检索结果-内蒙古大学图书馆

6th International Conference on Biological information and Biomedical engineering, BIBE 2022

作者： Sviridova, Nina Sawada, Kazuya Ikeguchi, Tohru Department of Information and Computer Technology Faculty of Engineering Tokyo University of Science Tokyo Japan International Research Center for Neurointelligence The University of Tokyo Tokyo Japan Department of Information and Computer Technology Graduate School of Engineering Tokyo University of Science Tokyo Japan

ISBN: (纸本)9783800759651

A human photoplethysmogram is a biological signal widely used for heart rate estimation, and it has a great potential for a variety of physiological and mental health monitoring applications. Photoplethysmogram is a highly complex, chaotic signal, and health monitoring applications beyond the heart rate estimation, such as mental health monitoring, may possibly require the extraction of photoplethysmogram dynamical properties that can be achieved by the application of nonlinear time series analysis. However, the applicability of nonlinear time series analysis imposes various requirements on the time series such as a sufficiently high sampling rate. This study aimed to investigate the effect of the sampling rate on the determinism of photoplethysmogram signals taken in reference conditions. The determinism, which is one of the fundamental properties of the dynamical system, was quantified by the recurrence quantification analysis, and the robustness of the determinism identification was verified by the surrogate data method. Results demonstrated that for the sampling frequency range 409.6~24.09 Hz only a minor decrease of determinism quantity is observed, thus confirming the consistency of the determinism detection in the photoplethysmogram time series of investigated sampling rates. © VDE VERLAG GMBH.

关键词： Harmonic analysis

来源：评论

学校读者我要写书评

暂无评论

Augmented Reality With Authentic GeometryGo App to Help Geometry Learning and Assessments

引用

IEEE Transactions on Learning Technologies 2023年第5期16卷 769-779页

作者： Hwang, Wu-Yuin Nurtantyana, Rio Purba, Siska Wati Dewi Hariyanti, Uun Suprapto National Dong Hwa University Department of Computer Science and Information Engineering College of Science and Engineering Hualien974 Taiwan National Central University Graduate Institute of Network Learning Technology Taoyuan City320 Taiwan Telkom University School of Computing Bandung40257 Indonesia Universitas Pelita Harapan Department of Master of Educational Technology Kota Tangerang15811 Indonesia Brawijaya University Information Systems Department Kota Malang65145 Indonesia State University Yogyakarta Department of Electronics Engineering Education Yogyakarta55281 Indonesia

We developed an Authentic GeometryGo (AGG) app to help students application of geometry in authentic contexts through authentic measurements and peer assessments. The study included an experimental group (EG) using an AGG app and a control group (CG) using paper-based methods. The results showed that the EG outperformed the CG in terms of estimation. Measuring authentic geometry shapes using the app could foster students' estimation. Furthermore, meaningful peer assessments with visual representations in authentic contexts can facilitate the evaluation of peers' work and improve students' geometry understanding. Therefore, we encourage educators to use augmented reality with appropriate learning activities to sharpen students' measurement quality and visual representations by measuring real geometry shapes and applying mathematics knowledge in authentic contexts. © 2008-2011 IEEE.

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

Multidomain Object Detection Framework Using Feature Domain Knowledge Distillation

引用

IEEE Transactions on Cybernetics 2024年第8期54卷 4643-4651页

作者： Jaw, Da-Wei Huang, Shih-Chia Lu, Zhi-Hui Fung, Benjamin C. M. Kuo, Sy-Yen National Taiwan University Department of Electrical Engineering Taipei106 Taiwan National Taipei University of Technology Department of Electronic Engineering Taipei106 Taiwan Fudan University School of Computer Science The Engineering Research Center of Cyber Security Auditing and Monitoring Ministry of Education Shanghai200433 China McGill University School of Information Studies MontrealQCH3A 1X1 Canada

