检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Chen, Jian Chen, Mingcong Zhao, Qingxiang Wang, Shuai Wang, Yihe Xiao, Ying Hu, Jian Chan, Danny Tat Ming Yeung, Kam Tong Leo Chan, David Yuen Chung Liu, Hongbin The School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100049 China Beijing100190 China Hong Kong Department of Biomedical Engineering City University of Hong Kong Hong Kong CAIR-HKISI-CAS HKSAR China The State Key Laboratory of Multimodal Artificial Intelligence Systems CASIA Beijing100190 China Department of Surgery The Chinese University of Hong Kong Hong Kong The State Key Laboratory of Management and Control for Complex Systems CASIA Beijing100190 China The School of Biomedical Engineering and Imaging Sciences King's College London LondonSE1 7EU United Kingdom

Traditional rigid endoscopes have challenges in flexibly treating tumors located deep in the brain, and low operability and fixed viewing angles limit its development. This study introduces a novel dual-segment flexible robotic endoscope MicroNeuro, designed to perform biopsies with dexterous surgical manipulation deep in the brain. Taking into account the uncertainty of the control model, an image-based visual servoing with online robot Jacobian estimation has been implemented to enhance motion accuracy. Furthermore, the application of model predictive control with constraints significantly bolsters the flexible robot's ability to adaptively track mobile objects and resist external interference. Experimental results underscore that the proposed control system enhances motion stability and precision. Phantom testing substantiates its considerable potential for deployment in neurosurgery. Copyright © 2024, The Authors. All rights reserved.

关键词： Visual servoing

来源：评论

学校读者我要写书评

暂无评论

Trackerless Freehand Ultrasound with Sequence Modelling and Auxiliary Transformation Over Past and Future Frames

Trackerless Freehand Ultrasound with Sequence Modelling and ...

引用

IEEE International Symposium on biomedical Imaging

作者： Qi Li Ziyi Shen Qian Li Dean C Barratt Thomas Dowrick Matthew J Clarkson Tom Vercauteren Yipeng Hu Department of Medical Physics and Biomedical Engineering Centre for Medical Image Computing Wellcome/EPSRC Centre for Interventional and Surgical Sciences University College London London U.K. State Key Laboratory of Robotics and System Harbin Institute of Technology Harbin China School of Biomedical Engineering & Imaging Sciences King’s College London London U.K.

Three-dimensional (3D) freehand ultrasound (US) reconstruction without a tracker can be advantageous over its two-dimensional or tracked counterparts in many clinical applications. In this paper, we propose to estimate 3D spatial transformation between US frames from both past and future 2D images, using feed-forward and recurrent neural networks (RNNs). With the temporally available frames, a further multi-task learning algorithm is proposed to utilise a large number of auxiliary transformation-predicting tasks between them. Using more than 40,000 US frames acquired from 228 scans on 38 forearms of 19 volunteers in a volunteer study, the hold-out test performance is quantified by frame prediction accuracy, volume reconstruction overlap, accumulated tracking error and final drift, based on ground-truth from an optical tracker. The results show the importance of modelling the temporal-spatially correlated input frames as well as output transformations, with further improvement owing to additional past and/or future frames. The best performing model was associated with predicting transformation between moderately-spaced frames, with an interval of less than ten frames at 20 frames per second (fps). Little benefit was observed by adding frames more than one second away from the predicted transformation, with or without LSTM-based RNNs. Interestingly, with the proposed approach, explicit within-sequence loss that encourages consistency in composing transformations or minimises accumulated error may no longer be required. The implementation code and volunteer data 1 will be made publicly available ensuring reproducibility and further research.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Lifelong-MonoDepth: Lifelong Learning for Multi-Domain Monocular Metric Depth Estimation

arXiv

引用

arXiv 2023年

作者： Hu, Junjie Fan, Chenyou Zhou, Liguang Gao, Qing Liu, Honghai Lam, Tin Lun The Chinese University of Hong Kong Shenzhen China The School of Artificial Intelligence South China Normal University China The School of Electronics and Communication Engineering Sun Yat-sen University Shenzhen China State Key Laboratory of Robotics and systems Harbin Institute of Technology Shenzhen China The School of Science and Engineering The Chinese University of Hong Kong Shenzhen China

