检索结果-内蒙古大学图书馆

14th Annual IEEE Applied Power Electronics Conference and Exposition, APEC 2025

作者： Ramos, Gabriel V. Parreiras, Thiago M. Zhao, Fangzhou Wang, Xiongfei De J. C.Filho, Braz Graduate Program in Electrical Engineering Universidade Federal de Minas Gerais Av. Antônio Carlos 6627 MG Belo Horizonte31270-901 Brazil Centro Federal de Educação Tecnológica de Minas Gerais Department of Electrical Engineering Belo Horizonte Brazil Aalborg University Department of Energy Aalborg Denmark Kth Royal Institute of Technology Division of Electric Power and Energy Systems Stockholm Sweden Universidade Federal de Minas Gerais Department of Electrical Engineering Belo Horizonte Brazil

ISBN: (纸本)9798331516116

The work proposes the Zero Harmonic Distortion Converter (ZHD) as a grid-connected grid-forming (GFM) converter due to its unique sinusoidal characteristic without capacitive filters, low parts count, and off-the-shelf power circuitry with a simple open-loop control structure that does not contribute to possible control interaction and resonances in grid-connected mode. These characteristic are reached by a harmonic cancellation in a three-winding transformer along with harmonic elimination using the Selective Harmonic Elimination Pulse Width Modulation (SHE PWM). The ZHD GFM converter is a compelling alternative for GFM battery energy storage systems (BESS) in medium-voltage applications. © 2025 IEEE.

关键词： Battery storage

来源：评论

学校读者我要写书评

暂无评论

Machine Speech Chain with Emotion Recognition

Machine Speech Chain with Emotion Recognition

引用

International Conference of Advanced informatics: Concept, Theory and Application (ICAICTA)

作者： Akeyla Pradia Naufal Dessi Puji Lestari Ayu Purwarianti Kurniawati Azizah Dipta Tanaya Sakriani Sakti School of Electrical Engineering and Informatics Bandung Institute of Technology Bandung Indonesia Faculty of Computer Science University of Indonesia Depok Indonesia Graduate School of Information Science Nara Institute of Science and Technology Nara Japan

ISBN: (数字)9798331520311

ISBN: (纸本)9798331520328

Developing natural speech recognition and speech synthesis systems requires speech data that authentically represents real emotions. However, this type of data is often challenging to obtain. Machine speech chain offers a solution to this challenge by using unpaired data to continue training models initially trained with paired data. Given the relative abundance of unpaired data compared to paired data, machine speech chain can be instrumental in recognizing emotions in speech where training data is limited. This study investigates the application of machine speech chain in speech emotion recognition and speech recognition of emotional speech. Our findings indicate that a model trained with 50% paired neutral emotion speech data and 22% paired non-neutral emotional speech data shows a reduction in Character Error Rate (CER) from 37.55% to 34.52% when further trained with unpaired neutral emotion speech data. The CER further decreases to 33.75% when additionally trained with combined unpaired speech data. The accuracy of recognizing non-neutral emotions ranged from 2.18% to 53.51 %, though the F1 score fluctuated, increasing by up to 20.6% and decreasing by up to 23.4%. These results suggest that the model demonstrates a bias towards the majority class, as reflected by the values of the two metrics.

关键词： Training Emotion recognition Accuracy Error analysis Natural languages Training data Speech recognition Speech enhancement Data models Speech synthesis

来源：评论

学校读者我要写书评

暂无评论

Analysis of the Brazilian Climate Data Influence on Soybean Pricing by Using Long Short-Term Memory Models

SSRN

引用

SSRN 2024年

作者： Oliva, Jefferson Tales Martelli, Otávio Pigozzo de Castro Barbosa, Marco Antônio Dal Molin, Viviane Casanova, Dalcimar Teixeira, Marcelo Graduate Program in Electrical and Computer Engineering Federal University of Technology-Paraná PR Pato Branco85503-390 Brazil Department of Academic Informatics Federal University of Technology-Paraná PR Pato Branco85503-390 Brazil Graduate Program in Production and Systems Engineering Federal University of Technology-Paraná PR Pato Branco85503-390 Brazil

