the few-shot variable condition bearing fault diagnosis. In this paper, EEMD module is introduced into RN to construct multi-dimensional fault characteristics of the original fault signal. Original signal decomposition, STFT transformation and splicing effectively improve the randomness and blindness of convolution operations, improve the accuracy of fault feature extraction in RN, and thus improve the overall diagnostic performance of the model. The experimental results showed that the proposed model obtained higher diagnostic accuracy than the matching network (MN) and RN meta-learning fault diagnosis (MLFD) methods. The accuracy of fault diagnosis of the model in 5Way-Nshot is >80%, and the accuracy of fault diagnosis in 5Way-10shot is the highest at 95.2%.

A Crack Detection Method for Civil Engineering Bridges Based on Feature Extraction and Parametric Modeling of Point Cloud Data

Accurate detection and analysis of cracks is critical for ensuring the safety and reliability of concrete bridges. Point cloud data (PCD) obtained from 3D scanning provides a promising avenue for automated crack assessment. However, processing the massive and unstructured PCD poses significant challenges in feature extraction and crack modeling. This paper proposes a novel method for bridge crack analysis by combining PCD feature extraction with a hierarchical neural network and Rodriguez rotation. The method first extracts crack features from PCD using outlier removal, denoising, and 3D coordinate conversion. A crack analysis model is then constructed by integrating multi-scale feature extraction and Rodriguez rotation into a hierarchical neural network, enabling the capture of both local and global crack patterns. Experiments on a benchmark data set demonstrate the effectiveness of the proposed approach, achieving 92.83% feature extraction accuracy, 95.73% parameter analysis accuracy, 93.51% recognition accuracy, and 0.91 F1 score. The method also shows improved efficiency compared to existing techniques. These results highlight the potential of the proposed PCD-based approach for accurate and efficient crack analysis in concrete bridges.

Fine-Grained High-Resolution Remote Sensing Image Change Detection by SAM-UNet Change Detection Model

Remote sensing image change detection is crucial for urban planning, environmental monitoring, and disaster assessment, as it identifies temporal variations of specific targets, such as surface buildings, by analyzing differences between images from different time periods. Current research faces challenges, including the accurate extraction of change features and the handling of complex and varied image contexts. To address these issues, this study proposes an innovative model named the Segment Anything Model-UNet Change Detection Model (SCDM), which incorporates the proposed center expansion and reduction method (CERM), Segment Anything Model (SAM), UNet, and fine-grained loss function. The global feature map of the environment is extracted, the difference measurement features are extracted, and then the global feature map and the difference measurement features are fused. Finally, a global decoder is constructed to predict the changes of the same region in different periods. Detailed ablation experiments and comparative experiments are conducted on the WHU-CD and LEVIR-CD public datasets to evaluate the performance of the proposed method. At the same time, validation on more complex DTX datasets for scenarios is supplemented. The experimental results demonstrate that compared to traditional fixed-size partitioning methods, the CERM proposed in this study significantly improves the accuracy of SOTA models, including ChangeFormer, ChangerEx, Tiny-CD, BIT, DTCDSCN, and STANet. Additionally, compared with other methods, the SCDM demonstrates superior performance and generalization, showcasing its effectiveness in overcoming the limitations of existing methods.

Model optimization and acceleration method based on meta-learning and model pruning for laser vision weld tracking system

Purpose This paper aims to propose a lightweight, high-accuracy object detection model designed to enhance seam tracking quality under strong arcs and splashes condition. Simultaneously, the model aims to reduce computational costs. Design/methodology/approach The lightweight model is constructed based on Single Shot Multibox Detector (SSD). First, a neural architecture search method based on meta-learning and genetic algorithm is introduced to optimize pruning strategy, reducing human intervention and improving efficiency. Additionally, the Alternating Direction Method of Multipliers (ADMM) is used to perform structural pruning on SSD, effectively compressing the model with minimal loss of accuracy. Findings Compared to state-of-the-art models, this method better balances feature extraction accuracy and inference speed. Furthermore, seam tracking experiments on this welding robot experimental platform demonstrate that the proposed method exhibits excellent accuracy and robustness in practical applications. Originality/value This paper presents an innovative approach that combines ADMM structural pruning and meta-learning-based neural architecture search to significantly enhance the efficiency and performance of the SSD network. This method reduces computational cost while ensuring high detection accuracy, providing a reliable solution for welding robot laser vision systems in practical applications.

