检索结果-内蒙古大学图书馆

IEEE International Conference on Systems, Man and Cybernetics

作者： Yubin Sheng Zuping Zhang Panrui Tang Bo Huang Yao Xiao School of Computer Science and Engineering Central South University Chang-sha China school of software Xinjiang University Urumqi China

ISBN: (数字)9781665410205

ISBN: (纸本)9781665410212

Continual Learning for Named Entity Recognition (CL-NER) is designed to train models capable of adapting to evolving data by continuously introducing new entity types. This approach is crucial in dynamic environments where data evolves, such as social media, healthcare, and legal documents, necessitating the model to retain the memory of previously learned entity types while learning to identify new ones. However, due to the neural network's tendency to acquire new knowledge and forget old knowledge in continual learning and the unique non-entity type annotations in NER tasks, CL-NER faces severe catastrophic forgetting and semantic drift issues. In this paper, we propose Enhanced Knowledge Distillation and Entropy-based Adaptive Pseudo Label Weights (EDAW) to address the catastrophic forgetting and semantic drift issues in CL-NER. Specifically, we develop an enhanced knowledge distillation method that combines Kullback-Leibler divergence and feature cosine discrepancy. This method effectively minimizes the variance in output probability distributions and aligns the internal feature spaces between new and old models, thus reducing catastrophic forgetting. Additionally, we propose an entropy-based adaptive pseudo label weight method that allows the model to assign different weights to pseudo labels with varying certainties during training, effectively alleviating semantic drift and error accumulation caused by erroneous relabeling of pseudo labels. Notably, this study pioneers the in-clusion of a Chinese dataset in CL-NER, enhancing the model's robustness and demonstrating its efficacy in a multilingual context. Experiments on fourteen CL-NER settings across four public NER datasets show that EDAW improves average Micro-F1 and Macro-F1 scores by 3.44% and 3.72%, respectively, over existing state-of-the-art(SOTA) methods. We make our code available at: https://***/livosr/EDAW/tree/master

关键词： Continuing education Knowledge engineering Training Adaptation models Social networking (online) Semantics Named entity recognition Data models Robustness Multilingual

来源：评论

学校读者我要写书评

暂无评论

Influence of Key Nodes in Industrial Control Malicious Code Modeling 3

Influence of Key Nodes in Industrial Control Malicious Code ...

引用

3rd International Conference on Electronic Information engineering and computer science, EIECS 2023

作者： Yang, Wei Yan, Hongwei Xu, Chao Yao, Yu Zhou, Jinlei Wang, Baile Wang, Danni Northeastem University Software College Shenyang China Northeastem University School of Computer Science and Engineering Shenyang China State Grid Liaoning Information and Communication Company Department of Cybersecurity Monitoring Shenyang China

ISBN: (纸本)9798350316674

Key nodes in complex networks play an important role in the structure of the entire network. Different nodes in the network often have different degrees, and the node with the highest degree in the network is usually called a key node. However, the heterogeneity of nodes is mostly neglected in the research of malware propagation models by scholars at home and abroad. Therefore, based on the SUIQMR model proposed in the industrial control coupling network and considering the role of key nodes in the network, an improved malware suppression strategy for key nodes in the immune network is obtained. The simulation results verify the effectiveness of the improved malware suppression strategy, showing that the immune key nodes can effectively suppress the spread of malware. © 2023 IEEE.

关键词： industrial control network key nodes Malware Propagation Model Suppression strategy

来源：评论

学校读者我要写书评

暂无评论

Symmetric Graph Contrastive Learning against Noisy Views for Recommendation

arXiv

引用

arXiv 2024年

作者： Zhao, Chu Yang, Enneng Liang, Yuliang Zhao, Jianzhe Guo, Guibing Wang, Xingwei Software College Northeastern University Shenyang China School of Computer Science and Engineering Northeastern University Shenyang China

