Wyniki wyszukiwania - BazTech

Ograniczanie wyników

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Sortuj według:

Ogranicz wyniki do:

Application of electromagnetic interference-bp technology in mechanical noise control of small DC electrodes

Cao Hui, Zhang Xiaoyan

Diagnostyka

2025

Vol. 26, No. 3

art. no. 2025306

With the widespread use of miniaturized electronic equipment in daily life, the problem of electromagnetic interference has become increasingly prominent, especially in precision instruments and communication equipment. To effectively reduce the causes of mechanical noise generated by small DC electrodes during operation and the electromagnetic interference effects on surrounding equipment, a mechanical noise control method that combines piezoelectric impedance technology and back-propagation neural networks is proposed. In the process, small DC motor electrodes were used as the research object, and the sources of mechanical noise generated by the motor were analyzed. At the same time, different analysis software was used to simulate and model the stator and rotor of the motor. The results show that when different algorithms are run on the training set and test set, when the amount of data increases to 560 and 1120 respectively, the method constructed in the experiment has the maximum fitness value, with values as high as 98.98% and 97.86%. When the training set is run, when the running time increases to 0.894s, the accuracy of the method constructed in the experiment to control mechanical noise reaches 91.68%. The application effect shows that when the material of the stator shell is steel, the occurrence of the maximum natural frequency of the stator is affected by the elastic modulus, which is far greater than the influence of the material density. The experiment provides new ideas and methods for noise and electromagnetic interference control of small DC electrodes.

A lightweight spatially-aware classification model for breast cancer pathology images

Jiang Liang, Zhang Cheng, Zhang Huan, Cao Hui

Biocybernetics and Biomedical Engineering

2024

Vol. 44, no. 3

586--608

Breast cancer is a prevalent malignant tumour with high global incidence. Its diagnosis relies primarily on the analysis of pathological breast images. Owing to the complex organisation of the tumour microenvironment, neural network models are essential as efficient classification tools in the field of pathological image analysis. This study introduced spatially-aware attention swift parallel convolution network (SPA-SPCNet), a lightweight and low-latency model for classifying breast pathologies. A novel module for multi-scale feature extraction was constructed using a depthwise separable convolution method. It focuses on the multi-scale features of pathological images to alleviate recognition problems caused by similar local features in breast cancer tissues. The module concatenates the convolutions of different kernels from three branches. Second, a lightweight dynamic spatially-aware attention module was introduced to integrate the visual graph convolutional architecture in a branch. This allowed the model to capture the spatial structure and relationships in image, enabling better handling of the unique spatial distribution relationship between breast cancer tissue structures. The other branch utilises a self-attention mechanism in the transformer. The module can dynamically adjust the attention of the model to different regions in the image, allowing it to focus on the key features of the complex spatial distribution of breast cancer tissue. This feature fusion method enabled the model to capture both global semantics and local details. Compared with existing lightweight models, the proposed model has advantages in terms of tissue structure classification accuracy, parameter quantity, floating-point operations, and real-time inference speed, providing a powerful tool for computer-aided breast pathological image classification.