检索结果-内蒙古大学图书馆

SSRN 2023年

作者： Heng, Xia Wang, Miao Wang, Zhong-Min Zhang, Jie He, Lang Fan, Lin School of Computer Science and Technology Xi’an University of Posts and Telecommunications Shaanxi Xi’an710121 China Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Shaanxi Xi’an710121 China Xi’an Key Laboratory of Big Data and Intelligent Computing Shaanxi Xi’an710121 China

Sleep staging is the basis of sleep quality assessment. In the process of scoring each sleep stage, some automatic sleep staging models often fail to effectively capture the more accurate long-range correlation coupling between the input sleep EEG signals and the output sleep stage, which leads to the extracted features cannot effectively distinguish the different sleep stage. In order to alleviate the long-term time series problem of sleep EEG signals and learn the discriminative features of each sleep stage in sleep EEG signals, we propose an end-to-end automatic sleep stage classification method based on raw single-channel sleep EEG signals, which can improve the attention to the discriminative features of each sleep stage. In the construction of the model, in order to learn the source domain information of the key part of the sleep EEG signal, SE-Block is added to Convolutional Neural network (CNN) to highlight the time-frequency domain features related to the sleep stage. Meanwhile, the attention mechanism is added to the decoding part of Bidirectional Recurrent Unit (Bi-GRU) to enhance the long-term memory ability of Bi-GRU and learn the conversion rules between sleep stages. To validate the accuracy and stability of the model, the Fpz-Cz channel and Pz-Oz channel EEG signals in the Sleep-EDF sleep dataset are used for 10-fold cross-validation. The classification accuracies obtained are 88.48% and 87.56%, respectively. The results show that our model has stronger ability to extract discriminative features, better representation ability, more stable performance and relatively simple structure. © 2023, The Authors. All rights reserved.

关键词： Frequency domain analysis

来源：评论

学校读者我要写书评

暂无评论

Large Model-Based data Augmentation for Imbalanced Text Classification

Large Model-Based Data Augmentation for Imbalanced Text Clas...

引用

Artificial Intelligence, networking and Information technology (AINIT), International Seminar on

作者： Dawei Zhang Rongxin Mi Peiyao Zhou Dawei Jin Manman Zhang Tianhang Song School of Computer Science Jiangsu University of Science and Technology Zhenjiang Jiangsu China National Computer Network Emergency Response Technical Team/Coordination Center of China Beijing China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences (CAS) Beijing China

ISBN: (数字)9798350385557

ISBN: (纸本)9798350385564

This study focuses on the application of large models to deal with imbalanced data problems in text classification. In view of the central position of text in web data and the negative impact of class imbalance on classifier performance, researchers have explored the method of using large models to generate high-quality minority class samples to enhance model performance. This paper reviews the technical progress of machine learning, deep learning, and large language models and their applications in text classification tasks. Although large models perform well in complex tasks due to their excellent language understanding ability, traditional machine learning and deep learning methods are popular in text classification scenarios that require fast response due to their simple structure and higher computational efficiency. This study proposes a data augmentation technique inspired by SMOTE, which uses a large language model combined with a simple prompt engineering strategy to generate high-quality minority samples. The experimental results show that the proposed method significantly improves the macro average precision, recall and F1 score on multiple text classification models, and effectively alleviates the challenge of class imbalance.

关键词： Deep learning Seminars Computational modeling Large language models Text categorization data augmentation data models

来源：评论

学校读者我要写书评

暂无评论

Crowdsourcing System for Multi-object Annotation in Surveillance Videos

Crowdsourcing System for Multi-object Annotation in Surveill...

引用

International Conference on Big data Computing and Communications (BIGCOM)

作者： Zheng Zhang Zixin Zhao Lan Zhang Xiangyang Li LINKE Lab University of Science and Technology of China School of Data Science University of Science and Technology of China School of Computer Science and Technology CAS Key Laboratory of Wireless-optical Communications University of Science and Technology of China

The collection and labeling of data is a labor-intensive task and this has given rise to a large market for data crowdsourcing transactions. While there are many publicly available video datasets, task-specific data is still scarce and requires Customized annotation services are required. Even with many excellent auxiliary models and tools, video annotation is still a lengthy and time-consuming task. To address these challenges, this paper provides a new and effective annotation method in which the annotator no longer just provides annotations, but also plays the role of a reviewer to review the annotation results of other annotators. This method focuses on surveillance video data, in addition, it also supports adding additional custom tasks (e.g., action tagging, person relationship recognition, video summarization, etc.). And in this paper we mainly consider the additional custom temporal action annotation task. In this paper, we develop rules for filtering frames or segments that need to be re-labeled based on the temporal information of the model inference results and rely on the correlation between target and time to determine the task relevance, and asynchronously assign the task to different annotators for and dynamically portray the ability of the annotators while annotation is in progress, so as to allocate tasks to achieve annotation and mutual review of annotators. We have experimentally demonstrated that this method can reduce costs and improve labeling accuracy.

