检索结果-内蒙古大学图书馆

2023 Conference on Lasers and Electro-Optics, CLEO 2023

作者： Kabir, Md Faiyaz Mia, Md Borhan Ahmed, Ishtiaque Jaidye, Nafiz Ahmed, Syed Z. Kim, Sangsik Department of Electrical and Computer Engineering Texas Tech University LubbockTX79409 United States Department of Physics and Astronomy Texas Tech University LubbockTX794094 United States School of Electrical Engineering Korea Advanced Institute of Science and Technology Daejeon34141 Korea Republic of

We show that a TM leaky mode realized by subwavelength gratings (SWGs) can eliminate crosstalk between proximate waveguides. Oscillating fields i n t he SWGs allow coupling coefficient components to counteract each ot... 详细信息

ISBN: (纸本)9781957171258

关键词： Crosstalk

来源：评论

学校读者我要写书评

暂无评论

Machine learning algorithms for predicting the risk of chronic kidney disease in type 1 diabetes patients: a retrospective longitudinal study

引用

Neural Computing and Applications 2024年第26期36卷 16545-16565页

作者： Chowdhury, Md Nakib Hayat Reaz, Mamun Bin Ibne Ali, Sawal Hamid Md Crespo, María Liz Cicuttin, Andrés Ahmad, Shamim Haque, Fahmida Bakar, Ahmad Ashrif A. Razak, Mohd Ibrahim Bin Shapiai Abd Bhuiyan, Mohammad Arif Sobhan Department of Electrical Electronic and Systems Engineering Universiti Kebangsaan Malaysia UKM Selangor Bangi43600 Malaysia Saidpur Cantonment Saidpur Nilphamari5310 Bangladesh Department of Electrical and Electronic Engineering Independent University Bangladesh Dhaka Bashundhara Bangladesh Department of Electrical Electronic and Systems Engineering Centre of Advanced Electronic and Communication Engineering Universiti Kebangsaan Malaysia UKM Selangor Bangi43600 Malaysia Malaysia-Japan International Institute of Technology Universiti Teknologi Malaysia Jalan Sultan Yahya Petra Kuala Lumpur54100 Malaysia Trieste34151 Italy Department of Computer Science and Engineering University of Rajshahi Rajshahi6205 Bangladesh Artificial Intelligence Resource Molecular Imaging Branch National Cancer Institute BethesdaMD United States Department of Electrical and Electronics Engineering Xiamen University Malaysia Selangor Bandar Sunsuria Sepang43900 Malaysia

Chronic kidney disease (CKD) is a significant concern for individuals with type 1 diabetes (T1D), impacting their quality of life and healthcare costs. Identifying T1D patients at greater risk of developing CKD is crucial for preventive measures. However, it is challenging due to the asymptomatic progression of CKD and limited nephrologist availability in many countries. This study explores machine learning algorithms to predict CKD risk in T1D patients using ten years of retrospective data from the Epidemiology of Diabetes Interventions and Complications clinical trial. Eleven machine learning algorithms were applied to twenty-two readily available features from T1D patients’ routine check-ups and self-assessments to develop 10-year CKD risk prediction models. In addition, we also proposed a heterogeneous ensemble model (STK) using a stacking generalization approach. The models’ performance was evaluated using different evaluation metrics and repeated stratified k-fold cross-validation. Several predictive models showed reliable performance in CKD risk prediction, with the proposed ensemble model being the best performing with an average accuracy of 0.97, specificity of 0.98, sensitivity/recall of 0.96, precision of 0.98, F1 score of 0.97, Kappa and MCC score of 0.94, AUROC of 0.99, and Precision-Recall curve of 0.99. The proposed machine learning approach could be applicable for CKD risk prediction in T1D patients to ensure the necessary precautions to overcome the risk. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Hybrid Modulation for a SHB-FB Converter Employed in An Integrated On-board Charger and Auxiliary Power Module

引用

IEEE Transactions on Transportation Electrification 2025年

作者： Liang, Ziwei Bijukchhe, Rajib Zhu, Liyan Bai, Hua Forouzesh, Mojtaba Samila, Myron Cebanov, Evgheni Phillips, Headley University of Tennessee department of electrical engineering and computer science KnoxvilleTN37923 United States Magna Powertrain Inc Advanced Engineering & e-Propulsion ON Vaughan Canada

This paper presents a highly integrated EV charger that offers multiple charging modes, including a three-phase input 11kW on-board charger (OBC), an 11kW vehicle-toload (V2L) and a 2.6kW auxiliary power module (APM). The proposed multilevel, three-port topology simultaneously achieves magnetic and circuit integration while accommodating a three-phase (3P) 400-V AC input and a 700V DC bus using 650V GaN HEMTs. A mathematical model of the zero voltage switching (ZVS) boundary of the stacked half-bridge-full-bridge (SHB-FB) converter in the proposed integrated charger is built. Based on this, one hybrid modulation (HM) method is further proposed to improve the full-range efficiency of the SHB-FB converter in the OBC and V2L modes. A prototype is built to validate the proposed integration method and the HM method. Experimental results validate the OBC, V2L and APM modes of the proposed integrated charger and the effectiveness of the HM in improving the medium- and light-load efficiency by achieving full-range ZVS or quasi-ZVS (QZVS). © 2015 IEEE.