Object detection techniques have been widely studied, utilized in various works, and have exhibited robust performance on images with sufficient luminance. However, these approaches typically struggle to extract valuable features from low-luminance images, which often exhibit blurriness and dim appearence, leading to detection failures. To overcome this issue, we introduce an innovative unsupervised feature domain knowledge distillation (KD) framework. The proposed framework enhances the generalization capability of neural networks across both low- and high-luminance domains without incurring additional computational costs during testing. This improvement is made possible through the integration of generative adversarial networks and our proposed unsupervised KD process. Furthermore, we introduce a region-based multiscale discriminator designed to discern feature domain discrepancies at the object level rather than from the global context. This bolsters the joint learning process of object detection and feature domain distillation tasks. Both qualitative and quantitative assessments shown that the proposed method, empowered by the region-based multiscale discriminator and the unsupervised feature domain distillation process, can effectively extract beneficial features from low-luminance images, outperforming other state-of-the-art approaches in both low- and sufficient-luminance domains. © 2013 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

PUF-Based Privacy-Preserving Simultaneous Authentication Among Multiple Vehicles in VANET

引用

IEEE Transactions on Vehicular Technology 2024年第5期73卷 6727-6739页

作者： Awais, Syed Muhammad Yucheng, Wu Mahmood, Khalid Akram, Muhammad Wahid Hussain, Shafiq Das, Ashok Kumar Park, Youngho Chongqing University School of Microelectronics and Communication Engineering Chongqing400044 China National Yunlin University of Science and Technology Graduate School of Intelligent Data Science Yunlin64002 Taiwan University of Lahore Department of Software Engineering Punjab Lahore54590 Pakistan University of Sahiwal Department of Computer Science Punjab Sahiwal57000 Pakistan International Institute of Information Technology Center for Security Theory and Algorithmic Research Telangana Hyderabad500032 India Kyungpook National University School of Electronics Engineering Daegu41566 Korea Republic of

The intellectual and immense attainment of a smart city and auto-mobile vehicles are gradually growing. This growth drives Vehicular Ad-Hoc network (VANET), a broadly operated complex network for inter-vehicular transmission to acquire information relevant to the vehicle location, road condition, traffic congestion, and speed. Generally, this information is procured through an open-source communication, which is susceptible to various security threats. In broad terms, the privacy of data in VANET is considered an imperative task. In this regard, many authentication protocols are formerly initiated for VANET. Most of these protocols are precarious owing to eavesdropping, replay, and impersonation attacks, etc. Furthermore, most existing protocols operates on enormous communication and computation rate, which turns them inadequate for VANET. This paper exhibits a lightweight privacy-preserving authentication protocol for n number of vehicles in VANET using the physical unclonable function (PUF) technique, and offers efficient and secure communication via public channels. Moreover, we evaluate our protocol formally and informally, showing that it is scalable, lightweight, and safe compared to formerly protocols. The rate of computation and communication is less than most related protocols. We also simulate the proposed scheme using the NS-3 simulator to measure its various network performance parameters. As a result, it is apparent through the beheld statistics that the presented protocol is beyond practical, efficient, and reliable for the secure dissemination of information in VANET. © 1967-2012 IEEE.

关键词： Vehicular ad hoc networks

来源：评论

学校读者我要写书评

暂无评论

An IoT-Based Microservice Platform for Virtual Puppetry Performance

引用

IEEE Access 2023年 11卷 103014-103032页

作者： Luo, Helin Lin, Yi-Bing Liao, Chen-Chi Huang, Yung-Hui Academia Sinica Research Center for Information Technology Innovation Taipei115 Taiwan Tainan National University of the Arts Graduate Institute of Animation and Film Art Tainan720 Taiwan National Yang Ming Chiao Tung University Department of Computer Science and Engineering Hsinchu300 Taiwan China Medical University College of Humanities and Sciences Taichung406 Taiwan National Cheng Kung University Miin Wu School of Computing Tainan701 Taiwan Asia University Department of Computer Science and Information Engineering Taichung413 Taiwan

