检索结果-内蒙古大学图书馆

24th International Electronics Symposium, IES 2022

作者： Abidin, Zainul Maulana, Eka Nurrohman, Muhammad Yogi Wardana, Fitri Candra Warsito Universitas Brawijaya Faculty of Computer Science Department of Computer Engineering Malang Indonesia Universitas Brawijaya Faculty of Engineering Department of Electrical Engineering Malang Indonesia Universitas Brawijaya Master Program in Environmental Resources and Development Management Postgraduate School Malang Indonesia Universitas Brawijaya Faculty of Mathematics and Natural Sciences Department of Chemistry Malang Indonesia

ISBN: (数字)9781665489713

ISBN: (纸本)9781665489713

In order to reduce Polyethylene Terephthalate (PET) bottle plastic waste, Universitas Brawijaya (UB) provided reverse osmosis drinking water in some buildings. Water monitoring is needed to keep the water quality. Therefore, a water monitoring system based on Total Dissolved Solids (TDS), pH, and water flow was proposed. Since the UB buildings have good internet connection (WiFi), Internet of Things (IoT) was employed to the system to support real time monitoring. So, data of TDS, pH, and water flow can be periodically sent to cloud and displayed to a specific website. The system worked very well and the data can be summarized and used by operator as indicators of performance of the reverse osmosis machine. When water quality and performance decrease, operator must check filters membrane or water pump for further maintenance to support long life use. Although the sensors have been calibrated properly, some measurement errors occur. The measurement error percentages of TDS and pH are 0.62% and 0.94%, respectively. © 2022 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Modular Self-Lock Origami: design, modeling, and simulation to improve the performance of a rotational joint

arXiv

引用

arXiv 2023年

作者： Zare, Samira Spaeth, Alex Suresh, Sandya Teodorescu, Mircea Department of Electrical and Computer Engineering University of California Santa Cruz United States SIP program University of California Santa Cruz United States Department of Computer Science and Engineering United States

Origami structures have been widely explored in robotics due to their many potential advantages. Origami robots can be very compact, as well as cheap and efficient to produce. In particular, they can be constructed in a flat format using modern manufacturing techniques. Rotational motion is essential for robotics, and a variety of origami rotational joints have been proposed in the literature. However, few of these are even approximately flat-foldable. One potential enabler of flat origami rotational joints is the inclusion of lightweight pneumatic pouches which actuate the origami’s folds;however, pouch actuators only enable a relatively small amount of rotational displacement. The previously proposed Four-Vertex Origami is a flat-foldable structure which provides an angular multiplier for a pouch actuator, but suffers from a degenerate state. This paper presents a novel rigid origami, the Self-Lock Origami, which eliminates this degeneracy by slightly relaxing the assumption of flat-foldability. This joint is analysed in terms of a trade-off between the angular multiplier and the mechanical advantage. Furthermore, the Self-Lock Origami is a modular joint which can be connected to similar or different joints to produce complex movements for various applications;three different manipulator designs are introduced as a proof of concept. Copyright © 2023, The Authors. All rights reserved.

关键词： Manipulators

来源：评论

学校读者我要写书评

暂无评论

Neurocognitive assessment under various human-robot teaming environments

Neurocognitive assessment under various human-robot teaming ...

引用

Annual International Conference of the IEEE engineering in Medicine and Biology Society (EMBC)

作者： Anna L. Packy Jayesh Jayahankar Arya Teymourlouei Joshua Stone Hyuk Oh Garrett E. Katz James A. Reggia Rodolphe J. Gentili Neuroscience and Cognitive Science Program University of Maryland College Park USA Department of Computer Science University of Maryland College Park USA Department of Electrical & Computer Engineering University of Maryland College Park USA Department of Kinesiology University of Maryland College Park USA Department of Electrical Engineering & Computer Science Syracuse University Syracuse USA

