检索结果-内蒙古大学图书馆

Chinese Event Extraction Method Based on Roformer Model

Wireless Communications and Mobile Computing 2023年第1期2023卷

作者： Qiang, Baohua Zhou, Xiangyu Wang, Yufeng Yang, Xianyi Wang, Yuemeng Tian, Jubo Chen, Peng Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin University of Electronic Technology Guilin541004 China Hebei Key Laboratory of Intelligent Information Perception and Processing The 54th Research Institute of CETC Shijiazhuang050081 China

Event extraction is an important research direction in the field of natural language processing. The current Chinese event extraction field still suffers from errors in the pretraining and fine-tuning stages, inability to directly handle texts with more than 512 tokens, and inaccurate event extraction due to insufficient semantic sample diversity. In this paper, we propose a Chinese event extraction method RoformerFC (Roformer model with FGM and CRF) based on the Roformer model to address the above problems. Firstly, our method utilizes the Roformer model based on rotary position embedding, which both moderates the errors in the pretraining and fine-tuning phases and allows the model to directly handle texts with more than 512 tokens;then, the adversarial networks based on FGM (fast gradient method) are realized to increase the diversity of semantic feature samples;finally, the classical CRF (conditional random fields) model is used to decode and identify the event element entity and its corresponding event role and event type. On the short text DuEE dataset, the microP, microR, and microF of our method improved 1.26%, 4.01%, and 2.68%, respectively, over the classical Chinese event extraction method BERT-CRF. On the long text JsEE dataset, the microP, microR, and microF of our method improved 2.26%, 5.03%, and 3.72%, respectively, over the classical Chinese event extraction method BERT-CRF. © 2023 Baohua Qiang et al.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

The Research of Retinopathy image Recognition Method Based on Vit 5

The Research of Retinopathy Image Recognition Method Based o...

引用

5th International Conference on Artificial Intelligence and Pattern Recognition, AIPR 2022

作者： Xu, Zongyu Xu, Xuebin Huang, Zihao School of Computer Science and Technology Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Xi'an University of Posts and Telecommunications Shaanxi Xi'an710121 China

来源：评论

学校读者我要写书评

暂无评论

Multi-scale fusion residual encoder-decoder approach for low illumination image enhancement

引用

The Journal of China Universities of Posts and Telecommunications 2022年第2期29卷 63-72页

作者： Pan Xiaoying Wei Miao Wang Hao Jia Fengzhu School of Computer Science and Technology Xi'an University of Posts and TelecommunicationsXi'an 710121China Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Xi'an University of Posts and TelecommunicationsXi'an 710121China School of Software Northwestern Polytechnical UniversityXi'an 710072China

The sensing light source of the line scan camera cannot be fully exposed in a low light environment due to the extremely small number of photons and high noise,which leads to a reduction in image quality.A multi-scale fusion residual encoder-decoder(FRED)was proposed to solve the *** directly learning the end-to-end mapping between light and dark images,FRED can enhance the image’s brightness with the details and colors of the original image fully restored.A residual block(RB)was added to the network structure to increase feature diversity and speed up network ***,the addition of a dense context feature aggregation module(DCFAM)made up for the deficiency of spatial information in the deep network by aggregating the context’s global multi-scale *** experimental results show that the FRED is superior to most other algorithms in visual effect and quantitative evaluation of peak signal-to-noise ratio(PSNR)and structural similarity index measure(SSIM).For the factor that FRED can restore the brightness of images while representing the edge and color of the image effectively,a satisfactory visual quality is obtained under the enhancement of low-light.