With the rapid advancements in autonomous driving and robot navigation, there is a growing demand for lifelong learning models capable of estimating metric (absolute) depth. Lifelong learning approaches potentially offer significant cost savings in terms of model training, data storage, and collection. However, the quality of RGB images and depth maps is sensor-dependent, and depth maps in the real world exhibit domain-specific characteristics, leading to variations in depth ranges. These challenges limit existing methods to lifelong learning scenarios with small domain gaps and relative depth map estimation. To facilitate lifelong metric depth learning, we identify three crucial technical challenges that require attention: i) developing a model capable of addressing the depth scale variation through scale-aware depth learning, ii) devising an effective learning strategy to handle significant domain gaps, and iii) creating an automated solution for domain-aware depth inference in practical applications. Based on the aforementioned considerations, in this paper, we present i) a lightweight multi-head framework that effectively tackles the depth scale imbalance, ii) an uncertainty-aware lifelong learning solution that adeptly handles significant domain gaps, and iii) an online domain-specific predictor selection method for real-time inference. Through extensive numerical studies, we show that the proposed method can achieve good efficiency, stability, and plasticity, leading the benchmarks by 8% ∼ 15%. The code is available at https://***/Freeformrobotics/Lifelong-MonoDepth. © 2023, CC BY.

关键词： Numerical methods

来源：评论

学校读者我要写书评

暂无评论

Optimization of Flexible Bronchoscopy Shape Sensing Using Fiber Optic Sensors

Optimization of Flexible Bronchoscopy Shape Sensing Using Fi...

引用

IEEE International Conference on robotics and Automation (ICRA)

作者： Xinran Liu Hao Chen Hongbin Liu School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing China Professor at Chinese Academy of Sciences Institute of Automation (CASIA) Executive Director for the Centre of AI and Robotics (CAIR) Hong Kong Institute of Science & Innovation Chinese Academy of Sciences An Adjunct Reader and Director of the Haptic Mechatronics and Medical Robotics (HaMMeR) lab at the School of Biomedical Engineering and Imaging Sciences King’s College London (KCL) UK

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

This work presents a novel shape evaluation and optimization approach for shape sensing, specifically targeting the constrained, irregular, and intricate spatial shapes of flexible bronchoscopes (FB) in human bronchial tree. The proposed evaluation criteria and optimization methods combine clinical significance related to bronchial anatomical structures and address issues related to singular points and discontinuities in traditional shape reconstruction models. Three-dimensional experiments were conducted within eight spatial complex configurations printed from a proportional bronchial model. The 3D experiment results demonstrate an average reduction of approximately 34.1% in shape reconstruction errors across all eight airway models compared to the traditional model, validating the effectiveness and feasibility.

关键词： Bronchoscopy Solid modeling Optical fiber sensors Three-dimensional displays Shape Atmospheric modeling Optimization methods

来源：评论

学校读者我要写书评

暂无评论

Therapeutic Effects of Different Ultrasound Intensity Stimulation on Brown Adipose Tissue for the Treatment of Type 2 Diabetes

SSRN

引用

SSRN 2024年

作者： Bat-Erdene, Badamgarav He, Min Dong, Jingsong Li, Ying Ta, Dean Department of Biomedical Engineering School of Information Science and Technology Fudan University Shanghai200438 China Academy for Engineering and Technology Fudan University Shanghai200433 China State Key Laboratory of Integrated Chips and Systems Fudan University Shanghai201203 China Department of Rehabilitation Medicine Huashan Hospital Fudan University Shanghai200040 China

Type 2 diabetes (T2D) is a persistent illness that has a high incidence rate. Still, there is no conclusive evidence on effectively improving blood sugar levels in patients through physical therapy. This study examined the regulatory effects of different intensities of low-intensity pulsed ultrasound (LIPUS) on T2D by stimulating brown adipose tissue (BAT). Eight-week-old C57BL/6J mice were divided into six groups (n = 10 per group): Control sham (C-Sham), Control-LIPUS (C-LIPUS), T2D-sham (T2D-Sham), T2D groups treated with LIPUS at spatial average-temporal-average intensity (Isata) of 60mW/cm² (T2D-L-60), 80mW/cm² (T2D-L-80), and 100mW/cm² (T2D-L-100). T2D was induced in mice through 12 weeks high-fat diet (HFD) followed by an intraperitoneal injection of streptozotocin (STZ) 120mg/kg. The T2D-LIPUS group received LIPUS stimulation for 20 minutes per day for 6 weeks. The LIPUS stimulation had a duty cycle of 20%, a frequency of 1 MHz, and Isata of 60mW/cm², 80mW/cm², 100mW/cm². Subsequently, glucose tolerance tests (GTT) and insulin tolerance tests (ITT) were performed, and body fat content in mice was analyzed using nuclear magnetic resonance (NMR). Metabolic changes were monitored using metabolic cages. The results indicated that 80mW/cm² intensity level significantly improved glucose tolerance, insulin sensitivity, and metabolic function after LIPUS exposure. Significant reductions in body fat content and enhanced thermogenesis were observed, highlighting the potential of LIPUS in T2D management. This provides the basis for the dose study of LIPUS in the treatment of T2D. © 2024, The Authors. All rights reserved.

