检索结果-内蒙古大学图书馆

Acoustics, Speech, and Signal Processing Workshops (ICASSPW), IEEE International Conference on

作者： Yuan Fang Hao Li Xueliang Zhang Fei Chen Guanglai Gao College of Computer Science Inner Mongolia University China Department of Electrical and Electronic Engineering Southern University of Science and Technology Shenzhen China Key Laboratory of Urban Land Resources Monitoring and Simulation Ministry of Natural Resources China

ISBN: (数字)9798350374513

ISBN: (纸本)9798350374520

This paper provides an overview of our submission to Task 2 of the Auditory EEG Challenge at ICASSP 2024 Signal Processing Grand Challenge (SPGC). We introduce a novel approach, employing a cross-attention-guided WaveNet with a coarse-to-fine generation strategy, aimed at enhancing the detailed reconstruction of Mel spectrograms from time-domain EEG. Specifically, the model utilizes WaveNet to sequentially reconstruct the envelope, 10-band Mel, 80-band Mel, and magnitude from coarse to fine granular levels. To bridge the gap between different modalities, we introduce a cross-attention mechanism, exploring correlations across modalities. A combined loss function is employed to refine the reconstruction performance. Notably, we achieved Pearson correlation values of 0.0651 ± 0.0153 for the validation set and 0.0413 ± 0.0169 for the heldout-subjects test set, securing the second position in the competition. We release the training code for our model online 1 .

关键词： Training Analytical models Correlation Brain modeling Electroencephalography Decoding Time-domain analysis

来源：评论

学校读者我要写书评

暂无评论

Unlocking the Secrets Behind Advanced Artificial Intelligence Language Models in Deidentifying Chinese-English Mixed Clinical Text: Development and Validation Study

引用

Journal of Medical Internet Research 2024年第1期26卷 e48443页

作者： Lee, You-Qian Chen, Ching-Tai Chen, Chien-Chang Lee, Chung-Hong Chen, Peitsz Wu, Chi-Shin Dai, Hong-Jie Dialogue System Technical Department Asustek Computer Inc Taipei Taiwan Intelligent System Laboratory Department of Electrical Engineering College of Electrical Engineering and Computer Science National Kaohsiung University of Science and Technology Kaohsiung Taiwan Department of Bioinformatics and Medical Engineering Asia University Taichung Taiwan Center for Precision Health Research Asia University Taichung Taiwan Electromagnetic Sensing Control and AI Computing System Laboratory Department of Electrical Engineering College of Electrical Engineering and Computer Science National Kaohsiung University of Science and Technology Kaohsiung Taiwan Knowledge Discovery and Data Mining Lab Department of Electrical Engineering College of Electrical Engineering and Computer Science National Kaohsiung University of Science and Technology Kaohsiung Taiwan Department of Chemical Engineering Feng Chia University Taichung Taiwan National Center for Geriatrics and Welfare Research National Health Research Institutes Zhunan Taiwan National Institute of Cancer Research National Health Research Institutes Tainan Taiwan School of Post-Baccalaureate Medicine College of Medicine Kaohsiung Medical University Kaohsiung Taiwan Center for Big Data Research Kaohsiung Medical University Kaohsiung Taiwan