This work uses machine learning to verify whether the Brazilian climate influences international soybean price prediction. For this, climatic data, dollar quotes, inflation, and annual soybean production were collected from different data sources. Then, the collected data were pre-processed and grouped by Brazilian state. Afterward, data from the five most productive Brazilian states are chosen, such as Mato Grosso (MT), Mato Grosso do Sul (MS), Goiás (GO), Paraná (PR), and Rio Grande do Sul (RS). Afterward, predictive models are built using the long short-term memory (LSTM) method, which is applied in each chosen state dataset considering two different settings: with and without climatic data. Thus, two models were built for each Brazilian state, totaling ten predictors. In the experimental evaluation, when trained with climatic data, the PR model achieved the lowest values of root mean squared error (RMSE) and mean absolute error (MAE). Regarding predictors trained without climate data, the RS and PR obtained the lowest values of RMSE and MAE, respectively. After conducting statistical hypothesis tests, no significant difference was found among models, stating, with 95% certainty, that, in this study, the Brazilian climatic data did not influence the model performance for predicting soybean prices. On the other hand, one of the main contributions of work is conducting an unprecedented study about soybean price prediction using Brazilian climatic data. © 2024, The Authors. All rights reserved.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Development of Buffer Zone into Living Lab-Garuda Smart City Framework: Systematic Review 10

Development of Buffer Zone into Living Lab-Garuda Smart City...

引用

10th International Conference on ICT for Smart Society, ICISS 2023

作者： Emmanuel, Gunadi Supangkat, Suhono Harso Gaol, Ford Lumban Ranti, Benny Bina Nusantara University Doctor of Computer Science Jakarta Indonesia Univ. Katolik Musi Charitas Fakultas Sains Dan Teknologi Palembang Indonesia School of Electrical Engineering and Informatics Institut Teknologi Bandung Bandung Indonesia Bina Nusantara University Binus Graduate Program-Doctor of Computer Science Computer Science Department Jakarta Indonesia

ISBN: (纸本)9798350339543

The phenomenon of urbanization in Indonesia is inevitable. The new residential and economic centers in suburban areas is also a problem in city development. The gradual planning and development of smart cities in a living lab require consideration of the right location for a living lab. This study wants to show that suburban areas as city buffer zones can become living laboratories for smart city development. The diversity of situations in cities and regencies across Indonesia, the potential for resources, and the problems faced are the challenges of developing a living lab-Garuda Smart City Framework. This research uses the method of reviewing the literature of research publications for the last five years (2019-2023) to obtain information on Smart City development in Indonesia. We collected selected articles from databases in Google Scholar, IEEE, and Scopus using the Publish and Perish 8. The search keywords used were garuda AND Smart city AND Framework. The findings show the potential and dynamics of buffer zones to become appropriate living laboratories. Smart city regional planning can more holistically involve neighborhoods and address urban issues. © 2023 IEEE.

关键词： Smart city

来源：评论

学校读者我要写书评

暂无评论

Soybean Price Prediction by Using Lstm Models Based on Brazilian Climatic Data

SSRN

引用

SSRN 2024年

作者： Oliva, Jefferson Tales Martelli, Otávio Pigozzo de Castro Barbosa, Marco Antônio Molin, Viviane Dal Casanova, Dalcimar Teixeira, Marcelo Graduate Program in Electrical Engineering Federal University of Technology-Paraná PR Pato Branco85503-390 Brazil Department of Academic Informatics Federal University of Technology-Paraná PR Pato Branco85503-390 Brazil Graduate Program in Production and Systems Engineering Federal University of Technology-Paraná PR Pato Branco85503-390 Brazil

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Physical Design of RISC-V based System-on-Chip using OpenLane

Physical Design of RISC-V based System-on-Chip using OpenLan...