关键词： Gallium nitride

来源：评论

学校读者我要写书评

暂无评论

Privacy-Preserving Load Forecasting via Personalized Model Obfuscation

Privacy-Preserving Load Forecasting via Personalized Model O...

引用

IEEE General Meeting Power& Energy Society

作者： Shourya Bose Yu Zhang Kibaek Kim Department of Electrical & Computer Engineering University of California Santa Cruz CA Mathematics and Computer Science Division Argonne National Laboratory IL

ISBN: (数字)9798350381832

ISBN: (纸本)9798350381849

The widespread adoption of smart meters provides access to detailed and localized load consumption data, suitable for training building-level load forecasting models. To mitigate privacy concerns stemming from model-induced data leakage, federated learning (FL) has been proposed. This paper addresses the performance challenges of short-term load forecasting models trained with FL on heterogeneous data, emphasizing privacy preservation through model obfuscation. Our proposed algorithm, Privacy Preserving Federated Learning (PPFL), incorporates personalization layers for localized training at each smart meter. Additionally, we employ a differentially private mechanism to safeguard against data leakage from shared layers. Simulations on the NREL ComStock dataset corroborate the effectiveness of our approach.

关键词： Training Privacy Load forecasting Federated learning Simulation Predictive models Data models Smart meters Voltage control Load modeling

来源：评论

学校读者我要写书评

暂无评论

A population randomization-based multi-objective genetic algorithm for gesture adaptation in human-robot interaction

引用

science China(Information sciences) 2021年第1期64卷 188-200页

作者： Luefeng CHEN Wanjuan SU Min LI Min WU Witold PEDRYCZ Kaoru HIROTA School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Department of Electrical and Computer Engineering University of Alberta Tokyo Institute of Technology

In recent years, vision-based gesture adaptation has attracted great attention from many experts in the field of human-robot interaction, and many methods have been proposed and successfully applied, such as particle swarm optimization and genetic algorithm. However, the reduction of the error and energy consumption of a robot while paying attention to more subtle attitude changes is very important and *** view of these problems, we propose a population randomization-based multi-objective genetic *** gesture signal is processed with a slight change by imitating the biological evolution mechanisms. In the proposed algorithm, a random out-of-order matrix is added in the process of population evolution synthesis to prevent the premature grouping convergence of the new population. The weights of the objective function and the elite retention strategy are adopted, and the most adaptable individuals in each generation are inherited directly in the next generation without any recombination or mutation. To verify the effectiveness of the algorithm, preliminary application experiments are performed on the gesture adaptation of a robotic arm. The results are compared with the original signal, and the comparison shows that by using the proposed method, the energy consumption is reduced, and the end error is decreased to less than 3 mm while ensuring the tracking effect of the robotic arm. These obtained results meet the communication requirements for human-robot interactions such as handshakes. Moreover, the proposed method has better performance, uses less energy, and has a smaller tracking error than the particle swarm optimization, the single-objective genetic algorithm, and the traditional multi-objective genetic algorithm. A preliminary application experiment indicates that the robotic arm can adapt to human gestures in real time.

关键词： multi-objective genetic algorithm gesture adaptation human-robot interaction

来源：评论

学校读者我要写书评

暂无评论

Cramér-Rao bounds of near-field positioning based on electromagnetic propagation model

引用

IEEE Transactions on Vehicular Technology 2023年第11期72卷 13808-13825页

作者： Chen, Ang Chen, Li Chen, Yunfei You, Changsheng Wei, Guo Yu, F. Richard University of Science and Technology of China CAS Key Laboratory of Wireless Optical Communication Hefei230027 China University of Durham Department of Engineering DurhamDH1 3LE United Kingdom Southern University of Science and Technology Department of Electronic and Electrical Engineering Shenzhen518055 China Carleton University Department of Systems and Computer Engineering OttawaONK1S 5B6 Canada