关键词： Crowdsourcing Costs Correlation Annotations Surveillance Manuals Tagging

来源：评论

学校读者我要写书评

暂无评论

Few-shot Object Detection with Camouflage Animals

Few-shot Object Detection with Camouflage Animals

引用

2021 International Conference on Computer Engineering and Innovative Application of VR, ICCEIA VR 2021

作者： Lei, Yi Lei, Lei Network and Data Security Key Laboratory of Sichuan Province University of Electr Onic Science and Technology of China China Primary School in Gao Sheng Zi yang China

Object detection is a hot issue in the field of computer vision, which is widely used in intelligent video surveillance, medical image analysis, and practice in the fields of military strategy. Previous object detection is based on a lot of training data, and for some special target, it is difficult to find enough annotation data to training model, so few-shot object detection was born. In this paper, a data set of animals with protective colors is constructed(CAD), which contains ten categories of different objects with high quality annotations. We combine the existing attention RPN and Feature Reweighting module to train our net, the experimental results prove that the Camouflage animals in nature can be well identified, and our results obtain 1.9% AP50, 1.2% AP75 improvement compared with before work. © Published under licence by IOP Publishing Ltd.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Communication is Verification: IoT Identifier System Using Device Fingerprints

Communication is Verification: IoT Identifier System Using D...

引用

International Conference on Big data Computing and Communications (BIGCOM)

作者： Yuan Ji Tian Ye Xiang-Yang Li LINKE Lab University of Science and Technology of China School of Data Science University of Science and Technology of China CAS Key Laboratory of Wireless-optical Communications School of Computer Science and Technology University of Science and Technology of China

With the gradual development of the Internet of Things, people rely more and more on the Internet of Things devices to assist their daily lives. The permissions of IoT devices make it easy for them to rescue or destroy our lives. This paper proposes a new scalable IoT security framework (ISDF), which uses the unforgeable physical layer characteristics of IoT devices as the verification basis to identify illegal devices. This framework combined with the identifier generation algorithm to generate a unique trusted identifier. Under the verification of more than a dozen devices such as bluetooth, wifi, and voice, the identifiers we generate have high robustness and stability, the accuracy of verification is more than 93%. Compared with existing solutions, our framework has the advantages of supporting multimodality and high verification success rate.

关键词： Bluetooth Systems architecture Speech recognition Fingerprint recognition Physical layer Robustness Internet of Things

来源：评论

学校读者我要写书评

暂无评论

Suppress Content Shift: Better Diffusion Features via Off-the-Shelf Generation Techniques

arXiv

引用

arXiv 2024年

作者： Meng, Benyuan Xu, Qianqian Wang, Zitai Yang, Zhiyong Cao, Xiaochun Huang, Qingming Institute of Information Engineering CAS China School of Cyber Security University of Chinese Academy of Sciences China Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS China Peng Cheng Laboratory China School of Computer Science and Tech. University of Chinese Academy of Sciences China Key Laboratory of Big Data Mining and Knowledge Management CAS China School of Cyber Science and Tech. Sun Yat-sen University Shenzhen Campus China

Diffusion models are powerful generative models, and this capability can also be applied to discrimination. The inner activations of a pre-trained diffusion model can serve as features for discriminative tasks, namely, diffusion feature. We discover that diffusion feature has been hindered by a hidden yet universal phenomenon that we call content shift. To be specific, there are content differences between features and the input image, such as the exact shape of a certain object. We locate the cause of content shift as one inherent characteristic of diffusion models, which suggests the broad existence of this phenomenon in diffusion feature. Further empirical study also indicates that its negative impact is not negligible even when content shift is not visually perceivable. Hence, we propose to suppress content shift to enhance the overall quality of diffusion features. Specifically, content shift is related to the information drift during the process of recovering an image from the noisy input, pointing out the possibility of turning off-the-shelf generation techniques into tools for content shift suppression. We further propose a practical guideline named GATE to efficiently evaluate the potential benefit of a technique and provide an implementation of our methodology. Despite the simplicity, the proposed approach has achieved superior results on various tasks and datasets, validating its potential as a generic booster for diffusion features. Our code is available at this url. © 2024, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Information and Sensing Beamforming Optimization for Multi-User Multi-Target MIMO ISAC Systems

Information and Sensing Beamforming Optimization for Multi-U...

