检索结果-内蒙古大学图书馆

2022 IEEE SmartWorld, 19th IEEE International Conference on Ubiquitous Intelligence and computing, 2022 IEEE International Conference on Autonomous and Trusted Vehicles Conference, 22nd IEEE International Conference on Scalable computing and Communications, 2022 IEEE International Conference on Digital Twin, 8th IEEE International Conference on Privacy computing and 2022 IEEE International Conference on Metaverse, SmartWorld/UIC/ATC/ScalCom/DigitalTwin/PriComp/Metaverse 2022

作者： Liu, Yongkang Pan, Donghui Zhang, Haifeng Zhong, Kai Anhui University Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Mathematical Science Anhui Hefei230601 China Institutes of Physical Science and Information Technology Anhui University Anhui Hefei230601 China

ISBN: (纸本)9798350346558

Predicting the remaining useful life (RUL) of bearings is important for the secure running and reducing maintenance costs of rotating machinery. In this article, a novel feature extraction and RUL prediction framework of bearing is proposed by utilizing time-frequency representations (TFRs) and deep neural network with double attention (DA-DNN). Firstly, TFRs are employed to extract the degradation features associated with RUL prediction, which can effectively cope with the non-stationary properties of bearing vibration data. The reduced dimensional TFRs are then used as the DA-DNN model input. Afterwards, DA-DNN is developed by employing the double attention structure to extract the key degradation features more efficiently. The dual-attention structure has ability to capture the degradationrelated features from two aspects of channel attention and spatial attention, which enables the network to focus on high RUL-relevant information. Finally, the experimental results demonstrate the effectiveness of DA-DNN, which shows higher performance in terms of prediction accuracy compared to other deep learning (DL) methods. © 2022 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Design of A 110-GHz On-Chip Antenna-Coupled Power-Adjustable Tripler based on Schottky Diodes

Design of A 110-GHz On-Chip Antenna-Coupled Power-Adjustable...

引用

IEEE International Workshop on Radio-Frequency Integration technology (RFIT)

作者： Ziru Chen Xiang Gao Dan Qiao Huanxin Li Heng Liu Xiangyuan Bu Jianping An School of Information and Electronics Beijing Institute of Technology Beijing China School of Cyberspace Science and Technology Beijing Institute of Technology Beijing China National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing Beijing China

ISBN: (数字)9798331541095

ISBN: (纸本)9798331541101

In this paper, we present the design of a 110-GHz on-chip antenna-coupled power-adjustable tripler based on the Schottky diodes. The design integrates two frequency triplers, on-chip antenna, and power synthesizing circuit on one single substrate. The input Ka-band signal is evenly divided via a power splitter into two signals, whose phase difference is adjusted with a phase shifter. Those two Schottky-diodes-tripled signals are synthesized by a 3-dB 90° coupler, and the output power is controllable by adjusting the phase difference between two signals after the power splitter. The simulation results show that the output power can be adjusted from -5 dBm to 17.67 dBm across - 25° to 85° phase difference range.

关键词： Radio frequency Schottky diodes Simulation Phase shifters Receivers System-on-chip Ka-band Antennas Power generation Substrates

来源：评论

学校读者我要写书评

暂无评论

Deep learning-based activity recognition and fine motor identification using 2D skeletons of cynomolgus monkeys

引用

Zoological Research 2023年第5期44卷 967-980页

作者： Chuxi Li Zifan Xiao Yerong Li Zhinan Chen Xun Ji Yiqun Liu Shufei Feng Zhen Zhang Kaiming Zhang Jianfeng Feng Trevor W.Robbins Shisheng Xiong Yongchang Chen Xiao Xiao School of Information Science and Technology Micro Nano System Center Fudan UniversityShanghai 200433China Department of Anesthesiology Huashan HospitalKey Laboratory of Computational Neuroscience and Brain-Inspired IntelligenceMinistry of EducationBehavioral and Cognitive Neuroscience CenterInstitute of Science and Technology for Brain-Inspired IntelligenceMOE Frontiers Center for Brain ScienceFudan UniversityShanghai 200433China Kuang Yaming Honors School Nanjing UniversityNanjingJiangsu 210023China Shanghai Key Laboratory of Intelligent Information Processing School of Computer ScienceFudan UniversityShanghai 200433China State Key Laboratory of Primate Biomedical Research Institute of Primate Translational MedicineKunming University of Science and TechnologyKunmingYunnan 650500China New Vision World LLC. Aliso ViejoCalifornia 92656USA Behavioural and Clinical Neuroscience Institute University of CambridgeCambridgeCB21TNUK