ISBN: (数字)9798350371499

ISBN: (纸本)9798350371505

Human-robot teaming has become increasingly important with the advent of intelligent machines. Prior efforts suggest that performance, mental workload, and trust are critical elements of human-robot dynamics that can be altered by the robot’s behavior. Most prior human-robot teaming studies used behavioral analyses, but a limited number used neural markers, without the use of physical robots and complex tasks. Here we combine behavioral and EEG cortical dynamics to examine cognitive-motor processes when individuals complete a complex task under various team environments with a robot. The results revealed that altering the robot quality affected both behavioral and EEG dynamics. Task completion with an experienced robot led to greater team performance and human trust along with lower mental workload compared to an inexperienced teammate or when individuals performed alone. EEG changes suggest that different attentional processes were engaged when humans worked with the robot and performed alone, and that visual processing was more prominent when teaming with an inexperienced teammate. This work can inform human cognitive-motor processes and the design of robotic controllers in human-robot teams.

关键词： Visualization Process control Humanoid robots Collaboration Human factors Control systems Electroencephalography Behavioral sciences engineering in medicine and biology Robots

来源：评论

学校读者我要写书评

暂无评论

FedClassAvg: Local Representation Learning for Personalized Federated Learning on Heterogeneous Neural Networks 22

FedClassAvg: Local Representation Learning for Personalized ...

引用

Proceedings of the 51st International Conference on Parallel Processing

作者： Jaehee Jang Heoneok Ha Dahuin Jung Sungroh Yoon Department of Electrical and Computer Engineering Seoul National University Republic of Korea Department of Electrical and Computer Engineering and Interdisciplinary Program in Artificial Intelligence Seoul National University Republic of Korea and AIIS ASRI and INMC Seoul National University Republic of Korea

ISBN: (纸本)9781450397339

Personalized federated learning is aimed at allowing numerous clients to train personalized models while participating in collaborative training in a communication-efficient manner without exchanging private data. However, many personalized federated learning algorithms assume that clients have the same neural network architecture, and those for heterogeneous models remain understudied. In this study, we propose a novel personalized federated learning method called federated classifier averaging (FedClassAvg). Deep neural networks for supervised learning tasks consist of feature extractor and classifier layers. FedClassAvg aggregates classifier weights as an agreement on decision boundaries on feature spaces so that clients with not independently and identically distributed (non-iid) data can learn about scarce labels. In addition, local feature representation learning is applied to stabilize the decision boundaries and improve the local feature extraction capabilities for clients. While the existing methods require the collection of auxiliary data or model weights to generate a counterpart, FedClassAvg only requires clients to communicate with a couple of fully connected layers, which is highly communication-efficient. Moreover, FedClassAvg does not require extra optimization problems such as knowledge transfer, which requires intensive computation overhead. We evaluated FedClassAvg through extensive experiments and demonstrated it outperforms the current state-of-the-art algorithms on heterogeneous personalized federated learning tasks.

关键词： Communication Efficient Resource Constraint Representation Learning Neural Networks Model Heterogeneity Federated Learning

来源：评论

学校读者我要写书评

暂无评论

Optimized Transmission Strategy for UAV-RIS 2.0 Assisted Communications Using Rate Splitting Multiple Access

Optimized Transmission Strategy for UAV-RIS 2.0 Assisted Com...

引用

IEEE Conference on Vehicular Technology (VTC)

作者： Aamer Mohamed Huroon Yu-Chih Huang Li-Chun Wang Department of Electrical Engineering and Computer Science International Graduate Program National Yang Ming Chiao Tung University Institute of Communications Engineering National Yang Ming Chiao Tung University Department of Electrical and Computer Engineering National Yang Ming Chiao Tung University

