检索结果-内蒙古大学图书馆

IEEE International Workshop on Imaging Systems and Techniques (IST)

作者： Aline A.S. Thomaz Jonathan A.S. Lima Cristiano J. Miosso Mylé ne C.Q. Farias Andrey S. Krylov Yong Ding Department of Electrical Engineering University of Brasilia (UnB) Brasilia Brazil Biomedical Engineering Graduate Program University of Brasilia (UnB) Brasilia Brazil Faculty of Computational Mathematics and Cybernetics Lomonosov Moscow State University Moscow Russia College of Information Science and Electronic Engineering Zhejiang University Zhejiang China

Magnetic Resonance Imaging (MRI) plays a major role in the diagnosis of several diseases. However, the acquisition of measurements in the k-space domain, which is the basis for image reconstruction, takes a long time compared to other imaging modalities and is comparatively costly. In this context, undersampled MRI reconstruction is an approach for decreasing the acquisition duration and the exam's final cost. With this objective, both Compressed Sensing (CS) and Deep Learning (DL) provide techniques for generating good quality MRI images from undersampled measurements. In this paper, we combine CS and DL methods in order to investigate the potential increase in image quality over each isolated approach. We use reconstructions from from highly undersampled MRI signals using two CS approaches, the L1 and total minimizations, as inputs to a U-Net. We also use, for comparison, the reconstructions from the same undersampled signals using L2 minimization, and also test them as inputs to a U-net. The goal is to evaluate whether the the U-Net can improve the results of the CS reconstructions after learning from degraded and original image pairs. Our experimental results suggest that the combination of L1 or TV minimization with U-Nets can improve reconstruction, in terms of objective image quality, over each technique used in isolation.

关键词： Image quality TV Magnetic resonance imaging Magnetic resonance Minimization Time measurement Sensors

来源：评论

学校读者我要写书评

暂无评论

MLRegTest: A Benchmark for the Machine Learning of Regular Languages

arXiv

引用

arXiv 2023年

作者： van der Poel, Sam Lambert, Dakotah Kostyszyn, Kalina Gao, Tiantian Verma, Rahul Andersen, Derek Chau, Joanne Peterson, Emily Clair, Cody St. Fodor, Paul Shibata, Chihiro Heinz, Jeffrey School of Mathematics Georgia Institute of Technology United States Department of Computer Science Haverford College United States Department of Linguistics Institute of Advanced Computational Science Stony Brook University United States Department of Computer Science Stony Brook University United States Department of Linguistics Stony Brook University United States Department of Advanced Sciences Graduate School of Science and Engineering Hosei University Japan

Synthetic datasets constructed from formal languages allow fine-grained examination of the learning and generalization capabilities of machine learning systems for sequence classification. This article presents a new benchmark for machine learning systems on sequence classification called MLRegTest, which contains training, development, and test sets from 1,800 regular languages. Different kinds of formal languages represent different kinds of long-distance dependencies, and correctly identifying long-distance dependencies in sequences is a known challenge for ML systems to generalize successfully. MLRegTest organizes its languages according to their logical complexity (monadic second order, first order, propositional, or restricted propositional) and the kind of logical literals (string, tier-string, subsequence, or combinations thereof). The logical complexity and choice of literal provides a systematic way to understand different kinds of long-distance dependencies in regular languages, and therefore to understand the capacities of different ML systems to learn such long-distance dependencies. Finally, the performance of different neural networks (simple RNN, LSTM, GRU, transformer) on MLRegTest is examined. The main conclusion is that performance depends significantly on the kind of test set, the class of language, and the neural network architecture. © 2023, CC BY.

关键词： Formal languages

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Model for Classifying Public Opinions on Energy Sector IHSG Stocks on the Twitter Social Media Platform

Deep Learning Model for Classifying Public Opinions on Energ...