The adoption of large-scale antenna arrays at high-frequency bands is widely envisioned in the beyond 5G wireless networks. This leads to the near-field regime where the wavefront is no longer planar but spherical, bringing new opportunities and challenges for communications and positioning. In this article, we improve the near-field positioning technology from the classical spherical wavefront model (SWM) to the more accurate and true electromagnetic propagation model (EPM). A generic near-field positioning model with different observation capabilities for three electric field types (vector, scalar, and overall scalar electric field) is developed based on the complete EPM. For these three observed electric field types, the Cramér-Rao bound (CRB) is adopted to evaluate the achievable estimation accuracy. The expressions of the CRBs for different electric field observations are derived by combining electromagnetic propagation concepts with estimation theory. Closed-form expressions can be further obtained as the terminal is assumed to be on the central perpendicular line (CPL) of the receiving antenna surface. Moreover, the above discussions are extended to the system with multiple receiving antennas. In this case, the CRBs using various electric field types are derived and the effect of different numbers of receiving antennas is deeply investigated. Numerical results are provided to quantify the CRBs and validate the analytical results. Also, the impact of different system parameters, including electric field type, wavelength, size of the receiving antenna, and number of antennas, is evaluated. © 1967-2012 IEEE.

关键词： Electric fields

来源：评论

学校读者我要写书评

暂无评论

Plasma Jet Deposition and Self-Sintering of Gold Nanoparticle Ink for Flexible Electronics 5

Plasma Jet Deposition and Self-Sintering of Gold Nanoparticl...

引用

5th IEEE International Flexible Electronics Technology Conference, IFETC 2023

作者： Manzi, Jacob Varghese, Tony Dhamala, Anupama Prakasan, Lakshmi Eixenberger, Josh Kandadai, Nirmala Estrada, David Subbaraman, Harish School of Electrical Engineering and Computer Science Oregon State University CorvallisOR97331 United States Micron School of Material Science and Engineering Boise State University BoiseID83725 United States Boise State University Department of Electrical and Computer Engineering BoiseID83725 United States Center for Advanced Energy Studies Boise State University BoiseID83725 United States Idaho National Laboratory Idaho FallsID83415 United States

ISBN: (纸本)9798350332094

Additive manufacturing has become a promising method for the fabrication of inexpensive, green, flexible electronics. Printed electronics on low-Temperature substrates like paper are very appealing for the flexible hybrid electronics market for their use in disposable and biocompatible electronic applications and in areas like packaging, wearables, and consumer electronics. Plasma-jet printing uses a dielectric barrier discharge plasma to focus aerosolized nanoparticles onto a target substrate. The same plasma can be used to change the properties of the printed material and even sinter in situ. The technology can also be utilized in space and microgravity environments since the plasma-Assisted deposition is independent of gravity. In this work, we show plasma voltage effect on deposition of gold nanoparticles and direct printing of flexible, conductive gold structures onto low-Temperature paper substrates without the need for thermal or photonic post-processing. The effects of plasma parameters on the conductivity and flexible reliability of the printed films are studied, and a paper-based LED electrode is demonstrated. © 2023 IEEE.

关键词： Substrates

来源：评论

学校读者我要写书评

暂无评论

Sound Tagging in Infant-centric Home Soundscapes

Sound Tagging in Infant-centric Home Soundscapes

引用

IEEE International Conference on Connected Health: Applications, Systems and engineering Technologies (CHASE)

作者： Mohammad Nur Hossain Khan Jialu Li Nancy L. McElwain Mark Hasegawa–Johnson Bashima Islam Department of Electrical and Computer Engineering Worcester Polytechnic Institute Department of Electrical and Computer Engineering University of Illinois Department of Human Development and Family Studies University of Illinois Beckman Institute for Advanced Science and Technology University of Illinois

ISBN: (数字)9798350345018

ISBN: (纸本)9798350345025

Certain environmental noises have been associated with negative developmental outcomes for infants and young children. Though classifying or tagging sound events in a domestic environment is an active research area, previous studies focused on data collected from a non-stationary microphone placed in the environment or from the perspective of adults. Further, many of these works ignore infants or young children in the environment or have data collected from only a single family where noise from the fixed sound source can be moderate at the infant's position or vice versa. Thus, despite the recent success of large pre-trained models for noise event detection, the performance of these models on infant-centric noise soundscapes in the home is yet to be explored. To bridge this gap, we have collected and labeled noises in home soundscapes from 22 families in an unobtrusive manner, where the data are collected through an infant-worn recording device. In this paper, we explore the performance of a large pre-trained model (Audio Spectrogram Transformer [AST]) on our noise-conditioned infant-centric environmental data as well as publicly available home environmental datasets. Utilizing different training strategies such as resampling, utilizing public datasets, mixing public and infant-centric training sets, and data augmentation using noise and masking, we evaluate the performance of a large pre-trained model on sparse and imbalanced infant-centric data. Our results show that fine-tuning the large pre-trained model by combining our collected dataset with public datasets increases the F1-score from 0.11 (public datasets) and 0.76 (collected datasets) to 0.84 (combined datasets) and Cohen's Kappa from 0.013 (public datasets) and 0.77 (collected datasets) to 0.83 (combined datasets) compared to only training with public or collected datasets, respectively.