关键词： image enhancement low illumination feature fusion residual network

来源：评论

学校读者我要写书评

暂无评论

Siamese Interaction and Fine-Tuning Representation of Chinese Semantic Matching Algorithm Based on RoBERTa-wwm-ext

引用

Mobile Information Systems 2023年第1期2023卷

作者： Qiang, Baohua Xi, Guangyong Wang, Yufeng Yang, Xianyi Wang, Yuemeng Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin University of Electronic Technology Guilin541004 China Hebei Key Laboratory of Intelligent Information Perception and Processing The 54th Research Institute of CETC Shijiazhuang050081 China

Semantic matching research is the cornerstone of research in the fields of natural language similarity measurement and sensor ontology matching (OM). In the existing Chinese semantic matching methods, there are some shortcomings, such as the single dimension of semantic expression, the insufficient expression of context semantic relations, and the insufficient interaction of semantic information between different sentences. This paper proposes a Chinese semantic matching algorithm based on RoBERTa-wwm-ext with Siamese interaction and fine-tuning representation (RSIFR). The RSIFR model initializes the model with RoBERTa-wwm-ext as a vector of text. Firstly, a Siamese structure with embedded soft alignment attention mechanism and BiLSTM is constructed to realize the information interaction between two sentences. Secondly, LSTM-BiLSTM network structure is constructed to enhance the expression of semantic logic before and after sentences. Then, build a training model with fine-tuning mechanism. Fine tune the text's eigenvector parameters through label supervision. Finally, the fusion vectors of the sentence pairs are inserted into the MLP network layer, resulting in semantic matching results. RSIFR model starts from a variety of dimensions, strengthens the expression ability of vectors to text semantic relations, deeply mines the semantic similarities and differences between different sentences, and generally improves the Chinese semantic matching performance. Experiments on the public dataset LCQMC show that our model outperforms existing Chinese semantic matching models. © 2023 Baohua Qiang et al.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Tomato Leaf Disease Identification and Growth Dataset Augmentation Based on UAE-GAN

Tomato Leaf Disease Identification and Growth Dataset Augmen...

引用

International Conference on intelligent Control and Information processing (ICICIP)

作者： Xin Li Fang Li Xiaonan Luo School of Computer Science and Information Security Guilin University of Electronic Technology Guilin China Center for Applied Mathematics of Guangxi (GUET) Guilin China Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin China Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin University of Electronic Technology Guilin China

ISBN: (数字)9798331516147

ISBN: (纸本)9798331516154

To delve into the characterization of growth disorders in different crops, it is important to support the model with a large amount of image data that includes a variety of disease types and disease levels to capture the typical and subtle differences of various diseases on plant leaves. However, the actual process of gathering data is challenging, sample coverage is challenging to accomplish, data capture is impeded, and the quality of the data is subpar. This work aims to address the issue of data shortages by employing technical methods. In particular, we creatively investigated the UAE-GAN approach, which naturally combines CycleGAN, U-Net, Variational Autoencoder VAE, and Autoencoder to increase the data. Among these, U-Net can precisely extract the small details of disease locations in crop photos and provide a strong basis for further processing thanks to its special codec architectural benefits. The Variational Autoencoder (VAE) significantly enhances the diversity of data by mapping the image to the latent space and sampling based on a certain probability distribution, so producing new image samples that are distinct from the original image yet inherently connected. Learning the coding and decoding of the original image is the foundation of autoencoders. If a mild disruption is introduced into the coding process, it can achieve data augmentation in another dimension and create a sequence of new images with just little modifications to the original image. The aforementioned models are closely linked with CycleGAN to efficiently map and convert in a variety of picture domains and to fully leverage CycleGAN's remarkable unsupervised image conversion capabilities. The perception ability, feature capture ability, and information conversion ability of the fusion model for crop image data are significantly improved, and the key elements of each link in the data enhancement process are comprehensively considered to ensure that the generated new image data can not o

关键词： Training image coding Autoencoders Data enhancement Crops Generators Data models Stability analysis Probability distribution Diseases

来源：评论

学校读者我要写书评

暂无评论

DreamLayer: Simultaneous Multi-Layer Generation via Diffusion Model

arXiv

引用

arXiv 2025年

作者： Huang, Junjia Yan, Pengxiang Cai, Jinhang Liu, Jiyang Wang, Zhao Wang, Yitong Wu, Xinglong Li, Guanbin Sun Yat-sen University China ByteDance Intelligent Creation Peng Cheng Laboratory China Guangdong Key Laboratory of Big Data Analysis and Processing China

