检索结果-内蒙古大学图书馆

Robotics, Artificial Intelligence and Intelligent Control (RAIIC), International Conference on

作者： Qilong Wang Junlei Song Chao Zuo Kaifeng Dong Fang Jin School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo- Exploration Ministry of Education Wuhan China Wuhan Second Ship Design and Research Institute Wuhan China

ISBN: (数字)9798350352627

ISBN: (纸本)9798350352634

Aeromagnetic surveys, renowned for their operational flexibility and high efficiency, serve as a crucial technique for measuring the geomagnetic field. However, aeromagnetic surveys are easily affected by magnetic interference from navigation platforms, making the compensation of aeromagnetic interference a crucial step in the measurement process. To address the inadequate consideration of nonlinear magnetic field interference in traditional compensation algorithms, this paper introduces an aeromagnetic compensation approach based on broad learning system. The broad learning system employs an incremental learning mechanism aimed at enhancing the precision of the network alongside the increase in nodes. With each expansion of the network node, computation is streamlined to calculating the pseudo-inverse of the expansion node, eliminating the necessity for retraining the entire network structure. Leveraging the nonlinear fitting characteristics of the broad learning system, this paper improves the accuracy of aeromagnetic interference compensation. Through UAV flight experiments, the broad learning system is compared with methodologies using particle swarm optimization (PSO) and BP neural network. Compared with PSO, training time was reduced by $21.3 \%$ and magnetic interference by $33.6 \%$. Compared with BP neural networks, training time was reduced by $34.9 \%$ and magnetic interference by $28.6 \%$. This paper provides references and ideas for the selection of aeromagnetic interference compensation algorithms.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Autonomous On-ramp Merge Strategy Using Deep Reinforcement Learning in Uncertain Highway Environment

Autonomous On-ramp Merge Strategy Using Deep Reinforcement L...

引用

2022 IEEE International Conference on Unmanned systems, ICUS 2022

作者： Wu, Sifan Tian, Daxin Zhou, Jianshan Duan, Xuting Sheng, Zhengguo Zhao, Dezong Beijing Key Laboratory For Cooperative Vehicle Infrastructure Systems&Safety Cooperative Control Beijing China Beijing Advanced Innovation Center For Big Data and Brain Computing Beijing China Department of Engineering and Design Richmond United Kingdom University of Sussex Richmond United Kingdom James Watt School of Engineering Glasgow United Kingdom University of Glasgow Glasgow United Kingdom

ISBN: (数字)9781665484565

ISBN: (纸本)9781665484565

On-ramp merge is a complex traffic scenario in autonomous driving. Because of the uncertainty of the driving environment, most rule-based models cannot solve such a problem. In this study, we design a Deep Reinforcement Learning (DRL) method to solve the issue of ramp merges in uncertain scenarios and modify the structure of the Twin Delayed Deep Deterministic policy gradient algorithm (TD3), using Long Short-Term Memory (LSTM) to select an action based on temporal information. The proposed method is applied in the on-ramp merge and verified in the Simulation of Urban Mobility (SUMO). Results show that the proposed method performs significantly better generalization in uncertain traffic scenarios. © 2022 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Adversarial Learning Network for Recovering Rppg Signals from Low-Resolution Images for Remote Heart Rate Measurement

SSRN

引用

SSRN 2024年

作者： Zhai, Dezhao Chen, Wei Li, Qinwei Yu, Ming Wu, Hang Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control School of Mechanical Engineering Tianjin University of Technology Tianjin300384 China Systems Engineering Institute Academy of Military Sciences People's Liberation Army Tianjin300161 China Tianjin Key Laboratory for Advanced Signal Processing Civil Aviation University of China Tianjin300300 China School of Artificial Intelligence Nankai University Tianjin300381 China