In this paper, we study the transmission strategy of a ground-based beyond diagonal reconfigurable intelligent surface (BD-RIS), a.k.a RIS 2.0, in a network where multiple unmanned aerial vehicles (UAVs) simultaneously transmit signals to the respective groups of users. It is assumed that each group is assigned subcarriers orthogonal to those assigned to other groups and rate splitting multiple access (RSMA) is adopted within each group. A corresponding mixed integer nonlinear programming problem (MINLP) is formulated, which aims to jointly optimize 1) allocation of BD-RIS elements to groups, 2) BD-RIS phase rotations, 3) rate allocation in RSMA, and 4) precoders. To solve the problem, we propose using generalized benders decomposition (GBD) augmented with a manifold-based algorithm. GBD splits the MINLP problem into two sub-problems, namely the primal and the relaxed master problem, which are solved alternately and iteratively. In the primal problem, we apply block coordinate descent (BCD) to manage the coupling of variables effectively. Moreover, we recognize the manifold structure in the phase rotation constraint of BD-RIS, enabling the Riemannian conjugate gradient (RCG). Simulation results demonstrate the effectiveness of the proposed approach in maximizing spectral efficiency.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Comparative Analysis of Deep Learning Models for Detection of Knee Osteoarthritis Disease through Mobile Apps 8

A Comparative Analysis of Deep Learning Models for Detection...

引用

8th International Conference on Wireless and Telematics, ICWT 2022

作者： Kardawi, Muhammad Yusuf Muchtar, Kahlil Nurdin, Yudha Maulina, Novi Muchallil, Sayed Universitas Syiah Kuala Department of Electrical and Computer Engineering Aceh Indonesia Aceh Indonesia Postgraduate Program School of Medicine Universitas Syiah Kuala Microbiology Department Universitas Syiah Kuala Aceh Indonesia

ISBN: (数字)9781665451222

ISBN: (纸本)9781665451222

Osteoarthritis is a progressive degenerative joint disease characterized by damage to joint cartilage and structural joint diarthrodial. As many as 80% of osteoarthritis patients will experience movement limitations, and 25% cannot carry out daily activities. At present, the stages of osteoarthritis diagnosis are through visual observations of the narrowing of joint and osteophyte gaps contained in X-ray images through the observation of radiology and assessing the severity of disorders. This study proposes a CAD (computer-Aided Design) support system to detect knee osteoarthritis based on X-ray images with deep learning (DL) techniques. In the design of the CAD-related architecture evaluation, including ResNet, VggNet, EfficientNet, and InceptionV3 in building a predictive model using the Convolutional Neural Network (CNN) based on Mobile Application and Cloud Computing to be able to classify normal knee and knee osteoarthritis with the percentage of testing accuracy each architecture is 93.17% on ResNet, 95.26% on VggNet, 94.64% in InceptionV3 and 96.59% on EfficientNet. The experimental results can be found through our project channel: https://***/EXj-7Dv6xGM © 2022 IEEE.

关键词： Cloud computing

来源：评论

学校读者我要写书评

暂无评论

Real-Time Computation of E-Field in Transcranial Magnetic Stimulation for Neuronavigation and Optimization

Real-Time Computation of E-Field in Transcranial Magnetic St...

引用

US National Committee of URSI National Radio Science Meeting (USNC-URSI NRSM)

作者： Nahian I. Hasan Moritz Dannhauer Dezhi Wang Zhi-De Deng Luis J. Gomez Elmore Family School of Electrical and Computer Engineering Purdue University WL Indiana USA National Institute of Mental Health Intramural Research Program National Institutes of Health USA

ISBN: (数字)9781946815200

ISBN: (纸本)9798331513979

Transcranial Magnetic Stimulation (TMS) is a non-invasive brain stimulation technique used for the treatment of depression, as well as various neurological and psychiatric disorders. There has been ongoing interest in developing fast E-field solvers that can be easily incorporated into neuronavigation systems to facilitate real-time E-field in targeted brain regions, optimizing dosing parameters.