This study proposes a web-based real-time remote-controlled virtual puppetry (avatar) performance platform called AvatarTalk to combine traditional Taiwanese puppetry, the Internet of Things (IoT), and 3D avatar models. AvatarTalk enables puppeteers to control avatar puppets on the web using either motion capture gloves or camera-based image recognition. This transformative performance approach not only facilitates remote performances and multi-screen presentations across various devices but also introduces a fresh gesture interpretation technique for dance artists. AvatarTalk supports a mechanism that can accommodate new control and puppet devices from other approaches through the IoT-based microservice concept. We develop a calibration procedure to enable the accurate capture of hand gestures to manipulate the movements of virtual puppets, empowering them to perform fundamental traditional puppetry poses such as nodding, bowing, and synchronized hand movements. We have conducted experiments to show the accuracy of AvatarTalk calibration. Our study indicates that AvatarTalk can almost detect the right gestures (98.75%-100% recall) and very seldom mistake the wrong gestures (90.8%-100% precision). Additionally, we also provide the mechanism to measure the delays of controlling the puppets. An analytic model is proposed to design the delay times of the messages between the control device of a puppeteer and the AvatarTalk server. In the current AvatarTalk implementation, if the message delay does not exceed 0.1 seconds, four puppeteers can synchronize their actions if the elapsed time between two actions of a puppeteer is longer than 0.3 second. © 2013 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

An Effective Automated Speaking Assessment Approach to Mitigating Data Scarcity and Imbalanced Distribution

An Effective Automated Speaking Assessment Approach to Mitig...

引用

2024 Findings of the Association for Computational Linguistics: NAACL 2024

作者： Lo, Tien-Hong Chao, Fu-An Wu, Tzu-I Sung, Yao-Ting Chen, Berlin Department of Computer Science and Information Engineering National Taiwan Normal University Taiwan Research Center for Psychological and Educational Testing National Taiwan Normal University Taiwan Department of Educational Psychology and Counseling National Taiwan Normal University Taiwan

ISBN: (纸本)9798891761193

Automated speaking assessment (ASA) typically involves automatic speech recognition (ASR) and hand-crafted feature extraction from the ASR transcript of a learner's speech. Recently, self-supervised learning (SSL) has shown stellar performance compared to traditional methods. However, SSL-based ASA systems are faced with at least three data-related challenges: limited annotated data, uneven distribution of learner proficiency levels and non-uniform score intervals between different CEFR proficiency levels. To address these challenges, we explore the use of two novel modeling strategies: metric-based classification and loss re-weighting, leveraging distinct SSL-based embedding features. Extensive experimental results on the ICNALE benchmark dataset suggest that our approach can outperform existing strong baselines by a sizable margin, achieving a significant improvement of more than 10% in CEFR prediction accuracy. © 2024 Association for Computational Linguistics.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Optimization of 3D Holographic Projection for a Medical Image System using Taguchi Method and Fuzzy Inference System

引用

Journal of Imaging science and Technology 2023年第4期67卷 1-7页

作者： Chou, Ming-Chung Huang, Tian-Hsiang Tsai, Jinn-Tsong Chen, Yen-Ming J. Hwang, Kao-Shing Huang, Wei-Tai Ho, Wen-Hsien Department of Medical Imaging and Radiological Sciences Kaohsiung Medical University Kaohsiung Taiwan Center for Big Data Research Kaohsiung Medical University Kaohsiung Taiwan Department of Medical Research Kaohsiung Medical University Hospital Kaohsiung Taiwan Department of Computer Science and Information Engineering National Penghu University of Science and Technology Penghu Taiwan Department of Computer Science and Artificial Intelligence National Pingtung University Pingtung Taiwan Department of Healthcare Administration and Medical Informatics Kaohsiung Medical University Kaohsiung Taiwan Department of Information Management National Kaohsiung University of Science and Technology Kaohsiung Taiwan Department of Electrical Engineering National Sun Yat-Sen University Kaohsiung Taiwan Department of Mechanical Engineering National Pingtung University of Science and Technology Pingtung Taiwan College of Professional Studies National Pingtung University of Science and Technology Pingtung Taiwan