关键词： Metabolism

来源：评论

学校读者我要写书评

暂无评论

BAN: A Universal Paradigm for Cross-Scene Classification Under Noisy Annotations From RGB and Hyperspectral Remote Sensing Images

引用

IEEE Transactions on Geoscience and Remote Sensing 2025年 63卷

作者： Chen, Wentang Wen, Yibin Zheng, Juepeng Huang, Jianxi Fu, Haohuan Sun Yat-sen University School of Artificial Intelligence Zhuhai519082 China Zhejiang University State Key Laboratory of Fluid Power and Mechatronic Systems Engineering Research Center for Design Engineering and Digital Twin of Zhejiang Province School of Mechanical Engineering Robotics Institute Hangzhou310027 China Southwest Jiaotong University Faculty of Geosciences and Engineering Chengdu610032 China China Agricultural University College of Land Science and Technology Beijing100107 China Ministry of Agriculture and Rural Affairs Key Laboratory of Remote Sensing for Agri-Hazards Beijing100125 China Tsinghua University Tsinghua Shenzhen International Graduate School Shenzhen518071 China Tsinghua University Ministry of Education Key Laboratory for Earth System Modeling Department of Earth System Science Beijing100190 China National Supercomputer Center in Shenzhen Shenzhen518071 China

While domain adaptation (DA) methods have made significant strides in remote sensing community, most current works assume that the source domain labels are accurate. However, limited emphasis has been placed on the scenario where source data are mislabeled with noisy annotations, which is more common in real applications and referred to as noisy DA (NDA). This article formulates remote sensing cross-scene classification on NDA scenarios and proposes a novel network called bilateral adaptation network (BAN), which consists of two parts: 1) forward learning (FL), which utilizes a model learning from the noisy source domain and transfers knowledge to target domain;and 2) backward learning (BL), which utilizes a dual model to acquire knowledge from the target domain and transfer it to source domain. We conduct two parts alternately and adopt a symmetrical Kullback-Leibler (KL) loss to align predictions of the model and its dual model in the same domain. This interactive strategy is able to explore bilateral relationships between domains, implicitly reducing label noise in the source domain. In addition, BAN could serve as a universal paradigm to not only improve the existing NDA methods but also enhance recent DA approaches. Comprehensive evaluations on three publicly available RGB-band remote sensing datasets and two hyperspectral datasets validate the superior effectiveness of our proposed BAN. BAN improves the average accuracy by 6.70%-15.70% on RGB datasets and overall accuracy (OA) by 1.36%-3.14% on hyperspectral datasets with flip-20% noise compared to other state-of-the-art DA and NDA approaches. Promising results indicate the potential of our approach in tackling more general and practical problems with noisy source domain. © 2025 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Banana Pseudostem-Inspired Fluidic Photothermal Structure Towards Efficient Solar Steam Generation and Continuous Salt Rejecting

SSRN

引用

SSRN 2023年

作者： Xiao, Juanxiu Li, Jiakai Lv, Rongxin Li, Guiqiu Luo, Wenqi Wang, Jiashui Xia, Meng Zhao, Peng Chen, Yongyao Wu, Senjia Chen, Qi Shen, Yijun Li, Meng Xiao, Wei Dong, Wang State Key Laboratory of Marine Resource Utilization in South China Sea State Key Laboratory of Digital Medical Engineering Key Laboratory of Biomedical Engineering of Hainan Province School of Biomedical Engineering Hainan University Haikou570228 China Key Laboratory of Crop Gene Resources and Germplasm Enhancement in Southern China Ministry of Agriculture Tropical Crops Genetic Resources Institute Chinese Academy of Tropical Agricultural Sciences Haikou571101 China MOE Key Laboratory of Low-grade Energy Utilization Technologies and Systems CQU-NUS Renewable Energy Materials & Devices Joint Laboratory School of Energy & Power Engineering Chongqing University Chongqing400044 China School of Resource and Environmental Sciences Hubei International Scientific and Technological Cooperation Base of Sustainable Resource and Energy Wuhan University Wuhan430072 China

