检索结果-内蒙古大学图书馆

SSRN 2023年

作者： Chen, Ya Mensah, Samuel Li, Junpeng School of Mechanical Engineering University of Science and Technology Beijing 30 Xueyuan Road Beijing100083 China Department of Computer Science University of Sheffield Western Bank SheffieldS10 2TN United Kingdom School of Computer Science and Engineering Beihang University 37 Xueyuan Road Beijing100191 China

The expressive power of deep neural networks appears to have brought great hope to image processing, natural language processing, speech processing, as well as other related subfields of AI. Although the usefulness of neural networks is evident in both theory and empirical studies, significant difficulties in their application still persist. More specifically, enabling deep neural networks to reasonover data for knowledge acquisition is arguably challenging. Neural networks have the ability to learn patterns and generalize over data via its connectivity, but often lack model interpretability, i.e., it is not always clear how neural networks reason over data. Enabling neural networks to symbolically reason is one way to bring explainability to neural networks, as well as to improve knowledge acquisition. In this paper, we propose a distributed representation that preserves symbolic deductive reasoning as a solution. We demonstratethat learning such representation can easily incorporate symbolic rules, which achieves improved link prediction performance for knowledge graph completion. © 2023, The Authors. All rights reserved.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Learning Distributed Representations of Knowledge that Preserve Deductive Reasoning

SSRN

引用

SSRN 2023年

The expressive power of deep neural networks appears to have brought great hope to vision, natural language processing, speech processing, as well as other related AI sub-fields. Although the usefulness of neural networks is evident in both theory and empirical studies, significant difficulties in their application still persist. More specifically, enabling deep neural networks to reason over data for knowledge acquisition is arguably challenging. Neural networks have the ability to learn patterns and generalize over data via its connectivity, but often lack model interpretability;i.e., it is not always clear how neural networks reason over data. Enabling neural networks to reason as like how humans use symbolic representations for reasoning is one way of bringing explainability to neural networks as well as improving knowledge acquisition. In this paper, we propose a distributed representation that preserves symbolic deductive reasoning as a solution. We demonstrate that learning such representation can easily incorporate symbolic rules, which achieves improved link prediction performance for knowledge graph completion. © 2023, The Authors. All rights reserved.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

A novel augmented reality-based simulator for enhancing orthopedic surgical training

引用

computers in Biology and Medicine 2025年 185卷 109536-109536页

作者： Wu, Luohong Seibold, Matthias Cavalcanti, Nicola A. Hein, Jonas Gerth, Tatiana Lekar, Roni Hoch, Armando Vlachopoulos, Lazaros Grabner, Helmut Zingg, Patrick Farshad, Mazda Fürnstahl, Philipp Research in Orthopedic Computer Science Balgrist University Hospital University of Zurich Lengghalde 5 Zurich8008 Switzerland Department of Orthopaedics Balgrist University Hospital University of Zurich Forchstrasse 340 Zurich8008 Switzerland Computer Vision and Geometry Group ETH Zurich Ramistrasse 101 Zurich8092 Switzerland Institute of Computer Science School of Engineering Zurich University of Applied Sciences Obere Kirchgasse 2 Winterthur8401 Switzerland Institute of Data Analysis and Process Design School of Engineering Zurich University of Applied Sciences Technikumstrasse 81 Winterthur8400 Switzerland

Background: Total Hip Arthroplasty (THA) is a well-established and common orthopedic surgery. Due to the complexity involved in THA, orthopedic surgeons require rigorous training. However, the current gold standard, the tutor-guided and -evaluated apprenticeship model is time-consuming, costly, and poses risks to patients. There is a pressing need for additional training resources to enhance the efficiency and safety of the training process. In this work, we present a novel Augmented Reality (AR)-based simulator designed for THA that helps enable a new self-paced training and learning paradigm without the need for instructors. Methods: The simulator reduces the need for instructors by integrating an AR guidance module and an automated performance evaluation module. Three types of AR guidance were developed: Overlay, Virtual Twin, and Sectional Views. A feasibility study was conducted with five resident surgeons and two senior surgeons to compare these guidance methods quantitatively and qualitatively. The automated performance evaluation module was assessed against manual performance evaluation using Bland-Altman analysis with limits of agreement (LoA) and Mann–Whitney U tests. Results: The quantitative feasibility results indicate the efficacy of the developed AR guidance, characterized by mean transitional and rotational deviation errors below 3 mm and 3 degrees. Based on the qualitative results, we provide recommendations for efficient AR guidance designs. The Bland-Altman analysis results (0.22±1.32mm with LoA −2.37 to 2.81 mm for distance deviation, 0.94±2.41 degrees with LoA −3.78 to 5.66 degrees for yaw deviation, −0.34±1.30 degrees with LoA −2.90 to 2.22 degrees for pitch deviation) and p-values of Mann–Whitney U tests (0.64 for distance deviation, 0.12 for yaw deviation, 0.11 for pitch deviation) indicate no statistically significant differences between the automated and manual performance evaluation at a significance level of 0.05. Conclusion: This work sh