Text-driven image generation using diffusion models has recently gained significant attention. To enable more flexible image manipulation and editing, recent research has expanded from single image generation to transparent layer generation and multi-layer compositions. However, existing approaches often fail to provide a thorough exploration of multi-layer structures, leading to inconsistent inter-layer interactions, such as occlusion relationships, spatial layout, and shadowing. In this paper, we introduce DreamLayer, a novel framework that enables coherent text-driven generation of multiple image layers, by explicitly modeling the relationship between transparent foreground and background layers. DreamLayer incorporates three key components, i.e., Context-Aware Cross-Attention (CACA) for global-local information exchange, Layer-Shared Self-Attention (LSSA) for establishing robust inter-layer connections, and Information Retained Harmonization (IRH) for refining fusion details at the latent level. By leveraging a coherent full-image context, DreamLayer builds inter-layer connections through attention mechanisms and applies a harmonization step to achieve seamless layer fusion. To facilitate research in multi-layer generation, we construct a high-quality, diverse multi-layer dataset including 400k samples. Extensive experiments and user studies demonstrate that DreamLayer generates more coherent and well-aligned layers, with broad applicability, including latent-space image editing and image-to-layer decomposition. Copyright © 2025, The Authors. All rights reserved.

关键词： image fusion

来源：评论

学校读者我要写书评

暂无评论

Prescribed Performance Control of Mobile Wheeled Inverted Pendulum Systems under Arbitrary Initial Conditions 8

Prescribed Performance Control of Mobile Wheeled Inverted Pe...

引用

8th IEEE International Conference on Advanced Robotics and Mechatronics, ICARM 2023

作者： Zhang, Mengshi Cao, Yu Yang, Bo Huang, Jian School of Artificial Intelligence and Automation Huazhong University of Science and Technology Key Laboratory of the Ministry of Education for Image Processing and Intelligent Control Wuhan430074 China Shenzhen Huazhong University of Science and Technology Research Institute ShenZhen518060 China

ISBN: (纸本)9798350300178

Mobile wheeled inverted pendulum (MWIP) is a typical naturally unstable underactuated system and it is very necessary to constrain its transient response to improve the overall safety. Prescribed performance control (PPC) is an effective method, however the system initial conditions are usually required to be known and constraint, otherwise it can lead to singularity problems. In practical systems, it is often difficult to obtain the exact initial state leading to limitations in the application of PPC. To overcome this issue, this paper presented a composite error transformation function to address the problem of initial condition dependence. A continuous bounded function was designed to compress the arbitrary initial error into the predefined bound to avoid singularities. After a set time, it was degraded to an original system error. Based on this composite transformation, a state feedback controller was proposed for the underactuated MWIP system to achieve the constraint outputs. Then, by employing the Lyapunov theorem, it was guaranteed that the closed-loop system would remain stable. Various numerical simulations under different initial conditions were carried out to prove the validity of the proposed controller. © 2023 IEEE.

关键词： Closed loop systems

来源：评论

学校读者我要写书评

暂无评论

Gland segmentation based on morphological clues and feature fusion

Gland segmentation based on morphological clues and feature ...

引用

image processing, Computer Vision and Machine Learning (ICICML), International Conference on

作者： Lingqi Zeng Huadeng Wang Junlin Guan Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin University of Electronic Technology Guilin China

The task of gland segmentation based on deep learning serves as a crucial auxiliary tool for diagnosing cancer. However, existing methods still exhibit shortcomings in handling gland adhesion and scale adaptability. To address these issues, we propose a gland segmentation approach that leverages morphological cues and multi-level feature fusion. By analyzing the morphological and imaging characteristics of glands, we have devised a novel scheme for label generation and loss weighting to guide model training. This scheme helps alleviate the challenge posed by the presence of adjacent glands and their adhesion. Additionally, by exploring the correlation between semantic features at different levels, we have developed a new feature fusion mechanism to mitigate issues related to model inaccuracies arising from variations in gland scales. Through experimental comparisons and discussions with classical and state-of-the-art methods, we demonstrate the effectiveness of our proposed approach.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Texture Features and Machine Learning Based Environmental Microorganism Microscopic image Classification

Texture Features and Machine Learning Based Environmental Mi...

