检索结果-内蒙古大学图书馆

Transfer learning approach to modeling multichannel gate-all-around nanosheet field-effect transistors under work function fluctuations

引用

engineering Applications of Artificial Intelligence 2025年 148卷

作者： Dash, Sagarika Li, Yiming Parallel and Scientific Computing Laboratory National Yang-Ming Chiao Tung University 1001 Ta-Hsueh Rd. Hsinchu300093 Taiwan Electrical Engineering and Computer Science International Graduate Program National Yang-Ming Chiao Tung University 1001 Ta-Hsueh Rd. Hsinchu300093 Taiwan Institute of Communications Engineering National Yang-Ming Chiao Tung University 1001 Ta-Hsueh Rd. Hsinchu300093 Taiwan Institute of Biomedical Engineering National Yang-Ming Chiao Tung University 1001 Ta-Hsueh Rd. Hsinchu300093 Taiwan Institute of Pioneer Semiconductor Innovation National Yang-Ming Chiao Tung University 1001 Ta-Hsueh Rd. Hsinchu300093 Taiwan Institute of Artificial Intelligence Innovation National Yang-Ming Chiao Tung University 1001 Ta-Hsueh Rd. Hsinchu300093 Taiwan Department of Electronics and Electrical Engineering National Yang-Ming Chiao Tung University 1001 Ta-Hsueh Rd. Hsinchu300093 Taiwan Department of Microelectronics National Yang-Ming Chiao Tung University 1001 Ta-Hsueh Rd. Hsinchu300093 Taiwan

Deep learning (DL) has significantly advanced various industries, including semiconductors, by providing sophisticated methods for analyzing emerging device data. Transfer learning (TL), a prominent DL topology, leverages knowledge from a pre-trained model to improve the performance of a specific target task. This study aims to apply TL to predict the impact of work function fluctuation (WKF) on the variability of threshold voltage (σVTH) in gate-all-around silicon nanosheet field-effect transistors (GAA Si NS FETs). We used TL to transfer knowledge from models trained on 1-channel (1ch) GAA Si NS FETs to more complex 4-channel (4ch) counterparts. The prediction accuracy is evaluated by using the mean square error(MSE), root mean square error (RMSE), and the mean absolute error(MAE) metrics. Our TL approach achieved an error rate of less than 1%, demonstrating high accuracy in predicting WKF effects on σ VTH of 4ch GAA Si NS FETs using only 500 samples. This study presents a pioneering application of TL using a one-dimensional (1D) convolutional neural network (CNN) long short-term memory (LSTM) topology in semiconductor device technology. The results effectively address the challenge of predicting σ VTH variations in advanced GAA Si NS FETs because of WKF, which eliminates the need for extensive semiconductor device simulations. © 2025 Elsevier Ltd

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A Machine Vision-Based Deep Learning Inference Approach of Biker Safety Hat Detection System 7

A Machine Vision-Based Deep Learning Inference Approach of B...

引用

7th IEEE International Conference on engineering Technologies and Applied Sciences, ICETAS 2020

作者： MacAlisang, Jonel Ordovez, Dennis P. Ledda, Mark Kristian C. Melegrito, Mark P. Obon, Ana Marie C. Technological University of the Philippines Technology Licensing Office- ITSO Manila Philippines EARIST General Education-Computer Department Manila Philippines Don Mariano Marcos Memorial State University Graduate Studies La Union Philippines Technological University of the Philippines Department of Electronics and Communications Engineering Manila Philippines University of the East Graduate Program Manila Philippines

ISBN: (纸本)9780738105048

In the Philippines road accidents were prevalent among motorcycle riders. The motorcyclist was required to wear their helmet when on the road. Some motorcyclists didn't follow the rules on wearing a helmet as safety precautions on the road. To address this, policymakers are focusing on enforcing safe and law-abiding behavior in traffic. There is, however, a lack of comprehensive data on the safety-critical behavioral metric of the use of motorcycle helmets, especially in developing countries where the main mode of transport is the motorcycle. Targeted enforcement and safety campaigns that are critical for accident reduction are prohibited by this shortage of knowledge. Hence, The researchers developed an algorithm for detecting the helmet that was worn by the motorcyclist, by using a deep learning approach the object detection was done successfully. Based on the annotated images, frames of video, and live feed data that was collected, To detect active bikes, the researchers taught the algorithm to use their helmets. An overview of the algorithm's success on an annotated research data set and a study of available data on the use of human-registered helmets indicate that our approach is extremely reliable. © 2020 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Developing an instrument for metavisualization and investigating relationships among dimensions of metavisualization