引用

International Conference on Acoustics, Speech, and Signal Processing (IcasSP)

作者： Minghe Zhu Lei Li Shuqiang Xia Tsung-Hui Chang School of Science & Engineering The Chinese University of Hong Kong Shenzhen Shenzhen Research Institute of Big Data ZTE Corporation State Key Laboratory of Mobile Network and Mobile Multimedia Technology

In this paper, we consider the joint beamforming design for simultaneous sensing and communication in a wireless multi-user system. Different from the existing works that mostly are for single target, we consider sensing the channel parameters of multiple targets while communicating with multiple users. The design goal is to minimize a weighted sum of the Cramer-Rao bounds (CRB) of target parameters subject to the communication sum rate and transmission power constraints. While the classical weighted minimum mean square error (WMMSE) and semidefinite relaxation (SDR) can be used to handle the problem, we propose to reformulate the problem into a max-min form, by leveraging the tightness of SDR, and solve it by a low-complex first-order method. Numerical results not only demonstrate the computation efficiency of the proposed algorithm but also its effectiveness in enhancing the sensing performance in practice.

关键词： Wireless communication Wireless sensor networks Array signal processing Signal processing algorithms Mean square error methods Minimax techniques Sensors

来源：评论

学校读者我要写书评

暂无评论

Adversarial Training Via Multi-Guidance and Historical Memory Enhancement

SSRN

引用

SSRN 2024年

作者： Zhao, Chenyu Qian, Yaguan Wang, Bin Gu, Zhaoquan Ji, Shouling Wang, Wei Zhang, Yanchun School of Science Zhejiang University of Science and Technology China Network and Data Security China School of Computer Science and Technology Harbin Institute of Technology Shenzhen China School of Computer Science and Technology Zhejiang University China Beijing Key Laboratory of Security and Privacy in Intelligent Transportation Beijing Jiaotong University China Institute for Sustainable Industries and Liveable Cities Victoria University Australia Peng Cheng Laboratory China

DNNs are often susceptible to the influence of adversarial examples, potentially leading to severe security issues. Adversarial training stands out as one of the most effective defenses. In this paper, we empirically demonstrate that weakly robust models maintain resilience to adversarial examples generated on a fully trained robust model. We propose a novel weight ensemble training method called Guided Adversarial Training (GAT). This method enhances both clean and adversarial accuracy through two guiding approaches (Self-Guidance and Expert-Guidance), as well as by improving the historical memory of member models' weights. The experiments prove that our method is effective in defending against most adversarial attacks. It emphasizes the need to maintain the diversity of decision boundaries of member models while improving the alignment with natural decision boundaries when ensemble the model weights. The code will be released after acceptance. © 2024, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Back to science in Searching for SARS-CoV-2 Origins