引用

International Conference on image, Vision and intelligent Systems, ICIVIS 2023

作者： Ouyang, Xinyu Yuan, Huaqian Zhou, Shangqi Fu, Yanyu Yang, Jinzhu Grzegorzek, Marcin Wang, Yuexi Li, Chen Microscopic Image and Medical Image Analysis Group College of Medicine and Biological Information Engineering Northeastern University Shenyang China Key Laboratory of Intelligent Computing in Medical Image Ministry of Education Northeastern University Shenyang China Institute of Medical Informatics University of Luebeck Luebeck Germany Department of Knowledge Engineering University of Economics in Katowice Katowice Poland Department of Rehabilitation Shengjing Hospital of China Medical University Shenyang China

ISBN: (纸本)9789819708543

In recent years, with the continuous development of molecular biology technology, the effective use of environmental microorganisms to solve the problem of pollution in the ecological environment has been widely used. However, the original microbial cultivation, environmental application and monitoring have the disadvantages of high degree of specialization, long time and high cost. In this case, the use of computer image processing and machine learning techniques for microbial identification and classification becomes a more efficient, economical and necessary method. This paper presents an environmental microorganism microscopic image classification method based on texture features and machine learning. In the research and experiments, microscopic images of microorganisms are cropped, grayed, data augmented, target areas segmented and extracted four types of texture features. The training set and test set are divided in a 1:1 ratio, and different recognition results are obtained based on different texture feature vectors and classifier models. Ultimately, the gradient-gray co-occurrence matrix feature combined with the Random Forest algorithm classifier achieves an F1-measure value of nearly 40%, which improves the work efficiency of environmental microbial researchers and related field workers. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Microorganisms

来源：评论

学校读者我要写书评

暂无评论

A flexible organohydrogel-based humidity sensor for noncontact artificial sensation

引用

Science China(Technological Sciences) 2022年第1期65卷 191-200页

作者： ZHANG Yu LI Chen YANG Han ZHAO Rui CHEN XinJian NIE BaoQing HU Liang Medical Image Processing Analysis and Visualization(MIPAV)School of Electronic and Information EngineeringSoochow UniversitySuzhou 215000China State Key Laboratory of Radiation Medicine and Protection School for Radiological and Interdisciplinary Sciences(RAD-X)and Collaborative Innovation Center of Radiation Medicine of Jiangsu Higher Education InstitutionsSoochow UniversitySuzhou 215000China

In this paper,we propose a simple organohydrogel based capacitive humidity sensor for noncontact artificial sensation *** sensor is simple in design and consists of a transparent polyacrylamide organohydrogel thin film attached on a flexible inter-digit electrode *** process of water absorption and desorption is reversible,thus the dielectric of the organohydrogel film as well as the overall capacitance is dependent on environmental *** water absorption capacity and structural reliability of the device have been largely improved by adding glycerol in the organohydrogel *** optimizing both the glycerol concentration and organohydrogel film thickness,the sensor can respond to cyclic humidity changes in a period of 300 *** addition,this sensor achieves a high relative capacitance increase(by 20 folds)in a wide relative humidity range(12%-95%).The sensor also exhibits high stability under different bending curvatures(up to 6.81 mm),wide temperature changes(20℃-40℃)and external pressures(0-8 N).To demonstrate the applications in wearable electronics,we found that the sensor was successful in detecting respiration intensity and rate as well as the difference in moisture content in various objects,i.e.,human skin and leaf *** sensor is highly sensitive and can be useful in the detection of the widerange of humidity changes.

关键词： humidity sensor organohydrogel wearable electronics

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：