引用

Journal of Advertising Research 2024年第1期64卷 747页

作者： Hsin-Yi Chang Theerapong Binali Yen-Jung Chang a Program of Learning Sciences and Institute for Research Excellence in Learning Sciences National Taiwan Normal University Taipei Taiwan b Department of Computer Science and Information Engineering National Taiwan Normal University Taipei Taiwan c Department of Graphic Arts and Communications National Taiwan Normal University Taipei Taiwan

ABSTRACTBackground and PurposeMetavisualization plays a key role in science and technological learning in which visualization is practiced. We conducted two sequential studies with the purposes to first develop an instrument that allows individuals to report or reflect on their metavisualization, and then validate the instrument and investigate the relationships among the dimensions of *** total of 320 university students participated in this *** exploratory factor analysis (EFA) in the first study and partial least squares – structural equation modeling (PLS-SEM) in the second study, the validity and reliability of the instrument measuring the four dimensions of metavisualization were reported, and a theoretical model delineating the relationships among the four variables was *** was found that metacognitive skills, rather than metacognitive knowledge, significantly contributed to the demonstration of epistemic knowledge and judgment criteria during visualization. Metacognitive knowledge may also play an indirect role in learners’ epistemic performance through its relation with metacognitive *** results provide insights to advance understanding of metavisualization and its relation to metacognition and epistemic practice. The validated instruments may be used for future quantitative or mixed research to advance understanding of the role metavisualization plays in various contexts of learning in science and technological education.

关键词： Metavisualization metacognition epistemic practice instrument development EFA PLS-SEM

来源：评论

学校读者我要写书评

暂无评论

An efficient multi-objective evolutionary approach for solving the operation of multi-reservoir system scheduling in hydro-power plants

arXiv

引用

arXiv 2021年

作者： Marcelino, Carolina Gil Leite, G.M.C. Delgado, C.A.D.M. De Oliveira, L.B. Wanner, E.F. Jiménez-Fernández, S. Salcedo-Sanz, S. Department of Signal Processing and Communications Universidad de Alcalá Spain Institute of Computing Federal University of Rio de Janeiro Brazil Post-Graduate Program in Systems Engineering and Computer Science Federal University of Rio de Janeiro Brazil Computing Department Federal Center of Technology Education of Minas Gerais Brazil

This paper tackles the short-term hydro-power unit commitment problem in a multi-reservoir system - a cascade-based operation scenario. For this, we propose a new mathematical modelling in which the goal is to maximize the total energy production of the hydro-power plant in a sub-daily operation, and, simultaneously, to maximize the total water content (volume) of reservoirs. For solving the problem, we discuss the Multi-objective Evolutionary Swarm Hybridization (MESH) algorithm, a recently proposed multiobjective swarm intelligence-based optimization method which has obtained very competitive results when compared to existing evolutionary algorithms in specific applications. The MESH approach has been applied to find the optimal water discharge and the power produced at the maximum reservoir volume for all possible combinations of turbines in a hydro-power plant. The performance of MESH has been compared with that of well-known evolutionary approaches such as NSGA-II, NSGA-III, SPEA2, and MOEA/D in a realistic problem considering data from a hydro-power energy system with two cascaded hydro-power plants in Brazil. Results indicate that MESH showed a superior performance than alternative multi-objective approaches in terms of efficiency and accuracy, providing a profit of $412,500 per month in a projection analysis carried out. © 2021, CC BY-NC-ND.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Scalable smartphone cluster for deep learning

arXiv

引用

arXiv 2021年

作者： Na, Byunggook Jang, Jaehee Park, Seongsik Kim, Seijoon Kim, Joonoo Jeong, Moon Sik Kim, Kwang Choon Heo, Seon Kim, Yoonsang Yoon, Sungroh Dept. of Electrical and Computer Engineering Seoul National University Seoul Korea Republic of Korea Institute of Science and Technology Seoul Korea Republic of Samsung Advanced Institute of Technology Samsung Electronics Suwon Korea Republic of Mobile Communications Business Samsung Electronics Suwon Korea Republic of ASRI INMC ISRC Interdisciplinary Program in AI Seoul National University Seoul Korea Republic of

Various deep learning applications on smartphones have been rapidly rising, but training deep neural networks (DNNs) has too large computational burden to be executed on a single smartphone. A portable cluster, which connects smartphones with a wireless network and supports parallel computation using them, can be a potential approach to resolve the issue. However, by our findings, the limitations of wireless communication restrict the cluster size to up to 30 smartphones. Such small-scale clusters have insufficient computational power to train DNNs from scratch. In this paper, we propose a scalable smartphone cluster enabling deep learning training by removing the portability to increase its computational efficiency. The cluster connects 138 Galaxy S10+ devices with a wired network using Ethernet. We implemented large-batch synchronous training of DNNs based on Caffe, a deep learning library. The smartphone cluster yielded 90% of the speed of a P100 when training ResNet-50, and approximately 43x speed-up of a V100 when training MobileNet-v1. © 2021, CC BY-NC-ND.