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

B3d-Ear: Binarized 3d Descriptors for Ear-Based Human Recognition

SSRN

引用

SSRN 2023年

作者： Ganapathi, Iyyakutti Iyappan Ali, Syed Sadaf Prakash, Surya Bakshi, Sambit Werghi, Naoufel C2PS & KUCARS Khalifa University Abu Dhabi United Arab Emirates ETIS CY Cergy Paris Université ENSEA CNRS UMR 8051 France Department of Computer Science and Engineering Indian Institute of Technology Indore India Department of Computer Science and Engineering National Institute of Technology Rourkela India

Generally, in the traditional 3D feature descriptors, real valued vectors are commonly used. However, their high computational complexity and space requirements during the matching process are major issues. We have proposed a robust method to compute binary 3D feature descriptors relying on correntropy, an online approximation to Renyi's quadratic entropy, from the real valued 3D feature descriptor. Our method has been applied to state-of-the-art 3D descriptors to obtain their binary equivalents. The recognition capability of the obtained binary descriptor vectors is assessed on databases comprising human 3D ears. Keypoints and their respective binary descriptors are matched using the proposed technique. The correspondence points between the image pair are computed using a distance metric and iterative closest point (ICP) is applied for final alignment of test and model pair images. Experimental results obtained demonstrate that our method yields binary descriptors with lower space and matching time complexities compared to their respective real valued descriptors, without sacrificing recognition performance. © 2023, The Authors. All rights reserved.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Physical-Layer Security in Short-Packet NOMA Systems with Untrusted Near Users

Physical-Layer Security in Short-Packet NOMA Systems with Un...

引用

IEEE International Conference on Communications Workshops, ICC

作者： Thai-Hoc Vu Quoc-Viet Pham Daniel Benevides da Costa Mérouane Debbah Sunghwan Kim Department of Electrical Electronic and Computer Engineering University of Ulsan Republic of Korea School of Computer Science and Statistics Trinity College Dublin Dublin 2 Ireland Technology Innovation Institute Masdar City Abu Dhabi United Arab Emirates

The evolution of diverse Intenet-of-things (IoT) applications towards Industry 5.0 has recently increased challenges in physical-layer security. In particular, short-packet communication (SPC) and non-orthogonal multiple access (NOMA) are being thoroughly integrated into IoT networks to achieve ultra-reliable low-latency communication (URLLC) applications and users' massive connectivity. Nevertheless, this creates a critical security flaw when untrusted-near users (NUs), using the same resource block as far users (FUs), can readily intercept FU's information with conventional NOMA. To mitigate such security threats, we propose a modified power allocation integrated beamforming (MPAIB) scheme to carry out the pairing procedure for SPC-enabled NOMA systems with multiple untrusted NUs. This scheme can simultaneously achieve joint objectives of preventing entrusted FU's leakage information and enhancing system coverage quality. For further performance improvement, we also design a dynamic power allocation strategy to maximize FU's average secrecy rate. Accordingly, we derive closed-form approximations for the average secrecy rate and throughput, and it is demonstrated that the throughput is a quasi-concavity function with respect to packet length. Numerical results show that our theoretical analyses are in good agreement with the simulation ones. Moreover, it also shows that the system's performance degrades significantly with the increase of multiple NUs and the probability of information leakage.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Application of LabVIEW to Determine Characteristics of Two-Terminal Passive Components 14

Application of LabVIEW to Determine Characteristics of Two-T...

引用

14th International Conference on Measurement, MEASUREMENT 2023

作者： Otomanski, Przemyslaw Pawlowski, Eligiusz Szlachta, Anna Poznan University of Technology Institute of Electrical Engineering and Electronics Piotrowo street 3A Poznań60-965 Poland Lublin University of Technology Faculty of Electrical Engineering and Computer Science Nadbystrzycka street 38A Lublin20-618 Poland Rzeszow University of Technology Department of Metrology and Measurement Systems W. Pola street 2 Rzeszow35-959 Poland

ISBN: (纸本)9788097262976

The paper discusses the topic of determining the current-voltage characteristics of two-terminal passive components. A virtual measurement instrument created in the LabVIEW environment using the NI USB-6211 data acquisition device is presented, as well as the results of tests performed for example elements. The described approach can also be applied to other measurement situations, such as for studying the self-heating effect of RTD. © 2023 Institute of Measurement science, Slovak Academy o.

关键词： Current voltage characteristics

来源：评论

学校读者我要写书评

暂无评论

An algorithm of NLOS error identification and mitigation in mobile location estimation

引用

International Journal of Security and Networks 2021年第2期16卷 98-104页

作者： Zhu, Changhong Xiao, Ning School of Computer Science and Engineering Guilin University of Aerospace Technology No. 2 Jinji Road Guangxi Guilin541004 China Department of Information Engineering Bowen College of Management Guilin University of Technology No. 317 Yanshan Street Guangxi Guilin541006 China

For the purpose of improving positioning accuracy of mobile station in the complex environment, a real-time non-line-of-sight (NLOS) identification and elimination method is proposed based on the characteristics of NLOS error. In this algorithm, Kalman filter (KF) is used to identify whether NLOS errors are included in range measurements in real time. According to the positive deviation characteristics of NLOS errors, there is a positive deviation between the smoothing curve of distance measurements and the real distance curve. The reconstructed line-of-sight measurements can be obtained by moving down the curve. The simulation results prove that the algorithm is better than traditional extended Kalman filter (EKF) and Wylie algorithm. Copyright © 2021 Inderscience Enterprises Ltd.

