检索结果-内蒙古大学图书馆

Proceedings of the Digital Image Computing: Technqiues and Applications (DICTA)

作者： Xinwen Liu Jing Wang S. Kevin Zhou Craig Engstrom Shekhar S. Chandra School of Electrical Engineering and Computer Science The University of Queensland Brisbane Australia The Commonwealth Scientific and Industrial Research Organisation Canberra Australia Center for Medical Imaging Robotics Analytic Computing & Learning (MIRACLE) School of Biomedical Engineering & Suzhou Institute for Advanced Research University of Science and Technology of China Suzhou China Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS Beijing China School of Human Movement and Nutrition Sciences The University of Queensland Brisbane Australia

ISBN: (数字)9798350379037

ISBN: (纸本)9798350379044

Deep neural networks have been widely studied to predict a medical condition, such as total knee replacement (TKR). It has shown that data of different modalities, such as imaging data, clinical variables, and demographic information, provide complementary information and thus can improve the prediction accuracy together. However, the data sources of various modalities may not always be of high quality, and each modality may have only partial information of medical condition. Thus, predictions from different modalities can be in conflict, and the final prediction may fail in the presence of such a conflict. Therefore, it is important to account for the reliability of each source data and the prediction output when making a final decision. In this paper, we propose an evidence-aware multimodal data fusion framework based on the Dempster-Shafer theory (DST). The backbone models contain an image branch, a non-image branch and a fusion branch. For each branch, there is an evidence network that takes the extracted features as input and outputs an evidence score, which is designed to represent the reliability of the output from the current branch. The output probabilities along with the evidence scores from multiple branches are combined with the Dempster's combination rule to make a final prediction. Experimental results on the public OA initiative (OAI) dataset for the TKR prediction task show that the proposed method has better performance by accounting for conflicts from various modalities.

关键词： Medical conditions Soft sensors Digital images Data integration Imaging Artificial neural networks Reliability theory Feature extraction Reliability engineering Knee replacement

来源：评论

学校读者我要写书评

暂无评论

A Distributed Framework for Deep Reinforcement Learning by Consensus

A Distributed Framework for Deep Reinforcement Learning by C...

引用

Chinese Control and Decision Conference, CCDC

作者： Bo Liu Shuang Zhu Peng Sun Qisheng Huang Zhengtao Ding Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China PowerChina Huadong Engineering Corporation Limited Hangzhou China College of Computer Science and Electronic Engineering Hunan University Changsha China School of Mechanical Engineering and Automation Harbin Institute of Technology Shenzhen Shenzhen China Department of Electrical and Electronic Engineering University of Manchester Manchester UK

This paper proposes a distributed training framework for deep reinforcement learning algorithms to address large-scale problems with privacy protection. First, we design a hierarchical decentralized communication topology with a server to alleviate the heavy burden on the central server. By pushing the model updating and data storage to the edge side, it not only unleashes the computing potential of the terminal devices but also shortens the response time. Second, the consensus algorithm is applied for all agents over the decentralized topology to approach each other, where each agent only requires neighboring information to achieve consensus. Then, the distributed training framework for deep Q-networks is designed based on the consensus algorithm, which consists of local learning and global consensus. Finally, the simulation demonstrates that the proposed distributed learning deep Q-networks shows better performance than its centralized learning counterpart.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Sociable Robotic Platform to Make Career Advices for Undergraduates 22nd

A Sociable Robotic Platform to Make Career Advices for Under...

