检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Gan, Weijie Sun, Yu Eldeniz, Cihat Liu, Jiaming An, Hongyu Kamilov, Ulugbek S. The Department of Computer Science & Engineering Washington University in St. Louis St. LouisMO63130 United States The Mallinckrodt Institute of Radiology Washington University in St. Louis St. LouisMO63130 United States The Department of Electrical & System Engineering Washington University in St. Louis St. LouisMO63130 United States The Mallinckrodt Institute of Radiology Department of Neurology Department of Biomedical Engineering Saint LouisMO63130 United States The Division of Biology and Biomedical Sciences Washington University in St. Louis St. LouisMO63130 United States The Department of Computer Science & Engineering and Electrical & Systems Engineering Washington University in St. Louis St. LouisMO63130 United States

Deep neural networks for medical image reconstruction are traditionally trained using high-quality ground-truth images as training targets. Recent work on Noise2Noise (N2N) has shown the potential of using multiple noisy measurements of the same object as an alternative to having a ground-truth. However, existing N2N-based methods are not suitable for learning from the measurements of an object undergoing nonrigid deformation. This paper addresses this issue by proposing the deformation-compensated learning (DeCoLearn) method for training deep reconstruction networks by compensating for object deformations. A key component of DeCoLearn is a deep registration module, which is jointly trained with the deep reconstruction network without any ground-truth supervision. We validate DeCoLearn on both simulated and experimentally collected magnetic resonance imaging (MRI) data and show that it significantly improves imaging quality. Copyright © 2021, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Hohmann transfer via constrained optimization

引用

Frontiers of Information Technology & Electronic engineering 2018年第11期19卷 1444-1458页

作者： Li XIE Yi-qun ZHANG Jun-yan XU State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources School of Control and Computer EngineeringNorth China Electric Power UniversityBeijing 102206China Beijing Institute of Electronic Systems Engineering Beijing 100854China

Inspired by the geometric method proposed by Jean-Pierre MAREC, we first consider the Hohmann transfer problem between two coplanar circular orbits as a static nonlinear programming problem with an inequality constraint. By the Kuhn-Tucker theorem and a second-order sufficient condition for minima, we analytically prove the global minimum of the Hohmann transfer. Two sets of feasible solutions are found: one corresponding to the Hohmann transfer is the global minimum and the other is a local minimum. We next formulate the Hohmann transfer problem as boundary value problems, which are solved by the calculus of variations. The two sets of feasible solutions are also found by numerical examples. Via static and dynamic constrained optimizations, the solution to the Hohmann transfer problem is re-discovered, and its global minimum is analytically verified using nonlinear programming.

关键词： Hohmann transfer Nonlinear programming Constrained optimization Calculus of variations

来源：评论

学校读者我要写书评

暂无评论

A Comparison of Machine Learning Algorithms for Fall Detection using Wearable Sensors

A Comparison of Machine Learning Algorithms for Fall Detecti...

引用

International Conference on Artificial Intelligence in Information and Communication (ICAIIC)

作者： Nicolas Zurbuchen Pascal Bruegger Adriana Wilde Institute of Complex Systems (iCoSys) School of Engineering and Architecture of Fribourg Switzerland HES-SO University of Applied Sciences and Arts Western Switzerland Fribourg Switzerland Centre for Health Technologies (CHT) School of Electronics and Computer Science University of Southampton Southampton United Kingdom

ISBN: (数字)9781728149851

ISBN: (纸本)9781728149868

The proportion of people 60 years old and above is expected to double globally to reach 22 % by 2050. This creates societal challenges such as the increase of age-related illnesses and the need for caregivers. Falls are a major threat for the elderly, often causing serious injuries especially when the fallen person stays on the ground for a long time without assistance. This paper presents the development of a Fall Detection system (FDS) using an accelerometer combined with a gyroscope worn at the waist. Data come from SisFall, a publicly available dataset containing records of Activities of Daily Living and falls. We compared five Machine Learning algorithms. We first applied preprocessing and a feature extraction stage before using five Machine Learning algorithms, allowing us to compare them. Ensemble learning algorithms such as Random Forest and Gradient Boosting have the best performance, with a Sensitivity and Specificity both close to 99%.

关键词： Feature extraction Sensors Legged locomotion Senior citizens Machine learning algorithms Accelerometers Biomedical monitoring

来源：评论

学校读者我要写书评

暂无评论

A reinforcement learning approach for the autonomous assembly of in-space habitats and infrastructures in uncertain environments 70

A reinforcement learning approach for the autonomous assembl...