Background: The widespread use of electronic health records in the clinical and biomedical fields makes the removal of protected health information (PHI) essential to maintain privacy. However, a significant portion of information is recorded in unstructured textual forms, posing a challenge for deidentification. In multilingual countries, medical records could be written in a mixture of more than one language, referred to as code mixing. Most current clinical natural language processing techniques are designed for monolingual text, and there is a need to address the deidentification of code-mixed text. Objective: The aim of this study was to investigate the effectiveness and underlying mechanism of fine-tuned pretrained language models (PLMs) in identifying PHI in the code-mixed context. Additionally, we aimed to evaluate the potential of prompting large language models (LLMs) for recognizing PHI in a zero-shot manner. Methods: We compiled the first clinical code-mixed deidentification data set consisting of text written in Chinese and English. We explored the effectiveness of fine-tuned PLMs for recognizing PHI in code-mixed content, with a focus on whether PLMs exploit naming regularity and mention coverage to achieve superior performance, by probing the developed models’ outputs to examine their decision-making process. Furthermore, we investigated the potential of prompt-based in-context learning of LLMs for recognizing PHI in code-mixed text. Results: The developed methods were evaluated on a code-mixed deidentification corpus of 1700 discharge summaries. We observed that different PHI types had preferences in their occurrences within the different types of language-mixed sentences, and PLMs could effectively recognize PHI by exploiting the learned name regularity. However, the models may exhibit suboptimal results when regularity is weak or mentions contain unknown words that the representations cannot generate well. We also found that the availability of cod

关键词： ChatGPT code mixing deidentification electronic health record large language model pretrained language model

来源：评论

学校读者我要写书评

暂无评论

Statistical Distance Based Deterministic Offspring Selection in SMC Methods

arXiv

引用

arXiv 2022年

作者： Kviman, Oskar Koptagel, Hazal Melin, Harald Lagergren, Jens Department of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm Sweden Science for Life Laboratory Stockholm Sweden

Over the years, sequential Monte Carlo (SMC) and, equivalently, particle filter (PF) theory has gained substantial attention from researchers. However, the performance of the resampling methodology, also known as offspring selection, has not advanced recently. We propose two deterministic offspring selection methods, which strive to minimize the Kullback-Leibler (KL) divergence and the total variation (TV) distance, respectively, between the particle distribution prior and subsequent to the offspring selection. By reducing the statistical distance between the selected offspring and the joint distribution, we obtain a heuristic search procedure that performs superior to a maximum likelihood search in precisely those contexts where the latter performs better than an SMC. For SMC and particle Markov chain Monte Carlo (pMCMC), our proposed offspring selection methods always outperform or compare favorably with the two state-of-the-art resampling schemes on two models commonly used as benchmarks from the literature. © 2022, CC BY-NC-ND.

关键词： Maximum likelihood

来源：评论

学校读者我要写书评

暂无评论

Spin-Torque-Driven Non-uniform Dynamics of an Antivortex Core in Truncated Astroid Shaped Nanomagnets

arXiv

引用

arXiv 2025年

作者： Aykin, Ahmet Koral Piskin, Hasan Kocaman, Bayram Yanik, Cenk Karakas, Vedat Arpaci, Sevdenur Ozbay, Aisha Gokce Carpentieri, Mario Finocchio, Giovanni Celegato, Federica Tiberto, Paola Lendinez, Sergi Novosad, Valentine Hoffmann, Axel Ozatay, Ozhan Boğaziçi University Physics Department Istanbul Turkey Boğaziçi University Mechanical Engineering Department Istanbul Turkey Department of Fundamental Sciences Faculty of Engineering Alanya Alaaddin Keykubat University Antalya07450 Turkey Siirt University Department of Electrical and Electronics Engineering Siirt Turkey Northwestern University Department of Electrical and Computer Engineering EvanstonIL United States TUBITAK National Metrology Institute UME Kocaeli Turkey Politecnico di Bari Department of Electrical & Information Engineering Bari Italy University of Messina Department of Mathematical and Computer Sciences Physical Sciences and Earth Sciences Messina Italy Torino Italy Argonne National Laboratory Materials Science Division LemontIL United States University of Illinois Urbana-Champaign Department of Materials Science and Engineering Materials Research Laboratory UrbanaIL United States SUNUM Sabanci University Nanotechnology Research and Application Center Istanbul34956 Turkey

