检索结果-内蒙古大学图书馆

10th IEEE International Conference on Cyber Security and Cloud Computing and 9th IEEE International Conference on Edge Computing and Scalable Cloud, CSCloud-EdgeCom 2023

作者： Yiwen, Liu Zhirong, Zhu Tangyan Wenkan, Wen Xiaoning, Peng Yuanquan, Shi Huaihua University School of Computer and Artificial Intelligence Huaihua Hunan418000 China Application in Hunan Province Universities Key Laboratory of Wuling-Mountain Health Big Data Intelligent Processing Huaihua Hunan418000 China Key Laboratory of Intelligent Control Technology for Wuling-Mountain Ecological Agriculture in Hunan Province Huaihua Hunan418000 China

ISBN: (纸本)9798350312461

In this paper, we propose a logistics International Inland Port resource allocation method based on intelligent edge scheduling, and we do a reasonable pre-allocation of logistics resources by building an edge network in the urban system. By using multiple integrated learning models and regional prevalence classification algorithms, the distribution demand of each sub-distribution point is predicted. The proposed method is able to cope with uncertainties such as high distribution volume, variable distribution situations or long transportation distances. We use the HuaiHua International Inland Port as the simulation object, and the simulation results show that the proposed method has the highest efficiency in logistics distribution and is still highly adaptive in emergency situations. © 2023 IEEE.

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

A Co-caching Strategy for Edges Based on Federated Learning and Regional Prevalence 1

引用

3rd EAI International Conference on Edge Computing and IoT, EAI ICECI 2022

作者： Zhu, Zhirong Liu, Yiwen Gao, Yanxia Wen, Wenkan Shi, Yuanquan Peng, Xiaoning School of Computer and Artificial Intelligence Huaihua University Hunan Huaihua418000 China Key Laboratory of Wuling-Mountain Health Big Data Intelligent Processing and Application in Hunan Province Universities Hunan Huaihua418000 China Key Laboratory of Intelligent Control Technology for Wuling-Mountain Ecological Agriculture in Hunan Province Hunan Huaihua418000 China

ISBN: (数字)9783031289903

ISBN: (纸本)9783031289897

With the rise of data storage computing and IoT technology. The increase in data volume and user demand, the accurate delivery of data and low latency during transmission become important factors that affect the end-user experience. To address this issue, previous authors have proposed the concept of edge computings. In the general environment of edge computing, reasonable scheduling of edge caches can largely achieve low latency and high efficiency, thus improving user experience. In this paper, based on existing research, we propose a combination of a joint learning framework for cache prediction based on region popularity and an edge collaborative cache value optimization method to further improve cache hit rate and cache utilization efficiency. The method obtains excellent expected results through simulation experiments. © 2023, ICST Institute for computer Sciences, Social Informatics and Telecommunications Engineering.

关键词： Edge computing

来源：评论

学校读者我要写书评

暂无评论

InferAligner: Inference-Time Alignment for Harmlessness through Cross-Model Guidance

arXiv

引用

arXiv 2024年

作者： Wang, Pengyu Zhang, Dong Li, Linyang Tan, Chenkun Wang, Xinghao Ren, Ke Jiang, Botian Qiu, Xipeng School of Computer Science Fudan University China Shanghai Key Laboratory of Intelligent Information Processing Fudan University China

With the rapid development of large language models (LLMs), they are not only used as general-purpose AI assistants but are also customized through further fine-tuning to meet the requirements of different applications. A pivotal factor in the success of current LLMs is the alignment process. Current alignment methods, such as supervised fine-tuning (SFT) and reinforcement learning from human feedback (RLHF), focus on training-time alignment and are often complex and cumbersome to implement. Therefore, we develop InferAligner, a novel inference-time alignment method that utilizes cross-model guidance for harmlessness alignment. InferAligner utilizes safety steering vectors extracted from safety-aligned model to modify the activations of the target model when responding to harmful inputs, thereby guiding the target model to provide harmless responses. Experimental results show that our method can be very effectively applied to domain-specific models in finance, medicine, and mathematics, as well as to multimodal large language models (MLLMs) such as LLaVA. It significantly diminishes the Attack Success Rate (ASR) of both harmful instructions and jailbreak attacks, while maintaining almost unchanged performance in downstream tasks. Copyright © 2024, The Authors. All rights reserved.

关键词： Alignment

来源：评论

学校读者我要写书评

暂无评论

Pattern Reconfigurable MIMO Antenna Based on Characteristic Mode Theory 4

Pattern Reconfigurable MIMO Antenna Based on Characteristic ...