Remote Photoplethysmography (rPPG) is a non-contact method for measuring heart rate (HR) through facial video, which has significant research value and application potential. However, in long-distance vital sign measurement tasks, the low resolution of facial images and insufficient pixels in the facial region severely degrade the quality of the rPPG signals, leading to a sharp decline in HR accuracy. To address this issue, this paper proposes an adversarial learning network for recovering rPPG signals from low-resolution images (ALRSL-HR). First, arbitrary resolution face images are fed into multi-channel network to extract rPPG signal features capturing rich rPPG information, generating rPPG feature blocks, and temporally aggregating for richer feature representation. These features are then inputted into the backbone network to generate adversarial examples of rPPG signals of varying qualities. Finally, a two-stage adversarial loss function is employed to enable the low-quality rPPG signals to learn the periodic characteristics of high-quality rPPG signals, recover the low-quality signals, and narrow the quality gap between rPPG signals from low-resolution images. Extensive experiments were conducted in this paper to validate the effectiveness of our model on the public COHFACE, UBFC-Phys and UBFC-rPPG datasets. The results of the experiments demonstrate that the proposed ALRSL-HR model can effectively recover degraded rPPG signals from low-resolution images. © 2024, The Authors. All rights reserved.

关键词： Photoplethysmography

来源：评论

学校读者我要写书评

暂无评论

Surgical Gesture Recognition in Open Surgery Based on 3DCNN and SlowFast

Surgical Gesture Recognition in Open Surgery Based on 3DCNN ...

引用

IEEE Information Technology, Networking, Electronic and Automation Control Conference

作者： Yutao Men Jian Luo Zixian Zhao Hang Wu Feng Luo Guang Zhang Ming Yu Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control School of Mechanical Engineering Tianjin University of Technology Tianjin China National Demonstration Center for Experimental Mechanical and Electrical Engineering Education(Tianjin University of Technology) Tianjin China Systems Engineering Institute Academy of Military Sciences People's Liberation Army Tianjin China

ISBN: (数字)9798350370805

ISBN: (纸本)9798350370812

In the field of computer-aided medicine, automated surgical gesture recognition is an important research direction. Its main applications include automated skills assessment, intraoperative guidance, and education and training systems. Current research has focused on robotic surgery, and there is less research on surgical gestures for open surgery. Therefore, in this study, a new simulated open surgery dataset was developed, and a series of surgical gestures for open surgery were defined for closure the abdomen surgery with the cooperation of professional doctors. In addition, this paper uses the classical algorithm 3DCNN and SlowFast model in the field of action recognition to perform offline recognition of surgical gestures for open surgery on the dataset. 3DCNN uses R3D and R(2+1)D models. The experimental results show that on the self-built open surgical dataset, the R3D model has the best surgical gesture recognition results, with an accuracy rate of 90.4%, a precision rate of 90.5%, and a recall rate of 90.0%.

关键词： Training Automation Accuracy Surgery Gesture recognition Medical services Information technology Robots Abdomen

来源：评论

学校读者我要写书评

暂无评论

Core-Shell Metal-Organic Frameworks with Tunable Shell Structure as Stationary Phase for High Performance Liquid Chromatography

SSRN

引用

SSRN 2023年

作者： Wang, Jiafei He, Yuqing Wan, Xiang Xie, Fazhi Sun, Yuanshe Li, Tong Xu, Qin Zhao, Donglin Qu, Qishu Key Laboratory of Functional Molecule Design and Interface Process Anhui Province Engineering Laboratory of Advanced Building Materials School of Materials and Chemical Engineering Anhui Jianzhu University Hefei230601 China Key Laboratory of Advanced Catalytic Materials and Reaction Engineering School of Chemistry and Chemical Engineering Hefei University of Technology Hefei230009 China Dalian Elite Analytical Instruments Co. Ltd. Dalian116023 China College of Chemistry and Chemical Engineering Yangzhou University Yangzhou225002 China