Spin textures that are not readily available in the domain structures of continuous magnetic thin films can be stabilized when patterned to micro/nano scales due to the dominant effect of dipolar magnetic interactions. Fabrication of such devices enables a thorough study of their RF dynamics excited by highly concentrated spin-polarized/pure-spin currents. For this purpose, in this study, we have employed a truncated astroid geometry to achieve stable magnetic antivortex core nucleation/annihilation which was detectable using the anisotropic magnetoresistance (AMR) at various temperatures. Furthermore, by depositing a soft magnetic thin film (20 nm thick permalloy) capped with a heavy-metal 2nm Pt layer, we were able to probe the spin orbit torque induced excitations accompanied by self-torque due to half-antivortex cores reminiscent of an isolated-antivortex, yielding GHz frequency oscillations with high quality factors (~50000). The observed RF oscillations can be attributed to a nonuniform domain wall oscillation mode close to the stable-antivortex core nucleation site as seen in micromagnetic simulations. This fundamental study of antivortex core response to spin currents is crucial for the assessment of their potential applications in high frequency spintronic devices such as reservoir computers. © 2025, CC BY-NC-ND.

关键词： Magnetic thin films

来源：评论

学校读者我要写书评

暂无评论

Improving GNSS positioning correction using Deep Reinforcement Learning with Adaptive Reward Augmentation Method 36

Improving GNSS positioning correction using Deep Reinforceme...

引用

36th International Technical Meeting of the Satellite Division of the Institute of Navigation, ION GNSS+ 2023

作者： Tang, Jianhao Li, Zhenni Guo, Rui Zhao, Haoli Wang, Qianming Liu, Ming Xie, Shengli Polycarpou, Marios School of Automation Guangdong University of Technology Guangzhou510006 China Guangdong-HongKong-Macao Joint Laboratory for Smart Discrete Manufacturing Guangzhou510006 China Techtotop Microelectronics Technology Co. Ltd. Guangzhou510006 China Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Hong Kong Key Laboratory of Intelligent Detection and The Internet of Things in Manufacturing Guangzhou510006 China Guangdong Key Laboratory of IoT Information Technology Guangzhou510006 China KIOS Research and Innovation Center of Excellence University of Cyprus Nicosia Cyprus

ISBN: (纸本)9780936406350

High-precision global navigation satellite system (GNSS) positioning for automatic driving in urban environments is an unsolved problem because of the influence of multipath effects. Recently, methods based on data-driven deep reinforcement learning (DRL) have been used to learn continual positioning-correction strategies without strict assumptions about model parameters, and are adaptable to nonstationary urban environments. However, these methods face two remaining challenges: 1) real-time data for training collected in nonstationary urban environments is inadequate because of issues such as response delay and signal interruption, which causes the performance degradation in DRL, 2) the existing methods use vehicle positions as the environment observations, ignoring the complex errors caused by multipath effects in urban environments. In this paper, we propose a novel DRL-based positioning-correction method with an adaptive reward augmentation method (ARAM), and use GNSS measurements instead of vehicle positions as the environment observations, for improving the GNSS positioning accuracy in nonstationary urban environments. To specify the accurate current state of the vehicle agent, we use the GNSS measurement observations, including the line-of-sight (LOS) vector and the pseudorange residual, to model complex environmental errors, and employ a long and short term memory (LSTM) module to learn the temporal aspects of the observations, which include the interference by multipath effects on the GNSS positioning in urban environments. To address the performance degradation caused by inadequate real-time training data, we employ ARAM to adaptively modify the matching of data between the source domain and target domain of the nonstationary urban environments, to leverage sufficient data from the source domain for training, and thus to improve the performance of DRL. Hence, based on ARAM and using the GNSS measurement observations, we construct an LSTM-based proximal pol

关键词：

来源：评论

学校读者我要写书评

暂无评论

Future Heat and Electricity Generation from Bertoni Plant in Morocco

Future Heat and Electricity Generation from Bertoni Plant in...