Solar-driven steam generation (SSG) is emerging as a promising off-grid strategy to relieve freshwater shortage. In recent years, extensive research works have been conducted to develop full biomass-based SSGs due to their unique hierarchical structural features. However, the long-term durability of biomass-based SSGs remains a concern. Herein, the discarded banana pseudostems have been demonstrated as an excellent potential SSG through a simple surface flame treatment. Firstly, the well-developed pore structure, superior light absorbance, extremely low thermal conductivity and superhydrophilic properties of the surface carbonized banana pseudostem (SCBP) have been well revealed respectively. In addition, it is also demonstrated that the SCBP evaporator can achieve an impressive evaporation rate of up to 2.548 kg∙m-2·h-1 with a 91.96% solar-thermal conversion efficiency superior to most reported biomass based SSGs. Furthermore, a SCBP inspired one-way fluidic photothermal structure is dedicatedly constructed. It is found that the salinity on the top surface of the SCBP evaporator remains far below 26 wt% and the evaporation rate is maintained at 2.384 kg∙m-2·h-1 in a 15 wt% NaCl solution even after 200 hours. Finally, from a proof-of-concept demonstration, the SCBP evaporator also shows an excellent water purification and seawater desalination performance in a real ocean situation. © 2023, The Authors. All rights reserved.

关键词： Sodium chloride

来源：评论

学校读者我要写书评

暂无评论

Volatolomics in healthcare and its advanced detection technology

引用

Nano Research 2022年第9期15卷 8185-8213页

作者： Wenwen Hu Weiwei Wu Yingying Jian Hossam Haick Guangjian Zhang Yun Qian Miaomiao Yuan Mingshui Yao School of Aerospace Science and Technology Xidian UniversityXi’an 730107China Interdisciplinary Research Center of Smart Sensors School of Advanced Materials and NanotechnologyXidian UniversityXi’an 730107China Faculty of Chemical Engineering and Russell Berrie Nanotechnology Institute Technion-Israel Institute of TechnologyHaifa 3200002Israel Department of Thoracic Surgery The First Affiliated Hospital of Xi’an Jiaotong UniversityXi’an 710061China Stomatology Hospital School of StomatologyZhejiang University School of MedicineClinical Research Center for Oral Diseases of Zhejiang Province Key Laboratory of Oral Biomedical Research of Zhejiang ProvinceCancer Center of Zhejiang UniversityHangzhou 310006China The Eighth Affiliated Hospital Sun Yat-sen UniversityShenzhen 518033China State Key Laboratory of Multi-phase Complex Systems Institute of Process EngineeringChinese Academy of SciencesBeijing 310006China Institute for Integrated Cell-Material Sciences Kyoto University Institute for Advanced StudyKyoto UniversityKyoto 606-8501Japan

Various diseases increasingly challenge the health status and life quality of human *** emitted from patients has been considered as a potential family of markers,volatolomics,for diagnosis/*** are two fundamental issues of volatolomics in *** one hand,the solid relationship between the volatolome and specific diseases needs to be clarified and *** the other hand,effective methods should be explored for the precise detection of *** comprehensive review articles had been published in this ***,a timely and systematical summary and elaboration is still *** this review article,the research methodology of volatolomics in healthcare is critically considered and given out,at ***,the sets of volatolome according to specific diseases through different body sources and the analytical instruments for their identifications are systematically ***,the advanced electronic nose and photonic nose technologies for volatile organic compounds(VOCs)detection are well *** existed obstacles and future perspectives are deeply thought and *** article could give a good guidance to researchers in this interdisciplinary field,not only understanding the cutting-edge detection technologies for doctors(medicinal background),but also making reference to clarify the choice of aimed VOCs during the sensor research for chemists,materials scientists,electronics engineers,etc.

