检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Wang, Ziyu Pan, Tengyu Li, Zhenyu Wang, Jianyong Li, Xiuxing Wu, Ji Department of Computer Science and Technology Tsinghua University Beijing China School of Computer Science and Technology Beijing Institute of Technology Beijing China School of Computer Science and Engineering Beihang University Beijing China

fMRI (functional Magnetic Resonance Imaging) visual decoding involves decoding the original image from brain signals elicited by visual stimuli. This often relies on manually labeled ROIs (Regions of Interest) to select brain voxels. However, these ROIs can contain redundant information and noise, reducing decoding performance. Additionally, the lack of automated ROI labeling methods hinders the practical application of fMRI visual decoding technology, especially for new subjects. This work presents TROI (Trainable Region of Interest), a novel two-stage, data-driven ROI labeling method for cross-subject fMRI decoding tasks, particularly when subject samples are limited. TROI leverages labeled ROIs in the dataset to pretrain an image decoding backbone on a cross-subject dataset, enabling efficient optimization of the input layer for new subjects without retraining the entire model from scratch. In the first stage, we introduce a voxel selection method that combines sparse mask training and low-pass filtering to quickly generate the voxel mask and determine input layer dimensions. In the second stage, we apply a learning rate rewinding strategy to fine-tune the input layer for downstream tasks. Experimental results on the same small sample dataset as the baseline method for brain visual retrieval and reconstruction tasks show that our voxel selection method surpasses the state-of-the-art method MindEye2 with an annotated ROI mask. © 2025, CC BY-NC-SA.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Robotic Anchoring system with Two Locomotion Modes for Preoperative Localization of Colorectal Cancer

Robotic Anchoring System with Two Locomotion Modes for Preop...

引用

2024 IEEE International Conference on Robotics and Biomimetics, ROBIO 2024

作者： Wang, Jiale Ren, Hao Yang, Liu Zhao, Haoxiang Zhang, Ruijia Shen, Yajing Hong Kong University of Science and Technology Department of Electronic and Computer Engineering Kowloon Hong Kong City University of Hong Kong Department of Biomedical Engineering Kowloon Hong Kong Institute of Robotics and Automatic Information System Nankai University China

ISBN: (纸本)9781665481090

At present, colorectal cancer is one of the most prevalent cancers in the world. Colectomy serves as an effective treatment option for this disease. Preoperative localization plays a vital role in the colectomy procedure. However, traditional preoperative localization techniques have a greater risk of infection and lower accuracy. Moreover, it is difficult for the previous anchoring robots to adapt to the unstructured environment of the GI tract because of their limited movement abilities. To address these challenges, this work develops a robotic anchoring system with two locomotion modes which can anchor in the designated position. Driven by the external magnetic field, the robot can achieve slipping and flipping in the stomach. When the gradients of the field increase, the robot is triggered to deploy the anchoring mechanism in the intestine. Two in vitro experiments are conducted in the stomach and intestine phantoms. The first experiment demonstrates that the robot system can achieve both slipping and flipping in the stomach and its average position error is 2.96mm. The second experiment shows that the robot system can anchor in the designated position near the tumor and can resist a peristalsis force of 0.82N from the intestine wall. © 2024 IEEE.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

TROI: Cross-Subject Pretraining with Sparse Voxel Selection for Enhanced fMRI Visual Decoding

TROI: Cross-Subject Pretraining with Sparse Voxel Selection ...

引用

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

作者： Ziyu Wang Tengyu Pan Zhenyu Li Ji Wu Xiuxing Li Jianyong Wang Department of Computer Science and Technology Tsinghua University Beijing China School of Computer Science and Engineering Beihang University Beijing China School of Computer Science and Technology Beijing Institute of Technology Beijing China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

关键词： Training Visualization Noise Training data Functional magnetic resonance imaging Brain modeling Decoding Labeling Speech processing Optimization

来源：评论

学校读者我要写书评

暂无评论

Elastic Collision Based-Interactive Path Planning system for Vascular Intervention Robots

Elastic Collision Based-Interactive Path Planning System for...

