检索结果-内蒙古大学图书馆

International Symposium on Applied Science 2024, ISAS 2024

作者： Raza, Aquib Ching, Congo Tak Shing Liu, Peng-Ta Phan, Thien-Luan Tran, Ngoc-Luan Nguyen, Ha Anh T. Rameez, Mohammad Li, Hung-Chung Linh, Dao Nguyen Phuong Van Hieu, Nguyen Tran, Trung Nghia National Taiwan University Taipei City10673 Taiwan Research Center for Information Technology Academia Sinica Taipei City11529 Taiwan Graduate Institute of Biomedical Engineering National Chung Hsing University Taichung402 Taiwan Department of Electrical Engineering National Chi Nan University Nantou County Taiwan Advanced Plant and Food Crop Biotechnology Center National Chung Hsing University Taichung402 Taiwan International Doctoral Program in Agriculture National Chung Hsing University Taichung402 Taiwan Fall Prevention Center Department of Physical Medicine & Rehabilitation Changhua Christian Hospital Changhua500 Taiwan Department of Physics and Electronic Engineering University of Science Vietnam National University - Ho Chi Minh City Ho Chi Minh City70000 Viet Nam Department of Computer Science University of York York HeslingtonYO10 5DD United Kingdom Undergraduate Program of Intellectual Creativity Engineering National Chung Hsing University Taichung402 Taiwan Ho Chi Minh City72409 Viet Nam HCMUT Vietnam National University Ho Chi Minh City Thu Duc Ho Chi Minh City71308 Viet Nam

This research introduces a deep learning framework that combines convolutional neural networks with autoencoders to improve the diagnostic accuracy of knee osteoarthritis. The study utilized a publicly available dataset from the Mendeley Data repository, where knee joint images were preprocessed using Contrast Limited Adaptive Histogram Equalization to enhance contrast and ensure consistent image sizing. Initially, an autoencoder was employed in an unsupervised manner to learn compressed representations of the data. These representations were then used to train a CNN to classify knee images into 'healthy' and 'osteoarthritic' categories. The model was trained using an 80:20 split for training and testing data, incorporating early stopping and data augmentation techniques to prevent overfitting and enhance generalization. Performance metrics such as accuracy, precision, recall, and the area under the Receiver Operating Characteristic curve (ROCAUC) were used to evaluate the model, resulting in a high test accuracy of 98.95%. The high precision and recall rates further confirmed the model's robustness in diagnosing KOA. To enhance interpretability, Gradient-weighted Class Activation Mapping (Grad-CAM) was applied to identify critical regions in the images that influenced the model's decisions. Additionally, t-Distributed Stochastic Neighbor Embedding (t-SNE) was used to visualize the high-dimensional encoded features in a two-dimensional space, providing deeper insights into how the model differentiates between classes. The promising results of this deep learning approach suggest its potential for broader applications in medical imaging diagnostics. By providing healthcare professionals with a tool that enhances diagnostic accuracy and operational efficiency, this framework lays the foundation for developing scalable, AI-driven diagnostic systems for various complex medical conditions. © 2025 Institute of Physics Publishing. All rights reserved.

关键词： Joints (anatomy)

来源：评论

学校读者我要写书评

暂无评论

Auxiliary Droop Frequency and Voltage Control for Grid-Forming Applied to Unbalanced Current Compensation 14

Auxiliary Droop Frequency and Voltage Control for Grid-Formi...

引用

14th IEEE International Symposium on Power Electronics for Distributed Generation Systems, PEDG 2023

作者： Marin-Hurtado, A. Escobar-Mejia, A. Gil-Gonzalez, W. Universidad Tecnológica de Pereira Electrical Engineering Graduate and Undergraduate Program Pereira Colombia

ISBN: (纸本)9798350328233

The virtual synchronous machine (VSM) has been a potential solution to control the grid-forming converters to integrate renewable energies (RES) into the grid. It is responsible for emulating the kinetic energy and static/dynamic properties of conventional synchronous generators to solve the stability problems due to decrease inertia in the systems with high levels of RES. This has been increasing in the distribution grids where is common the single-phase loads and the current unbalance, which causes stability problems as the intensified frequency oscillations and the frequency deviation in the system. The VSM control is common in converters present in the balance system. However, the VSM control implementation in converters present in the unbalanced system is not a straightforward task due as the unbalances intensify the power oscillations to cause the VSM to have abnormal behavior. Nevertheless, the frequency and voltage droops controls are commonly used in the converters present in the unbalanced system, but they are used as grid-following converters. Therefore, this paper proposes an auxiliary droop frequency and voltage control (AFV) scheme to integrate into a virtual synchronous machine (VSM-AFV) in order to improve a four-wire power system's stability during an unbalanced system. This approach is based on droop frequency and voltage control, and its law control is obtained from a system's active power and reactive power flow exchange equation. Changes in the active power of the VSM based on unbalances presented in the distribution grid are considered to show the performance of the VSM-AFV. Results show that the VSM-AFV controller presents lower ROCOF, steady-state errors in output reactive power, and output current of a four-leg three-phase voltage source converter (4-LVSC) when compared to the VSM approach. © 2023 IEEE.