引用

22nd International Conference on Human computer Interaction,HCII 2020

作者： Mithsara, W. K. Malithi Manawadu, Udaka A. De Silva, P. Ravindra S. Robotics and Intelligent Systems Laboratory Department of Computer Science University of Sri Jayewardenepura Nugegoda Sri Lanka Robot Engineering Laboratory Graduate School of Computer Science and Engineering University of Aizu Aizuwakamatsu Japan

ISBN: (纸本)9783030601164

Most of the undergraduates couldn’t figure out a proper direction for their future careers since advising depends on the person and students show aversion in revealing their information to other humans. This research focused on creating a social robotic platform to interact with undergraduates in the field of computer science to realize possible career paths, as recent researches show social companion robots tend to form a stronger bond, which helps the addressee to share their information easily. The robot was created as a tabletop robot employing minimalistic design with a friendly view attached with speech synthesis for communicating purposes. Data was collected from 202 persons, who followed a degree in computer science. Data contains their experience, qualifications, and skills. Thereafter an artificial neural network was created using supervised learning to predict the career path with 95% performance accuracy. The experiment was performed by engaging 15 students from the final year who are a doing degree in computer science and they were asked to provide feedback on the interactions with the robot. The gathered responses highlighted robot animacy, interaction, technology and usefulness. Therefore, from the results it can be concluded that a majority of the students accepted the robot, interacted without hesitation and had friendly conversations with the robot where they valued the generated output from the robot. © 2020, Springer Nature Switzerland AG.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Learning Deep Nets for Gravitational Dynamics with Unknown Disturbance through Physical Knowledge Distillation: Initial Feasibility Study

arXiv

引用

arXiv 2022年

作者： Lin, Hongbin Gao, Qian Chu, Xiangyu Dou, Qi Deguet, Anton Kazanzides, Peter Samuel Au, K.W. Department of Mechanical and Automation Engineering The Chinese University of Hong Kong Hong Kong Shenzhen Institute of Artificial Intelligence and Robotics for Society School of Science and Engineering The Chinese University of Hong Kong Shenzhen China Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong Department of Computer Science Johns Hopkins University United States

Learning high-performance deep neural networks for dynamic modeling of high Degree-Of-Freedom (DOF) robots remains challenging due to the sampling complexity. Typical unknown system disturbance caused by unmodeled dynamics (such as internal compliance, cables) further exacerbates the problem. In this paper, a novel framework characterized by both high data efficiency and disturbance-adapting capability is proposed to address the problem of modeling gravitational dynamics using deep nets in feedforward gravity compensation control for high-DOF master manipulators with unknown disturbance. In particular, Feedforward Deep Neural Networks (FDNNs) are learned from both prior knowledge of an existing analytical model and observation of the robot system by Knowledge Distillation (KD). Through extensive experiments in high-DOF master manipulators with significant disturbance, we show that our method surpasses a standard Learning-from-Scratch (LfS) approach in terms of data efficiency and disturbance adaptation. Our initial feasibility study has demonstrated the potential of outperforming the analytical teacher model as the training data increases. © 2022, CC BY.

关键词： Dynamics

来源：评论

学校读者我要写书评

暂无评论

MUCOR: A Multiparty Conversation Based Robotic Interface to Evaluate Job Applicants 22nd

MUCOR: A Multiparty Conversation Based Robotic Interface to ...

引用

22nd International Conference on Human computer Interaction,HCII 2020

作者： Senaratna, H.A.S.D. Manawadu, Udaka A. Hansika, W.K.N. Samarasinghe, S.W.A.M.D. De Silva, P. Ravindra S. Robotics and Intelligent Systems Laboratory Department of Computer Science University of Sri Jayewardenepura Nugegoda Sri Lanka Robot Engineering Laboratory Graduate School of Computer Science and Engineering University of Aizu Aizuwakamatsu Japan

ISBN: (纸本)9783030601164

"MUCOR" is a robotic interface made up of three small-sized, table-top robots that go through Linkedin profiles of job applicants and discuss the applicants’ information. Robots categorize applicants into ordered levels based on their competencies mentioned. Robots built following minimalist design concepts consist of a cylindrical head and a body that occupy less space. A score is calculated for each candidate and categorized into levels by a model built including Agglomerative Clustering and Gaussian Mixture Model. The model itself identifies the number of levels into which the applicants can be categorized, through the iterations. MUCOR is built for job recruiters who spend more time to find background information about applicants prior to an interview. Conversation among robots and the user creates a Passive Social Interface in which the user does not involve in the conversation, but gain knowledge by listening. The recruiter only has to input the LinkedIn IDs into a mobile application and listen to the conversation among robots. MUCOR was experimented with professional recruiters and their feedback highlighted that the synchronization of speech with the robot’s body movements has a fair impact on the user experience about the robot behavior. © 2020, Springer Nature Switzerland AG.