Graph Contrastive Learning (GCL) leverages data augmentation techniques to produce contrasting views, enhancing the accuracy of recommendation systems through learning the consistency between contrastive views. However, existing augmentation methods, such as directly perturbing interaction graph (e.g., node/edge dropout), may interfere with the original connections and generate poor contrasting views, resulting in sub-optimal performance. In this paper, we define the views that share only a small amount of information with the original graph due to poor data augmentation as noisy views (i.e., the last 20% of the views with a cosine similarity value less than 0.1 to the original view). We demonstrate through detailed experiments that noisy views will significantly degrade recommendation performance. Further, we propose a model-agnostic Symmetric Graph Contrastive Learning (SGCL) method with theoretical guarantees to address this issue. Specifically, we introduce symmetry theory into graph contrastive learning, based on which we propose a symmetric form and contrast loss resistant to noisy interference. We provide theoretical proof that our proposed SGCL method has a high tolerance to noisy views. Further demonstration is given by conducting extensive experiments on three real-world datasets. The experimental results demonstrate that our approach substantially increases recommendation accuracy, with relative improvements reaching as high as 12.25% over nine other competing models. These results highlight the efficacy of our method. The code is available at https://***/user683/SGCL. © 2024, CC BY.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Transforming Diabetes Care: A Review of IoT-Based Mobile Health Systems 10th

Transforming Diabetes Care: A Review of IoT-Based Mobile He...

引用

10th EAI International Conference on IoT Technologies for Health-Care, HealthyIoT 2023, and 4th EAI International Conference on Wearables in Healthcare, HealthWear 2023

作者： Ashfaq, Fiza Ahad, Abdul Hussain, Mudassar Madeira, Filipe Department of Computer Science University of Management and Technology Sialkot51040 Pakistan School of Software Northwestern Polytechnical University Shaanxi Xian China Istanbul34467 Turkey /Pole of Digital Literacy and Social Inclusion Polytechnic Institute of Santarem Santarem2001-904 Portugal Department of Computer Science and Creative Technologies Global College of Engineering and Technology Muscat Oman

ISBN: (纸本)9783031719103

Diabetes, a chronic ailment requiring ongoing care and monitoring, has undergone a healthcare shift thanks to the Internet of Things (IoT). Real-time monitoring, individualized treatment plans, and improved patient-provider communication are all features of IoT-based mobile health solutions. This study explores the components, functionalities, benefits, and disadvantages of IoT-based mobile health systems for the management of diabetes. It investigates wearable sensors, smartphone apps, and linked devices like glucose meter and monitors, placing a focus on their precision, dependability, and usability. The study explores data analytics techniques that allow for customized advice and actions. Patients can effectively control their diabetes with the use of individualized treatments and real-time monitoring. The research also looks into the data analytical methods used in IoT-based mobile health systems for the treatment of diabetes. IoT-based mobile health system issues and implications are also covered. These include issues with data security and privacy, platform and device compatibility, standardization of data formats, and ensuring that all people with diabetes have equal access to technology. Healthcare workers, academics, and policymakers may learn more about the potential of IoT-based mobile health systems to revolutionize diabetes treatment through this thorough assessment. © ICST Institute for computer sciences, Social Informatics and Telecommunications engineering 2024.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

MOKD: Cross-domain Finetuning for Few-shot Classification via Maximizing Optimized Kernel Dependence 41

MOKD: Cross-domain Finetuning for Few-shot Classification vi...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Tian, Hongduan Liu, Feng Liu, Tongliang Du, Bo Cheung, Yiu-Ming Han, Bo TMLR Group Hong Kong Baptist University Hong Kong Department of Computer Science Hong Kong Baptist University Hong Kong TMLR Group University of Melbourne Australia Sydney AI Centre The University of Sydney Australia National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence School of Computer Science Wuhan Univeristy China

In cross-domain few-shot classification, nearest centroid classifier (NCC) aims to learn representations to construct a metric space where few-shot classification can be performed by measuring the similarities between samples and the prototype of each class. An intuition behind NCC is that each sample is pulled closer to the class centroid it belongs to while pushed away from those of other classes. However, in this paper, we find that there exist high similarities between NCC-learned representations of two samples from different classes. In order to address this problem, we propose a bi-level optimization framework, maximizing optimized kernel dependence (MOKD) to learn a set of class-specific representations that match the cluster structures indicated by labeled data of the given task. Specifically, MOKD first optimizes the kernel adopted in Hilbert-Schmidt independence criterion (HSIC) to obtain the optimized kernel HSIC (opt-HSIC) that can capture the dependence more precisely. Then, an optimization problem regarding the opt-HSIC is addressed to simultaneously maximize the dependence between representations and labels and minimize the dependence among all samples. Extensive experiments on Meta-Dataset demonstrate that MOKD can not only achieve better generalization performance on unseen domains in most cases but also learn better data representation clusters. The project repository of MOKD is available at: https://***/tmlr-group/MOKD. Copyright 2024 by the author(s)

