检索结果-内蒙古大学图书馆

Efficient Atrophy Mapping: A Single-Step U-Net Approach for Rapid Brain Change Estimation 3

Efficient Atrophy Mapping: A Single-Step U-Net Approach for ...

3rd IEEE International Conference on Metrology for eXtended Reality, Artificial Intelligence and Neural engineering, MetroXRAINE 2024

作者： Raciti, Riccardo Rondinella, Alessia Puglisi, Lemuel Guarnera, Francesco Ravì, Daniele Battiato, Sebastiano University of Catania Dept. of Math and Computer Science Catania Italy School of Physics Engineering and Cs University of Hertfordshire Hatfield United Kingdom

ISBN: (纸本)9798350378009

The estimation of brain atrophy is crucial for eval-uating brain diseases and analyzing neurodegeneration. Existing methods for computing atrophy maps often suffer from lengthy processing times due to the computational cost of multi-step processing. In this work, we propose a novel technique for atrophy map calculation using a single U-net-based architecture. This approach consolidates multiple traditional medical imaging processing steps into a single process, aiming to accelerate the computational time required. Specifically, our method estimates structural changes by generating a flow map from two longitudinal Magnetic Resonance Imaging (MRI) scans of the same subject. We trained and evaluated our system on a dataset comprising 2000 Tl-weighted MRI scans sourced from two different public datasets on Alzheimer's Disease. Experimental results demonstrate a considerable reduction in execution time while maintaining atrophy mapping performance comparable to state-of-the-art solutions. We believe that our pipeline could significantly benefit clinical applications for measuring brain atrophy, especially in scenarios requiring the evaluation of large cohorts, such as clinical trials. Our code is freely available at https://***/Efficient Atrophy Mapping: A Single-Step U-net Approach for Rapid Brain Change Estimation. © 2024 IEEE.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Validation of IoT Networks in Precision Agriculture 2

Validation of IoT Networks in Precision Agriculture

引用

2nd International Conference on Artificial Intelligence and Machine Learning Applications, AIMLA 2024

作者： Seth, Jyoti Reddy, M. Sudhakara Pandey, Arvind Kumar Vivekananda Global University Department of Computer Science & Engineering Jaipur India School of Sciences Department of Physics & Electronics Karnataka Bangalore India ARKA JAIN University Department of Computer Science & IT Jharkhand Jamshedpur India

ISBN: (纸本)9798350349221

the idea of net of things (IoT) has received remarkable traction over the past decade and is utilized in various programs, such as precision agriculture, to enhance productiveness and efficiencies even as decreasing fees. The implementation of IoT systems in precision agriculture heavily is based at the accuracy of statistics gathered from the community nodes, thus the validation of IoT nets is of maximum significance. This article objectives to provide an overview of validation strategies for IoT networks deployed in precision agriculture and how they can be in addition optimized. The validation procedure begins with the selection of sampling protocols appropriate for accurate statistics series, sensor deployment and installation, and parameterization of sensing nodes. In the end, techniques inclusive of anomaly detection and authentication of recognized phenomena are used to weed out mistakes and maliciously inserted records. Additionally, validation strategies, which includes those the usage of okay-fold move-validation or bootstrapping, can be used to reduce variability between more than one samples. © 2024 IEEE.

关键词： Precision agriculture

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Applications for Online Partial Discharge Detection, Classification, and Localization in Power Transformers: A Review 4

Machine Learning Applications for Online Partial Discharge D...

引用

4th International Conference on Smart Grid and Renewable Energy, SGRE 2024

作者： Tag, Ameera Refaat, Shady S. Kameli, Sayed Mohammad Saleh, Mohammad Alshaikh Texas A&M University at Qatar Electrical and Computer Engineering Department Doha Qatar University of Hertfordshire School of Physics Engineering and Computer Science Department of Engineering United Kingdom Texas A&M University Department of Electrical and Computer Engineering College Station United States

ISBN: (纸本)9798350306262

The power transformer is a crucial asset and a fundamental component of the power grid. Assets undergo aging due to the stresses present in insulation materials. Partial discharges (PDs) are the most common fault source in power transformers and an excellent indicator of aging. The detection, classification, and localization of PD activities in power transformers are persisting challenges, while techniques utilizing machine learning (ML) are widely sought to deal with those challenges. Existing ML techniques show promising results with an elevated level of accuracy and precision. However, there is a lack of conventional ML-based real-time monitoring capability. Therefore, this paper presents a comprehensive review of the application of ML techniques for online PD activity detection, classification, and localization in power transformers, focusing on supervised, unsupervised, semi-supervised, and reinforcement learning techniques. In addition, this paper explores the challenges, future trends, perspectives, and outlook of machine learning for online transformer fault analysis. © 2024 IEEE.