关键词： Smartphones

来源：评论

学校读者我要写书评

暂无评论

Predicting Metabolic Syndrome With Machine Learning Models of Hybrid Analysis

Predicting Metabolic Syndrome With Machine Learning Models o...

引用

IEEE International Conference on Consumer Electronics-Taiwan (ICCE-TW)

作者： Yi-Syuan Wu Wei-Yun Wang Hao-Yi Wu Chao-Wen Chen Chi-Ming Chu Cheng-Wei Wu Department of Surgery Division of Trauma and Surgical Critical Care Kaohsiung Medical University Hospital Kaohsiung Medical University Kaohsiung Taiwan Master Program of E-Learning for Multimedia and Network Communications National I-Lan University Yilan Taiwan Department of Nursing Tri-Service General Hospital Songshan Branch and School of Nursing National Defense Medical Center Taipei Taiwan Department of Nursing Tri-Service General Hospital National Defense Medical Center Taipei Taiwan Department of Surgery Trauma and Critical Care Service Kaohsiung Medical University Hospital Kaohsiung Medical University Kaohsiung Taiwan School of Public Health National Defense Medical Center Taipei Taiwan Department of Computer Science and Information Engineering National I-Lan University Yilan Taiwan

The study uses machine learning to determine the accuracy of different algorithms for predicting MetS. Early prediction of MetS through routine health screening is an important goal for preventive medicine. The subjects in this study were employees aged 20 to 65 years old who signed a consent form for in-hospital health screening data were collected from 2015 to 2020. Total of 3538 individuals who underwent health screening were included in this study. Baseline characteristics of the 315 participants diagnosed with metabolic syndrome and 3222 participants without metabolic syndrome. This is a machine learning approach to identify metabolic syndrome using biochemical values and lifestyle habits. We found that the F1 score for detection of metabolic syndrome by neural network is the most accurate and higher compared to other models. Our study also identified some new indicators, including heart rhythm, RBC, WBC, Hb, and uric acid, as candidates for better detection of metabolic syndrome.

关键词：

来源：评论

学校读者我要写书评

暂无评论

THz Emission from Exchange-Coupled Fe/Ru/Ni Spintronic Emitters

THz Emission from Exchange-Coupled Fe/Ru/Ni Spintronic Emitt...

引用

International Conference on Infrared and Millimeter Waves

作者： R. Adam C. Greb D. E. Bürgler D. Cao S. Heidtfeld F. Wang J. Cheng D. Chakraborty I. Komissarov H. Hardtdegen M. Mikulics M. Büscher C. M. Schneider Roman Sobolewski Research Centre Jülich Peter Grünberg Institute (PGI-6) Jülich Germany Institut für Laser- und Plasmaphysik Heinrich Heine Universität Düsseldorf Düsseldorf Germany College of Physics Center for Marine Observation and Communications Qingdao University Qingdao China Materials Science Graduate Program University of Rochester Rochester New York USA Laboratory for Laser Energetics University of Rochester Rochester New York USA Department of Electrical and Computer Engineering University of Rochester Rochester New York USA Research Centre Jülich Ernst Ruska Centre for Microscopy and Spectroscopy with Electrons Jülich Germany Faculty of Physics University Duisburg-Essen Duisburg Germany Department of Physics University of California Davis Davis California USA

We explored THz emission from $\mathrm{Si}^{2} / \mathrm{SiO}_{2} / / \mathrm{Ta} / \mathrm{Fe} / \mathrm{Ru} /$ $\mathrm{Ni} / \mathrm{Al}_{2} \mathrm{O}_{3}$ spintronic emitters. We tuned magnetization alignment of Fe and Ni layers by varying the interlayer exchange coupling (IEC) strength using a range of Ru layer thickness t. Depending on IEC strength, magnetization hysteresis shows either ferromagnetic $(t=1.1 \mathrm{~nm}, 1.5 \mathrm{~nm})$, antiferromagnetic $(t=1.3 \mathrm{~nm})$ or canted $(t=1.7 \mathrm{~nm}, 1.9 \mathrm{~nm})$ relative alignment. Competition between IEC and an external magnetic field results in a dramatic difference in THz emission from the ferromagnetically (FM) and anti-ferromagnetically (AFM) coupled structures. The resulting THz emission from IEC structures is a result of an interference of THz transiens generated by the individual $\mathrm{Fe} / \mathrm{Ru}$ and $\mathrm{Ru} / \mathrm{Ni}$ emitters.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Analysis of Negative Capacitance MOSFETs Characteristic with Spacer

Analysis of Negative Capacitance MOSFETs Characteristic with...