关键词： Human robot interaction

来源：评论

学校读者我要写书评

暂无评论

A Lightweight Model for Perceptual Image Compression via Implicit Priors

arXiv

引用

arXiv 2025年

作者： Wei, Hao Zhou, Yanhui Jia, Yiwen Ge, Chenyang Anwar, Saeed Mian, Ajmal National Key Laboratory of Human-Machine Hybrid Augmented Intelligence Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University Xi’an710049 China School of Information and Telecommunication Xi’an Jiaotong University Xi’an710049 China Department of Computer Science and Software Engineering The University of Western Australia Crawley PerthWA6009 Australia

Perceptual image compression has shown strong potential for producing visually appealing results at low bitrates, surpassing classical standards and pixel-wise distortion-oriented neural methods. However, existing methods typically improve compression performance by incorporating explicit semantic priors, such as segmentation maps and textual features, into the encoder or decoder, which increases model complexity by adding parameters and floating-point operations. This limits the model’s practicality, as image compression often occurs on resource-limited mobile devices. To alleviate this problem, we propose a lightweight perceptual Image Compression method using Implicit Semantic Priors (ICISP). We first develop an enhanced visual state space block that exploits local and global spatial dependencies to reduce redundancy. Since different frequency information contributes unequally to compression, we develop a frequency decomposition modulation block to adaptively preserve or reduce the low-frequency and high-frequency information. We establish the above blocks as the main modules of the encoder-decoder, and to further improve the perceptual quality of the reconstructed images, we develop a semantic-informed discriminator that uses implicit semantic priors from a pretrained DINOv2 encoder. Experiments on popular benchmarks show that our method achieves competitive compression performance and has significantly fewer network parameters and floating point operations than the existing state-of-the-art. We will release the code and trained models. Copyright © 2025, The Authors. All rights reserved.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Shape Manipulation of Bevel-Tip Needles for Prostate Biopsy Procedures: A Comparison of Two Resolved-Rate Controllers

arXiv

引用

arXiv 2024年

作者： Wang, Yanzhou Al-Zogbi, Lidia Liu, Jiawei Shepard, Lauren Ghazi, Ahmed Tokuda, Junichi Leonard, Simon Krieger, Axel Iordachita, Iulian The Department of Mechanical Engineering The Laboratory for Computational Sensing and Robotics Johns Hopkins University BaltimoreMD United States The Laboratory of Computational Sensing and Robotics Johns Hopkins University BaltimoreMD United States The Brady Urological Institute Johns Hopkins University BaltimoreMD United States The Department of Radiology Brigham and Women's Hospital Harvard Medical School BostonMA United States The Department of Computer Science The Laboratory for Computational Sensing and Robotics Johns Hopkins University BaltimoreMD United States

Prostate cancer diagnosis continues to encounter challenges, often due to imprecise needle placement in standard biopsies. Several control strategies have been developed to compensate for needle tip prediction inaccuracies, however none were compared against each other, and it is unclear whether any of them can be safely and universally applied in clinical settings. This paper compares the performance of two resolved-rate controllers, derived from a mechanics-based and a data-driven approach, for bevel-tip needle control using needle shape manipulation through a template. We demonstrate for a simulated 12-core biopsy procedure under model parameter uncertainty that the mechanics-based controller can better reach desired targets when only the final goal configuration is presented even with uncertainty on model parameters estimation, and that providing a feasible needle path is crucial in ensuring safe surgical outcomes when either controller is used for needle shape manipulation. © 2024, CC BY-NC-ND.

关键词： Controllers

来源：评论

学校读者我要写书评

暂无评论

Where to Place a Pile?

Where to Place a Pile?