引用

Artificial Intelligence Robotics, Signal and Image Processing (AIRoSIP), International Conference on

作者： Bambang Sulistio Yaya Heryadi Lukas Wayan Suparta Ilvico Sonata Computer Science Department Binus Graduate Program – Doctor of Computer Science Bina Nusantara University Jakarta Indonesia Cognitive Engineering Research Group Universitas Katolik Indonesia Atma Jaya Jakarta Indonesia Department of Electrical Engineering Faculty of Industrial Technology Institut Teknologi Nasional Yogyakarta Yogyakarta Indonesia

ISBN: (数字)9798350327472

ISBN: (纸本)9798350327489

Capital market transactions provide an opportunity for investors to acquire ownership of company shares and capital gains, as well as dividends. However, alongside the benefits, there are risks of capital loss and liquidation, leading to stress and depression due to profit targets and decision-making errors. To mitigate the risk of decision-making errors in investment, data analysis is needed, including sentiment analysis, which influences stock prices. This study aims to develop a new deep learning model to classify Indonesian public opinion on JCI stocks, especially the Energy sector, obtained from the Twitter social media platform. The model will perform sentiment analysis and categorize opinions as negative, neutral, or positive. We created a dataset that was trained using Bidirectional Encoder Representations from Transformers (BERT) to summarize the analysis of public sentiment above so that it can assist investors in studying public sentiment as a reference for investing with a yield precision of 76%, Recall of 77%, and F1-score on 76%.

关键词： Deep learning Sentiment analysis Analytical models Social networking (online) Blogs Decision making Text categorization Bidirectional control Transformers Encoding

来源：评论

学校读者我要写书评

暂无评论

Strong Field Optical Hall Effect in 2D Weyl Semimetal

arXiv

引用

arXiv 2024年

作者： Farooq, M. Umar Hashmi, Arqum Tani, Mizuki Yabana, Kazuhiro Ishikawa, Kenichi L. Huang, Li Otobe, Tomohito Department of Physics Southern University of Science and Technology Guangdong Shenzhen China Department of Nuclear Engineering and Management Graduate School of Engineering The University of Tokyo 7-3-1 Hongo Bunkyo-ku Tokyo113-8656 Japan Kyoto619-0215 Japan Center for Computational Sciences University of Tsukuba Tsukuba305-8577 Japan Shenzhen518045 China

The study of interplay between the geometric nature of Bloch electrons and transverse responses under strong field offers new opportunities for optoelectronic applications. Here, we present a comprehensive study of the strong-field response of Weyl Dirac nodes in bilayer T'-WTe2 using time-dependent first-principles formalism. The electron dynamics is explored focusing on the mid-infrared frequency, ranging from the perturbative to nonperturbative regime. In the nonperturbative regime, the high-harmonic generation (HHG) spectra under a strong field clearly exhibit a plateau and energy cutoffs for both longitudinal and anomalous Hall (transverse) currents, with the latter being due to the large interband Berry curvature of the Weyl-Dirac semimetal. For the longitudinal harmonics, the intraband contributions increase with intensity, resulting in a complex interplay between interband polarization and intraband motions. Remarkably, if we take a comprehensive all-band perspective enabled by time-dependent density functional calculations, the anomalous Hall responses are purely attributed to the interband processes, even in the nonperturbative regime, thus Hall HHG can be crucial to understand the carrier dynamics. Our findings suggest that HHG associated with the ultrafast strong-field driven electron dynamics holds immense potential for exploring the nonlinear high Hall responses in Weyl semimetal. Copyright © 2024, The Authors. All rights reserved.

关键词： Dynamics

来源：评论

学校读者我要写书评

暂无评论

Sex-based Disparities in Brain Aging: A Focus on Parkinson's Disease

arXiv

引用

arXiv 2023年

作者： Beheshti, Iman Booth, Samuel Ko, Ji Hyun Department of Human Anatomy and Cell Science University of Manitoba WinnipegMB Canada Kleysen Institute for Advanced Medicine Health Science Centre WinnipegMB Canada Graduate Program in Biomedical Engineering University of Manitoba WinnipegMB Canada

INTRODUCTION: Parkinson’s disease (PD) is linked to faster brain aging. Sex is recognized as an important factor in PD, such that males are twice as likely as females to have the disease and have more severe symptoms and a faster progression rate. Despite previous research, there remains a significant gap in understanding the function of sex in the process of brain aging in PD patients. METHODS: The T1-weighted MRI-driven brain-predicted age difference (i.e., brain-PAD: the actual age subtracted from the brain-predicted age) was computed in a group of 373 PD patients (mean age ± SD: 61.37 ± 9.81, age range: 33–85, 34% female) from the Parkinson’s Progression Marker Initiative database using a robust brain-age estimation framework that was trained on 949 healthy subjects. Linear regression models were used to investigate the association between brain-PAD and clinical variables in PD, stratified by sex. All female PD patients were used in the correlational analysis while the same number of males were selected based on propensity score matching method considering age, education level, age of symptom onset, and clinical symptom severity. RESULTS: Despite both patient groups being matched for demographics, motor and non-motor symptoms, it was observed that males with Parkinson's disease (PD-M) exhibited a significantly higher mean brain age-delta than their female counterparts (PD-F) (t(256)= 2.50, p = 0.012). In the propensity score-matched PD-M group (PD-M*), brain-PAD was found to be associated with a decline in general cognition, a worse degree of sleep behavior disorder, reduced visuospatial acuity, and caudate atrophy. Conversely, no significant links were observed between these factors and brain-PAD in the PD-F group. DISCUSSION: Having 'older' looking brains in PD-M than PD-F supports the idea that sex plays a vital function in PD, such that the PD mechanism may be different in males and females. This study has the potential to broaden our understanding of dissim