关键词： volatolomics electronic nose disease diagnosis sensor artificial olfaction volatile organic compounds

来源：评论

学校读者我要写书评

暂无评论

Towards Autonomous Robotic Ultrasound Scanning Using the Reinforcement Learning-Based Volumetric Data Navigation Method

Towards Autonomous Robotic Ultrasound Scanning Using the Rei...

引用

WRC Symposium on Advanced robotics and Automation (WRC SARA)

作者： Cuifeng Shen Zhaokun Deng Jinzhi Wang Shuangyi Wang Chen Chen Department of Mechanics and Engineering Science College of Engineering State Key Laboratory for Turbulence and Complex Systems Peking University Beijing P. R. China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing China Centre for Artificial Intelligence and Robotics Hong Kong Institute of Science & Innovation Chinese Academy of Sciences Hong Kong China

Ultrasound scanning is an indispensable diagnostic tool in modern medicine, but obtaining an accurate standard plane relies heavily on the sonographer’s skill and expertise. This paper presents a novel approach toward autonomous robotic ultrasound scanning using a reinforcement learning-based navigation method with volumetric ultrasound data. The proposed method enables an ultrasound robot to autonomously acquire high-quality 2D standard planes from patients, thereby reducing the need for human intervention. The core of the approach is a deep reinforcement learning algorithm that detects 2D standard planes within the 3D ultrasound volume and guides the ultrasound probe to extract high-quality standard planes. To assess the effectiveness of the 2D standard plane detection method, an evaluation was conducted using a realworld ultrasound dataset, and a comparison was made between its performance and that of other state-of-the-art autonomous approaches. The simulation experiment was also conducted to validate the autonomous robotic ultrasound acquisition workflow. Results demonstrate that the reinforcement learning-based volumetric data navigation method outperforms existing techniques in terms of standard plane accuracy and is very effective for volumetric data-based robotic navigation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Editorial: Characterization and application of magneto-sensitive soft materials

引用

Frontiers in Materials 2023年 10卷

作者： Zhang, Zhili Li, Decai Yu, Miao Niu, Xiaodong Li, Weihua Institute of Magnetic Fluids School of Mechanical Electronic and Control Engineering Beijing Jiaotong University Beijing China State Key Laboratory of Tribology Tsinghua University Beijing China Key Laboratory for Optoelectronic Technology and Systems Ministry of Education College of Optoelectronic Engineering Chongqing University Chongqing China Department of Mechanical Engineering College of Engineering Shantou University Shantou China School of Mechanical Materials Mechatronic and Biomedical Engineering University of Wollongong WollongongNSW Australia

Magnetic fluids are nanocolloids made up of nanometer-sized ferromagnetic particles dispersing in a carrier liquid (typically comprises three parts: base carrier liquid, surfactant, and ferromagnetic particles). Since the particles are easier to agglomerate, ferromagnetic particles are typically coated with surfactants to prevent agglomeration. Magnetic nanoparticles are uniformly disseminated in the carrier liquid with the assistance of surfactants, which play a crucial role in the magnetic fluid composition. Li et al. systematically studied the coating state and colloidal stability of oleic acid (OA) and 3-(N,N-Dimethylmyristylammonio) propanesulfonate (DP) coated magnetite nanoparticles in the polar and apolar carrier liquid. The total Gibbs interfacial energy was analyzed based on Van Oss-Chaudhry-Good and DLVO theory to describe the behaviors of coated particles in solvents. Zang et al. studied the effect of different fatty acids as surfactants on the rheological properties of magnetic fluids. The results showed that the mixed fatty acids showed greater viscosity growth and a greater slope of the viscosity growth curve than the magnetic fluids dispersed with a single acid. This indicates that the mixed fatty acids have more stable rheological properties. The viscousity-temperature performance of kerosene-base magnetic fluids at low temperatures can be improved by adjusting the ratio of mixed fatty acids. The most typical application of magnetic liquids is sealing, which has the outstanding advantages of zero leakage, long life and low resistance. Magnetic fluid seals as a class of non-contact sealing technology have been a research focus. In order to solve the problem of the pole shoes in the ferrofluid seal are easily damaged under the situation of the large radial beating of the main shaft. Liu et al. proposed a new structure of the ferrofluid seal that use a redial-changed ring magnet as the magnetic source. Considering that the ring magnets have problems o

关键词： magnetic fluids (MF) magnetorheological fluids (MRF) magneto-sensitive soft materials non-contact sealing torsional vibration damper intelligent material energy absorber

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：