检索结果-内蒙古大学图书馆

IEEE Transportation Electrification Conference and Expo (ITEC)

作者： Ezekiel Olayiwola Arogunjo Joseph Olorunfemi Ojo Electrical and Computer Engineering Department Laboratory for Electric Machines and Power Electronics Tennessee Technological University Cookeville TN USA

This paper aims at analyzing the effect of the zero dynamics of the Dual Active Bridge Isolated Bidirectional dc-dc converter (DAB) on the dynamics of the complete DAB system. It also explains its influence on controller design for the DAB system. In carrying out these analyses, the state space model of the DAB, as well as the first harmonic approximation (FHA) of the model are derived. The ZVS and the stability analysis of the system are undertaken based on the FHA model of the system. The system is shown to be stable for a constant output voltage operation for the entire power range while it is unstable for the constant power load (CPL) operation for load demands close to the system maximum power. It is also shown that the transformer winding currents are part of the zero dynamic states and are always stable regardless of the operating conditions of the system.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Characterization of Single Event Functional Interrupts in COTS and Rad-Hard ARM Microcontrollers

Characterization of Single Event Functional Interrupts in CO...

引用

IEEE Space Computing Conference (SCC)

作者： Stefania Esquer Jesse K. Mee Heather M. Quinn Brian D. Sierawski Ronald D. Schrimpf Engineering Department Electrical and Computer Vanderbilt University Nashville TN USA SPACER Lab The Air Force Research Laboratory Kirtlan AFB NM USA

ISBN: (数字)9798350384536

ISBN: (纸本)9798350384543

This work evaluated the single event functional interrupt (SEFI) response of the commercial-off-the-shelf (COTS) and radiation hardened Cortex-M4 (M4) micro controllers with the Armv7-M ISA. The micro controllers were exposed to 200 MeV protons. The COTS M4 was further evaluated under carbon ions and alpha particles to assess if the control bits that depend on the software could have a significant influence on the SEFI cross section for this ISA. The SEU results show that both micro controllers can experience multiple-cell upsets (MCUs), which could facilitate the accumulation of multiple-bit upsets (MBUs). MBUs could be a concern even for radiation hardened systems with ECC, because ECC crashes the system (SEFI) to correct MBUs.

关键词： Protons Radiation effects Radiation hardening (electronics) Microcontrollers Alpha particles Ions Software Error correction codes Carbon Testing

来源：评论

学校读者我要写书评

暂无评论

Deep learning for automatically predicting early haematoma expansion in Chinese patients

引用

Stroke & Vascular Neurology 2021年第4期6卷 610-614,I0067-I0072页

作者： Jia-wei Zhong Yu-jia Jin Zai-jun Song Bo Lin Xiao-hui Lu Fang Chen Lu-sha Tong Department of Neurology Zhejiang University School of Medicine Second Affiliated HospitalHangzhouChina College of Computer Science and Technology Zhejiang UniversityHangzhouChina State Key Laboratory of Fluid Power and Mechatronic Systems Zhejiang University School of Mechanical EngineeringHangzhouChina Department of Computer Science and Engineering Nanjing University of Aeronautics and AstronauticsNanjingChina

Background and purpose Early haematoma expansion is determinative in predicting outcome of intracerebral haemorrhage(ICH)*** aims of this study are to develop a novel prediction model for haematoma expansion by applying deep learning model and validate its prediction *** Data of this study were obtained from a prospectively enrolled cohort of patients with primary supratentorial ICH from our *** developed a deep learning model to predict haematoma expansion and compared its performance with conventional non-contrast CT(NCCT)*** evaluate the predictability of this model,it was also compared with a logistic regression model based on haematoma volume or the BAT *** A total of 266 patients were finally included for analysis,and 74(27.8%)of them experienced early haematoma *** deep learning model exhibited highest C statistic as 0.80,compared with 0.64,0.65,0.51,0.58 and 0.55 for hypodensities,black hole sign,blend sign,fluid level and irregular shape,*** the C statistics for swirl sign(0.70;p=0.211)and heterogenous density(0.70;p=0.141)were not significantly higher than that of the deep learning ***,the predictive value for the deep learning model was significantly superior to that of the logistic model of haematoma volume(0.62;p=0.042)and the BAT score(0.65;p=0.042).Conclusions Compared with the conventional NCCT markers and BAT predictive model,the deep learning algorithm showed superiority for predicting early haematoma expansion in ICH patients.