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Efficient Power Transfer via Induced Virtual Critical Coupling in an Overcoupled Silicon Nitride Microresonator

Efficient Power Transfer via Induced Virtual Critical Coupli...

引用

2023 Conference on Lasers and Electro-Optics, CLEO 2023

作者： Hinney, Jakob Kim, Seunghwi Flatt, Graydon J.K. Datta, Ipshita Alii, Andrea Lipson, Michal Department of Electrical Engineering Columbia University New YorkNY10027 United States Photonics Advanced Science Research Catm City University of New Yor New YorkNY10031 United States Department of Applied Physics and Applied Mathematics Columbia University New YorkNY10027 United States Physics Program Graduate Center City University of New York New YorkNY10016 United States

We induce virtual critical coupling in an overcoupled photonic microresonator using complex-frequency pulses. We observe efficient cavity storage as an incident pulse of time constant 138 ps suppresses the resonant tr... 详细信息

ISBN: (纸本)9781957171258

关键词： Microresonators

来源：评论

学校读者我要写书评

暂无评论

Towards Zero Static Friction at the Microscale

引用

Physical Review Letters 2024年第23期133卷

作者： Li, Tengfei Peng, Deli Wang, Yelingyi Li, Guangliang Yang, Dinglin Tian, Kaiwen Ouyang, Wengen Urbakh, Michael Zheng, Quanshui Center for Nano and Micro Mechanics Tsinghua University Beijing China Department of Engineering Mechanics Tsinghua University Beijing China Institute of Superlubricity Technology Research Institute Tsinghua University in Shenzhen Shenzhen China Department of Engineering Mechanics School of Civil Engineering Wuhan University Wuhan China School of Chemistry The Sackler Center for Computational Molecular and Materials Science Tel Aviv University Tel Aviv Israel Center of Double Helix Tsinghua Shenzhen International Graduate School Shenzhen China

Static friction, a ubiquitous physical phenomenon, plays a significant role in natural processes and industrial applications. Its influence is particularly notable in the field of controlled micromanipulation and precision manufacturing, where static friction often exceeds kinetic friction and leads to material damage and unpredictable behaviors. In this study, we report the first experimental observation of the elimination of static friction peak in sliding micrometer contacts of layered materials, achieved through a technique involving selective etching of the amorphous edges of single crystalline surfaces. Our findings are consistent with theoretical models and simulations that predicted the absence of static friction between two atomically flat, pristine, weakly interacting, incommensurate solid surfaces. In this state, thermally induced spontaneous actuation in graphite homogeneous junctions was observed at temperatures slightly above room temperature (around 40 °C), with contact sizes up to 100 μm2. These results have significant implications for improving our understanding and control of static friction, opening up promising opportunities for the application of micromechanical devices and precision mechanical systems. © 2024 American Physical Society.

关键词： Micromanipulators

来源：评论

学校读者我要写书评

暂无评论

Lightweight Pedestrian Detection through Guided Filtering and Deep Learning 10

Lightweight Pedestrian Detection through Guided Filtering an...