引用

International Conference on Biomimetic Intelligence and Robotics & Medical Robotics Forum, ICBIR+MRF 2024

作者： Cao, Sheng Guo, Shuxiang Guo, Jian Wang, Jian Wang, Bin Ding, Mingchao Aerospace Center Hospital The Key Laboratory of Convergence Medical Engineering System and Healthcare Technology School of Life Science Ministry of Industry and Information Technology Beijing Institute of Technology Beijing100081 China Shenzhen Institute of Advanced Biomedical Robot Company Limited Guangdong Province Shenzhen518000 China Department of Electronic and Electrical Engineering Southern University of Science and Technology Guangdong Shenzhen518055 China

As population aging intensifies, the incidence of cardiovascular and cerebrovascular diseases has continued to rise. Vascular interventional surgery, known for its minimal trauma, rapid recovery, and clear effectiveness, requires doctors to perform procedures in radiation environments while wearing lead aprons. The advent of vascular intervention robots has provided a system-level solution to protect doctors from radiation and enhance outcomes. Currently, preoperative path planning for these robots predominantly relies on automatically generated paths, calculated by setting constraints and minimizing costs. However, this method lacks incorporation of physicians' expertise and consideration of elastic collision. Therefore, this study has designed an interactive path planning system for vascular intervention robot based on elastic collision. By establishing a simulation environment, doctors can use a manipulator to control virtual catheters and guidewires. While considering deformations, they maneuver the guidewire to the target position and record the current motion trajectory to guide the procedure in actual surgeries. Experimental tests have been conducted, confirming the system's effectiveness and feasibility. © 2024 The Authors.

关键词： Robot programming

来源：评论

学校读者我要写书评

暂无评论

Study on AC Transient Overvoltage Suppression of LCC-HVDC Sending End system Based on DC Current Control Optimization 8

Study on AC Transient Overvoltage Suppression of LCC-HVDC Se...

引用

8th Asia Conference on Power and Electrical engineering, ACPEE 2023

作者： Wang, Yang Zhu, Jianhang Li, Yingbiao Hu, Jiabing Ma, Shicong Wang, Tiezhu Huazhong University of Science and Technology School of Electrical and Electronic Engineering Wuhan China China Electric Power Research Institute Power System Department Beijing China

ISBN: (纸本)9798350345520

The receiving end system AC fault of the line-commutated-converter based high voltage direct current (LCC-HVDC) system will lead to commutation failure (CF) in inverter. During the fault and its recovery, AC transient low voltage and transient overvoltage (TOV) will occur in the sending end system. The TOV has the risk of triggering the disorderly off-grid of the nearby renewable power generations, and in a serious situation, it will threaten the power system can not maintain secure and steady operation. Therefore, this paper analyzes the mechanism involved of the AC transient voltage during the AC fault and the recovery period first. It reveals that the key factor causing the TOV of the sending end system is the setting of the DC current reference value. Then, a DC current reference value limit method based on the AC TOV sampling value is proposed, which is used to accelerate DC current recovery and suppress the TOV of sending end system. Finally, based on the CIGRE Benchmark test model, the transient voltage analysis results and the validity of the designed control method are demonstrated by electromagnetic transient simulation. © 2023 IEEE.

关键词： HVDC power transmission

来源：评论

学校读者我要写书评

暂无评论

Towards Robust Temporal Activity Localization Learning with Noisy Labels 30

Towards Robust Temporal Activity Localization Learning with ...