Composite SSU spheres were prepared by coating SiO2 core-shell spheres (SiO2@dSiO2) with a metal-organic framework UiO-66. By controlling the concentration of Zr4+, the obtained SSU spheres have two different morphologies: layer-on-sphere and spheres-on-sphere. The structure of the layer-on-sphere is the surface of SiO2@dSiO2 covered with a layer of UiO-66 nanocrystals. SSU with this structure has only a characteristic pore size of about 1 nm belonging to UiO-66 and is therefore not suitable as a packed stationary phase for high performance liquid chromatography. The spheres-in-sphere structure of SSU has a 45 nm mesopores formed by the accumulation of UiO-66 nanocrystals on the surface of SiO2@dSiO2 in addition to the characteristic micropores of UiO-66 of about 1 nm. Moreover, SiO2@dSiO2 was coated with UiO-66 both inside and outside the pores, resulting in a 27% loading of UiO-66 in the SSU. The SSU spheres were packed into columns and tested for the separation of xylene isomers, aromatics, biomolecules, acidic and basic mixtures. With both micropores and mesopores, SSU achieves excellent separation of both small and large molecules. Efficiencies up to 48150, 50452 and 41318 plates m-1 were achieved for m-xylene, p-xylene and o-xylene, respectively. The relative standard deviations of the retention times of anilines for run-to-run, day-to-day and column-to-column were all lower than 6.1%. The results demonstrate the SSU possessing great prospect for high performance chromatographic separation. © 2023, The Authors. All rights reserved.

关键词： High performance liquid chromatography

来源：评论

学校读者我要写书评

暂无评论

GUEST EDITORIAL

引用

China Communications 2023年第2期 3-6页

作者： Yuan Wu Xu Chen Feng Lyu Xianfu Chen Xumin Huang Jie Gao Yueyue Dai Tony Q.S.Quek Yan Zhang the State Key Laboratory of Internet of Things for Smart City University of Macau the Department of Computer and Information Science University of Macau Sun Yat-sen University Sun Yat-sen University Institute of Advanced Networking and Computing Systems Sun Yat-sen University National and Local Joint Engineering Laboratory the School of Computer Science and Engineering Central South University the VTT Technical Research Centre of Finland the School of Automation Guangdong University of Technology the School of Information Technology Carleton University Huazhong University of Science and Technology Singapore University of Technology and Design(SUTD) the IEEE Communications Society Technical Committee on Green Communications and Computing(TCGCC)

With the growing maturity of the advanced edge-cloud collaboration and integrated sensing-communication-computing systems, edge intelligence has been envisioned as one of the enabling technologies for ubiquitous and l...

关键词：

来源：评论

学校读者我要写书评

暂无评论

Advancing electrochemical impedance analysis through innovations in the distribution of relaxation times method

引用

Joule 2024年第7期8卷 1958-1981页

作者： Maradesa, Adeleke Py, Baptiste Huang, Jake Lu, Yang Iurilli, Pietro Mrozinski, Aleksander Law, Ho Mei Wang, Yuhao Wang, Zilong Li, Jingwei Xu, Shengjun Meyer, Quentin Liu, Jiapeng Brivio, Claudio Gavrilyuk, Alexander Kobayashi, Kiyoshi Bertei, Antonio Williams, Nicholas J. Zhao, Chuan Danzer, Michael Zic, Mark Wu, Phillip Yrjänä, Ville Pereverzyev, Sergei Chen, Yuhui Weber, André Kalinin, Sergei V. Schmidt, Jan Philipp Tsur, Yoed Boukamp, Bernard A. Zhang, Qiang Gaberšček, Miran O'Hayre, Ryan Ciucci, Francesco Department of Mechanical and Aerospace Engineering The Hong Kong University of Science and Technology Hong Kong Metallurgical and Materials Engineering Colorado School of Mines Golden80401 United States Beijing Key Laboratory of Green Chemical Reaction Engineering and Technology Department of Chemical Engineering Tsinghua University Beijing China Green Energy Storage Trento38123 Italy Department of Manufacturing and Production Engineering Faculty of Mechanical Engineering and Ship Technology Institute of Machine and Materials Technology Gdańsk University of Technology Gdańsk Poland Electrode Design for Electrochemical Energy Systems University of Bayreuth Bayreuth Germany School of Chemistry University of New South Wales Sydney Australia School of Advanced Energy Sun Yat-Sen University Shenzhen China Sustainable Energy Center CSEM Neuchâtel2002 Switzerland Interdisciplinary Faculty of Science and Engineering Shimane University Matsue Japan Centre for Electronic and Optical Materials National Institute for Materials Science Tsukuba Japan Department of Civil and Industrial Engineering University of Pisa Pisa Italy Department of Materials Imperial College London Exhibition Road LondonSW7 2AZ United Kingdom Department of Chemical Engineering Massachusetts Institute of Technology Cambridge02139 United States Electrical Energy Systems University of Bayreuth Bayreuth Germany Ruder Boskovic Institute Zagreb Croatia Department of Materials and Minerals Resources Engineering National Taipei University Taipei Taiwan Finland Johann Radon Institute for Computational and Applied Mathematics Linz Austria School of Science and Engineering Nanjing Tech. University Nanjing China Karlsruhe Germany Department of Materials Science and Engineering University of Tennessee KnoxvilleTN37996 United States Physical Science Division Pacific Northwest National Laboratory RichlandWA99354 United States Systems Engineering for Electrical Energy Storage University of B