关键词： Labeled data

来源：评论

学校读者我要写书评

暂无评论

Web-Based AI Assistant for Medical Imaging: A Case Study on Predicting Spontaneous Preterm Birth via Ultrasound Images 25th

Web-Based AI Assistant for Medical Imaging: A Case Study on...

引用

25th International Conference on Web Information Systems engineering, WISE 2024

作者： Bi, Weichen Shao, Zijian Han, Yudong Du, Jiaqi Wei, Yuan Guo, Lijuan Wu, Tianchen Li, Shuang Ma, Yun Institute for Artificial Intelligence Peking University Beijing China School of Electronics Engineering and Computer Science Peking University Beijing China Peking University Third Hospital Beijing China National Centre for Healthcare Quality Management in Obstetrics Beijing China School of Software and Microelectronics Peking University Beijing China

ISBN: (纸本)9789819605729

The potential for artificial intelligence (AI) in analyzing medical images is vast and promises significant future advancements. It brings opportunities for community and remote-area hospitals to be equipped with professional capabilities once exclusive to top-tier medical institutions. However, applying in-lab AI methods to real-world applications of medical imaging is challenging due to the complexity of gathering training datasets as well as the need for intricate systems and specialized devices. In this paper, we demonstrate how the web platform could benefit the application of AI methods in medical imaging based on the lightweight design, cross-platform portability, streamlined distribution and deployment of the web. Specifically, we design and implement a web-based assistant for predicting spontaneous preterm births via ultrasound images. During the development phase, we leverage crowdsourcing on the web to annotate ultrasound images and gather domain-specific features to train the AI model for predicting spontaneous preterm birth. During the deployment phase, we employ WebAR to present AI-assisted diagnostic insights for physicians. Evaluation results show that our system achieves an AUC of 0.769, nearing the diagnostic proficiency of top-tier physicians. Besides, our WebAR system exhibits only 527.2–1754.2 ms latency, enabling effective assisted diagnosis. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Ultrasonic imaging

来源：评论

学校读者我要写书评

暂无评论

Design and implementation of unmanned aerial vehicle localization and light tracking system

引用

The Journal of China Universities of Posts and Telecommunications 2023年第4期30卷 67-74页

作者： Xu Ming Dong Chen Li Hanlu Luo Qiming Wang Lizi Zhang Wanru Liu Huixin School of Digital Media and Design Arts Beijing University of Posts and TelecommunicationsBeijing 100876China School of Information and Communication Engineering Beijing University of Posts and TelecommunicationsBeijing 100876China State Key Laboratory of Networking and Switching Technology Beijing University of Posts and TelecommunicationsBeijing 100876China School of Computer Science(National Pilot Software Engineering School) Beijing University of Posts and TelecommunicationsBeijing 100876China

Unmanned aerial vehicles(UAV)are applied widely and profoundly in various ***,high-precision positioning and tracking in multiple scenarios are the core requirements for UAV *** ensure stable communication of UAVs in denial environments with substantial electromagnetic interference,a systematic solution is proposed based on a deep learning algorithm for target detection and visible light for UAV *** the cost and computational power limitations on the hardware,the you only look once(YOLO)v4-Tiny model is used for static target detection of the UAV *** UAV tracking,and a light tracker that can adjust the angle of emitted light and focus it on the target is used for dynamic tracking ***,achieving the primary conditions of UAV optical communication with good secrecy is also suitable for dynamic *** UAV tracker positions the UAV model by returning the coordinates and calculating the time delay,and then controls the spotlight to target the *** order to facilitate the deployment of deep learning models on hardware devices,the lighter and more efficient model is selected after *** trained model can achieve 99.25%accuracy on the test *** dynamic target detection can reach 20 frames per second(FPS)on a computer with an MX520 graphics processing unit(GPU)and 6 GB of random access memory(RAM).Dynamic target detection on a Jetson Nano can reach 5.4 FPS.