关键词： Voltage control

来源：评论

学校读者我要写书评

暂无评论

Adaptive Virtual Synchronous Machine Applied to Four-Leg Three-Phase VSC

Adaptive Virtual Synchronous Machine Applied to Four-Leg Thr...

引用

2021 IEEE Southern Power Electronics Conference, SPEC 2021

作者： Marin-Hurtado, A.J. Escobar-Mejia, A. Alzate-Gomez, A. Gil-Gonzalez, W. Universidad Tecnológica de Pereira Electrical Engineering Graduate and Undergraduate Program Pereira Colombia Institución Universitaria Pascual Bravo Electrical Engineering Program Medellín Colombia

ISBN: (纸本)9781665436236

Nowadays, the power distribution grid is dominated by single-phase loads that produce unbalance currents, which cause stability problems and large frequency deviations in power systems. The Virtual Synchronous Machine (VSM) method has been proposed for renewable energy sources to reproduce the static and dynamic properties of the traditional synchronous generator, injecting/absorbing active/reactive power to/from the grid. However, the implementation and design of a VSM are not straightforward tasks, especially in an unbalanced network. Because it is necessary to compute and adjust the required inertia and damping parameters during unbalanced currents. Therefore, this paper proposes an adaptive inertia control scheme for a Four-Leg Three-Phase Voltage Source Converter (4LVSC), using the VSM approach, to improve a four-wire power system stability and compensate unbalanced currents. The proposed adaptive inertia comprises a Proportional-Integral (PI), and a Linear Quadratic Regulator (LQR) controller, which uses an optimization problem to minimize the power change and frequency droop when unbalances are presented in a power system. Time-domain simulations have been carried out on a unbalance four-wire power system considering active power variations to evaluate both the power and frequency responses using both controllers. Results show that the LQR-VSM controller presents lower frequency oscillations when compared to the VSM with constant inertia approach. © 2021 IEEE.

关键词： Frequency response

来源：评论

学校读者我要写书评

暂无评论

Optimal Indirect Power Predictive Controller in the Alpha-Beta Reference Frame for Grid-Connected Converters

Optimal Indirect Power Predictive Controller in the Alpha-Be...

引用

2019 FISE-IEEE/CIGRE Conference - Living the Energy Transition, FISE/CIGRE 2019

作者： Murillo-Yarce, D. Marulanda-Durango, J.J. Mejía, A. Escobar Alzatc-Gómez, A. Engineering Systems Faculty of Engineering Universidad de Talca Curicó Chile Electrical Engineering Graduate and Undergraduate Program Universidad Tecnológica de Pereira Pereira Colombia

ISBN: (纸本)9781728142302

This article presents an indirect power predictive optimal controller applicable to grid-connected converters. The VSI converter is used as an interface between distributed generators, energy storage systems and the ac-grid. The objective of the research project is to develop a controller with high static and dynamic features, that performs with low computational burden and low switching stress. The first step to develop the controller is to select the appropiate reference frame. The αβ frame is used for its simple structure and easy implementation. Then, the proposed methodology consider the controller performance to define the sampling period, the prediction horizon and the switching pattern. Results show that an increment in the sampling period results in a major harmonic content, and if the prediction horizon increases, the number of calculations is higher without improving the controller performance. The main features of the proposed controller are: low sampling times and a two-steps prediction horizon. With these features the VSI efficiency rises, while the systems's losses and harmonic distortion are reduced. © 2019 IEEE.