关键词： Curve fitting

来源：评论

学校读者我要写书评

暂无评论

Advanced eHealth with Explainable AI: Secured by Blockchain with AI-Empowered Block Sensitivity for Adaptive Authentication

Advanced eHealth with Explainable AI: Secured by Blockchain ...

引用

IEEE International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC)

作者： Joy Dutta Hossien B. Eldeeb Tu Dac Ho Department of Computer Science C2PS Research Center Khalifa University Abu Dhabi UAE Electrical Engineering Division University of Cambridge Cambridge UK Faculty of Information Technology and Electrical Engineering Norwegian University of Science and Technology (NTNU) Trondheim Norway

ISBN: (数字)9798350362244

ISBN: (纸本)9798350362251

This paper presents an innovative, yet secure, eHealth framework that leverages Explainable Artificial Intelligence (XAI) and blockchain technology to enhance transparency and security in the IoT-edge-cloud continuum. The framework incorporates SHapley Additive exPlanations (SHAP) to provide real-time, model-agnostic explanations for AI predictions, enabling personalized health monitoring and informed decisionmaking in healthcare. To strengthen data security, a consortium blockchain is employed, and AI is utilized to identify block data sensitivity at the edge within blockchain-integrated IoT architectures using Random Forest (RF) algorithm. This approach achieves high accuracy in validating block sensitivity, enabling efficient selection of authentication mechanisms in the proof of authentication (PoAh) consensus within the consortium blockchain. This ensures heightened protection for sensitive data and contributes to improved overall blockchain performance. The proposed framework is evaluated in an edge computing environment and demonstrates significant potential for advancing security and authentication in eHealth, representing a substantial advancement in healthcare technology.

关键词： Technological innovation Sensitivity Explainable AI Data security Scalability Authentication Electronic healthcare Consensus protocol Reliability Protection

来源：评论

学校读者我要写书评

暂无评论

Networking Architecture and Key Supporting Technologies for Human Digital Twin in Personalized Healthcare: A Comprehensive Survey

arXiv

引用

arXiv 2023年

作者： Chen, Jiayuan Yi, Changyan Okegbile, Samuel D. Cai, Jun Shen, Xuemin College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Jiangsu Nanjing211106 China Department of Electrical and Computer Engineering Concordia University MontrealQCH3G 1M8 Canada Department of Electrical and Computer Engineering University of Waterloo WaterlooONN2L 3G1 Canada

Digital twin (DT), referring to a promising technique to digitally and accurately represent actual physical entities, has attracted explosive interests from both academia and industry. One typical advantage of DT is that it can be used to not only virtually replicate a system’s detailed operations but also analyze the current condition, predict the future behavior, and refine the control optimization. Although DT has been widely implemented in various fields, such as smart manufacturing and transportation, its conventional paradigm is limited to embody non-living entities, e.g., robots and vehicles. When adopted in human-centric systems, a novel concept, called human digital twin (HDT) has thus been proposed. Particularly, HDT allows in silico representation of individual human body with the ability to dynamically reflect molecular status, physiological status, emotional and psychological status, as well as lifestyle evolutions. These prompt the expected application of HDT in personalized healthcare (PH), which can facilitate the remote monitoring, diagnosis, prescription, surgery and rehabilitation, and hence significantly alleviate the heavy burden on the traditional healthcare system. However, despite the large potential, HDT faces substantial research challenges in different aspects, and becomes an increasingly popular topic recently. In this survey, with a specific focus on the networking architecture and key technologies for HDT in PH applications, we first discuss the differences between HDT and the conventional DTs, followed by the universal framework and essential functions of HDT. We then analyze its design requirements and challenges in PH applications. After that, we provide an overview of the networking architecture of HDT, including data acquisition layer, data communication layer, computation layer, data management layer and data analysis and decision making layer. Besides reviewing the key technologies for implementing such networking architecture in

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Continuous-variable measurement-device-independent quantum key distribution in free-space channels

引用

Physical Review A 2023年第4期108卷 042621-042621页

作者： Masoud Ghalaii Stefano Pirandola School of Electronic and Electrical Engineering University of Leeds Leeds LS2 9JT United Kingdom Department of Computer Science University of York York YO10 5GH United Kingdom

The field of space communications is the realm of communication technologies where diffraction and atmospheric effects, both of which contribute to loss and noise, become overriding. The pertinent questions here are how and at which rate information (secret keys) can be securely transferred (shared) among users under such supposedly severe circumstances. In the present work we study continuous-variable quantum key distribution in a measurement-device-independent configuration over free-space optical links. We assess the turbulence regime and provide a composable finite-size key rate analysis of the protocol for such links. We study both short-range, horizontal communication links as well as slant paths to, e.g., high-altitude platform station systems.

关键词： Quantum communication

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：