引用

Renewable Energy and Hydrogen Technologies (GlobConHT), IEEE IAS Global Conference on

作者： Meisam Mahdavi Francisco Jurado Konrad Schmitt Ricardo Alan Verdú Ramos Department of Electrical Engineering University of Jaén Linares Jaén Spain Electrical and Computer Engineering Department Texas Tech University Lubbock TX USA Associated Laboratory of Ilha Solteira Bioenergy Research Institute (IPBEN) São Paulo State University Ilha Solteira SP Brazil

Morocco's energy sector heavily depends on fossil fuel imports to meet a large portion of the country's primary energy demand. However, costly energy imports along with the growing national energy need, pushed Morocco to look for alternative energy resources. One of these alternatives is Stevia rebaudiana (Bertoni), a native plant in Paraguay. This plant is now an important agricultural crop for the production of a high-potency natural sweetener in Canada, the USA, Switzerland, Germany, and France. Nevertheless, it is not produced in Morocco, but research conducted on the crop yield of this agricultural plant shows its great potential for cultivation in Morocco. The dry leaf yield of Bertoni depends on its variety and cultivated region. Stevia has great potential to be a commercial crop for biological sweeteners and energy production. Therefore, in the present paper, the potential of heat and electric energy generated by Bertoni's dry leaf in various regions of Morocco with different weather conditions are studied. The results show that Bertoni's dry leaves are good biomass resources for energy generation in the Moroccan regions of Berkane, Larache, Marrakech, Rabat, and Sefrou.

关键词： Electric potential Plants (biology) Crops Production Biomass Thermal pollution Sugar

来源：评论

学校读者我要写书评

暂无评论

Hydrothermally Synthesis of Binary Niznfe2o4-Cnt Nanocomposite for Energy Storage Application

SSRN

引用

SSRN 2023年

作者： Ghadimi, Laleh Saleh Tabrizi, Amin Goljanian Rezaie, Ehsan Parvini, Elahe Tavakoli, Mahmoud Abouzari-Lotf, Ebrahim Hajalilou, Abdollah Arsalani, Nasser Pahlevani, Majid Department of Electrical and Computer Engineering Queen's University KingstonON Canada Research Laboratory of Polymer Department of Organic and Biochemistry Faculty of Chemistry University of Tabriz Iran Laboratory for Advanced Materials Faculty of Natural Sciences Comenius University Bratislava842 15 Slovakia Soft and Printed Microelectronics Laboratory Institute of Systems and Robotics University of Coimbra Coimbra Portugal Electrochemical Energy Storage Helmholtzstraße 11 UlmD-89081 Germany

Our research aimed to enhance carbon-based electrochemical double-layer capacitors (EDLCs) by incorporating faradic redox processes. We synthesized a Ni0.5Zn0.5Fe2O4-Carbon Nanotube (NZF-CNT) nanocomposite via hydrothermal methods at various pH levels. X-ray diffraction (XRD) analysis at pH 12 confirmed the formation of spinel nickel-zinc ferrite with 15 nm particles. X-ray photoelectron spectroscopy (XPS) verified cation distribution changes, and high-resolution transmission electron microscopy (HRTEM) revealed well-arranged NZF crystals around CNTs. The successful fusion of NZF and CNTs into the nanocomposite framework was demonstrated. NZF-CNT exhibited a remarkable specific capacitance of approximately 368 F/g at 1.25 A/g, surpassing pure ferrite's 110 F/g. Even after 5000 charge/discharge cycles at 1 A/g, it retained 88.5% of its initial capacitance. Our findings showcase the potential of NZF-CNT as a promising material for energy storage devices, offering a unique combination of EDLC and pseudo-capacitive properties. This approach opens new avenues for improving supercapacitor performance and their diverse applications. © 2023, The Authors. All rights reserved.