关键词： Controllers

来源：评论

学校读者我要写书评

暂无评论

Interfacial-Layer-Free Ge0.95Si0.05Nanosheet FeFETs

引用

IEEE Transactions on Electron Devices 2024年第3期71卷 1758-1763页

作者： Hsieh, Wan-Hsuan Chen, Yu-Rui Liu, Yi-Chun Zhao, Zefu Lee, Jia-Yang Tu, Chien-Te Huang, Bo-Wei Wang, Jer-Fu Lee, M.H. Liu, C.W. Graduate Institute of Electronics Engineering National Taiwan University Taipei10617 Taiwan Institute and Undergraduate Program of Electro-Optical Engineering Graduate School of Advance Technology National Taiwan University Taipei10617 Taiwan National Taiwan University Graduate School of Advance Technology Taipei10617 Taiwan Graduate Institute of Electronics Engineering Graduate Institute of Photonics and Optoelectronics Graduate School of Advanced Technology National Taiwan University Department of Electrical Engineering Taipei10617 Taiwan

The substantial memory window (MW) of 1.8 V is achieved by utilizing stacked two nanosheet (NS) gate-all-around (GAA) Ge0.95 Si0.05 ferroelectric field-effect transistors (FeFETs), employing a low write voltage of 2 V. The channel phosphorus concentration 1E18 cm-3 is used to erase the absence of interfacial layer (IL) can reduce the operation voltage. An isotropic wet etching process is employed for channel release. The stacked two NSs offer the advantages of reducing cell-to-cell variation and doubling the read current. Additionally, the stability of data storage is demonstrated with the data retention of >1E4 s, linearly extrapolated to a span of 10 years, and exhibiting high endurance >1E11 cycles. The thermal budget is as low as 400 °C. © 1963-2012 IEEE.

关键词： III-V semiconductors

来源：评论

学校读者我要写书评

暂无评论

Gait proficiency index in children aged 3.5 to 9.5 years old

引用

Research on Biomedical engineering 2021年第2期37卷 429-437页

作者： das Neves, Ana Maria Bender Seidenfuss de Souza, Leandro Daniel Aires, Andréia Gomes Souza, Thalita Borges Giacomazzi, Leandro Peserico Dachi, Édison Pereira Baptista, Rafael Reimann School of Technology Graduate Program in Electrical Engineering PUCRS Porto Alegre Brazil School of Health and Life Sciences Undergraduate Program in Physical Education PUCRS Porto Alegre Brazil School of Technology Undergraduate Program in Electrical Engineering PUCRS Porto Alegre Brazil School of Technology Associate Degree Program in Industrial Automation and Embedded Systems SENAI Porto Alegre Brazil School of Technology and School of Health and Life Sciences Pontifical Catholic University of Rio Grande do Sul Av. Ipiranga 6681 Partenon Porto Alegre90619-900 Brazil

Introduction: The purpose of this study is to present a novel approach for gait assessment called gait proficiency index (GPI) using only ground reaction forces (GRF)-derived parameters. Material and methods: Barefoot gait from 51 healthy children was evaluated with the GPI in this study. The participants walked at their self-selected speed along a 6-m walkway with 8 force platforms placed in pairs. The force-time analysis resulted in a dynamic symmetry assessment (DSA) that is the result of vertical GRF component distribution for all gait cycles both the left and right foot. DSA and impulse calculation from GRF led to the calculation of the GPI, which is the relationship between the impulse of load response and mid-stance and impulse of terminal stance and pre-swing of both right and left feet multiplied by the DSA index. The children were divided into three groups with 17 participants each and classified according to age (mean age ± standard deviation): G1 (4.39 ± 0.511), G2 (6.33 ± 0.639), G3 (8.49 ± 0.636). Results: The results show that as children mature, the GPI seems to increase from G1 to G2 and decreases from G2 to G3 and that both the standard deviations and coefficient of variation decrease with the increase of age. Conclusions: This can be an indicative that the index can assess improvements in gait quality through age. However, there was no statistical significance between the groups in this variable. Also, the correlation between either DSA and age or GPI and age found is weak to make other conclusions but that the study of adults should be included to either validate or refute the use of GPI. © 2021, Sociedade Brasileira de Engenharia Biomedica.

关键词： Biophysics

来源：评论

学校读者我要写书评

暂无评论

Student engagement through mathematical applications in electrical power systems

Student engagement through mathematical applications in elec...

引用

113th Annual ASEE Conference and Exposition, 2006

作者： Osorno, Bruno California State University Northridge United States Department of Electrical and Computer Engineering California State University Northridge United States Electric Power Systems Graduate and Undergraduate Program

Historically, electrical engineering students have been very proficient in the application of mathematics. At California State University we have experienced, recently, a negative shift of mathematical interest and therefore a lack of progress in the understanding of basic concepts that require a strong mathematical background. This problem stems from the lack of mathematical skills and studying habits. One way to solve this problem is to engage our students into the application of mathematics with simple, yet, powerful problems. An assessment of such engagement occurs every week with a quiz that spans the material covered during the previous week and tests some of the mathematical and engineering skills. This paper attempts to show the results of such assessment and the outcome of a class in which such approach was tasted. During this semester we are testing this technique again in a different course. © American Society for engineering Education, 2006.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Generalized Predictive Controller Applied in a Bidirectional DC-DC Converter 16

Generalized Predictive Controller Applied in a Bidirectional...