Two dimensional projections of three dimensional (3D) objects are used to teach anatomy. These projections are relatively unrealistic, and medical students cannot easily and accurately grasp the position and shape of each anatomical structure. As a remedy, 3D holographic projections allow for 3D anatomical structures to be projected in space without the use of worn contraptions. This study designed a method for optimizing 3D holographic projections with respect to the quality characteristics of 3D imaging definition and stereoscopic quality. The Taguchi method was used to determine the factors that most greatly influenced these quality characteristics, and the Delphi method and fuzzy theory were used to quantify image quality. Among three main factors of material of the projection panel, thickness of the projection panel, and angle made by the projection panel with the horizontal plane, thickness was the most influential. The optimal combination of factors was acrylic material, a thickness of 1 mm, and an angle of 45°. This paper's method aids medical pedagogy and can be used by the holographic projection manufacturing industry to optimize 3D imaging definition and stereoscopic quality. © 2023 Society for Imaging science and Technology.

关键词： Taguchi methods

来源：评论

学校读者我要写书评

暂无评论

Submarine Hunter: Efficient and Secure Multi-Type Unmanned Vehicles

引用

computers, Materials & Continua 2023年第7期76卷 573-589页

作者： Halah Hasan Mahmoud Marwan Kadhim Mohammed Al-Shammari Gehad Abdullah Amran Elsayed Tag eldin Ala R.Alareqi Nivin A.Ghamry Ehaa A.Lnajjar Esmail Almosharea Computer Center University of BaghdadBaghdad6751Iraq Department of Management Science and Engineering Dalian University of TechnologyLiaoningDalian116024China Department of Information Technology Faculty of Computer Sciences and Information Technology AL Razi UniversitySana’aYemen Faculty of Engineering and Technology Future University in EgyptNew Cairo11835Egypt Faculty of Engineering Mechanics Dalian University of TechnologyLiaoningDalian116024China Faculty of Computers and Artificial Intelligence Cairo UniversityGizaEgypt Department of Business Administration Dalian University of TechnologyLiaoningDalian116024China College of Software Engineering Dalian University of TechnologyChina

Utilizing artificial intelligence(AI)to protect smart coastal cities has become a novel vision for scientific and industrial *** of these AI technologies is using efficient and secure multi-environment Unmanned Vehicles(UVs)for anti-submarine *** study’s contribution is the early detection of a submarine assault employing hybrid environment UVs that are controlled using swarm optimization and secure the information in between UVs using a decentralized cybersecurity *** Dragonfly Algorithm is used for the orientation and clustering of the UVs in the optimization approach,and the Re-fragmentation strategy is used in the network layer of the TCP/IP protocol as a cybersecurity *** research’s noteworthy findings demonstrate UVs’logistical capability to promptly detect the target and address the problem while securely keeping the drone’s geographical *** results suggest that detecting the submarine early increases the likelihood of averting a *** dragonfly strategy of sensing the position of the submersible and aggregating around it demonstrates the reliability of swarm intelligence in increasing access *** communication between Unmanned Aerial Vehicles(UAVs)improves the level of secrecy necessary for the *** swarm navigation is based on a peer-to-peer system,which allows each UAV to access information from its ***,in turn,helps the UAVs to determine the best route to take and to avoid collisions with other *** dragonfly strategy also increases the speed of the mission by minimizing the time spent finding the target.

关键词： Unmanned vehicles unmanned aerial vehicles unmanned underwater vehicles high altitude unmanned aerial vehicles anti-submarine warfare re-fragmentation dragonfly algorithm

来源：评论

学校读者我要写书评

暂无评论

CAMRI Loss: Improving the Recall of a Specific Class without Sacrificing Accuracy

CAMRI Loss: Improving the Recall of a Specific Class without...