引用

4th International Applied Computational Electromagnetics Society Symposium in China, ACES-China 2021

作者： Tian, Minmin Cheng, G.S. Sun, Y.T. Huang, Z.X. Auhui University Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Hefei230601 China

ISBN: (纸本)9781733509619

A pattern reconfigurable dual-port multiple-input multiple-output (MIMO) antenna system utilizing Characteristic mode theory is proposed at 2.45GHz. By using the selective incentives of four characteristic modes, six pairs of balanced inductive exciter (BIEs) and the antenna are integrated to realize the selective incentives of the four patterns. In the feeder network, by changing the state of the PIN diode, the two ports realize selective incentive to obtain four working states. The test results show that the pattern reconfiguration technique is reliable and can be used in other types of structures. © 2021 Applied Computational Electromagnetics Society (ACES).

关键词： MIMO systems

来源：评论

学校读者我要写书评

暂无评论

A Chinese Sentiment Analysis Model Incorporating Knowledge Graph and Deep Learning 7

A Chinese Sentiment Analysis Model Incorporating Knowledge G...

引用

7th International Conference on Electrical, Mechanical and computer Engineering, ICEMCE 2023

作者： Zhao, Shengping Chen, Jinlong Qin, Xingguo School of Computer Science and Information Security Guilin University of Electronic Technology Guilin China School of Computer Science and Information Security Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin University of Electronic Technology Guangxi Guilin541004 China

ISBN: (纸本)9798350382877

With the rapid growth of social media and e-commerce, users are generating large amounts of textual review data on these platforms. Analyzing and mining these comment data is important for governments, enterprises, and consumers to make decisions. Therefore, sentiment analysis, especially for Chinese comments, has become an area of wide interest in industry and academia. Aiming at the characteristics of Chinese online reviews, this paper applies the techniques of knowledge graph and deep learning around sentence-level sentiment analysis and designs a sentiment analysis model that integrates different information such as sentiment knowledge graph and serialized annotation in a deep learning model to improve the accuracy and effectiveness of sentiment analysis of Chinese online reviews. This is important for improving products and services, understanding user needs, and making more informed business and policy decisions. © 2023 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Artificial intelligence-based pathological analysis of liver cancer:Current advancements and interpretative strategies

引用

iLIVER 2024年第1期3卷 82-89页

作者： Guang-Yu Ding Jie-Yi Shi Xiao-Dong Wang Bo Yan Xi-Yang Liu Qiang Gao Department of Liver Surgery and Transplantation Liver Cancer InstituteZhongshan HospitalShanghai 200032China Key Laboratory of Carcinogenesis and Cancer Invasion of Ministry of Education Fudan UniversityShanghai 200032China School of Computer Science and Technology Xidian UniversityXi'an 710126China School of Computer Science Shanghai Key Laboratory of Intelligent Information ProcessingFudan UniversityShanghai 200433China Institute of Biomedical Sciences Fudan UniversityShanghai 200030China State Key Laboratory of Genetic Engineering Fudan UniversityShanghai 200433China

In recent years,significant advances have been achieved in liver cancer management with the development of artificial intelligence(AI).AI-based pathological analysis can extract crucial information from whole slide images to assist clinicians in all aspects from diagnosis to prognosis and molecular ***,AI techniques have a“black box”nature,which means that interpretability is of utmost importance because it is key to ensuring the reliability of the methods and building trust among clinicians for actual clinical *** this paper,we provide an overview of current technical advancements in the AI-based pathological analysis of liver cancer,and delve into the strategies used in recent studies to unravel the“black box”of AI's decision-making process.

关键词： Liver cancer Artificial intelligence Pathology Interpretative model

来源：评论

学校读者我要写书评

暂无评论

STMAD:A Simple Multimodal Anomaly Detection for Thyroid Medical Information 17

STMAD:A Simple Multimodal Anomaly Detection for Thyroid Medi...

引用

17th International Congress on Image and signal processing, BioMedical Engineering and Informatics, CISP-BMEI 2024

作者： Xu, Wentong Fu, Chao Yu, Jing Si, Caifeng Li, Zuoyong Li, Chaochao Fan, Haoyi School of Computer and Artificial Intelligence Zhengzhou University Zhengzhou450001 China First Affiliated Hospital of Zhengzhou University Department of Ultrasound Henan Zhengzhou450052 China School of Computer and Big Data Minjiang University Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Fuzhou350121 China

ISBN: (纸本)9798331507398

Anomaly detection has been widely explored by training an out-of-distribution detector with only normal data. Medical image analysis, as a common tool, faces the challenge of how to further enhance the detection performance for thyroid cancer, especially with the application of various deep learning methods in the thyroid-related field. In this paper, we validate the effectiveness of sonographic feature descriptions (textual information) for thyroid cancer diagnosis. Building on this, we propose a simple multimodal self-supervised framework that leverages both textual and image modalities for thyroid cancer anomaly detection. Results on a private dataset demonstrate the effectiveness and superiority of our proposed method compared to advanced methods. © 2024 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Hybrid of Spans and Table-Filling for Aspect-Level Sentiment Triplet Extraction 30

Hybrid of Spans and Table-Filling for Aspect-Level Sentiment...