引用

70th International Astronautical Congress, IAC 2019

作者： Moser, Joshua Cooper, John Neilan, James Chapin, Liam Glassner, Samantha Komendera, Erik Department of Mechanical Engineering Virginia Polytechnic Institute State University United States Autonomous Integrated Systems Research Branch NASA Langley Research Center Flight Software System Branch NASA Langley Research Center Department of Computer Science Virginia Polytechnic Institute State University United States Department of Mechanical Engineering Northeastern University

NASA Langley Research Center has developed a robotic unit, the Assembler, for use in the domain of autonomous in-space assembly, capable of reconfiguration and collaboration. A known part of space mission scheduling and the autonomous collaborative assembly problem is task assignment. This problem can be thought of as a Markov decision process framing of a job shop scheduling problem which allows for a reinforcement learning solution to approximate the optimal policies for task assignment. The research presented here initiates the evaluation of reinforcement learning to that end. Simulation results show that the policies determined through reinforcement learning performed better than random and greedy policies. These promising results will support further research into the applicability and optimality of reinforcement learning in increasingly complex scenarios. Copyright © 2019 by the International Astronautical Federation (IAF). All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Transforming Disaster Risk Reduction With AI and Big Data: Legal and Interdisciplinary Perspectives

引用

Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery 2025年第2期15卷

作者： Chun, Kwok P. Octavianti, Thanti Dogulu, Nilay Tyralis, Hristos Papacharalampous, Georgia Rowberry, Ryan Fan, Pingyu Everard, Mark Francesch-Huidobro, Maria Migliari, Wellington Hannah, David M. Marshall, John Travis Calasanz, Rafael Tolosana Staddon, Chad Ansharyani, Ida Dieppois, Bastien Lewis, Todd R. Ponce, Juli Ibrean, Silvia Ferreira, Tiago Miguel Peliño-Golle, Chinkie Mu, Ye Delgado, Manuel Davila Espinoza, Elizabeth Silvestre Keulertz, Martin Gopinath, Deepak Li, Cheng School of Architecture and Environment University of the West of England Bristol United Kingdom Geneva Switzerland Construction Agency Hellenic Air Force Cholargos Greece Department of Land Environment Agriculture and Forestry University of Padova Legnaro Italy Georgia State University College of Law AtlantaGA United States Department of Urban Planning and Design The University of Hong Kong Hong Kong Department of Geography The University of Hong Kong Hong Kong Law School University of Barcelona Catalonia Barcelona Spain Birmingham Institute for Sustainability & Climate Action and School of Geography Earth & Environmental Sciences University of Birmingham Birmingham United Kingdom Department of Computer Science and Systems Engineering Universidad de Zaragoza Zaragoza Spain Department of Agriculture Universitas Samawa Sumbawa Besar Indonesia Coventry University Coventry United Kingdom UN Volunteer United Nations Volunteers Bonn Germany University of the West of England School of Engineering Bristol United Kingdom EcoWaste Coalition Manila Philippines Department of Geography University of California Santa BarbaraCA United States Birmingham City Business School Birmingham City University Birmingham United Kingdom Inclima Fornebu Oslo Norway American University of Beirut Beirut Lebanon Department of Ecology Yangzhou University Yangzhou China

Managing complex disaster risks requires interdisciplinary efforts. Breaking down silos between law, social sciences, and natural sciences is critical for all processes of disaster risk reduction. It is essential to explore how AI enhances understanding of legal frameworks and environmental management, while also examining how legal and environmental factors may limit AI's role in society. From a co-production review perspective, drawing on insights from lawyers, social scientists, and environmental scientists, principles for responsible data mining are proposed based on safety, transparency, fairness, accountability, and contestability. This discussion offers a blueprint for interdisciplinary collaboration to create adaptive law systems based on AI integration of knowledge from environmental and social sciences. When social networks are useful for mitigating disaster risks based on AI, the legal implications related to privacy and liability of the outcomes of disaster management must be considered. Fair and accountable principles emphasize environmental considerations and foster socioeconomic discussions related to public engagement. AI also has an important role to play in education, bringing together the next generations of law, social sciences, and natural sciences to work on interdisciplinary solutions in harmony. Although emerging AI approaches can be powerful tools for disaster management, they must be implemented with ethical considerations and safeguards to address concerns about bias, transparency, and privacy. The responsible execution of AI approaches, based on the dynamic interplay between AI, law, and environmental risk, promotes sustainable and equitable practices in data mining. © 2025 The Author(s). WIREs Data Mining and Knowledge Discovery published by Wiley Periodicals LLC.