引用

作者： Nishiyama, Daiki Fukuchi, Kazuto Akimoto, Youhei Sakuma, Jun Master's Program in Computer Science Degree Programs in Systems and Information Engineering Graduate School of Science and Technology University of Tsukuba Tsukuba-shi305-8577 Japan RIKEN Center for Advanced Intelligence Project Tokyo103-0027 Japan Department of Computer Science Faculty of Engineering Information and Systems University of Tsukuba Tsukuba-shi305-8577 Japan

In real world applications of multiclass classification models, misclassification in an important class (e.g., stop sign) can be significantly more harmful than in other classes (e.g., no parking). Thus, it is crucial to improve the recall of an important class while maintaining overall accuracy. For this problem, we found that improving the separation of important classes relative to other classes in the feature space is effective. Existing methods that give a class-sensitive penalty for cross-entropy loss do not improve the separation. Moreover, the methods designed to improve separations between all classes are unsuitable for our purpose because they do not consider the important classes. To achieve the separation, we propose a loss function that explicitly gives loss for the feature space, called class-sensitive additive angular margin (CAMRI) loss. CAMRI loss is expected to reduce the variance of an important class due to the addition of a penalty to the angle between the important class features and the corresponding weight vectors in the feature space. In addition, concentrating the penalty on only the important class hardly sacrifices separating the other classes. Experiments on CIFAR-10, GTSRB, and AwA2 showed that CAMRI loss could improve the recall of a specific class without sacrificing accuracy. In particular, compared with GTSRB's second-worst class recall when trained with cross-entropy loss, CAMRI loss improved recall by 9%. © 2023 The Institute of Electronics, information and Communication Engineers.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Maximizing Harvested Energy in Natural Energy Powered RF WPT with Nonlinear EH Model

引用

IEEE Transactions on Wireless Communications 2025年

作者： Zhang, Xiang Xiong, Ke Chen, Wei Fan, Pingyi Gao, Bo Letaief, Khaled Ben Collaborative Innovation Center of Railway Traffic Safety School of Computer Science and Technology Engineering Research Center of Network Management Technology for High Speed Railway Ministry of Education China Beijing Jiaotong University National Engineering Research Center of Advanced Network Technologies Beijing100044 China Department of Electronic Engineering China Tsinghua University Beijing National Research Center for Information Science and Technology Beijing100084 China Department of Electrical and Computer Engineering Hong Kong Hong Kong

In the typical radio frequency (RF)-based wireless power transfer (WPT) system, the wireless power station (WPS) connected to the grid transmits energy to charge low-power sensors via radio signals. Such a system may not be green and also difficult to deploy in some special areas including deserts and mountainous areas, because it depends on the grid. To achieve a green RF WPT system design, this paper considers that the WPS is powered by natural energy sources rather than the grid. To explore the maximal total amount of the energy that can be harvested by the sensors, we focus on the offline setting, so similar to many existing works on offline optimization, we assume that the WPS knows prior knowledge about energy arrivals and channel changes, and then formulate an optimization problem to maximize the total harvested energy via optimizing the WPS's time-domain transmit power subject to multiple constraints, including the finite battery capacity at the WPS, the causal relationship between the natural energy harvesting and the WPT, and the transmit power budget of the WPS, where for practicality, the nonlinear energy harvesting (EH) model is also taken into account. To solve this non-convex problem, we first equivalently transform it by using the epigraph reformulation and the variable substitution, and then use the first-order Taylor expansion to get an approximate convex version. Then, we present a successive convex approximation (SCA)-based algorithm to improve the accuracy of the obtained solution for approaching the optimal one. For the special case with a single sensor, we further propose a branch and bound (BB)-based algorithm that is able to get a more accurate solution with lower complexity than the SCA-based one. Numerical results demonstrate that the proposed algorithms are able to achieve the near-global optimal solution. As the average recharge rate increases, compared with the other two baselines, i.e., the greedy power (GP) policy and the constant pow

关键词： Budget control

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：