关键词： Transcranial magnetic stimulation Depression Real-time systems Brain stimulation Optimization

来源：评论

学校读者我要写书评

暂无评论

Camera-based Motion Correction for PET/MR Brain Imaging

Camera-based Motion Correction for PET/MR Brain Imaging

引用

2022 IEEE Nuclear Science Symposium, Medical Imaging Conference, and Room Temperature Semiconductor Detector Conference, IEEE NSS MIC RTSD 2022

作者： Fisher, Jonathan Groll, Andrew Kim, Chris C. Innes, Derek Levin, Craig S. Stanford University Department of Electrical Engineering CA United States Molecular Imaging Program Stanford University Department of Radiology CA United States Stanford University Department of Computer Science CA United States Stanford University Physics Electrical Engineering and Bioengineering Department of Radiology CA United States

ISBN: (纸本)9781665488723

In this work, we evaluated the performance of a camera-based rigid body motion correction solution in PET studies. We compared the image quality obtained by reconstructing a static phantom scan to those obtained by reconstructing a moving phantom scan with and without applying motion correction. Our suggested solution uses a camera to track a 3D marker attached to the object to be imaged (in this work, a resolution phantom). This data was incorporated in the multiple acquisition frames (MAF) image reconstruction algorithm to compensate for motion. While we got multiple spatially shifted replicas of the resolution phantom in the motion study's reconstructed image when motion correction was not applied, the motion-corrected image was comparable to the static image, with some degradation in spatial resolution (3.2-4.2 vs. 2.8-3.2 mm) and lower peak to valley ratio (indicating lower contrast to noise ratio). The context of the results presented is in PET/MR imaging, but in principle, this motion compensation method could be used in any type of medical imaging modality. © 2022 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

NEW INSIGHTS FOR THE STABILITY-PLASTICITY DILEMMA IN ONLINE CONTINUAL LEARNING 11

NEW INSIGHTS FOR THE STABILITY-PLASTICITY DILEMMA IN ONLINE ...

引用

11th International Conference on Learning Representations, ICLR 2023

作者： Jung, Dahuin Lee, Dongjin Hong, Sunwon Jang, Hyemi Bae, Ho Yoon, Sungroh Department of Electrical and Computer Engineering Seoul National University Korea Republic of DeepBrain AI Inc. Korea Republic of Department of Cyber Security Ewha Womans University Korea Republic of Interdisciplinary Program in Artificial Intelligence Seoul National University Seoul08826 Korea Republic of

The aim of continual learning is to learn new tasks continuously (i.e., plasticity) without forgetting previously learned knowledge from old tasks (i.e., stability). In the scenario of online continual learning, wherein data comes strictly in a streaming manner, the plasticity of online continual learning is more vulnerable than offline continual learning because the training signal that can be obtained from a single data point is limited. To overcome the stability-plasticity dilemma in online continual learning, we propose an online continual learning framework named multi-scale feature adaptation network (MuFAN) that utilizes a richer context encoding extracted from different levels of a pre-trained network. Additionally, we introduce a novel structure-wise distillation loss and replace the commonly used batch normalization layer with a newly proposed stability-plasticity normalization module to train MuFAN that simultaneously maintains high plasticity and stability. MuFAN outperforms other state-of-the-art continual learning methods on the SVHN, CIFAR100, miniImageNet, and CORe50 datasets. Extensive experiments and ablation studies validate the significance and scalability of each proposed component: 1) multi-scale feature maps from a pre-trained encoder, 2) the structure-wise distillation loss, and 3) the stability-plasticity normalization module in MuFAN. Code is publicly available at https://***/whitesnowdrop/MuFAN. © 2023 11th International Conference on Learning Representations, ICLR 2023. All rights reserved.

关键词： Stability

来源：评论

学校读者我要写书评

暂无评论

Minimization of fanout in switching networks 15

Minimization of fanout in switching networks

引用

15th Annual Symposium on Switching and Automata Theory, SWAT 1974

作者： Hayes, John P. Department of Electrical Engineering and Computer Science Program University of Southern California Los AngelesCA90007 United States

The problem of finding the minimum amount of fanout needed to realize a switching function f is investigated. Fanout-free functions are defined, and necessary and sufficient conditions for a function to be fanout-free are derived. A measure '(f) called the input fanout index, is introduced which represents the minimum number of input variables that fan out in any realization of f. I is shown that t(f), can be determined from the prime implicants and implicates of f. Another measure of fanout u(f), which is the minimum numbe r of signal lines that must fan out in any network realizing f is defined, and some of the properties of u(f) are examined. © 2021 IEEE. All rights reserved.

关键词： Switching networks

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：