Video-based action recognition is becoming a vital tool in clinical research and neuroscientific study for disorder detection and ***,action recognition currently used in non-human primate(NHP)research relies heavily on intense manual labor and lacks standardized *** this work,we established two standard benchmark datasets of NHPs in the laboratory:Monkeyin Lab(Mi L),which includes 13 categories of actions and postures,and MiL2D,which includes sequences of two-dimensional(2D)skeleton ***,based on recent methodological advances in deep learning and skeleton visualization,we introduced the Monkey Monitor Kit(Mon Kit)toolbox for automatic action recognition,posture estimation,and identification of fine motor activity in *** the datasets and Mon Kit,we evaluated the daily behaviors of wild-type cynomolgus monkeys within their home cages and experimental environments and compared these observations with the behaviors exhibited by cynomolgus monkeys possessing mutations in the MECP2 gene as a disease model of Rett syndrome(RTT).Mon Kit was used to assess motor function,stereotyped behaviors,and depressive phenotypes,with the outcomes compared with human manual *** Kit established consistent criteria for identifying behavior in NHPs with high accuracy and efficiency,thus providing a novel and comprehensive tool for assessing phenotypic behavior in monkeys.

关键词： Action recognition Fine motor identification Two-stream deep model 2D skeleton Non-human primates Rett syndrome

来源：评论

学校读者我要写书评

暂无评论

Combating Online Misinformation Videos: Characterization, Detection, and Future Directions

arXiv

引用

arXiv 2023年

作者： Bu, Yuyan Sheng, Qiang Cao, Juan Qi, Peng Wang, Danding Li, Jintao Institute of Computing Technology Chinese Academy of Sciences University of Chinese Academy of Sciences China Institute of Computing Technology Chinese Academy of Sciences China Key Lab of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China

With information consumption via online video streaming becoming increasingly popular, misinformation video poses a new threat to the health of the online information ecosystem. Though previous studies have made much progress in detecting misinformation in text and image formats, video-based misinformation brings new and unique challenges to automatic detection systems: 1) high information heterogeneity brought by various modalities, 2) blurred distinction between misleading video manipulation and nonmalicious artistic video editing, and 3) new patterns of misinformation propagation due to the dominant role of recommendation systems on online video platforms. To facilitate research on this challenging task, we conduct this survey to present advances in misinformation video detection. We first analyze and characterize the misinformation video from three levels including signals, semantics, and intents. Based on the characterization, we systematically review existing works for detection from features of various modalities to techniques for clue integration. We also introduce existing resources including representative datasets and useful tools. Besides summarizing existing studies, we discuss related areas and outline open issues and future directions to encourage and guide more research on misinformation video detection. The corresponding repository is at https://***/ICTMCG/Awesome-Misinfo-Video-Detection. © 2023, CC BY-NC-SA.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

OpenViewer: Openness-Aware Multi-View Learning 39

OpenViewer: Openness-Aware Multi-View Learning

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Du, Shide Fang, Zihan Tan, Yanchao Wang, Changwei Wang, Shiping Guo, Wenzhong College of Computer and Data Science Fuzhou University Fuzhou China Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou China Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology Jinan China

ISBN: (纸本)157735897X

Multi-view learning methods leverage multiple data sources to enhance perception by mining correlations across views, typically relying on predefined categories. However, deploying these models in real-world scenarios presents two primary openness challenges. 1) Lack of Interpretability: The integration mechanisms of multi-view data in existing black-box models remain poorly explained;2) Insufficient Generalization: Most models are not adapted to multi-view scenarios involving unknown categories. To address these challenges, we propose OpenViewer, an openness-aware multi-view learning framework with theoretical support. This framework begins with a Pseudo-Unknown Sample Generation Mechanism to efficiently simulate open multi-view environments and previously adapt to potential unknown samples. Subsequently, we introduce an Expression-Enhanced Deep Unfolding Network to intuitively promote interpretability by systematically constructing functional prior-mapping modules and effectively providing a more transparent integration mechanism for multi-view data. Additionally, we establish a Perception-Augmented Open-Set Training Regime to significantly enhance generalization by precisely boosting confidences for known categories and carefully suppressing inappropriate confidences for unknown ones. Experimental results demonstrate that OpenViewer effectively addresses openness challenges while ensuring recognition performance for both known and unknown samples. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Multi-task learning

来源：评论

学校读者我要写书评

暂无评论

GACL-Net:Hybrid Deep Learning Framework for Accurate Motor Imagery Classification in Stroke Rehabilitation

