检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Li, Yudong Feng, Yuhao Zhou, Wen Zhao, Zhe Shen, Linlin Hou, Cheng Hou, Xianxu School of Computer Science and Software Engineering Shenzhen University China Tencent AI Lab China LIESMARS Wuhan University China School of AI and Advanced Computing Xi’an Jiaotong-Liverpool China

Large Language Models (LLMs) have gained significant attention in the field of natural language processing (NLP) due to their wide range of applications. However, training LLMs for languages other than English poses significant challenges, due to the difficulty in acquiring large-scale corpus and the requisite computing resources. In this paper, we propose ChatFlow, a cross-language transfer-based LLM, to address these challenges and train large Chinese language models in a cost-effective manner. We employ a mix of Chinese, English, and parallel corpus to continuously train the LLaMA2 model, aiming to align cross-language representations and facilitate the knowledge transfer specifically to the Chinese language model. In addition, we use a dynamic data sampler to progressively transition the model from unsupervised pre-training to supervised fine-tuning. Experimental results demonstrate that our approach accelerates model convergence and achieves superior performance. We evaluate ChatFlow on popular Chinese and English benchmarks, the results indicate that it outperforms other Chinese models post-trained on LLaMA-2-7B. © 2024, CC BY.

关键词： Cost effectiveness

来源：评论

学校读者我要写书评

暂无评论

Transient Stability of Transmission and Distribution Grids with Grid-Forming Inverter-Based Resources: Phasor Domain Modeling

Transient Stability of Transmission and Distribution Grids w...

引用

IEEE General Meeting Power& Energy Society

作者： Xuheng Lin Ziang Zhang Reza Pourramezan Department of Electrical and Computer Engineering Binghamton University - Suny Binghamton NY U.S.A. Advanced Grid Innovation Lab for Energy New York Power Authority Albany NY USA

ISBN: (数字)9798350381832

ISBN: (纸本)9798350381849

This paper presents phasor domain models for three distinct grid-forming (GFM) control strategies applied to inverter-based resources (IBR), including droop-based control, virtual synchronous machine (VSM) control, and dispatchable virtual oscillator control (dVOC). These control strategies address stability issues in low-inertia power systems, a prominent challenge amid the transition to renewable energy. The study addresses a research gap by investigating real-time phasor models for comprehensive renewable energy integration assessments, particularly in transmission and distribution systems (T&D), offering computational efficiency and precision. Two key contributions outlined by this paper include the development of a unified GFM phasor-domain model for real-time grid-level stability analysis and the introduction of a T&D co-simulation approach using the ePHASORSIM solver to explore the impact of different levels of IBR penetration on the stability of the system after a fault. This study aims to provide a better understanding of the generator-IBR interaction on T&D systems, offering a new tool for system planning and analysis.

关键词： Renewable energy sources Computational modeling Power system stability Stability analysis Real-time systems Planning Transient analysis Synchronous machines Oscillators Grid forming

来源：评论

学校读者我要写书评

暂无评论

A Trade-Off Study Between the Primary and Transient Responses of Grid-Forming Inverters

A Trade-Off Study Between the Primary and Transient Response...

引用

Annual Conference of Industrial Electronics Society

作者： Xuheng Lin Xiaoge Huang Ziang Zhang Reza Pourramezan Department of Electrical and Computer Engineering Binghamton University - SUNY Binghamton NY U.S.A. Advanced Grid Innovation Lab for Energy New York Power Authority Albany NY USA

ISBN: (数字)9781665464543

ISBN: (纸本)9781665464550

The control parameters of the grid-forming (GFM) inverter-based resources (IBRs) directly impact power system dynamics. The primary control requires the GFM inverter to balance generation and load. It is also preferred that a GFM inverter maintain the terminal frequency after a power system fault. In this paper, we investigate the trade-off between the primary control objective and the transient response. To quantify the transient performance of the GFM inverter, we introduce a new real-time transient stability index (TSI). This index plays a crucial role in our investigation, as it allows us to compare the performance trade-offs of different sets of GFM control parameters.

关键词： Transient response Stability criteria Reinforcement learning Power system stability Inverters Real-time systems Indexes Transient analysis Inverter-based resource Grid forming

来源：评论

学校读者我要写书评

暂无评论

Modified U-Net Architeture based Ischemic Stroke Lesions Segmentation 21

Modified U-Net Architeture based Ischemic Stroke Lesions Seg...