引用

China CDC weekly 2023年第14期5卷 315-317页

作者： William J Liu Wenwen Lei Xiaozhou He Peipei Liu Qihui Wang Zhiqiang Wu Yun Tan Shuhui Song Gary Wong Jian Lu Jingkun Jiang Qiang Wei Mingkun Li Juncai Ma Xiaozhong Peng Yixue Li Baoxu Huang Yigang Tong Jun Han Guizhen Wu NHC Key Laboratory of Biosafety National Institute for Viral Disease Control and PreventionChinese Center for Disease Control and PreventionBeijingChina CAS Key Laboratory of Pathogen Microbiology and Immunology Institute of MicrobiologyChinese Academy of SciencesBeijingChina NHC Key Laboratory of Systems Biology of Pathogens Institute of Pathogen BiologyChinese Academy of Medical Sciences&Peking Union Medical CollegeBeijingChina Shanghai Institute of Hematology State Key Laboratory of Medical GenomicsNational Research Center for Translational MedicineRuijin Hospital Affiliated to Shanghai Jiao Tong University School of MedicineShanghaiChina Beijing Institute of Genomics Chinese Academy of Sciencesand China National Center for BioinformationBeijingChina Laboratory of Molecular Virology and Immunology Institut Pasteur of ShanghaiChinese Academy of SciencesShanghaiChina State Key Laboratory of Protein and Plant Gene Research Center for BioinformaticsSchool of Life SciencesPeking UniversityBeijingChina School of Environment Tsinghua UniversityBeijingChina National Pathogen Resource Center Chinese Center for Disease Control and Prevention(China CDC)BeijingChina Microbial Resource and Big Data Center Chinese National Microbiology Data Center(NMDC)Institute of MicrobiologyChinese Academy of SciencesBeijingChina State Key Laboratory of Medical Molecular Biology Department of Molecular Biology and BiochemistryInstitute of Basic Medical SciencesMedical Primate Research CenterNeuroscience CenterChinese Academy of Medical SciencesSchool of Basic MedicinePeking Union Medical CollegeBeijingChina School of Life Science and Technology ShanghaiTech UniversityShanghaiChina Bio-Med Big Data Center Key Laboratory of Computational BiologyCAS-MPG Partner Institute for Computational BiologyShanghai Institute of Nutrition and HealthUniversity of Chinese Academy of SciencesChinese Academy of SciencesShanghaiChina China Animal Health and Epidemiology Center Qingdao CityShandong ProvinceChi

In recent decades,emerging and re-emerging human-infecting pathogens have been represented as huge threats to public health and have become a global concern(1).After outbreaks of two coronaviruses(CoVs),severe acute respiratory syndrome coronavirus(SARS-CoV)and Middle East respiratory syndrome coronavirus(MERS-CoV),severe acute respiratory syndrome coronavirus 2(SARS-CoV-2)became the first-known pandemic hastening CoV with tremendous wrecking to the world(2).The origin tracing of these emerging pathogens is of great significance in infectious disease prevention and control(3–4).The origin of SARS-CoV-2 remains elusive after the more than 3-year pandemic,though scientists around the world are making great *** the experience of studying many other infectious pathogens,origin tracing is systematic and time-consuming *** supposed origins of many infectious pathogens are still in debate,including SARS-CoV and human immunodeficiency virus,etc(5).

关键词： prevention respiratory acute

来源：评论

学校读者我要写书评

暂无评论

An Efficient Deep Transfer Learning network for Characterization of Stroke Patients’ Motor Execution from Multi-Channel EEG-Recordings

An Efficient Deep Transfer Learning Network for Characteriza...

引用

Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

作者： Oluwarotimi Williams Samuel Mojisola Grace Asogbon Frank Kulwa Alistair A. McEwan Sunday Timothy Aboyeji Rami Khushaba Peng Fang Guanglin Li School of Computing and Data Science Research Centre University of Derby Derby United Kingdom Shenzhen Institute of Advanced Technology (SIAT) Chinese Academy of Sciences (CAS) Shenzhen China CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems SIAT-CAS Shenzhen China Australian Centre for Field Robotics Sydney University Chippendale NSW Australia

ISBN: (数字)9798350371499

ISBN: (纸本)9798350371505

Recent advances in stroke rehabilitation technology have been focused on developing Intelligent Rehabilitation Robots (IRR) that can effectively engage post-stroke patients (PSP) in intuitive motor training for full function recovery. Most existing rehabilitation robots incorporate functionalities that are passive in nature, constraining PSP to predetermined trajectories that often deviate from patients’ limb movement intentions, consequently hindering recovery. To resolve this issue, a robust deep-transfer learning driven network (DTLN) is developed to adequately characterize PSP’s motion intention signatures from neural oscillations towards achieving intuitive and active training. Thus, we investigated and proposed the utilization of mu-frequency spectrum (muFS) based CWT approach for Scalograms construction, which serves as inputs to the DTLN model that characterizes multiple classes of PSP’s motor execution signatures from multi-channel electroencephalography (EEG) recordings. Then, we evaluated the proposed method using EEG data from six PSP and compared the decoding results to those of related approaches under similar experimental settings. The proposed method resulted in a significant increment of 10.84 % - 13.19% decoding accuracy across stroke patients and better convergence in comparison to other methods. Additionally, the method exhibited distinct task separability for individual motor execution signature across patients. In conclusion, our method offers a consistently accurate decoding of motor tasks that could enable intuitively active robotic training in PSPs with impaired motor function.

关键词： Training Accuracy Transfer learning Stroke (medical condition) Motors Assistive robots Electroencephalography Decoding Trajectory Robots

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：