关键词： Risk management

来源：评论

学校读者我要写书评

暂无评论

A novel Q-learning-based routing scheme using an intelligent filtering algorithm for flying ad hoc networks (FANETs)

引用

Journal of King Saud University - computer and Information Sciences 2023年第10期35卷

作者： Hosseinzadeh, Mehdi Ali, Saqib Ionescu-Feleaga, Liliana Ionescu, Bogdan-Stefan Yousefpoor, Mohammad Sadegh Yousefpoor, Efat Ahmed, Omed Hassan Rahmani, Amir Masoud Mehmood, Asif Institute of Research and Development Duy Tan University Da Nang Viet Nam School of Medicine and Pharmacy Duy Tan University Da Nang Viet Nam Department of Information Systems College of Economics and Political Science Sultan Qaboos University Al Khoudh Muscat Oman Department of Accounting and Audit Bucharest University of Economic Studies Bucharest 010374 Romania Department of Management Information System Bucharest University of Economic Studies Bucharest 010374 Romania Department of Computer Engineering Dezful Branch Islamic Azad University Dezful Iran Department of Information Technology University of Human Development Sulaymaniyah Iraq Future Technology Research Center National Yunlin University of Science and Technology Yunlin Taiwan Department of Biomedical Engineering Gachon University Gyeonggi-do Seongnam-si 13120 South Korea

The flying ad hoc network (FANET) is an emerging network focused on unmanned aerial vehicles (UAVs) that has attracted the attention of researchers around the world. Due to the cooperation between UAVs in this network, data transfer between these UAVs is very essential. Routing protocols must determine how to make routing paths for each UAV with others in a wireless ad hoc network to facilitate the data transmission between UAVs. Nowadays, reinforcement learning (RL), especially Q-learning, is an effective response for solving existing challenges in the routing approaches and adding features such as autonomous, self-adaptive, and self-learning to these approaches. In this paper, Q-learning is used to enhance and increase network performance, and a Q-learning-based routing method using an intelligent filtering algorithm called QRF is presented for FANETs. The main innovation in this paper is that QRF manages the size of the state space using the proposed filtering algorithm. This will increase the convergence rate of the Q-learning-based routing algorithm. On the other hand, QRF regulates the learning parameters related to Q-learning so that this scheme is better adapted to the FANET environment. In the last step, the network simulator version 2 (NS2) is employed to execute the simulation process related to QRF. In this process, five evaluation criteria, namely energy consumption, packet delivery rate, overhead, end-to-end delay, and network longevity are evaluated, and the results obtained from QRF are compared with those of QFAN, QTAR, and QGeo. The simulation results in this paper show that QRF makes a balanced energy distribution between UAVs and thus extends the network longevity. Moreover, the intelligent filtering algorithm designed in QRF has reduced delay in the routing process but is associated with communication overhead. © 2023 The Author(s)

关键词： Flying ad hoc networks (FANETs) Q-learning Reinforcement learning (RL) Routing Unmanned aerial vehicles (UAVs)

来源：评论

学校读者我要写书评

暂无评论

Mathematical Modelling of Electrically Controlled Filters of Microwave, subTHz and THz-bands on the Base of Grapheneand-Dielectric Multilayer Structure

Mathematical Modelling of Electrically Controlled Filters of...

引用

International Conference for Young Scientists on Issues of Physics and Technology in Science, Power Industry and Medicine 2019, IPTSPIM 2019

作者： Smirnov, I.A. Cherckesova, L.V. Zhebrun, E.A. Kleimenkin, D.V. Department of Cybersecurity of Information Systems Don State Technical University Gagarin Sq. 1 Rostov-on-Don344000 Russia Department of Mathematics and Computer Sciences Don State Technical University Gagarin Sq. 1 Rostov-on-Don344000 Russia Joint Stock Company "research Institute of Microelectronic Equipment" "progress" Cherepanov passage 54 Moscow125183 Russia Information System and Radio Engineering Department Don State Technical University Gagarin Sq. 1 Rostov-on-Don344000 Russia