引用

European Conference on Mobile Robots (ECMR)

作者： Miroslav Kulich David Woller Sarah Carmesin Masoumeh Mansouri Libor Přeučil Czech Institute of Informatics Robotics and Cybernetics Czech Technical University in Prague Prague Czech Republic Department of Cybernetics Faculty of Electrical Engineering Czech Technical University in Prague Prague Czech Republic School of Computer Science University of Birmingham Birmingham United Kingdom

When planning missions for autonomous machines in real-world scenarios, such as open-pit mining, painting, or harvesting, it is important to consider how the machines will alter the working environment during their operations. Traditional planning methods treat such changes, like piles built during drilling, as constraints given to the planner that depend on the machine's trajectory. The goal is to find a trajectory that satisfies these constraints. However, our approach formulates the planning problem as finding optimal positions for changes, such as piles, along the machine's trajectory. We propose a heuristic solver and provide extensive experimental evaluations.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Efficient Extended Ant Colony Optimization for Capacitated Electric Vehicle Routing

Efficient Extended Ant Colony Optimization for Capacitated E...

引用

IEEE Symposium Series on Computational Intelligence (SSCI)

作者： Bo-Cheng Lin Xiao-Fang Liu Yi Mei Institute of Robotics and Automatic Information System College of Artificial Intelligence Nankai University Tianjin China Tianjin Key Laboratory of Intelligent Robotics Nankai University Tianjin China School of Engineering and Computer Science Victoria University of Wellington Wellington New Zealand

ISBN: (纸本)9781665487696

With the rapid development of electric vehicle (EV) freight industry, the capacitated electric vehicle routing problem (CEVRP) becomes a challenging and significant prob-lem. CEVRP considers both the cargo capacity of EVs and the battery capacity of EVs, resulting in the difficulty of the construction of feasible solutions. In this paper, we propose an extended ant colony optimization (EACO) algorithm, which uses a pheromone matrix to record the routing information of customers and charging stations for solution construction. Two route construction methods: coarse route construction method and fine route construction method, are developed to generate a customer service sequence with recharging stations. In the coarse route construction method, cargo capacity constraints are ignored and the selection of recharging stations depends on the remaining battery power after the routing of customers only. In the fine routing construction method, the cargo capacities are considered to better evaluate the remaining battery power of vehicles if a return to depots is necessary in the current construction step. After the construction of routing, the giant tour is split and local search is applied to improve solution quality. Experiments show that the proposed EACO is moderate effective. The fine routing construction shows higher exploration ability and performs better than coarse routine construction.

关键词： Industries Ant colony optimization Customer services Charging stations Routing Electric vehicles Batteries

来源：评论

学校读者我要写书评

暂无评论

Modular HfOx-RRAM for On-Demand Micromodular Electronics

IEEE Electron Device Letters

引用

IEEE Electron Device Letters 2025年

作者： Kurup, Siddharth Bhattacharya, Swagat Banner, Rebecca K. Yue, Kaifan Ayyappan, Praveen Raj Aziz, Daniel Elly, Hubert N. Barton, Kira L. Hasler, Jennifer Filler, Michael A. Vogel, Eric M. Georgia Institute of Technology School of Electrical and Computer Engineering AtlantaGA30332 United States Georgia Institute of Technology School of Materials Science and Engineering AtlantaGA30332 United States University of Michigan Department of Robotics Ann ArborMI48109 United States Georgia Institute of Technology School of Chemical and Biomolecular Engineering AtlantaGA30332 United States University of Michigan Department of Mechanical Engineering Ann ArborMI48109 United States

Micromodular metal-HfOx-metal resistive random-access memories (RRAM) were fabricated, transferred to foreign substrates, and contacted using high-resolution electrohydrodynamic jet (e-jet) printing. The modular RRAM exhibited bipolar switching at low operating voltages and multi-level analog resistance states programmable using variable amplitude voltage pulses. These variable resistance RRAMs were also integrated with an amplifier and a bandpass filter to modulate their gain and corner frequencies. This work enables integration of high-quality RRAM devices in modular circuits and paves the way for microscale heterogeneous integration at the device level. © 1980-2012 IEEE.

关键词： RRAM

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：