引用

21st IEEE International Conference on Sciences and Techniques of Automatic Control and computer engineering, STA 2022

作者： Abdmouleh, Nabil Echtioui, Amira Kallel, Fathi Hamida, Ahmed Ben Advanced Technologies for Medicine and Signals ENIS Sfax University ATMS Lab Sfax Tunisia National Engineering School of Electronics and Communications Sfax University Tunisia College of Computer Science King Khaled University 'KKU' Department Is Saudi Arabia

ISBN: (纸本)9781665482615

An ischemic stroke transpires when part of the brain tissue is unable to get oxygen and nutrients due to the interruption or the reduction of blood supply. A stroke is a medical emergency that can lead to serious complications if left untreated. Early action can reduce potential brain damage and other consequences. Therefore, quantitative assessment of ischemic stroke lesions using magnetic resonance imaging (MRI) is paramount for an accurate and decisive diagnosis. However, a diagnosis of hundreds of MRI-generated slices by trained specialists is time-consuming and requires painstaking attention to details. Automating this process using advanced image segmentation methods allows an exact localization of the tissue presenting lesions and provide an approximation of its volume. Automatic detection of lesions provides faster answers and better assessments to assist medical practitioners. In this paper, we propose a novel method for ischemic stroke lesions detection based on a modified UNet architecture. We use the data from 2015 Ischemic Stroke Lesion Segmentation Challenge (ISLES 2015) for performance evaluation of our proposed method. Experiments have shown that the latter outperforms the state-of-the-art methods. © 2022 IEEE.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Research of Intelligent Fault Diagnosis Based on Machine Learning 4

Research of Intelligent Fault Diagnosis Based on Machine Lea...

引用

4th International Conference on computer Network, Electronic and Automation, ICCNEA 2021

作者： Ding, Ziwei Zhou, Jiangwei Liu, Bailin Bai, Wanmin School Of Computer Science And Engineering Xi'an Technological University Xi'an710021 China State And Provincial Joint Engineering Lab Of Advanced Network Monitoring And Control Xi'an710021 China

ISBN: (纸本)9781665444866

Large-scale equipment in different industries is becoming more and more electronic, complicated and integrated. In order to provide technical support for the normal operation of industrial equipment, fault diagnosis becomes extremely important. Intelligent fault diagnosis, as the name suggests, is to combine fault diagnosis and artificial intelligence theory to replace traditional fault diagnosis methods in a smarter way to obtain more accurate diagnosis results. Machine learning has become a current technical hotspot. In view of its advantages in efficiently extracting information and processing large amounts of data, more and more attention has been paid in the field of fault diagnosis. This paper systematically introduces the related concepts of machine learning and fault diagnosis, and summarizes fault diagnosis methods and applications based on support vector machines and neural networks. Finally, this paper makes a further outlook on the development of intelligent fault diagnosis technology based on machine learning. © 2021 IEEE.

关键词： Failure analysis

来源：评论

学校读者我要写书评

暂无评论

Research and Design of Decimal Network DDNS 4

Research and Design of Decimal Network DDNS

引用

4th International Conference on computer Network, Electronic and Automation, ICCNEA 2021

作者： Wang, Zhongsheng Liu, Zhang School Of Computer Science And Engineering Xi'an Technological University Xi'an710021 China State And Provincial Joint Engineering Lab. Of Advanced Network Monitoring And Control Xi'an China

ISBN: (纸本)9781665444866

Internet domain name is consists of characters, numbers, or both of them. when a client access to a website, it first send a request to local domain name server (DNS), if there is no record, local DNS request to higher authorities, until the root name servers, and get the correct record after return to local, and the cache to the local server, the process logic is complex. It's expensive in time and space. Decimal Network digital domain name system(DDNS) can directly find the target network terminal through the routing rules, without the need for domain name resolution and other conversion process, and then quickly establish the connection, reducing the scale of routing table of each forwarding node in the network, thus saving huge time and space costs. This paper introduces the concept of digital domain name system, the structure of digital domain name system, the grammar and extension of digital domain name system, the mapping of digital domain name system and IP address, and the resource record in digital domain name system. It will show the characteristics and advantages of digital domain name in a more comprehensive and detailed way. © 2021 IEEE.

关键词： Internet protocols

来源：评论

学校读者我要写书评

暂无评论

Research of Image De-noising Based on Deep Learning

Research of Image De-noising Based on Deep Learning

引用

International Conference on computer Network, Electronic and Automation (ICCNEA)

作者： Kai Li Zhongsheng Wang School of Computer Science and Engineering Xi’an Technological University Xi’an China State and Provincial Joint Engineering Lab. of Advanced Network Monitoring and Control Xi'an Technological University Xi'an China

Image denoising is a technology to restore the image by changing the information before and after the image sequence. The restored image will become very clear, and it is used a lot now. Due to the imperfect equipment, when the image is transmitted, it will be affected by noise, thus losing the original details. In order to solve this problem and make the noise image clear and obvious, this paper proposes an image denoising method based on deep learning, and constructs the image denoising network structure based on convolutional neural network. At the same time, the directional propagation algorithm is optimized to speed up the training speed of the model and effectively improve the denoising effect. By comparing the experimental data of the classical algorithm experiment, it is concluded that this study has achieved a better denoising effect. Finally, the key issues of image denoising research are summarized, and the development trend of future research in this field is discussed.

关键词：

来源：评论

学校读者我要写书评

暂无评论

SimiDTR: Deep Trajectory Recovery with Enhanced Trajectory Similarity 28th

SimiDTR: Deep Trajectory Recovery with Enhanced Trajectory ...