引用

International Symposium on VLSI Technology, Systems and Applications

作者： Yu-Chun Lee Sekhar Reddy Kola Chieh-Yang Chen Min-Hui Chuang Yiming Li Parallel and Scientific Computing Laboratory Institute of Biomedical Engineering EECS International Graduate Program Institute of Communications Engineering Department of Electrical and Computer Engineering National Chiao Tung University Hsinchu Taiwan Center for mmWave Smart Radar System and Technologies National Chiao Tung University 1001 Ta-Hsueh Rd Hsinchu Taiwan

ISBN: (数字)9781728142326

ISBN: (纸本)9781728142333

In this work, our study comprises of design and investigation on negative capacitance (NC), metal-oxide-semiconductor (MOS) field effects transistors (MOSFETs) with spacer and source/drain (S/D) overlap engineering. The scope of the work is to boost the performance and high-energy efficiency of the studied NC-MOSFETs by using the ferro electric material (FE). The NC-MOSFETs with the spacer technology can achieve the admirable I on /I off ratio and subthreshold swing (SS), compared with planar MOSFETs. It makes device scaling possible by eliminating the short channel effect (SCE). We further estimated the effect of FE thickness and spacer, which are another critical parameter of obtaining better electrical characteristics and reducing SS.

关键词： Capacitance Iron Semiconductor device modeling MOSFET Integrated circuit modeling Mathematical model Ferroelectric materials

来源：评论

学校读者我要写书评

暂无评论

Ultrafast circuit protection for unmanned systems

Ultrafast circuit protection for unmanned systems

引用

2019 International Conference on communications, Information System, and computer engineering, CISCE 2019

作者： Kao, Chih-Hong Huang, Sy-Ruen He, Bo-Rong Lin, Hsiung-Cheng School of Computer Science Minnan Normal University Lab of Granular Computing ZhangZhou Fujjan China Department of Electrical Engineering Feng Chia University Taichung Taiwan Ph.D. Program of Electrical and Communications Engineering Feng Chia University Taichung Taiwan Department of Electrical Engineering Chin-Yi University of Technology Taichung Taiwan

ISBN: (纸本)9781728136813

With increasing dependence on precision electronic equipment, self-protection is becoming essential. The protection circuits commonly used before were fuses and circuit breakers which, however, they are not enough for the current need of high-speed protection circuits and automated engineering logic. In this paper, we develop a new ultrahigh-speed protection circuit, which is over exceeded 20 times faster than traditional circuits and has the ability to self-recover when any failure occurs. With the new circuit developed, it is not necessary to do manual restart and will meet the future needs of protection for electronic precision equipment. This design provides greater convenience and reliability for the unmanned equipment for the future. © 2019 IEEE.

关键词： Timing circuits

来源：评论

学校读者我要写书评

暂无评论

Improving Response Quality in a Knowledge-Grounded Chat System Based on a Sequence-to-Sequence Neural Network

Improving Response Quality in a Knowledge-Grounded Chat Syst...

引用

International Conference on Big Data and Smart Computing (BIGCOMP)

作者： Sihyung Kim Harksoo Kim Oh-Woog Kwon Young-Gil Kim Program of Computer and Communications Engineering Kangwon National University ChunCheon-si Gangwon-do Republic of Korea ETRI Yuseong-gu Daejeon Republic of Korea

A knowledge-grounded chat model based on a sequence-to-sequence neural network is proposed to perform more natural question answering. The previous chat model suffered from the same words being repeated during decoding. To reduce this word repetition, we propose a new decoding mechanism that considers the generation distribution of previously generated words. In experiments with question-answering sentences that are semi-automatically constructed, the proposed model outperformed a representative knowledge-grounded chat model, with a better accuracy of 4.35% p in finding answer phases. In addition, it demonstrated 1.63-2.05%p better results in all evaluation measures such as BLEU and ROUGE for evaluating the quality of responses and 2.83%p better results in evaluation measures such as distinct-1 for evaluating the diversity of responses.

关键词： Decoding Knowledge based systems Encoding Computational linguistics Neural networks Computational modeling Knowledge discovery

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：