引用

Computers, Materials & Continua 2025年第4期83卷 517-536页

作者： Chayut Bunterngchit Laith H.Baniata Mohammad H.Baniata Ashraf ALDabbas Mohannad A.Khair Thanaphon Chearanai Sangwoo Kang State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of AutomationChinese Academy of SciencesBeijing100190China School of Computing Gachon UniversitySeongnam13120Republic of Korea Computer Science Department Faculty of Information TechnologyThe World Islamic Sciences and Education UniversityAmman11947Jordan Intelligent Systems Department Faculty of Artificial IntelligenceAl-Balqa Applied UniversityAl-Salt19117Jordan IT Infrastructure Department Qatrana Cement CompanyAmman11821Jordan Division of Industrial and Logistics Engineering Technology Faculty of Engineering and TechnologyKing Mongkut’s University of Technology North BangkokRayong CampusRayong21120Thailand

Stroke is a leading cause of death and disability worldwide,significantly impairing motor and cognitive *** rehabilitation is often hindered by the heterogeneity of stroke lesions,variability in recovery patterns,and the complexity of electroencephalography(EEG)signals,which are often contaminated by *** classification of motor imagery(MI)tasks,involving the mental simulation of movements,is crucial for assessing rehabilitation strategies but is challenged by overlapping neural signatures and patient-specific *** address these challenges,this study introduces a graph-attentive convolutional long short-term memory(LSTM)network(GACL-Net),a novel hybrid deep learning model designed to improve MI classification accuracy and ***-Net incorporates multi-scale convolutional blocks for spatial feature extraction,attention fusion layers for adaptive feature prioritization,graph convolutional layers to model inter-channel dependencies,and bidi-rectional LSTM layers with attention to capture temporal *** on an open-source EEG dataset of 50 acute stroke patients performing left and right MI tasks,GACL-Net achieved 99.52%classification accuracy and 97.43%generalization accuracy under leave-one-subject-out cross-validation,outperforming existing state-of-the-art ***,its real-time processing capability,with prediction times of 33–56 ms on a T4 GPU,underscores its clinical potential for real-time neurofeedback and adaptive *** findings highlight the model’s potential for clinical applications in assessing rehabilitation effectiveness and optimizing therapy plans through precise MI classification.

关键词： Motor imagery EEG stroke rehabilitation deep learning brain-computer interface

来源：评论

学校读者我要写书评

暂无评论

Ship flame segmentation by fusing DASPP and PE-SCAM attention 3

Ship flame segmentation by fusing DASPP and PE-SCAM attentio...

引用

3rd International Conference on Neural Networks, information and Communication Engineering, NNICE 2023

作者： Zheng, Xuecong Chen, Li Chen, Yaojie School of Computer Science and Technology Wuhan University of Science and Technology Hubei Wuhan430065 China Wuhan Institute of Marine Electric Propulsion Hubei Wuhan430065 China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Hubei Wuhan430065 China

ISBN: (纸本)9798350335972

To solve the problem that the flame area of small targets on ships can not be easily segmented and the flame boundary is obviously affected by other background such as smoke, this experiment improves DeepLabV3+ algorithm from the following three aspects. Firstly, Dense Atrous Spatial Pyramid Pooling (DASPP) was improved to enhance the extraction and utilization of flame boundary and small target flame features. Secondly, in order to avoid the influence of background such as smoke around the flame, the high-level flame features and shallow flame features obtained by DASPP were combined with the improved Attention Mechanism (PE-SCAM) to obtain more context information in spatial and channel dimensions, so as to enhance the processing effect of the model on the flame and its boundaries. Finally, the traditional cross loss function is optimized to reduce the influence caused by the imbalance of positive and negative samples between the flame and the background. Experimental results show that the MIou of the proposed algorithm on the ship flame data set reaches 88.43%, which can realize the accurate segmentation of small target flames and flame boundaries on the basis of ensuring high real-time performance. © 2023 IEEE.

关键词： Ships

来源：评论

学校读者我要写书评

暂无评论

Radiologist-in-the-Loop Self-Training for Generalizable CT Metal Artifact Reduction

引用

IEEE Transactions on Medical Imaging 2025年第6期44卷 2504-2514页

作者： Ma, Chenglong Li, Zilong Li, Yuanlin Han, Jing Zhang, Junping Zhang, Yi Liu, Jiannan Shan, Hongming Fudan University Institute of Science and Technology for Brain-inspired Intelligence Moe Frontiers Center for Brain Science Key Laboratory of Computational Neuroscience and Brain-Inspired Intelligence Shanghai200433 China Fudan University Shanghai Key Laboratory of Intelligent Information Processing School of Computer Science Shanghai200433 China Shanghai Ninth People's Hospital Department of Oral Maxillofacial Head and Neck Oncology China Shanghai Jiao Tong University School of Medicine College of Stomatology China Shanghai Key Laboratory of Stomatology Shanghai Research Institute of Stomatology National Center for Stomatology National Clinical Research Center for Oral Diseases Shanghai200011 China Sichuan University School of Cyber Science and Engineering Chengdu Sichuan610065 China