Electrochemical impedance spectroscopy (EIS) is widely used in electrochemistry, energy sciences, biology, and beyond. Analyzing EIS data is crucial, but it often poses challenges because of the numerous possible equivalent circuit models, the need for accurate analytical models, the difficulties of nonlinear regression, and the necessity of managing large datasets within a unified framework. To overcome these challenges, non-parametric models, such as the distribution of relaxation times (DRT, also known as the distribution function of relaxation times, DFRT), have emerged as promising tools for EIS analysis. For example, the DRT can be used to generate equivalent circuit models, initialize regression parameters, provide a time-domain representation of EIS spectra, and identify electrochemical processes. However, mastering the DRT method poses challenges as it requires mathematical and programming proficiency, which may extend beyond experimentalists’ usual expertise. Post-inversion analysis of DRT data can be difficult, especially in accurately identifying electrochemical processes, leading to results that may not always meet expectations. This article examines non-parametric EIS analysis methods, outlining their strengths and limitations from theoretical, computational, and end-user perspectives, and provides guidelines for their future development. Moreover, insights from survey data emphasize the need to develop a large impedance database, akin to an impedance genome. In turn, software development should target one-click, fully automated DRT analysis for multidimensional EIS spectra interpretation, software validation, and reliability. Particularly, creating a collaborative ecosystem hinged on free software could promote innovation and catalyze the adoption of the DRT method throughout all fields that use impedance data. © 2024 Elsevier Inc.

关键词： Electrochemical impedance spectroscopy

来源：评论

学校读者我要写书评

暂无评论

An Ontology-based Knowledge Modeling towards Eco-design for Additive Manufacturing

引用

Procedia CIRP 2024年 122卷 760-765页

作者： Yanan Wang Tao Peng Samyeon Kim Yi Xiong Yunlong Tang Renzhong Tang State Laboratory of Fluid Power Components and Mechatronic Systems School of Mechanical Engineering Zhejiang University Hangzhou 310058 China Department of Mechanical Engineering Jeonju University Jeonju-si Jeollabuk-do 55069 South Korea School of System Design and Intelligent Manufacturing Southern University of Science and Technology Shenzhen 518055 China Mechanical and Aerospace Engineering Department Monash University Melbourne 3800 Australia Materials Science and Engineering Department Monash University Melbourne 3800 Australia Zhejiang Province Key Laboratory of Advanced Manufacturing Technology School of Mechanical Engineering Zhejiang University Hangzhou 310058 China

Owing to the unique technological merits of additive manufacturing (AM), design for AM, particularly eco-design for AM, has been gaining attention in improving the sustainable performance of AM-fabricated (AMed) parts. The main challenge in harvesting potential sustainability benefits is how to capture the impact of design on sustainable performance. Though several existing studies adopted quantitative evaluation on AM sustainability and investigated the relationships between design information and sustainability information of AMed part, the sustainability information is still unavailable in the design phase. This hardly guides eco-design for AM in practice. To support the increasing industrial applications of AM, this paper illustrates related knowledge, that is, material-process-structure-ecoProperty (MPSeP) relationships to connect design and sustainability information in eco-design for AM. An ontology-based method is proposed to model the MPSeP relationships of the AMed part in a structured way. An example of an AMed hydraulic valve body was used to demonstrate the MPSeP modeling process. It is discussed that how the constructed model effectively assists AM designers through providing eco-design recommendation, and enables design software tools to perform sustainability analysis towards eco-design for AM.