关键词： patients expansion predicting

来源：评论

学校读者我要写书评

暂无评论

Mangrove Tree Propagules Classification via Deep Learning

Mangrove Tree Propagules Classification via Deep Learning

引用

2023 International Conference on Digital Applications, Transformation and Economy, ICDATE 2023

作者： Centeno, Jenette C. Cruz, Jennifer C. Dela Alba, Arjay R. Romasanta, Arlene A. Ballado, Alejandro H. Novelero, Jilbert M. Mapua University School of Electrical Electronics and Computer Engineering Intramuros Manila Philippines Bulacan State University College of Engineering Bulacan City of Malolos Philippines Management Information Systems Service Department of Information and Communications Technology Manila Philippines Academic Affairs Mapua Malayan Colleges of Mindanao Davao City Philippines

ISBN: (纸本)9798350310689

Examining a machine learning model that can predict the type of mangrove species, from the images of the different mangrove tree propagules, is the objective of this study. Dataset used here were downloaded online. For propagule classification tool, transfer learning using Deep Network Designer app was used. Convolution Neural Network (CNN) based on the inception architecture was used where GoogleNet model was the exact design. Global warming is already happening, and these trees play important roles in lessening the impact of climate change. Classifying what type of mangrove trees to plant according to proper mangrove zonation will help a lot and will give a greater fighting chance to protect coastlines and people during extreme weather conditions and a whole lot more because these trees can also give food, medicine, timber, and habitat for marine species, and other animals. During the classification experiment/validation, an average of 99.7% accuracy was achieved. © 2023 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Simulation and Control Solutions for Accessible Surgical Robotics in Developing Nations

Simulation and Control Solutions for Accessible Surgical Rob...

引用

International Workshop on Wearable and Implantable Body Sensor Networks (BSN)

作者： K. E. Ch Vidyasagar Renu Karadula Mahesh Suraram Manob Jyoti Saikia Biomedical Sensors and Systems Lab University of Memphis Memphis TN USA Department of Biomedical Engineering Osmania University Hyderabad India Department of Electrical and Computer Engineering University of Memphis Memphis TN USA

ISBN: (数字)9798331530143

ISBN: (纸本)9798331530150

Robotic-assisted medical procedures have grown remarkably since the late 1980s, demonstrating outcomes comparable to or better than laparoscopic surgery, including reduced blood loss, less postoperative pain, improved cosmetic results, and quicker recovery. Surgeons using robotic systems experience less physiological stress compared to traditional open approaches. The incorporation of robotic surgery allows tele-mentoring and telesurgery. Through telesurgery, surgeons can perform operations from a distance, cutting down on travel time and removing geographical restrictions to enhance surgical productivity. In developing nations with a general lack of healthcare professionals and resources, the expansion of robotic procedures will be a true game changer. Challenges hindering this expansion include fragmentation, high costs, and a steep learning curve, limiting access to smaller hospitals and creating disparities in the training of surgeons. For example, the first urologic robotic system in India was installed at AIIMS, New Delhi, in 2006. Yet, India's global contribution to robotic surgery is less than 0.1%, with only 76 systems across 66 centers and over 500 trained surgeons in 2021. To address these issues, we designed a physical prototype and virtual simulation system. The prototype features three control modes: GUI, joystick, and color-based sorting for two serial manipulator arms, offering flexible training for surgeons. It can also be used in rehabilitation, diagnosis, and other procedures. The virtual simulation provides cost-effective, comprehensive training, reducing the need for expensive installations and accelerating the learning curve. This dual approach makes advanced medical training more accessible and affordable, potentially democratizing robotic surgery for all medical practitioners.

