Haowei Yang - IEEE Xplore Author Profile

Showing 1-10 of 10 results

Results

Zero sample learning is an effective method for data deficiency. The existing embedded zero sample learning methods only use the known classes to construct the embedded space, so there is an overfitting of the known classes in the testing process. This project uses category semantic similarity measures to classify multiple tags. This enables it to incorporate unknown classes that have the same mea...Show More
This study introduces an innovative application of Conditional Generative Adversarial Networks (C-GAN) integrated with Stacked Hourglass Networks (SHGN) aimed at enhancing image segmentation, particularly in the challenging environment of medical imaging. We address the problem of overfitting, common in deep learning models applied to complex imaging datasets, by augmenting data through rotation a...Show More
In the field of natural language processing, text classification, as a basic task, has important research value and application prospects. Traditional text classification methods usually rely on feature representations such as the bag of words model or TF-IDF, which overlook the semantic connections between words and make it challenging to grasp the deep structural details of the text. Recently, G...Show More
The internal structure and operation mechanism of large-scale language models are analyzed theoretically, especially how Transformer and its derivative architectures can restrict computing efficiency while capturing long-term dependencies. Further, we dig deep into the efficiency bottleneck of the training phase, and evaluate in detail the contribution of adaptive optimization algorithms (such as ...Show More
This study introduces an innovative unsupervised method for medical image feature extraction, leveraging spatial stratification techniques. To expedite image recognition, the study proposes a novel weight-based objective function. The algorithm segments image pixels into multiple subdomains and accesses the image through a quadtree structure. Additionally, a threshold optimization technique utiliz...Show More
The diagnosis of brain cancer relies heavily on medical imaging, with MRI serving as the primary tool. Precise segmentation of brain tumors in MRI scans is essential, and this project seeks to develop a specialized algorithm using the U-Net architecture for this purpose. The proposed approach integrates a residual network and a context information enhancement module, along with a void space convol...Show More
This paper designed and developed a mobile intelligent diagnosis system for gallstone disease based on deep learning. It can be used offline on Android phones to realize automatic recognition of medical images of gallstone disease. This project intends to take Xilinx company's newly released ZYNQ Super Scale+ MPSoC as the research object, and innovatively introduce it to the hardware and software ...Show More
Neural networks with relatively shallow layers and simple structures may have limited ability in accurately identifying pneumonia. In addition, deep neural networks also have a large demand for computing resources, which may cause convolutional neural networks to be unable to be implemented on terminals. Therefore, this paper will carry out the optimal classification of convolutional neural networ...Show More
The traditional SegNet architecture commonly encounters significant information loss during the sampling process, which detrimentally affects its accuracy in image semantic segmentation tasks. To counter this challenge, we introduce an innovative encoder-decoder network structure enhanced with residual connections. Our approach employs a multi-residual connection strategy designed to preserve the ...Show More
The spread of COVID-19 has brought a huge disaster to the world, and the automatic segmentation of infection regions can help doctors to make diagnosis quickly and reduce workload. However, there are several challenges for the accurate and complete segmentation, such as the scattered infection area distribution, complex background noises, and blurred segmentation boundaries. To this end, in this a...Show More