引用

IEEE Asia-Pacific Conference on Circuits and Systems

作者： Muhammad Fauzan Raihan Fadhil Yanuarsyah Muhammad Hanif Hibatullah Radithya Arisaputra Infall Syafalni Nana Sutisna Trio Adiono Makoto Ikeda School of Electrical Engineering and Informatics Bandung Institute of Technology Indonesia University Center of Excellence on Microelectronics Indonesia System Design Laboratory School of Engineering The University of Tokyo Tokyo Japan Graduate School of Engineering The University of Tokyo Tokyo Japan

ISBN: (数字)9798350378771

ISBN: (纸本)9798350378788

Open-source tools for designing integrated circuits are crucial for electrical engineering students. However, more references are necessary to promote the tools to the academic environments. This paper presents design and implementation of a PicoSoC (Pico System-on-Chip) using the OpenLane automated VLSI flow. The PicoSoC comprises several modules, including the PicoRV32 CPU, UART and SPI peripherals, and memory blocks. The design methodology encompasses RTL simulation, macro hardening, core hardening, full-chip hardening, and gatelevel simulation. The results indicate successful physical design and functional verification, demonstrating that the gate-level simulation outputs align with those from RTL simulation. The work is useful for designing the physical layout of digital circuits, SoC architecture development, and also promoting open-source IC design tools in academic environments.

关键词： Layout Logic gates Very large scale integration System-on-chip Design tools Central Processing Unit Pins Hardware design languages Digital circuits Physical design

来源：评论

学校读者我要写书评

暂无评论

Is Attention All You Need for EEG to Predict Neurological Outcomes in Cardiac Arrest?

Is Attention All You Need for EEG to Predict Neurological Ou...

引用

2024 IEEE-EMBS International Conference on Biomedical and Health informatics, BHI 2024

作者： Dionisio, Jefferson Rizwan, Muhammad Suzuki, Hidetaka Hassan, Kazi Mahmudul Chanpornpakdi, Ingon Lin, Lian-Yu Tanaka, Toshihisa Lin, Che Tokyo University of Agriculture and Technology Tokyo Japan Japanese Red Cross Musashino Hospital Department of Emergency and Critical Care Tokyo Japan National Taiwan University College of Medicine and Hospital Division of Cardiology Department of Internal Medicine Taipei Taiwan Artificial Intelligence of Things Taiwan International Graduate Program Academia Sinica Taipei Taiwan National Taiwan University Department of Electrical Engineering Taipei Taiwan Graduate Institute of Communication Engineering National Taiwan University Taipei Taiwan National Taiwan University Center for Advanced Computing and Imaging in Biomedicine Taipei Taiwan Department of Smart Medicine and Health Informatics National Taiwan University Taipei Taiwan

ISBN: (纸本)9798350351552

Sudden cardiac arrest (SCA) poses a significant health challenge, necessitating accurate predictions of neurological outcomes in comatose patients, where good outcomes are defined as the recovery of most cognitive functions. Electroencephalogram (EEG) serves as a valuable biomarker for monitoring neurological states due to its rich, time-dependent information. This study aims to predict neurological outcomes using early EEG data by employing the Transformer model, which leverages multi-headed attention to identify patterns in lengthy sequences such as hour-long EEG recordings. Unlike traditional methods that use subsampled EEG epochs, we utilize the entire EEG sequences, subdivided into time steps, allowing our model to capture detailed temporal patterns via the attention mechanism. Moreover, we trained our proposed model using each EEG recording as an individual data sample but evaluated our model through aggregated patient-wise predictions. This approach allows us to boost the data sample size. Our results demonstrate promising predictive performance, achieving an AUROC of 0.82 and AUPRC of 0.90 on the holdout test set and an AUROC of 0.73 and AUPRC of 0.93 on an external test set with patient-wise predictions. This study highlights the potential of utilizing attention mechanisms to capture important time series progressions across EEG sequences for improving SCA prognosis. © 2024 IEEE.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Non-Hermitian selective thermal emitter for thermophotovoltaics

Non-Hermitian selective thermal emitter for thermophotovolta...