关键词： Supercapacitor

来源：评论

学校读者我要写书评

暂无评论

Variable Speed Drive Connected Motor Load Emulator for a Multi-Converter-Based Hardware Testbed System

IEEE Open Journal of Industry Applications

引用

IEEE Open Journal of Industry Applications 2021年 2卷 337-346页

作者： Wang, Shuyao Ma, Yiwei Wang, Jingxin Tolbert, Leon M. Wang, Fred Department of Electrical Engineering and Computer Science University of Tennessee KnoxvilleTN37996 United States KnoxvilleTN37932 United States Power Electronics and Electric Machinery Research Center Oak Ridge National Laboratory KnoxvilleTN37932 United States

A variable speed drive (VSD) based induction motor power emulator is presented in this paper, which is intended to be used in a real-time multi-converter-based hardware testbed (HTB) system. The presented HTB load emulator can accurately reflect the dynamic performance of a VSD-based load with multiple control algorithms without requiring significant computational resources and simulation time. Therefore, the developed VSD load emulator can not only mimic VSD-driven motor load performance, but also can be flexibly integrated into electric power grid emulators or simulators, which enable more detailed power grid analyses by providing a more accurate model for this particular type of load. This paper discusses the specification of the developed VSD-based load emulator, including multiple control schemes, and the physical realization in a power grid emulator. Finally, the accuracy of the VSD load emulator is demonstrated with experimental results. © 2020 IEEE.

关键词： Variable speed drives

来源：评论

学校读者我要写书评

暂无评论

Welcome to 2023 9th International Conference on Signal Processing and Communication (ICSC)

2023 9th International Conference on Signal Processing and C...

引用

2023 9th International Conference on Signal Processing and Communication, ICSC 2023 2023年 vi-vii页

作者： Whittow, William G. Kurinec, Santosh K. Sharma, Satish K. Lall, Brejesh Pachori, Ram Bilas Deb, Sujay Karandikar, Abhay Sachan, Amit Wolfson School of Mechanical Electrical and Manufacturing Engineering Loughborough University LEICS LE11 3TU United Kingdom IEEE Electrical & Microelectronics Engineering Rochester Institute of Technology New York United States Department of Electrical and Computer Engineering San Diego State University United States Bharti School of Telecom Technology & Management India Department of Electrical Engineering Indian Institute of Technology Delhi India Department of Electronics and Communication Engineering Indraprastha Institute of Information Technology Delhi India The Department of Science & Technology Indian Institute of Technology Kanpur India Media Intelligence Jio India

来源：评论

学校读者我要写书评

暂无评论

Map2Schedule: An End-to-End Link Scheduling Method for Urban V2V Communications

arXiv

引用

arXiv 2023年

作者： Zhang, Lihao Sun, Haijian Sun, Jin Parasuraman, Ramviyas Ye, Yinghui Hu, Rose Qingyang The School of Electrical and Computer Engineering University of Georgia AthensGA United States The School of Computing University of Georgia AthensGA United States Shanxi Key Laboratory of Information Communication Network and Security Xi’an University of Posts & Telecommunications China The Electrical and Computer Engineering Department Utah State University LoganUT United States

Urban vehicle-to-vehicle (V2V) link scheduling with shared spectrum is a challenging problem. Its main goal is to find the scheduling policy that can maximize system performance (usually the sum capacity of each link or their energy efficiency). Given that each link can experience interference from all other active links, the scheduling becomes a combinatorial integer programming problem and generally does not scale well with the number of V2V pairs. Moreover, link scheduling requires accurate channel state information (CSI), which is very difficult to estimate with good accuracy under high vehicle mobility. In this paper, we propose an end-to-end urban V2V link scheduling method called Map2Schedule, which can directly generate V2V scheduling policy from the city map and vehicle locations. Map2Schedule delivers comparable performance to the physical-model-based methods in urban settings while maintaining low computation complexity. This enhanced performance is achieved by machine learning (ML) technologies. Specifically, we first deploy the convolutional neural network (CNN) model to estimate the CSI from street layout and vehicle locations and then apply the graph embedding model for optimal scheduling policy. The results show that the proposed method can achieve high accuracy with much lower overhead and latency. © 2023, CC BY.

关键词： Channel state information

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：