引用

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

作者： Liu, Daizong Qu, Xiaoye Fang, Xiang Dong, Jianfeng Zhou, Pan Nan, Guoshun Tang, Keke Fang, Wanlong Cheng, Yu Wangxuan Institute of Computer Technology Peking University China School of Cyber Science and Engineering Huazhong University of Science of Technology China Interdisciplinary Graduate Programme Nanyang Technological University Singapore College of Computer Science and Technology Zhejiang Gongshang University China School of Cyberspace Security Beijing University of Posts and Telecommunications China Cyberspace Institute of Advanced Technology Guangzhou University China Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong

ISBN: (纸本)9782493814104

This paper addresses the task of temporal activity localization (TAL). Although recent works have made significant progress in TAL research, almost all of them implicitly assume that the dense frame-level correspondences in each video-query pair are correctly annotated. However, in reality, such an assumption is extremely expensive and even impossible to satisfy due to subjective labeling. To alleviate this issue, in this paper, we explore a new TAL setting termed Noisy Temporal activity localization (NTAL), where a TAL model should be robust to the mixed training data with noisy moment boundaries. Inspired by the memorization effect of neural networks, we propose a novel method called Co-Teaching Regularizer (CTR) for NTAL. Specifically, we first learn a Gaussian Mixture Model to divide the mixed training data into preliminary clean and noisy subsets. Subsequently, we refine the labels of the two subsets by an adaptive prediction function so that their true positive and false positive samples could be identified. To avoid single model being prone to its mistakes learned by the mixed data, we adopt a co-teaching paradigm, which utilizes two models sharing the same framework to teach each other for robust learning. A curriculum strategy is further introduced to gradually learn the moment confidence from easy to hard. Experiments on three datasets demonstrate that our CTR is significantly more robust to the noisy training data compared to the existing methods. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Gaussian distribution

来源：评论

学校读者我要写书评

暂无评论

A Way of Making Smart Health Through Collaborating Machine Learning with the Bibliometrics 4

A Way of Making Smart Health Through Collaborating Machine L...

引用

4th IEEE International Conference on Advance Computing and Innovative Technologies in engineering, ICACITE 2024

作者： Vignesh, T. Sruthi, P.S. Mohanraj, T. Kumar, Gaurav Varkale, Akshay Sheela, M.Sahaya Prince Shri Venkateshwara Padmavathy Engineering College Department of Computer Science and Engineering TN India Nehru Institute of Technology Department of Computer Science and Business System Tamil Nadu T.M. Palayam India Karpagam Academy of Higher Education Department of Computer Science Engineering India Chitkara University Chitkara Centre for Research and Development Himachal Pradesh India M.P Bhopal India Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Electronics and Communication Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350360165

It datasets are widely utilized, shared, and repurposed without providing enough context for understanding the decision-making processes that led to their creation. It is necessary to modify system creation and use procedures to handle the concrete effects of how knowledge for model building is envisioned and used in real-world applications as AI systems assume more and more important roles. Documents are created at every phase of the data generation lifecycle to improve communication, aid in decision-making, and highlight the need of careful data work. By putting out this paradigm, we want to shed light on the choices and duties that are often disregarded while creating datasets, which is a crucial first step in bridging the duty of care gap in AI. This framework provides an essential and important resource for guaranteeing ethical AI activities, and it is in line with current developments in auditing procedures. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Conceptual Study and Performance Analysis of Tandem Multi-Antenna Spaceborne SAR Interferometry

Journal of Remote Sensing

引用

Journal of Remote Sensing 2024年第1期4卷 548-566页

作者： Fengming Hu Feng Xu Robert Wang Xiaolan Qiu Chibiao Ding Yaqiu Jin Key Laboratory for Information Science of Electromagnetic Waves(MoE) Fudan UniversityShanghai 200433China Department of Space Microwave Remote Sensing System Aerospace Information Research InstituteChinese Academy of SciencesBeijing 100190China School of Electronic Electrical and Communication EngineeringUniversity of Chinese Academy of SciencesBeijing 101408China National Key Laboratory of Science and Technology on Microwave Imaging Aerospace Information Research InstituteChinese Academy of SciencesBeijing 100094China