关键词： Training Medical robotics Costs Hospitals Surgery Prototypes Robot sensing systems Manipulators Robots Medical diagnostic imaging

来源：评论

学校读者我要写书评

暂无评论

Optimal Power Control Based-Metaheuristic Algorithm Based Variable Speed Wind Energy System of DFIG

Optimal Power Control Based-Metaheuristic Algorithm Based Va...

引用

International Smart Grid Workshop and Certificate Program (ISGWCP)

作者： Boussaid Ibrahim Harrouz Abdelkader Merahi Farid Ibrahim Yaichi Ilhami Colak Korhan Kayisli Virgil Dumbrava Electrical Engineering Department Laboratory of sustainable development and computer science (LDDI) University of Adrar Adrar Algeria Laboratory of sustainable development and computer science (LDDI) University of Adrar Adrar Algeria Electrical Engineering Department Automatic Laboratory of Setif University of Ferhat Abbas Setif1 Setif Algeria Department of Electrical Electronics Eng. Faculty of Engineering Architecture Nisantasi University Istanbul Turkey Department of Electric Power Systems Polytechnic University of Bucharest Bucharest Romania

This article presents a novel method for controlling a doubly fed induction generator (DFIG) wind energy system in the presence of variable wind speeds. In order to achieve decoupling control of the active and reactive power, the rotor-side converter (RSC) of the DFIG is controlled using field-oriented control (FOC). The system is very complicated and nonlinear, making it challenging to adjust the PI gains appropriately. The present research proposes the utilization of the Grey Wolf Optimization (GWO) algorithm as an approach to optimize the gains of a Proportional-Integral (PI) regulator. The simulation results demonstrate that the GWO-PI provides a lower criterion value and an improved response than the conventional PI.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Data Dimension Reduction makes ML Algorithms efficient

Data Dimension Reduction makes ML Algorithms efficient

引用

2022 International Conference on Emerging Technologies in Electronics, Computing and Communication, ICETECC 2022

作者： Khan, Wisal Turab, Muhammad Ahmad, Waqas Ahmad, Syed Hasnat Kumar, Kelash Luo, Bin Anhui University School of Computer and Technology Hefei230039 China Mehran Uni. of Enginerring & Technology Dept: Computer Systems Engineering Hyderabad Pakistan Northwestern Polytechnical University School of Aeronautics Shaanxi Xi'an710129 China Mehran Uni. of Enginerring & Technology Department Electrical Engineering Hyderabad Pakistan

ISBN: (纸本)9781665490870

Data dimension reduction (DDR) is all about mapping data from high dimensions to low dimensions, various techniques of DDR are being used for image dimension reduction like Random Projections, Principal Component Analysis (PCA), the Variance approach, LSA-Transform, the Combined and Direct approaches, and the New Random Approach. Auto-encoders (AE) are used to learn end-to-end mapping. In this paper, we demonstrate that pre-processing not only speeds up the algorithms but also improves accuracy in both supervised and unsupervised learning. In pre-processing of DDR, first PCA based DDR is used for supervised learning, then we explore AE based DDR for unsupervised learning. In PCA based DDR, we first compare supervised learning algorithms accuracy and time before and after applying PCA. Similarly, in AE based DDR, we compare unsupervised learning algorithm accuracy and time before and after AE representation learning. Supervised learning algorithms including support-vector machines (SVM), Decision Tree with GINI index, Decision Tree with entropy and Stochastic Gradient Descent classifier (SGDC) and unsupervised learning algorithm including K-means clustering, are used for classification purpose. We used two datasets MNIST and FashionMNIST Our experiment shows that there is massive improvement in accuracy and time reduction after pre-processing in both supervised and unsupervised learning. © 2022 IEEE.

关键词： Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Gamified Rehabilitation and Physiotherapy Using MediaPipe for Posture and Hand Gesture Recognition

Gamified Rehabilitation and Physiotherapy Using MediaPipe fo...