引用

16th Brazilian Power Electronics Conference, COBEP 2021

作者： Da Silva, Daniel Abreu Macedo Do Nascimento, Andre Cavalcante De Barros Araujo, Rejane De Souza Melo, Rogerio Jose Federal University of Pará Electrical Engineering Graduate Program Belém Brazil Federal Institute of Pará Department of Education Control and Industrial Processes Information and Communication Belém Brazil Undergraduate Electrical Engineering Estácio College Belém Brazil

ISBN: (纸本)9781665421294

This work proposes the project of the Generalized Predictive Controller (GPC), this is applied to a bidirectional converter, whose topology is the non-isolated Buck and Boost derived bidirectional DC-DC, present on a DC Nanogrid. The system consists of a primary bus, represented by Vdc, with high voltage, which is feeded by a renewable energy source that generates 175 V and a secondary source, represented by VBatt, with low voltage from a 48 V battery. The objective is to develop robustness and performance analysis, and ensure reference tracking and rejection of disturbance of this predictive controller when used in a bidirectional converter present in the aforementioned situation. In addition to analyzing how the control weighting factor interferes in the robustness and performance of this controller in this situation. © 2021 IEEE.

关键词： Controllers

来源：评论

学校读者我要写书评

暂无评论

Color recognition robot

Color recognition robot

引用

IEEE International Conference on Communication Software and Networks

作者： Darma, Jessie Frederick Setyawan, Leonardy Kuantama, Endrowednes Undergraduate Program in Electrical Engineering University of Pelita Harapan UPH Tower Lippo Village Tangerang 15811 Indonesia Pelita Harapan University Graduate Program in Electrical Engineering University of Pel Ita Harapan Plaza Semanggi Jl. Jend. Sudirman Kav. 50 Jakarta 12930 Indonesia

ISBN: (纸本)9781612844855

The advance of robotic technology will bring ease to human life not only in the industrial sector but also the education and entertainment sector. In this research, an idea of a robot that can classify objects according to their color is proposed. The classification process depends on several sensors such as light sensor, color sensor, and touch sensor. The designed robot is able to tell the difference out of three colors that show different intensity in a short time. The objects consist of three balls with different colors that need to be classified into three different places. This robot uses a 12 volt battery as a supply and a dc motor to move around. To collect the object, this robot is using a vacuum tube instead of a hand, which is more frequently used in this type of robot. © 2011 IEEE.

关键词： DC motors

来源：评论

学校读者我要写书评

暂无评论

Hand-puppet robot control

Hand-puppet robot control

引用

2011 IEEE 3rd International Conference on Communication Software and Networks, ICCSN 2011

作者： Setyawan, Leonardy Kesaulja, Leonardus Mario Darma, Jessie Kuantama, Endrowednes Undergraduate Program in Electrical Engineering University of Pelita Harapan UPH Tower Lippo Village Tangerang 15811 Indonesia Pelita Harapan University Graduate Program in Electrical Engineering University of Pel Ita Harapan Plaza Semanggi Jl. Jend. Sudirman Kav. 50 Jakarta 12930 Indonesia

ISBN: (纸本)9781612844855

This research aims to create a robot that is controlled by the hand-puppet using the microcontroller which is equipped with a pair of transmitter and receiver data. The command will be sent from the hand-puppet to the robot which forms the interaction between the user and the robot. This robot has several motions which depend on the hand-puppet's motion combinations. The hand-puppet can control the robot because it is equipped with three types of sensors (reed sensor, flex sensor, and tilt sensor). The reed sensor is placed at the right hand of the hand-puppet whereas the tilt sensor is placed at the left hand of the hand-puppet, and the flex sensor is placed in the hand-puppet's mouth. This robot will move forward, backward, and rotate according to the hand-puppet's motion combinations. These motions are actuated by the 12 V DC motor. By equipping it with LEDs arranged to dot matrix, this robot can also show a variety of expressions. This research is expected to further develop the types of robots with new variations and the interaction with humans. © 2011 IEEE.

关键词： Microcontrollers

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：