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

Stabilization of switched systems with unstable modes via mode-partition-dependent ADT

引用

Journal of the Franklin Institute 2023年第2期360卷 1308-1326页

作者： Jin, Cui-Li Wang, Qing-Guo Wang, Rui Wu, Di Key Laboratory of Intelligent Control and Optimization for Industrial Equipment of Ministry of Education and School of Control Science and Engineering Dalian University of Technology Dalian116024 China Institute of Artificial Intelligence and Future Networks Beijing Normal University at ZhuhaiGuangdong Key Lab of AI and Multi-Modal Data Processing BNU-HKBU United International College Zhuhai519087 China Key Laboratory of Advanced Technology for Aerospace Vehicles Liaoning Province and School of Aeronautics and Astronautics Dalian University of Technology Dalian116024 China

This paper concerns the stability of switched systems orchestrating between unstable modes. First, a mode partition is applied to select stabilizing switching from the switching between modes from different subsets. Second, a piecewise Lyapunov-like function is applied to decline at stabilizing switching times. Then, the stability criteria build on mode-partition-dependent average dwell time by collecting enough stabilizing switching behavior to stabilize the destabilizing switching behavior and unstable modes. Finally, the simulation verification shows the feasibility and effectiveness of the method. © 2022 The Franklin Institute

关键词： Stability criteria

来源：评论

学校读者我要写书评

暂无评论

Novel measuring techniques with applications in pattern classification and diagnostic process under Pythagorean fuzzy environment

Novel measuring techniques with applications in pattern clas...

引用

2023 International Conference on New Trends in Computational Intelligence, NTCI 2023

作者： Ejegwa, Paul Augustine Zhang, Yanxiong Li, Haiqing Feng, Yuming Institute of Intelligent Information Processing South China Business College Guangdong University of Foreign Studies Guangdong Guangzhou510545 China Joseph Sarwuan Tarka University Department of Mathematics Makurdi Nigeria Chongqing Three Gorges University Key Laboratory of Intelligent Information Processing and Control Chongqing Wanzhou404100 China

ISBN: (纸本)9798350380859

Distance and similarity measures are significant tools for information measure applicable in real-world under Pythagorean fuzzy domain. Some techniques for the computation of distance and similarity have been investigated between Pythagorean fuzzy sets (PFSs), notwithstanding with low performance indexes. To resolve these setbacks, this paper introduces some new measuring techniques with reliable performance in comparison to similar measures. The new techniques are confirmed with a number of theoretic results to illustrate their aptness as unfailing information measuring methods. Certain numerical experiments are carried out to ascertain the advantages of the proposed measures over the existing measures. We demonstrate the applications of the novel techniques in real-life decision-making situations pertaining to pattern recognition and disease diagnostic process where patterns and diseases are encapsulated in Pythagorean fuzzy pairs. © 2023 IEEE.

关键词： Fuzzy sets

来源：评论

学校读者我要写书评

暂无评论

Analysis of MFCS topology for high efficiency and long lifetime

Analysis of MFCS topology for high efficiency and long lifet...

引用

第43届中国控制会议

作者： Hongfu Xiang Jiajian Wu Zhen Wang Jie Wang Xi Li School of Artificial Intelligence and Automation Key Laboratory of Image Processing and Intelligent Control of Education MinistryHuazhong University of Science and Technology Shenzhen Huazhong University of Science and Technology Research Institute

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

Multi-stack fuel cell system(MFCS) are an important basis for large-scale application of solid oxide fuel cell(SOFC)technology,MFCS can provide higher system power and longer service *** the number of stacks increases,different topologies can be formed between stacks,including parallel structures and series structures,and the physical characteristics of MFCS will also *** this study,the degradation of the stacks is first considered,and the system model of series structure and parallel structure including the degradation of the stacks is *** parallel structure proposed in this paper is the key to ensure the high efficiency and long lifetime of *** the simulation of systems with different topologies,it is found that the power generation efficiency of the systems caused by the topologies varies greatly in different output power *** efficiency of the parallel structure in the low power stage is significantly better than that of the series structure,and the parallel structure is more conducive to the high efficiency of the system in the whole *** topological structures also have a greater impact on the degradation of *** degradation rates of stacks in parallel structures are close to each other,and the state of stacks is more *** overall life of the system in parallel structures is also better than that in series structures.

关键词： SOFC MFCS topological structure stack degradation

来源：评论

学校读者我要写书评

暂无评论

Expanding Hyperspherical Space for Few-Shot Class-Incremental Learning

Expanding Hyperspherical Space for Few-Shot Class-Incrementa...

引用

IEEE Workshop on Applications of Computer Vision (WACV)

作者： Yao Deng Xiang Xiang Key Lab of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China

In today’s ever-changing world, the ability of machine learning models to continually learn new data without forgetting previous knowledge is of utmost importance. However, in the scenario of few-shot class-incremental learning (FSCIL), where models have limited access to new instances, this task becomes even more challenging. Current methods use prototypes as a replacement for classifiers, where the cosine similarity of instances to these prototypes is used for prediction. However, we have identified that the embedding space created by using the relu activation function is incomplete and crowded for future classes. To address this issue, we propose the Expanding Hyperspherical Space (EHS) method for FSCIL. In EHS, we utilize an odd-symmetric activation function to ensure the completeness and symmetry of embedding space. Additionally, we specify a region for base classes and reserve space for unseen future classes, which increases the distance between class distributions. Pseudo instances are also used to enable the model to anticipate possible upcoming samples. During inference, we provide rectification to the confidence to prevent bias towards base classes. We conducted experiments on benchmark datasets such as CIFAR100 and miniimageNet, which demonstrate that our proposed method achieves state-of-the-art performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dynamic Neural Radiance Field From Defocused Monocular Video

arXiv

引用

arXiv 2024年

作者： Luo, Xianrui Sun, Huiqiang Peng, Juewen Cao, Zhiguo Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of AIA Huazhong University of Science and Technology China College of Computing and Data Science Nanyang Technological University Singapore