Structural tensor and frequency guided semi-supervised segmentation for medical images.

The method of semi-supervised semantic segmentation entails training with a limited number of labeled samples alongside many unlabeled samples, aiming to reduce dependence on pixel-level annotations. Most semi-supervised semantic segmentation methods primarily focus on sample augmentation in spatial dimensions to reduce the shortage of labeled samples. These methods tend to ignore the structural information of objects. In addition, frequency-domain information also supplies another perspective to evaluate information from images, which includes different properties compared to the spatialdomain. In this study, we attempt to answer these two questions: (1) is it helpful to provide structural information of objects in semi-supervised semantic segmentation tasks for medical images? (2) is it more effective to evaluate the segmentation performance in the frequency domain compared to the spatial domain for semi-supervised medical image segmentation? Therefore, we seek to introduce structural and frequency information to improve the performance of semi-supervised semantic segmentation for medicalimages. We present a novel structural tensor loss (STL) to guide feature learning on the spatial domain for semi-supervised semantic segmentation. Specifically, STL utilizes the structural information encoded in the tensors to enforce the consistency of objects across spatial regions, thereby promoting more robust and accurate feature extraction. Additionally, we proposed a frequency-domain alignment loss (FAL) to enable the neural networks to learn frequency-domain information across different augmented samples. It leverages the inherent patterns present in frequency-domain representations to guide the network in capturing and aligning features across diverse augmentation variations, thereby enhancing the model's robustness for the inputting variations. We conduct our experiments on three benchmark datasets, which include MRI (ACDC) for cardiac, CT (Synapse) for abdomen organs, and ultrasound image (BUSI) for breast lesion segmentation. The experimental results demonstrate that our method outperforms state-of-the-art semi-supervised approaches regarding the Dice similaritycoefficient. We find the proposed approach could improve the final performance of the semi-supervised medical image segmentation task. It will help reduce the need for medical image labels. Our code will are available at https://github.com/apple1986/STLFAL.

A Spatio-Temporal Capsule Neural Network with Self-Correlation Routing for EEG Decoding of Semantic Concepts of Imagination and Perception Tasks.

Decoding semantic concepts for imagination and perception tasks (SCIP) is important for rehabilitation medicine as well as cognitive neuroscience. Electroencephalogram (EEG) is commonly used in the relevant fields, because it is a low-cost noninvasive technique with high temporal resolution. However, as EEG signals contain a high noise level resulting in a low signal-to-noise ratio, it makes decoding EEG-based semantic concepts for imagination and perception tasks (SCIP-EEG) challenging. Currently, neural network algorithms such as CNN, RNN, and LSTM have almost reached their limits in EEG signal decoding due to their own short-comings. The emergence of transformer methods has improved the classification performance of neural networks for EEG signals. However, the transformer model has a large parameter set and high complexity, which is not conducive to the application of BCI. EEG signals have high spatial correlation. The relationship between signals from different electrodes is more complex. Capsule neural networks can effectively model the spatial relationship between electrodes through vector representation and a dynamic routing mechanism. Therefore, it achieves more accurate feature extraction and classification. This paper proposes a spatio-temporal capsule network with a self-correlation routing mechaninsm for the classification of semantic conceptual EEG signals. By improving the feature extraction and routing mechanism, the model is able to more effectively capture the highly variable spatio-temporal features from EEG signals and establish connections between capsules, thereby enhancing classification accuracy and model efficiency. The performance of the proposed model was validated using the publicly accessible semantic concept dataset for imagined and perceived tasks from Bath University. Our model achieved average accuracies of 94.9%, 93.3%, and 78.4% in the three sensory modalities (pictorial, orthographic, and audio), respectively. The overall average accuracy across the three sensory modalities is 88.9%. Compared to existing advanced algorithms, the proposed model achieved state-of-the-art performance, significantly improving classification accuracy. Additionally, the proposed model is more stable and efficient, making it a better decoding solution for SCIP-EEG decoding.