Deep learning usually achieves good performance in the supervised way, which requires a large amount of labeled data. However, manual labeling of electrocardiograms (ECGs) is laborious that requires much medical ...

• Fusing consistency regularization and pseudo-labeling for CVD detection.
• Utilizing all unlabeled ECGs in semi-supervised learning.
• Deploying the CVD detection algorithm to a heterogeneous SoC.
• The scheme has good potential for ...

Graph-based models for Electrocardiogram (ECG) incorporate physiological spatial information among ECG leads in elegant manners. It is unachievable for convolution-based models. Nevertheless, existing ECG graph models heavily rely on manually pre-...

• Heuristic algorithms are applied for Electrocardiogram graph structure learning.
• Node-embedding GraphSAGE is employed to enhance model continuously in searching.
• Honest-GE further shows superiority over existing methods with ...

Deep cardiovascular disease (CVD) detection usually achieves good performance with large-scale labeled electrocardiograms (ECGs), but manual labeling of ECGs is tedious. Semi-supervised learning (SSL) aims to improve model performance through ...

• Proposed a corn seed spacing detection method based on image stitching and YOLOX.
• The image stitching method based on “speed-rate” linkage could stitch multiple seed bed images into seed bed panoramic images.
• YOLOX has been applied ...

Corn seed spacing is fundamental for detecting doubles and misses and calculating the seed spacing conformity and variation. These factors are essential for optimizing the corn seeding operation system and improving the quality of corn seeding. ...

Display Omitted

• A calibration approach for DEM solid–liquid mixing was developed.
• Discrete element simulations were used for mixing soils with liquid amendments.
• DEM parameters of a contact model named Kneading were calibrated.
• An amendment ...

Liquid soil amendments could improve the characteristics of soils and positively affect crop yields by mixing them with soils evenly. However, the lack of a scientific approach to model the mix by the discrete element method (DEM) limited the ...

Nowadays, the increase in computing power and data volume boosts the development of deep learning. However, computational resources and the high cost of data labeling are two main obstacles to employing algorithms in various applications. ...

• Knowledge distillation and generative self-supervised learning are incorporated.
• Dual distillations are contained in the stage of pre-training and fine-tuning.
• Bi-directional knowledge distillation enhance teacher models in ...

Gate all around field effect transistor (GAAFET) presents a resurgence ascribed to its enhanced gate electrostatic controllability by virtue of surrounding gate structure in coping with increasingly serious power consumption dissipation and short ...

Display Omitted

• For the first time, a double channeled nanotube gate all around field effect transistor (DC NT GAAFET) has been designed and simulated, the DC NT GAAFET is studied by rigorous Sentaurus TCAD simulation, the simulated results are assessed ...

• Established and calibrated a Soil-Straw composite model.
• A vertical active rotation straw cleaning method has been proposed.
• Designed a vertical stubble cleaning and soil crushing device.
• Structural parameters were optimized ...

Strip tillage is a necessary technical means to solve blockage problems during the no-tillage sowing process under the condition of total straw return to the field. However, the large amount of straw on the surface, thick stems, and slow ...

• Improved UNet network enhances maize crop row segmentation.
• Adaptive perspective transformation corrects image distortions.
• Detects maize at various growth stages and under complex field conditions.
• Provides technical support ...

Crop-row line detection is key to realizing the accurate spraying of crops; however, it is challenging because of uneven lighting, weeds, and missing plants within rows. In this study, we propose an automatic detection method for maize width and ...

This article studies the influence of different structures and components of GIS on the propagation characteristics of partial discharge signals, and summarizes the influence mechanism. Firstly, the attenuation of basin insulators on various frequency ...

This article proposes a GIS multi-point discharge separation technology based on amplitude ratio clustering, which has been validated through experiments in the air, GIS laboratory validation, and GIS on-site detection. It has been proven that this ...

This article analyzes the circuit breaker opening failure and overhead ground wire breakage of the 2213 outgoing line at a certain substation due to multiple lightning strikes, which resulted in the tripping of the 220kV busbar and main transformer. ...

Reducing acquisition time in Cardiac Magnetic Resonance Imaging (MRI) brings several benefits, such as improved patient comfort, reduced motion artifacts and increased doctors’ work efficiency, but it may lead to image blurring during the ...

Pests are diverse and the available datasets often contain an uneven number of examples for different pests (a.k.a., the long-tail distribution). This poses a great challenge to learning-based classification methods, especially deep networks, and ...

In this paper, a new algorithm is devised to show how a complete electromagnetic vector sensor (EMVS) system enables handling the target detection and localization problem in interference-dominant scenarios. Specifically, our recently ...

The UNet series networks have been a leader in the field of medical image segmentation since their introduction. However, encoder and decoder structures of the traditional UNet series network are complex, with a large number of parameters and ...

Display Omitted

• Our novel medical image segmentation network-GFUNet is proposed, bridging the MLP-like paradigm and the Fourier transform.
• Global Filters are introduced To extract frequency domain features and improve the performance in the proposed ...

Almost all existing causal feature selection methods are proposed without considering the problem of sample selection bias. However, in practice, as data-gathering process cannot be fully controlled, sample selection bias often occurs, leading to spurious ...

Usually, manual labeling of large-scale electrocardiograms (ECGs) for deep learning is always expensive, as it requires considerable effort and time from cardiologists. Currently, contrastive learning can utilize unlabeled ECGs to ...

• Dense lead contrast (DLC) conducts an effective self-supervised pre-training.
• ...

Display Omitted

• A new approach for measuring angle of repose (AOR) was developed.
• Point cloud data of a heap were fully utilized for determination of AOR.
• The uncertainty of the AOR measurements was significantly weakened.
• Developed approach ...

The angle of repose (AOR) is an indicator of the fluidity of granular materials. The uncertainty for determining the material AOR includes the deviation in the global shape of repeatedly generated heaps and measurement uncertainty for each heap. ...

In this study, the manure block model is established by the discrete element method through the combination of uniaxial compression physical test and simulation test. The model optimizes the propeller blade structure. Finally,...

• The HMB model of organic fertilizer is established and calibrated.
• A method of ...

In organic fertilizer application, it is difficult for existing chain-type fertilizer transport devices to cut and break organic fertilizer blocks during operation. The fertilizer transport process does not effectively disturb the ...