引用

Recent Trends in Microelectronics, Automation, Computing and Communications systems (ICMACC), International Conference on

作者： K.E.Ch Vidyasagar G. N. K. Anantha Sai Munagala Ruchita Manob Jyoti Saikia Biomedical Sensors and Systems Lab University of Memphis Memphis TN USA Department of Biomedical Engineering Osmania University Hyderabad India Electrical and Computer Engineering Department University of Memphis Memphis TN USA

ISBN: (数字)9798350366570

ISBN: (纸本)9798350366587

Introduction: Rehabilitation for conditions affecting mobility, such as stroke, muscle atrophy, and others, poses significant challenges in traditional physiotherapy practices. Engaging patients in enjoyable exercises is crucial for maintaining compliance with rehabilitation protocols. In response, this paper introduces a pioneering game-based approach to rehabilitation, leveraging posture detection technology. Materials and Methods: A game-based rehabilitation system was developed utilizing deep learning techniques through the MediaPipe framework for posture and hand gesture recognition. The system analyzes user posture in real time via a webcam and translates these movements into game controls, allowing patients to interact with popular games like Subway Surfers to simulate physical activities such as running and jumping. Latency between patient movements and in-game responses was measured across three hardware configurations (8GB, 12GB, and 16GB RAM) to evaluate system performance and responsiveness. Results and Discussion: Latency decreased with higher RAM, with the lowest measured at 430 ms on a 16GB configuration. This real-time responsiveness enhances patient engagement, making the rehabilitation process more immersive and effective. By leveraging posture detection technology, this innovative system bridges the gap between the necessity of rehabilitation exercises and the appeal of gaming, offering a promising solution for improving treatment outcomes across diverse age groups and conditions.

关键词： Hands Tracking Webcams System performance Refining Random access memory Games Gesture recognition Stroke (medical condition) Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Multilevel functional quantification of movements for EDR in the cloud/on-premises systems

Multilevel functional quantification of movements for EDR in...

引用

2023 Mexican International Conference on computer Science, ENC 2023

作者： Alarcón, Alan Ignacio Delgado Anaya, Eleazar Aguirre Duarte, Nidia Asunción Cortez García, Gina Gallegos Escuela Superior de Cómputo I.P.N Department of Computer Systems Engineering Mexico city Mexico Instituto Politécnico Nacional Cibersecurity Laboratory Centro de Investigación en Computación Mexico city Mexico

ISBN: (纸本)9798350393156

This article presents the results of a process to quantify the computational costs required by movements in endpoint detection and response (EDR) systems based on Moving Target Defense (MTD), under conditions close to real production. Our approach focuses on the different levels of abstraction in which a movement can be executed, including movements within the system, movements within the running application or service, movements within the operating system, and interactions beyond the boundaries of the operating system. A taxonomy of classification by type of movement executed at an end point is presented. The taxonomy considers the characteristics and the impact on the consumption of resources necessary for the execution of the movements in the endpoint. The process includes designing and selecting the most representative test scenarios that closely real-world environments. It also involves defining key variables to quantify, such as execution time and resource consumption. We report the tools and technologies used for executing the tests and collecting quantified data. Finally, we analyze and discuss of the achieved best results. This analysis provides a clear understanding of the implications and consequences of each type of movement, identifying patterns and trends in it is execution. The results enable informed decision-making when implementing MTD-based strategies. © 2023 IEEE.

关键词： Taxonomies

来源：评论

学校读者我要写书评

暂无评论

Novel Wideband Beamformers for AESAs

Novel Wideband Beamformers for AESAs

引用

Antennas and Propagation Society International Symposium

作者： Luke J. Kipfer Rick W. Kindt Marinos N. Vouvakis Department of Electrical and Computer Engineering University of Massachusetts Amherst MA USA Naval Research Laboratory Washington DC USA

This work describes a RF beamforming phased array architecture enabled by a novel wideband polyphase combiner/divider that generates 36 differential I/Q pairs (144 outputs) over 10-20GHz (66% fractional bandwidth). The polyphase combiner is designed in LTCC technology and fuses together two stacked parallel-plate waveguide (PPWG) radial power combiners with a 5-stage PPWG branch-line hybrid coupler. Through rigorous full-wave simulations, it is shown that multiple wideband 0°, 90°, 180°, and 270° phases are produced with <7° phase imbalance, ±1dB amplitude error, and better than 0.5dB excess insertion loss over most of the design bandwidth.

关键词：

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：