引用

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Nuo, Minghua Guo, Chaofan College of Computer Science Inner Mongolia University Inner Mongolia Hohhot010021 China National & Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian Inner Mongolia Hohhot010021 China Inner Mongolia Key Laboratory of Mongolian Information Processing Technology Inner Mongolia Hohhot010021 China

ISBN: (纸本)9782493814104

Aspect Sentiment Triplet Extraction (ASTE) has become an emerging task in sentiment analysis research. Recently, researchers have proposed different tagging schemes, containing tagging of words, tagging of word-pairs, and tagging of spans. However, the first two of these methods are often insufficient for the identification of multi-word terms, while the span tagging can label the entire phrase span, but it lacks the interactive information between words. In this paper, we propose Hybrid of Spans and Table-filling (S&T) model which combining span with table-filling. Specifically, S&T model achieve full fusion of syntactic and contextual features through cross-attention and generate the structures of word-pair table through Biaffine. Then, our model converts it to a span table by computing semantic distance based on syntactic dependency tree, which can enrich each unit of span table with semantic and interactive information. Meanwhile, the initial sentence features are constructed as simple phrase tables to enhance textual information of the phrase itself. In decoding, we define 8 types of labels for identifying three dimensions including aspect, opinion, and sentiment. Finally, the extensive experiments on widely-used dataset show S&T model achieves competitive results in ASTE task, the results certify the effectiveness and robustness of our S&T model. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Filling

来源：评论

学校读者我要写书评

暂无评论

GNEA: A Novel GCN-based Network Embedding Algorithm for Semantic Social Network 10

GNEA: A Novel GCN-based Network Embedding Algorithm for Sema...

引用

10th International Symposium on System Security, Safety, and Reliability, ISSSR 2024

作者： Zhao, Jinbo He, Jinling Du, Yuanhan Tang, Ming Xu, Xiaolong Nanjing University of Posts and Telecommunications Jiangsu Key Laboratory of Big Data Security and Intelligent Processing Nanjing China State Grid Jiangsu Electric Power Company Limited Nanjing China Nanjing University of Posts and Telecommunications School of Computer Science Nanjing China

ISBN: (纸本)9798350362930

With the development of semantic social networks, social networks become more complex and their size expands rapidly, which brings significant challenges to social network analysis. Network Embedding can transform the network from a high-dimensional adjacency matrix to a low-dimensional one, which has excellent foreground in link prediction, vertex classification, and graph visualization. Nowadays, most algorithms are proposed for static networks with little consideration of the dynamic changes in the network. However, most real-world networks change over time. Directly applying static network embedding algorithms to dynamic networks will result in poor stability, flexibility, and efficiency. Because of these shortcomings, we propose a graph convolution-based dynamic network representation learning algorithm (GNEA), which combines Graph Convolutional Network (GCN) with Long Short-Term Memory (LSTM) to train the time series networks. GCN is applied to extract features in the network, and LSTM is utilized to capture temporal information. GNEA can not only perform characterization learning on the network but also obtain more abundant information during the dynamic evolution of the network. GNEA is compared with several typical algorithms on the datasets Stochastic Block Model (SBM), Autonomous Systems (AS), and Digital Bibliography and Library Project (DBLP). The results prove that GNEA has good performance in MAP and precision@k. © 2024 IEEE.

关键词： Complex networks

来源：评论

学校读者我要写书评

暂无评论

Joint Image Restoration For Domain Adaptive Object Detection In Foggy Weather Condition

Joint Image Restoration For Domain Adaptive Object Detection...

引用

IEEE International Conference on Image processing

作者： Jing Ma Meng Lin Gang Zhou Zhenhong Jia School of Computer Science and Technology Xinjiang University Urumqi China Xinjiang Key Laboratory of Signal Detection and Processing Urumqi China

ISBN: (数字)9798350349399

ISBN: (纸本)9798350349405

Driven by deep learning, object detection methods have made significant progress in recent years. However, there is still a domain shift between synthetic foggy data and real foggy data, this leads to a undesirable decrease in detection results when applying the algorithm model trained on synthetic foggy datasets. In this article, we design a domain-adaptive YOLOX object detection algorithm by joint image restoration, in order to improve object detection performance in foggy scenes. Specially, we design an end-to-end domain adaptive framework that combines dehazing module and YOLOX together. To achieve feature alignment, we introduced a domain classifier in the feature spaceand discuss its optimal placement in the framework. Experimental results show that the proposed domain adaptation method achieved 62.60 percent mAP on real foggy image datasets RTTs, outperforming other state-of-the-art methods.

关键词： Deep learning Adaptation models Object detection Feature extraction Data models Image restoration Classification algorithms

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：