Dynamic Neural Radiance Field (NeRF) from monocular videos has recently been explored for space-time novel view synthesis and achieved excellent results. However, defocus blur caused by depth variation often occurs in video capture, compromising the quality of dynamic reconstruction because the lack of sharp details interferes with modeling temporal consistency between input views. To tackle this issue, we propose D2RF, the first dynamic NeRF method designed to restore sharp novel views from defocused monocular videos. We introduce layered Depth-of-Field (DoF) volume rendering to model the defocus blur and reconstruct a sharp NeRF supervised by defocused views. The blur model is inspired by the connection between DoF rendering and volume rendering. The opacity in volume rendering aligns with the layer visibility in DoF rendering. To execute the blurring, we modify the layered blur kernel to the ray-based kernel and employ an optimized sparse kernel to gather the input rays efficiently and render the optimized rays with our layered DoF volume rendering. We synthesize a dataset with defocused dynamic scenes for our task, and extensive experiments on our dataset show that our method outperforms existing approaches in synthesizing all-in-focus novel views from defocus blur while maintaining spatial-temporal consistency in the scene. Copyright © 2024, The Authors. All rights reserved.

关键词： Volume rendering

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

Cross-Domain Few-Shot Incremental Learning for Point-Cloud Recognition

Cross-Domain Few-Shot Incremental Learning for Point-Cloud R...

引用

IEEE Workshop on Applications of Computer Vision (WACV)

作者： Yuwen Tan Xiang Xiang Key Lab of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China

Sensing 3D objects is critical when 2D object recognition is not accessible. A robot pre-trained on a large point-cloud dataset will encounter unseen classes of 3D objects after deploying it. Therefore, the robot should be able to learn continuously in real-world scenarios. Few-shot class-incremental learning (FSCIL) requires the model to learn from few-shot new examples continually and not forget past classes. However, there is an implicit but strong assumption in the FSCIL that the distribution of the base and incremental classes is the same. In this paper, we focus on cross-domain FSCIL for point-cloud recognition. We decompose the catastrophic forgetting into base class forgetting and incremental class forgetting and alleviate them separately. We utilize the base model to discriminate base samples and new samples by treating base samples as in-distribution samples, and new objects as out-of-distribution samples. We retain the base model to avoid catastrophic forgetting of base classes and train an extra domain-specific module for all new samples to adapt to new classes. At inference, we first discriminate whether the sample belongs to the base class or the new class. Once classified at the model level, test samples are then passed to the corresponding model for class-level classification. To better mitigate the forgetting of new classes, we adopt the soft label and hard label replay together. Extensive experiments on synthetic-to-real incremental 3D datasets show that our proposed method can balance the performance between the base and new objects and outperforms the previous state-of-the-art methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Microgrid energy management strategy considering microgrid economy and rSOC stability: A model-based study

Microgrid energy management strategy considering microgrid e...

引用

第43届中国控制会议

作者： Haizhou Huang Zhiping Xia Xinkai Shan Jie Wang Xi Li School of Artificial Intelligence and Automation Key Laboratory of Image Processing and Intelligent Control of Education MinistryHuazhong University of Science and Technology Shenzhen Huazhong University of Science and Technology Research Institute

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

Microgrids possess the ability to use renewable energy efficiently and play an increasingly significant role in environmental protection and sustainable development. Meanwhile, reversible solid oxide fuel cell(rSOC) is currently a new type of energy conversion and storage. Combining with microgrid systems is a great way to benefit from its high capacity, high efficiency, and cleanliness. However, r SOC's complex system of coupled heat, electricity, and gas presents a significant challenge in finding energy management strategies for microgrid applications containing rSOC. In this study, for a microgrid system combining rSOC, battery energy storage system(BESS), solar photovoltaic(PV), and wind turbine generator(WTG), we propose a model-based energy management strategy that simultaneously takes into account the economy of the microgrid system and the stability of the rSOC system. First of all, the microgrid is modeled with great detail, including the wind turbine, solar panels, battery storage system, and rSOC. In addition, the microgrid energy management problem is framed as a mathematical programming problem, with the attention focusing on the costs of BESS aging and operational energy loss of rSOC. In particular,this study also proposes a penalty strategy to reduce the power fluctuation amplitude of the rSOC system and reduce the mode switching frequency of the rSOC system. Using the solver, solving for each device's target power in a microgrid. The actual power operating curve is output by tracking the target power under slope constraints using the Simulink model. We then conduct a case study using data from Wuhan, China. Our research shows that compared with the control strategy based on rule control,the control strategy proposed in this study can reduce the power variation amplitude of the rSOC system by 79%, reduce the mode switching frequency by 85%, reduce the system operating cost by 4.5% and increase the energy self-sufficiency rate by9%.

关键词： Microgrid Reversible solid oxide cell Multiple constraints Energy management system

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：