关键词： additive manufacturing eco-design for additive manufacturing ontology model sustainability

来源：评论

学校读者我要写书评

暂无评论

Federated Graph Learning via Constructing and Sharing Feature Spaces for Cross-Domain IoT

引用

IEEE Internet of Things Journal 2025年

作者： Chen, Jiale Zhuo, Shengda He, Jinchun Qiu, Wangjie Zhang, Qinnan Xiong, Zehui Zheng, Zhiming Tang, Yin Chen, Min Wang, Changdong Huang, Shuqiang Jinan University College of Cyber Security Guangzhou China Beihang University Institute of Artificial Intelligence Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing Beijing100191 China Zhongguancun Laboratory Beijing China Singapore University of Technology and Design Information Systems Technology and Design 487372 Singapore Jinan University School of Management Guangzhou China South China University of Technology School of Computer Science and Engineering Guangzhou China Sun Yat-sen University School of Computer Guangzhou China Jinan University College of Cyber Security of Jinan University China Guangdong Key Laboratory of Data Security and Privacy Preserving Guangzhou China

The Internet of Things (IoT) collects large volumes of diverse data, with graph data as a critical component, and extensively utilizes Federated Graph Learning (FGL) to process this data while preserving data security. However, the graph data collected by different IoT institutions are relatively independent due to various factors (e.g., data collection methods, geographical locations), and data access is restricted to local environments due to privacy constraints, IoT institutions typically possess heterogeneous feature spaces. Aggregating under these conditions could potentially contaminate local graph representations. Unfortunately, most existing FGL methods tend to overlook this issue. To address this challenge, we propose Federated Graph Learning via Constructing and Sharing Features (FedCSF), a novel FGL framework designed to build a globally consistent feature space and share it among IoT institutions. To construct and extract the feature space, we employ an uniform feature initialization across IoT institutions and design an encoder to extract both global and local feature relationships, thereby facilitating effective collaboration across data from different IoT institutions. Furthermore, we introduce an independent adaptive aggregation strategy to eliminate the integration of harmful knowledge, ensuring that the contributions from each IoT institution are effectively integrated into the global model. We theoretically analyze the convergence of FedCSF. To validate the effectiveness of FedCSF, we conducted extensive experiments under various settings (i.e., cross-datasets, and cross-domains), demonstrating its significant advantages of FedCSF in terms of performance, convergence speed, and practical adaptability © 2014 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Uncertainty aware and explainable diagnosis of retinal disease

arXiv

引用

arXiv 2021年

作者： Singh, Amitojdeep Sengupta, Sourya Rasheed, Mohammed Abdul Jayakumar, Varadharajan Lakshminarayanan, Vasudevan Theoretical and Experimental Epistemology Laboratory School of Optometry and Vision Science University of Waterloo WaterlooON Canada Department of Systems Design Engineering University of Waterloo WaterlooON Canada

Deep learning methods for ophthalmic diagnosis have shown considerable success in tasks like segmentation and classification. However, their widespread application is limited due to the models being opaque and vulnerable to making a wrong decision in complicated cases. Explainability methods show the features that a system used to make prediction while uncertainty awareness is the ability of a system to highlight when it is not sure about the decision. This is one of the first studies using uncertainty and explanations for informed clinical decision making. We perform uncertainty analysis of a deep learning model for diagnosis of four retinal diseases - age-related macular degeneration (AMD), central serous retinopathy (CSR), diabetic retinopathy (DR), and macular hole (MH) using images from a publicly available (OCTID) dataset. Monte Carlo (MC) dropout is used at the test time to generate a distribution of parameters and the predictions approximate the predictive posterior of a Bayesian model. A threshold is computed using the distribution and uncertain cases can be referred to the ophthalmologist thus avoiding an erroneous diagnosis. The features learned by the model are visualized using a proven attribution method from a previous study. The effects of uncertainty on model performance and the relationship between uncertainty and explainability are discussed in terms of clinical significance. The uncertainty information along with the heatmaps make the system more trustworthy for use in clinical settings. © 2021, CC BY.

关键词： Eye protection

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：