Report is devoted to investigations of graphene meta-surfaces for the transmission of radiation induced by plasmons in subTHz and THz ranges, cell of which consists of structures based on graphene ring and graphene nano-tape. It create regimes of radiation transmission - transparency windows induced by electric dipole resonances. Resonant frequency of transparency window can be dynamically tuned in wide band of subTHz and THz bands by changing the chemical potential (Fermi energy) of graphene by applying external electric field (gating) instead of re-fabricating of structures. Questions of possibilities of electronic controlled filters creating of subTHz and THz bands grounded on different configurations of graphene meta-surfaces are discussed;their characteristics and frequency dependencies are investigated. Mathematical modelling and electrodynamic calculation of the filters characteristics of subTHz and THz bands grounded on multilayer structures of "graphene-dielectric" type are carried out. From results of mathematical modelling it follows that periodic layered microstructures "graphene-dielectric" type can be used for creation of subTHz and THz bands broadband filters of planar construction, controlling by electric field and fast tuning at small changes in Fermi energy level of graphene. © Published under licence by IOP Publishing Ltd.

关键词： Graphene

来源：评论

学校读者我要写书评

暂无评论

Anchor-based spatio-temporal attention 3D convolutional networks for dynamic 3D point cloud sequences

arXiv

引用

arXiv 2020年

作者： Wang, Guangming Chen, Muyao Liu, Hanwen Yang, Yehui Liu, Zhe Wang, Hesheng The Department of Automation Institute of Medical Robotics Key Laboratory of System Control and Information Processing Ministry of Education Key Laboratory of Marine Intelligent Equipment System of Ministry of Education Shanghai Jiao Tong University Shanghai200240 China Beijing Advanced Innovation Center for Intelligent Robots and Systems Beijing Institute of Technology China The Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai200240 China The Department of Computer Science and Technology University of Cambridge

With the rapid development of measurwement technology, LiDAR and depth cameras are widely used in the perception of the 3D environment. Recent learning based methods for robot perception most focus on the image or video, but deep learning methods for dynamic 3D point cloud sequences are underexplored. Therefore, developing efficient and accurate perception method compatible with these advanced instruments is pivotal to autonomous driving and service robots. An Anchor-based Spatio-Temporal Attention 3D Convolution operation (ASTA3DConv) is proposed in this paper to process dynamic 3D point cloud sequences. The proposed convolution operation builds a regular receptive field around each point by setting several virtual anchors around each point. The features of neighborhood points are firstly aggregated to each anchor based on the spatio-temporal attention mechanism. Then, anchor-based 3D convolution is adopted to aggregate these anchors' features to the core points. The proposed method makes better use of the structured information within the local region and learns spatio-temporal embedding features from dynamic 3D point cloud sequences. Anchor-based Spatio-Temporal Attention 3D Convolutional Neural Networks (ASTA3DCNNs) are built for classification and segmentation tasks based on the proposed ASTA3DConv and evaluated on action recognition and semantic segmentation tasks. The experiments and ablation studies on MSRAction3D and Synthia datasets demonstrate the superior performance and effectiveness of our method for dynamic 3D point cloud sequences. Our method achieves the state-of-the-art performance among the methods with dynamic 3D point cloud sequences as input on MSRAction3D and Synthia datasets. Copyright © 2020, The Authors. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Real Time Indoor Positioning system for Smart Grid based on UWB and Artificial Intelligence Techniques

Real Time Indoor Positioning System for Smart Grid based on ...

引用

Conference on Technologies for Sustainability (Sustech)

作者： Long Cheng Hao Chang Kexin Wang Zhaoqi Wu Power System Consulting ABB Inc. Raleigh NC USA Computer and Systems Engineering Rensselaer Polytechnic Institute Troy NY USA School of Mathematics University of Minnesota Twin Cities Minneapolis MN USA University of Illinois at Urbana-Champaign Champaign IL USA

ISBN: (数字)9781728131085

ISBN: (纸本)9781728131092

Indoor positioning system plays an important role in smart grid. Although GPS is the predominant outdoor positioning technology, it is unsuitable to be used in many fields of smart grid for three main reasons: first, signals sent from GPS could easily get blocked by solid materials such as metal or brick; second, the complex electromagnetic interference induced by electrical circuits greatly affects GPS signals; third, GPS can only achieve meter-level real time positioning accuracy, which is far from sufficient for many requirements of smart grid applications. Some other indoor positioning technologies, such as Bluetooth, Wi-Fi, ultrasound, infrared and RFID, fail in either the positioning accuracy, the positioning range, or the positioning speed required in many smart grid applications. Therefore, this paper proposes a real time indoor positioning system for smart gird based on a more promising technology, ultra-wideband (UWB). UWB is suitable for real-time localization in smart grid because UWB has short radio frequency pulse duration and wide bandwidth, which can minimize the effects of multipath interference and allow for high-resolution ranging and easier material penetration. In addition, since high-accuracy position information is required in many smart grid fields, a comprehensive framework integrating several artificial intelligence techniques, including outlier detection, line-of-sight/non-line-of-sight classification, filter design, range measurement correction and maximum likelihood localization estimation, is also proposed to further improve the positioning accuracy. At last, the performance of this system is verified through a series of experiments.