引用

28th International Conference on Database Systems for advanced Applications, DASFAA 2023

作者： Zhang, Yupu Deng, Liwei Zhao, Yan Chen, Jin Xie, Jiandong Zheng, Kai University of Electronic Science and Technology of China Chengdu China School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China Shenzhen Institute for Advanced Study University of Electronic Science and Technology of China Chengdu China Department of Computer Science Aalborg University Aalborg Denmark Cloud Database Innovation Lab of Cloud BU Huawei Technologies Co. Ltd. Chengdu China

ISBN: (纸本)9783031306365

The pervasiveness of GPS-equipped smart devices and the accompanying deployment of sensing technologies generates increasingly massive amounts of trajectory data that cover applications such as personalized location recommendation and urban transportation planning. Trajectory recovery is of utmost importance for incomplete trajectories (resulted from the constraints of devices and environment) to enable their completeness and reliability. To achieve effective trajectory recovery, we propose a novel trajectory recovery framework, namely Deep Trajectory Recovery with enhanced trajectory Similarity (SimiDTR), which is capable of contending with the complex mobility regularity found in trajectories in continuous space. In particular, we design a rule-based information extractor to extract the spatial information related to an incomplete trajectory, which is then fed into a deep model based on attention mechanism to generate a tailored similar trajectory for the incomplete trajectory. Finally, we use a deep neural network model to recover the incomplete trajectory with the blessing of its similar trajectory. An extensive empirical study with real data offers evidence that the framework is able to advance the state of the art in terms of effectiveness for trajectory recovery, especially in scenes with sparse trajectory data. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Recovery

来源：评论

学校读者我要写书评

暂无评论

Interpretive Clinical Measurements Prediction and Diagnosis in ICU with Multi-Task Attention-Guided Sequential Feature Learning 7

Interpretive Clinical Measurements Prediction and Diagnosis ...

引用

7th Asian Conference on Artificial Intelligence Technology, ACAIT 2023

作者： Zhao, Peng Xiao, Yan Lei, Yuqing Ren, Yazhou Xu, Zenglin Chongqing Medical University School of Basic Medical Sciences Chongqing China University of Electronic Science And Technology of China School of Computer Science And Engineering Chengdu China University of Electronic Science And Technology of China Shenzhen Institute For Advanced Study Shenzhen China Harbin Institute of Technology Shenzhen School of Computer Science And Technology Shenzhen China Peng Cheng National Lab Center of Artificial Intelligence Shenzhen China

ISBN: (纸本)9798350359145

During the outbreak of COVID-19, it is particularly important to improve clinical decision making for critically ill patients in intensive care units (ICU). Machine learning has become increasingly important in healthcare analysis with the wide adoption of Electronic Health Records (EHR). Many deep learning algorithms, such as Recurrent Neural Networks (RNNs), have been developed to deal with clinical time series data to predict the health status of patients, such as mortality, ventilation, and phenotype, etc. Despite RNN being successful in medical tasks, the special traits of data, such as long temporality, high dimensionality, existence of missing values, and multi-labels, have brought challenges to either shallow or deep learning algorithms. Motivated by the fact that the progress of diseases may vary over time, to address these challenges, we proposed a multi-task attention-guided recurrent neural network for learning sequential features (MASFL) model, which employs recurrent units and an attention mechanism. The recurrent units can memorize the past progressive information of patients after entering ICU, while the attention mechanism can selectively utilize this information for different prediction tasks. Meanwhile, the attention also helps to interpret the relationship between the clinical time series data and the prediction result. Furthermore, in order to solve undesirable local solutions for the patient's length-of-stay task, we develop an ordinal regression loss to address the issue. According to the experiments on MIMIC-III, we demonstrate that the proposed model can improve the prediction performance over state-of-the-art prediction approaches. © 2023 IEEE.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

AsyFOD: An Asymmetric Adaptation Paradigm for Few-Shot Domain Adaptive Object Detection

AsyFOD: An Asymmetric Adaptation Paradigm for Few-Shot Domai...

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Yipeng Gao Kun-Yu Lin Junkai Yan Yaowei Wang Wei-Shi Zheng School of Computer Science and Engineering Sun Yat-sen University China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China Pengcheng Lab

In this work, we study few-shot domain adaptive object detection (FSDAOD), where only a few target labeled images are available for training in addition to sufficient source labeled images. Critically, in FSDAOD, the data scarcity in the target domain leads to an extreme data imbalance between the source and target domains, which potentially causes over-adaptation in traditional feature alignment. To address the data imbalance problem, we propose an asymmetric adaptation paradigm, namely AsyFOD, which leverages the source and target instances from different perspectives. Specifically, by using target distribution estimation, the AsyFOD first identifies the target-similar source instances, which serves to augment the limited target instances. Then, we conduct asynchronous alignment between target-dissimilar source instances and augmented target instances, which is simple yet effective for alleviating the over-adaptation. Extensive experiments demonstrate that the proposed AsyFOD outperforms all state-of-the-art methods on four FSDAOD benchmarks with various environmental variances, e.g., 3.1% mAP improvement on Cityscapes-to-FoggyCityscapes and 2.9% mAP increase on Sim10k-to-Cityscapes. The code is available at https://***/Hlings/AsyFPD.

关键词：

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：