Metal artifacts in computed tomography (CT) images can significantly degrade image quality and impede accurate diagnosis. Supervised metal artifact reduction (MAR) methods, trained using simulated datasets, often struggle to perform well on real clinical CT images due to a substantial domain gap. Although state-of-the-art semi-supervised methods use pseudo ground-truths generated by a prior network to mitigate this issue, their reliance on a fixed prior limits both the quality and quantity of these pseudo ground-truths, introducing confirmation bias and reducing clinical applicability. To address these limitations, we propose a novel radiologist-in-the-loop self-training framework for MAR, termed RISE-MAR, which can integrate radiologists' feedback into the semi-supervised learning process, progressively improving the quality and quantity of pseudo ground-truths for enhanced generalization on real clinical CT images. For quality assurance, we introduce a clinical quality assessor model that emulates radiologist evaluations, effectively selecting high-quality pseudo ground-truths for semi-supervised training. For quantity assurance, our self-training framework iteratively generates additional high-quality pseudo groundtruths, expanding the clinical dataset and further improving model generalization. Extensive experimental results on multiple clinical datasets demonstrate the superior generalization performance of our RISE-MAR over state-of-the-art methods, advancing the development of MAR models for practical application. © 2025 IEEE.

关键词： Computerized tomography

来源：评论

学校读者我要写书评

暂无评论

Prototype-Guided Representation Distribution Optimization for Change Detection in High-Resolution Remote Sensing Imagery

Prototype-Guided Representation Distribution Optimization fo...

引用

Signal, information and Data processing (ICSIDP), IEEE International Conference on

作者： Guoqing Wang He Chen Xin Wei Junqing Shi Liang Chen Wenchao Liu National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing Beijing Institute of Technology Beijing China Institute of Remote Sensing Satellite China Academy of Space Technology Beijing China

ISBN: (数字)9798331515669

ISBN: (纸本)9798331515676

Change detection is the process of automatically extracting change areas from bi-temporal remote sensing images. The key of deep learning-based change detection methods is to extract features that represent changes/non-changes. Most of the existing methods only enhance the representation ability of the changed regions through the model architecture design, but lack further constraints in the representation space. This paper introduces a prototype-guided representation distribution optimization method. By comparing pixel features with prototypes, confusing pixels can be determined, and these pixels are adaptively weighted during learning, so that similar representations are closer and different representations are farther apart. In addition, the representation distribution is also applied as transferred knowledge to knowledge distillation for lightweight CD model. Experimental results on two public datasets show the effectiveness of the proposed method.

关键词： Adaptation models Accuracy Space technology Optimization methods Prototypes Feature extraction Data processing Data models Remote sensing

来源：评论

学校读者我要写书评

暂无评论

Global information Edge Augmentation Network for Remote Sensing Image Continuous Super-Resolution

Global Information Edge Augmentation Network for Remote Sens...

引用

Signal, information and Data processing (ICSIDP), IEEE International Conference on

作者： Shize Gao Yong Lei Jingya Zhang Guoqing Wang Wenchao Liu National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing Beijing Institute of Technology Beijing China Institute of Remote Sensing Satellite China Academy of Space Technology Beijing China

ISBN: (数字)9798331515669

ISBN: (纸本)9798331515676

The continuous-scale super-resolution (SR) method for remote sensing (RS) images has the potential to achieve flexible scale SR with a single network, representing a significant research area in the field of RS. However, the majority of prevailing methods learn features from localization, thereby neglecting the global semantic coherence of RS images. This results in unbalanced SR outcomes. Furthermore, the optimization strategy based on the multilayer perceptron (MLP) utilized in the implicit neural representation (INR) method results in blurred reconstructed image edges. To address these issues, a novel continuous-scale SR method for RS images, a global information edge augmentation network (GIEAN), is proposed. Initially, the global state space model (GSSM) aggregates the global information of the image from diverse perspectives and learns the contextual interactions at disparate locations of the image globally. Subsequently, the dual edge enhancement module (DEEM) learns the image body and edges independently through the main branch and edge branch, respectively, with the objective of enhancing the edge component of the SR results. Extensive experimental evaluation on the UCMerced dataset demonstrates the superiority of GIEAN over existing continuous-scale SR techniques.

关键词： Image edge detection Aggregates Superresolution Semantics Coherence Feature extraction Sensors Remote sensing Image reconstruction Optimization

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：