引用

10th IEEE Global Conference on Consumer Electronics, GCCE 2021

作者： Muchtar, Kahlil Saddami, Khairun Bintang, Akhyar Cenggoro, Tjeng Wawan Pardamean, Bens Lin, Chih-Yang Ernita, Tia Universitas Syiah Kuala Department of Electrical And Computer Engineering Aceh Indonesia Universitas Syiah Kuala Department of Electrical And Computer Engineering Aceh Indonesia Bina Nusantara University School of Computer Science Bina Nusantara University Bioinformatics And Data Science Research Center Computer Science Department Jakarta Indonesia Bina Nusantara University BINUS Graduate Program-Master of Computer Science Program Bina Nusantara University Bioinformatics And Data Science Research Center Computer Science Department Jakarta Indonesia Yuan-Ze University Department of Electrical And Engineering Taoyuan Taiwan

ISBN: (纸本)9781665436762

In this paper, we propose a novel approach to locate and detect moving pedestrians in a video. Our proposed method first locates the region of interest (ROI) using a background subtraction algorithm based on guided filtering. This novel background subtraction algorithm allows our method to also filter unexpected noises at the same time, which could benefit the performance of our proposed method. Subsequently, the pedestrians are detected using YOLOv3 within the provided ROI. Our experiments showed that the proposed method has a competitive performance in the CDNET2014 dataset with a fast-processing time. © 2021 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Embedded, micro-interdigitated flow fields in high areal-loading intercalation electrodes towards seawater desalination and beyond

arXiv

引用

arXiv 2023年

作者： Do, Vu Q. Reale, Erik R. Loud, Irwin Rozzi, Paul G. Tan, Haosen Willis, David A. Smith, Kyle C. Department of Mechanical Science and Engineering University of Illinois at Urbana-Champaign UrbanaIL United States Department of Mechanical Engineering Southern Methodist University DallasTX75275 United States Department of Materials Science and Engineering University of Illinois at Urbana-Champaign UrbanaIL United States Computational Science and Engineering Program University of Illinois at Urbana-Champaign UrbanaIL United States Beckman Institute for Advanced Science and Technology University of Illinois at Urbana-Champaign UrbanaIL United States

Faradaic deionization (FDI) is a promising technology for energy-efficient water desalination using porous electrodes containing redox-active materials. Herein, we demonstrate for the first time the capability of a symmetric FDI flow cell to produce freshwater (100X lower permeability compared to common redox-flow battery electrodes, for which millimetric flow-channel widths were used exclusively in the past. Total desalination thermodynamic energy efficiency (TEE) was improved by more than ten-fold relative to unpatterned electrodes: 40.0% TEE for brackish water, 11.7% TEE for hypersaline brine, and 7.4% TEE for seawater-salinity feeds. Water transport between diluate and brine streams and charge efficiency losses resulting from (electro)chemical effects are implicated as limiting energy efficiency and water recovery, motivating their investigation for enhancing future FDI performance. Copyright © 2023, The Authors. All rights reserved.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Spin-orbit-locked hyperbolic polariton vortices carrying reconfigurable topological charges

引用

eLight 2022年第1期2卷 143-153页

作者： Mingsong Wang Guangwei Hu Saroj Chand Michele Cotrufo Yohannes Abate Kenji Watanabe Takashi Taniguchi Gabriele Grosso Cheng‑Wei Qiu Andrea Alù Photonics Initiative Advanced Science Research CenterCity University of New YorkNew York CityNY 10031USA Department of Electrical and Computer Engineering National University of SingaporeSingapore 116083Singapore Department of Physics and Astronomy The University of GeorgiaAthensGA 30602USA Research Center for Functional Materials National Institute for Materials ScienceTsukubaIbaraki 305‑0044Japan International Center for Materials Nanoarchitectonics National Institute for Materials ScienceTsukubaIbaraki 305‑0044Japan Physics Program Graduate CenterCity University of New YorkNew YorkNY 10016USA

The topological features of optical vortices have been opening opportunities for free-space and on-chip photonic technologies,e.g.,for multiplexed optical communications and robust information *** a parallel but disjoint effort,polar anisotropic van der Waals nanomaterials supporting hyperbolic phonon polaritons(HP2s)have been leveraged to drastically boost light-matter *** far HP2 studies have been mainly focusing on the control of their amplitude and scale *** we report the generation and observation of mid-infrared hyperbolic polariton vortices(HP2Vs)associated with reconfigurable topological ***-shaped gold disks coated with a flake of hexagonal boron nitride are exploited to tailor spin-orbit interactions and realise deeply subwavelength *** complex interplay between excitation spin,spiral geometry and HP2 dispersion enables robust reconfigurability of the associated topological *** results reveal unique opportunities to extend the application of HP2s into topological photonics,quantum information processing by integrating these phenomena with single-photon emitters,robust on-chip optical applications,sensing and nanoparticle manipulation.

关键词： Hyperbolic polariton vortex Light-matter interactions Spin-orbit interaction Topological charge Reconfigurability

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：