引用

2023 Conference on Lasers and Electro-Optics, CLEO 2023

作者： Prasad, Ciril S. Raphaelson, Samuel C. Naik, Gururaj V. Department of Electrical and Computer Engineering Rice University HoustonTX77005 United States Applied Physics Graduate Program Smalley-Curl Institute Rice University HoustonTX77005 United States Department of Material Science and NanoEngineering Rice University HoustonTX United States

ISBN: (纸本)9781957171258

Selective thermal emitters can boost the efficiency of heat-to-electricity conversion in thermophotovoltaic systems only if their spectral selectivity is high. We demonstrate a non-Hermitian metasurface-based selective emitter operating at 1200 K in a GaSb-thermophotovoltaic cell. © Optica Publishing Group 2023 © 2023 The Author(s)

关键词： III-V semiconductors

来源：评论

学校读者我要写书评

暂无评论

Detecting Model Poisoning Attacks Via Dummy Symbol Insertion for Secure Over-the-Air Federated Learning

Detecting Model Poisoning Attacks Via Dummy Symbol Insertion...

引用

Consumer Communications and Networking Conference, CCNC IEEE

作者： Hang Zhou Yi-Han Chiang Caijuan Chen Xiaoyan Wang Yusheng Ji Information Systems Architecture Science Research Division National Institute of Informatics Tokyo Japan Department of Electrical and Electronic Systems Engineering Osaka Metropolitan University Osaka Japan Graduate School of Science and Engineering Ibaraki University Hitachi Japan

ISBN: (数字)9798331508050

ISBN: (纸本)9798331508067

With the rapid advancement of intelligent IoT services, the need for high-quality and efficient wireless communication has become increasingly critical for information exchanges and collaborations among intelligent edge devices such as autonomous mobile robots (AMRs), robots in smart factories, and surveillance cameras, etc., Federated Learning (FL) is a promising distributed learning framework by exploring the computation capability on edge devices while protecting data privacy of users. On the other hand, Over-the-Air (OTA) computation techniques is a new paradigm of integrated computation and communication. OTA based FL (OTA-FL) can enhance spectrum efficiency by leveraging the superposition properties of wireless channels for model aggregations. The implementation of OTA-FL on edge devices can further protect user data privacy for clients, improve the throughput of inter-device communications, and enhance the distributed learning performance. However, despite these advantages, the convergence of OTA-FL systems remain vulnerable to model poisoning attacks, presenting significant challenges. In this study, we address these vulnerabilities by proposing a two-phase detection mechanism that secures OTA-FL system while preserving high spectral efficiency. Our simulation results demonstrate that under varying conditions, our approach can make distributed learning more secure and communication-efficient.

关键词： Computer aided instruction Data privacy Federated learning Distance learning Wireless networks Computational modeling Surveillance Symbols Throughput Convergence

来源：评论

学校读者我要写书评

暂无评论

Influence of Anisotropy Constant on Writability in Heated-Dot Magnetic Recording

引用

Journal of the Magnetics Society of Japan 2024年第5期48卷 81-87页

作者： Kobayashi, T. Nakatani, Y. Tagawa, I. Graduate School of Informatics and Engineering Univ. of Electro-Communications 1-5-1 Chofugaoka Chofu182-8585 Japan Electrical and Electronic Engineering Tohoku Institute of Technology 35-1 Yagiyama-Kasumicho Sendai982-8577 Japan Graduate School of Engineering Mie Univ 1577 Kurimamachiya-cho Tsu514-8507 Japan

We discuss the influence of the anisotropy constant on writability, taking account of 10 years of archiving and adjacent track interference in 4 Tbpsi shingled heated-dot magnetic recording (HDMR), using our stochastic calculation employing the Néel-Arrhenius model with a Stoner-Wohlfarth dot. The bit error rate is calculated and the result is analyzed using the mean magnetization reversal number per unit time as a function of the writing time. We confirm the stochastic calculation result by employing a micromagnetic simulation. HDMR has a certain margin for erasure-after-write, since half of the writing time determined by field is for the magnetic dot and the rest is for the nonmagnetic spacing. HDMR also has a certain margin for the dot aspect ratio, since the dot is relatively large. Therefore, the combination of a small anisotropy constant and a large dot volume can be used to improve write-error. When we choose a small anisotropy constant, the mean magnetization reversal number per unit time in the opposite direction to the recording direction is negligible. Furthermore, the writing time determined by medium is longer. Therefore, the bit error rate caused by write-error is low for a small anisotropy constant. © 2024 by the Magnetics Society of Japan.

关键词： Stochastic systems

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：