关键词： Training Performance evaluation Pediatrics Working environment noise Noise Tagging Transformers

来源：评论

学校读者我要写书评

暂无评论

Development of a Near-Field Sensor for Diagnosis of Liver Diseases Using 3D-EM Simulation of Mouse Model

Development of a Near-Field Sensor for Diagnosis of Liver Di...

引用

2023 IEEE Microwaves, Antennas, and Propagation Conference, MAPCON 2023

作者： Samaddar, Poulami Gaddam, Sunil Rahman, Md Mirazur Dey, Shuvashis Roy, Sayan Mitra, Dipankar Arunachalam, Shivaram P. Microwave Engineering & Imaging Laboratory Division of Gastroenterology and Hepatology Department of Medicine Mayo Clinic RochesterMN United States North Dakota State University Department of Electrical and Computer Engineering FargoND United States University of Missouri-Kansas City Division of Energy Matter and Systems School of Science and Engineering Kansas CityMO United States University of Wisconsin-La Crosse Department of Computer Science & Computer Engineering La CrosseWI United States

ISBN: (纸本)9798350328264

In this work, we studied the response of an antipodal Vivaldi antenna in the presence of different types of mice liver models. The scope of the study was limited to two types of liver diseases, i.e., nonalcoholic steatohepatitis (NASH) and fibrosis. The complex dielectric properties of each liver type were measured using the open-ended coaxial probe dielectric spectroscopy method. A Vivaldi antenna for near-field sensing was designed and then simulated in CST Studio to determine the antenna characteristics. The antenna performance from the simulation matched the reflection coefficients (S11) measurements collected with the fabricated antenna in an anechoic chamber. This verified antenna was used for further measurements of different liver models placed near the antenna. The antenna response, S11 measurements, varied from one tissue type to another, demonstrating the potential of using the Vivaldi antenna as a near-field sensor to differentiate liver disease models from the healthy liver model. © 2023 IEEE.

关键词： Antipodal Vivaldi antenna complex permittivity dielectric property fibrosis liver disease microstrip antenna Nonalcoholic steatohepatitis

来源：评论

学校读者我要写书评

暂无评论

Assessing the Robustness of nnU-Net in the Detection of Prostate Lesions via Bi-Parametric MRI

Assessing the Robustness of nnU-Net in the Detection of Pros...

引用

2023 IEEE EMBS Special Topic Conference on Data science and engineering in Healthcare, Medicine and Biology, IEEECONF 2023

作者： Zaridis, Dimitrios I. Mylona, Eugenia Tachos, Nikolaos Kalantzopoulos, Charalampos Pezoulas, Vasileios C. Koutsouris, Dimitrios D. Matsopoulos, George K. Marias, Kostas Tsiknakis, Manolis Fotiadis, Dimitrios I. National Technical University of Athens School of Electrical and Computer Engineering Biomedical Engineering Laboratory AthensGR15773 Greece Forth Biomedical Research Institute Ioannina Greece University of Ioannina Ioannina Greece Forth Institute of Computer Science Heraklion Greece Hellenic Mediterranean University Department of Electrical and Computer Engineering Crete Heraklion Greece FORTH-IMBB Ioannina Greece University of Ioannina Unit of Medical Technology and Intelligent Information Systems Materials Science and Engineering Department IoanninaGR 45110 Greece

ISBN: (纸本)9798350383386

Within the scope of prostate cancer diagnostic imaging, distinguishing lesions is challenging due to their subtle appearance and the prostate gland's complexity. This study employed the nnU-Net, a state-of-the-art medical image segmentation model, on a dataset of 301 patients from 2 openly available datasets to identify whether lesion sizes are affecting the model's performance. By applying t-SNE dimensionality reduction algorithm among dice score and respective lesion sizes, we found that nnU-Net behaves differently for lesions smaller than 9mm compared to lesions larger than 15mm. These insights can inform specialized training approaches for future deep learning models in prostate lesion *** Relevance: The main contributions of this study is, to investigate whether lesion sizes affects nnU-Net's deficiency leading to the development of more specialized models in respect to these factors. © 2023 IEEE.

关键词： Urology

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：