关键词： unmanned aerial vehicles deep learning light tracking target detection unmanned aerial vehicles location unmanned aerial vehicles tracking

来源：评论

学校读者我要写书评

暂无评论

Fused Gromov-Wasserstein graph mixup for graph-level classifications 23

Fused Gromov-Wasserstein graph mixup for graph-level classif...

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Xinyu Ma Xu Chu Yasha Wang Yang Lin Junfeng Zhao Liantao Ma Wenwu Zhu School of Computer Science Peking University Department of Computer Science and Technology Tsinghua University School of Computer Science Peking University and National Research and Engineering Center of Software Engineering Peking University

Graph data augmentation has shown superiority in enhancing generalizability and robustness of GNNs in graph-level classifications. However, existing methods primarily focus on the augmentation in the graph signal space and the graph structure space independently, neglecting the joint interaction between them. In this paper, we address this limitation by formulating the problem as an optimal transport problem that aims to find an optimal inter-graph node matching strategy considering the interactions between graph structures and signals. To solve this problem, we propose a novel graph mixup algorithm called FGWMixup, which seeks a "midpoint" of source graphs in the Fused Gromov-Wasserstein (FGW) metric space. To enhance the scalability of our method, we introduce a relaxed FGW solver that accelerates FGWMixup by improving the convergence rate from O(t-1) to O(t-2). Extensive experiments conducted on five datasets using both classic (MPNNs) and advanced (Graphormers) GNN backbones demonstrate that FGWMixup effectively improves the generalizability and robustness of GNNs. Codes are available at https://***/ArthurLeoM/FGWMixup.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning Architecture for Facial Skin Treatment Recommender 22

Reinforcement Learning Architecture for Facial Skin Treatmen...

引用

22nd IEEE/ACIS International Conference on software engineering Research, Management and Applications, SERA 2024

作者： Jin, Jennifer Kim Dajani, Khalil Kim, Mira Kim, Soo Dong Khan, Bilal Jin, Daniel Hyun California State University Computer Science and Engineering San BernardinoCA92407 United States California State University Department of Computer Science FullertonCA92831 United States School of Software Soongsil University Seoul Korea Republic of Loma Linda University Medical Center Department of Radiology Loma lindaCA92354 United States

ISBN: (纸本)9798350391343

In the domain of facial skin treatment, personalization of treatment methods and management of treatment effectiveness among users/patients become the key challenges. Our approach to addressing the challenges is to develop a treatment recommender by utilizing a policy of reinforcement learning and continuously optimizing the policy to learn the variability. We leverage algorithmic decision-making through the Reinforcement Learning (RL) model's policy to personalize recommendations according to the unique characteristics and treatment responses of each user. This RL-based recommender should provide a high performance of personalizing treatment recommendations and continue to learn user-specific effectiveness of treatment methods. Preliminary results demonstrate the system's capacity to provide targeted, effective skin care recommendations, significantly enhancing user satisfaction and adherence to treatments. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Part-based Person Re-Identification with Swin Transformer

Part-based Person Re-Identification with Swin Transformer

引用

Pattern Recognition and Artificial Intelligence (PRAI), International Conference on

作者： Yusong Qin Pu Huang Yao Zhou Zengxi Huang School of Computer Science and Software Engineering Xihua University Chengdu China School of Computer and Software Engineering and the Sichuan Xihua Jiaotong Forensics Center Xihua University Chengdu China

Person re-identification(Re-ID) is a crucial task in computer vision, which aims to match pedestrian images captured in non-overlapping camera views. It has significant implications for public safety applications. However, current methods primarily rely on global features and thus are vulnerable to background clutters and occlusion. To address these issues, this paper proposes a part-based Re-ID method using the Swin Transformer. In this method, we first utilize human pose estimation method to detect the body keypoints of a pedestrian. We then extract local windows and patches centered at these keypoints, so as to minimize the involvement of background and occlusion information in the down-stream re-identification. These body parts in pose guided windows are fed to the Swin Transformer network. The hierarchical structure of Swin Transformer also enables the proposed method more robust to multi-scale problems. Our experimental results on both holistic and occluded datasets, i.e., Market-1501, DukeMTMC-reID, and Occluded-Duke, demonstrate that the proposed method is on par with the 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

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：