Multi-baseline synthetic aperture radar interferometry(InSAR),capable of mapping 3D surface model with high precision,is able to overcome the ill-posed problem in the single-baseline *** tandem SAR mission utilizes a two-stage global coverage to get the dual-baseline interferograms,which achieves the trade-off between the unwrapping errors and height ***,the baseline adjustment will decrease the timeliness of the data acquisition,which is not suitable for monitoring temporal changes of the ground *** a SAR mission with the single-pass multi-baseline acquisition will improve the practical capability in fast 3D *** the asymptotic 3D phase unwrapping proposed for the airborne array InSAR system,it is possible to get a reliable 3D reconstruction using very sparse acquisitions but the interferograms should follow the optimal baseline *** this article,a new concept of tandem multi-antenna SAR interferometry system for acquiring optimal single-pass multi-baseline interferograms is *** indicators,i.e.,expected relative height precision and successful phase unwrapping rate,are selected to optimize the system ***,taking the satellites with two antennas as an example,the performances of various baseline configurations in typical scenarios and the impact of different error sources are investigated *** simulation-based experiments demonstrate that the proposed system acquires the optimal MB interferograms for asymptotic 3D phase unwrapping,and thus enables good performance in both urban and forest area in a single *** system has the potential applications in accurate digital surface model acquisition,3D target recognition,and biomass estimation.

关键词： tandem sar synthetic aperture radar monitoring temporal changes multi baseline interferometry D surface modeling d surface model unwrapping errors baseline adjustment

来源：评论

学校读者我要写书评

暂无评论

Honeypot Comparison of Attack Detection and Mitigation of SSH Attack 3

Honeypot Comparison of Attack Detection and Mitigation of SS...

引用

3rd IEEE Delhi Section Flagship Conference, DELCON 2024

作者： Ali, Wasif Sajid, Ahthasham Ghodke, Tanvi Ajit Malik, Rida Malik, Neeru Kaushik, Keshav Riphah Institute of System Engineering Riphah International University Department of Cyber Security Islamabad Pakistan Pimpri Chinchwad University Department of Computer Science and Engineering Maharashtra India School of Engineering & Technology Pimpri Chinchwad University Maharashtra Pune India Amity School of Engineering and Technology Amity University Mohali India

ISBN: (纸本)9798331518592

This research study addresses the importance of honeypots at multiple levels, which includes but not limited to placement in network or group of networks working alongside in an organization. This paper talks about the usage of multiple honeypots working alongside to log useful data for the mitigation of ongoing bot or actual attack this approach helps the organization better understand the threat they are dealing and the techniques which they can use to overcome the gap of the unseen security risks. The comparison will shed better light to the working and attack patterns of the ongoing attacks, gaining more confidence on using the honeypot for better protection. This allows strategic, optimized and critical insight to the evolving attack patterns. © 2024 IEEE.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

ICSGD-Momentum: SGD Momentum based on Inter-gradient Collision 22

ICSGD-Momentum: SGD Momentum based on Inter-gradient Collisi...

引用

22nd IEEE International Conference on Industrial Informatics, INDIN 2024

作者： Zou, Weidong Cao, Weipeng Xia, Yuanqing Zhong, Bineng Li, Dachuan School of Automation Beijing Institute of Technology Beijing China Shenzhen China Guangxi Key Lab of Multi-source Information Mining & Security Guangxi Normal University Guilin China Research Institute of Trustworthy Autonomous Systems Southern University of Science and Technology Shenzhen China Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China

ISBN: (纸本)9798331527471

Deep neural networks (DNNs) are widely used in fields like computer vision and natural language processing. A key component of DNN training is the optimizer. SGD-Momentum is popular in many DNN methodologies, such as ResNet and DenseNet, due to its simplicity and effectiveness. However, its slow convergence rate limits its use. To overcome this, we introduce inter-gradient collision into SGD-Momentum, inspired by the elastic collision model in physics. This new method, called ICSGD-Momentum, aims to improve convergence. We provide theoretical proof of convergence and establish a regret bound for ICSGD-Momentum. Experiments on benchmarks including function optimization, CIFAR-100, ImageNet, Penn Treebank, COCO, and YCB-Video show that ICSGD-Momentum accelerates training and enhances the generalization performance of DNNs compared to optimizers like SGD-Momentum, Adam, RAdam, Adabound, and AdaBelief. © 2024 IEEE.

关键词： Deep neural networks

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：