关键词： Smart grids Real-time systems Global Positioning system Position measurement Signal processing algorithms Pollution measurement Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

State of the Art of Audio- and Video-Based Solutions for AAL

arXiv

引用

arXiv 2022年

作者： Aleksic, Slavisa Atanasov, Michael Agius, Jean Calleja Camilleri, Kenneth Čartolovni, Anto Climent-Pérez, Pau Colantonio, Sara Cristina, Stefania Despotovic, Vladimir Ekenel, Hazım Kemal Erakin, Ekrem Florez-Revuelta, Francisco Germanese, Danila Grech, Nicole Sigurðardóttir, Steinunn Gróa Emirzeoğlu, Murat Iliev, Ivo Jovanovic, Mladjan Kampel, Martin Kearns, William Klimczuk, Andrzej Lambrinos, Lambros Lumetzberger, Jennifer Mucha, Wiktor Noiret, Sophie Pajalic, Zada Pérez, Rodrigo Rodriguez Petrova, Galidiya Petrovica, Sintija Pocta, Peter Poli, Angelica Pudane, Mara Spinsante, Susanna Salah, Albert Ali Santofimia, Maria Jose Islind, Anna Sigríður Stoicu-Tivadar, Lacramioara Tellioğlu, Hilda Zgank, Andrej Leipzig University of Applied Sciences Germany TU Wien Austria Department of Anatomy University of Malta Malta Centre for Biomedical Cybernetics Faculty of Engineering Department of Systems and Control Engineering Malta Catholic University of Croatia Croatia Universidad de Alicante Spain Institute of Information Science and Technologies The National Research Council of Italy Italy Department of Systems and Control Engineering University of Malta Malta University of Luxembourg Luxembourg Dept. of Computer Engineering Istanbul Technical University Turkey Reykjavik University School of Computer Science Iceland Sağlık Bilimleri Fakültesi Fizyoterapi ve Rehabilitasyon Karadeniz Technical University Research Information System Turkey TU Sofia Bulgaria Singidunum University Belgrade Serbia University of South Florida United States SGH Warsaw School of Economics Poland Department of Communication and Internet Studies Cyprus University of Technologies Cyprus Technical University of Vienna Austria VID Specialized University Oslo Norway Getafe University Hospital Spain Riga Technical University Latvia University of Zilina Slovakia Università Politecnica Marche Italy Utrecht University Netherlands Universidad de Castilla-La Mancha Spain Reykjavik University Iceland University Politehnica Timisoara Romania University of Maribor Slovenia

It is a matter of fact that Europe is facing more and more crucial challenges regarding health and social care due to the demographic change and the current economic context. The recent COVID-19 pandemic has stressed this situation even further, thus highlighting the need for taking action. Active and Assisted Living (AAL) technologies come as a viable approach to help facing these challenges, thanks to the high potential they have in enabling remote care and support. Broadly speaking, AAL can be referred to as the use of innovative and advanced Information and Communication Technologies to create supportive, inclusive and empowering applications and environments that enable older, impaired or frail people to live independently and stay active longer in society. AAL capitalizes on the growing pervasiveness and effectiveness of sensing and computing facilities to supply the persons in need with smart assistance, by responding to their necessities of autonomy, independence, comfort, security and safety. The application scenarios addressed by AAL are complex, due to the inherent heterogeneity of the end-user population, their living arrangements, and their physical conditions or impairment. Despite aiming at diverse goals, AAL systems should share some common characteristics. They are designed to provide support in daily life in an invisible, unobtrusive and user-friendly manner. Moreover, they are conceived to be intelligent, to be able to learn and adapt to the requirements and requests of the assisted people, and to synchronise with their specific needs. Nevertheless, to ensure the uptake of AAL in society, potential users must be willing to use AAL applications and to integrate them in their daily environments and lives. In this respect, video- and audio-based AAL applications have several advantages, in terms of unobtrusiveness and information richness. Indeed, cameras and microphones are far less obtrusive with respect to the hindrance other wearable sensors may

关键词： computer vision

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：