关键词： Partial discharges

来源：评论

学校读者我要写书评

暂无评论

Design of artificial biomimetic channels with Na^(+)permeation rate and selectivity potentially outperforming the natural sodium channel

引用

Nano Research 2024年第9期17卷 8638-8646页

作者： Zhi Zhu Yan Zhao Chao Chang Shaojian Yan Tingyu Sun Shiyu Gu Yangmei Li Dengsong Zhang Chunlei Wang Xiao Cheng Zeng School of Optical-Electrical and Computer Engineering University of Shanghai for Science and TechnologyShanghai 200093China Innovation Laboratory of Terahertz Biophysics National Innovation Institute of Defense TechnologyBeijing 100071China School of Physics Peking UniversityBeijing 100871China International Joint Laboratory of Catalytic Chemistry College of SciencesShanghai UniversityShanghai 200444China Department of Materials Science and Engineering City University of Hong KongHong Kong 999077China

Artificial ion channels that enable high-efficiency ion transport have important implications in nanofluidics and biomedical applications such as drug ***,we show a simulation-based chemical design of a biomimetic sodium channel that possesses permeation rate and selectivity potentially higher than those of the state-of-the-art natural vertebrate voltage-gated sodium ***,our theoretical findings have undergone empirical testing,aligning well with the Arrhenius law as derived from a diverse range of experimental *** high-efficiency ion transport is achieved by anchoring the carboxylate functional groups within the channel filter.A key chemical guiding principle underlying the ion channel design is that the free-energy barrier for the Na^(+)passage across the channel should be comparable to typical thermal energy at room *** the implementation of the chemical design,we found that the relatively low free-energy barrier can be attributed to the compensation effect of the carboxylate groups to the partially lost oxygen shell of the ion within the ion channel,as well as to the consonant vibration of the ions inside and outside the *** mechanistic understanding brings new insight,at the molecular level,into the high-efficiency ion transport across the designed membrane *** proof of principle achieved from the simulations will stimulate future experimental confirmation and potential applications of the high-performance artificial channels in nanofluidics and in bioinspired iontronics.

关键词： sodium channels anchoring carboxylate functional groups molecular dynamics simulations low free-energy barrier for ion passage thermal kinetic energy

来源：评论

学校读者我要写书评

暂无评论

A Review on the Applications of Blockchain-Based Smart Contracts in the Smart Grid 4

A Review on the Applications of Blockchain-Based Smart Contr...

引用

4th International Conference on Smart Grid and Renewable Energy, SGRE 2024

作者： Saleh, Mohammad Alshaikh Khatri, Sunil P. Ghrayeb, Ali Refaat, Shady S. Texas A&M University Department of Electrical and Computer Engineering College Station United States Texas A&M University at Qatar Department of Electrical and Computer Engineering Doha Qatar University of Hertfordshire School of Physics Engineering and Computer Science United Kingdom

ISBN: (纸本)9798350306262

Investigations in industrial and computational research emphasize the progress of blockchain-enabled smart contracts due to their resilient features, which include decen-tralised transaction storage, autonomous contract regulation enforcement, and distributed trust creation. Blockchain-powered smart contracts can transform operational frameworks in various sectors aiming for superior service delivery. The advantages this technology brings involve a multitude of applications that span industries as cryptocurrencies, logistics systems, agricultural practices, real estate operations, and energy trading among others. Notably though one crucial emerging application is within smart grids (SG). The decentralization aspect of blockchain is one of the most significant leaps in computing for smart grids. The application of blockchain aligns with the vision of having a decentralized electric grid by distributing renewable energy sources. Therefore, numerous efforts are being conducted to examine the prospects for the relevance of smart contracts and blockchain to the smart grid system. To this end, this paper aims to review the essential elements of blockchain-based smart contracts to emphasize their current capabilities for enhancing the transition to a decentralized smart grid with proposals on future research directions. © 2024 IEEE.

关键词： Smart contract

来源：评论

学校读者我要写书评

暂无评论

Strong nonlinear optical processes with extraordinary polarization anisotropy in inversionsymmetry broken two-dimensional PdPSe

引用

Light(science & Applications) 2024年第8期13卷 1524-1533页

作者： Song Zhu Ruihuan Duan Xiaodong Xu Fangyuan Sun Wenduo Chen Fakun Wang Siyuan Li Ming Ye Xin Zhou Jinluo Cheng Yao Wu Houkun Liang Junichiro Kono Xingji Li Zheng Liu Qi Jie Wang School of Electrical and Electronic Engineering Nanyang Technological University639798 SingaporeSingapore School of Material Science and Engineering Nanyang Technological University639798 SingaporeSingapore CINTRA CNRS/NTU/THALES UMI 3288Research Techno PlazaNanyang Technological University637371 SingaporeSingapore School of Materials Science and Engineering Harbin Institute of Technology150001 HarbinChina Department of Chemistry National University of Singapore117543 SingaporeSingapore GPL Photonics Lab State Key Laboratory of Applied OpticsChangchun Institute of OpticsFine Mechanics and PhysicsChinese Academy of Sciences130033 ChangchunChina School of Electronics and Information Engineering Sichuan University610064 ChengduSichuanChina School of Physical and Mathematical Sciences Nanyang Technological University637371 SingaporeSingapore Departments of Electrical and Computer Engineering Physics and Astronomyand Materials Science and NanoEngineeringRice UniversityHoustonTXUSA

Nonlinear optical activities,especially second harmonic generation(SHG),are key phenomena in inversion-symmetrybroken two-dimensional(2D)transition metal dichalcogenides(TMDCs).On the other hand,anisotropic nonlinear optical processes are important for unique applications in nano-nonlinear photonic devices with polarization functions,having become one of focused research topics in the field of nonlinear ***,the strong nonlinearity and strong optical anisotropy do not exist simultaneously in common 2D ***,we demonstrate strong secondorder and third-order susceptibilities of 64 pm/V and 6.2×10^(-19)m^(2)/V^(2),respectively,in the even-layer PdPSe,which has not been discovered in other common TMDCs(e.g.,MoS2).Strikingly,it also simultaneously exhibited strong SHG anisotropy with an anisotropic ratio of~45,which is the largest reported among all 2D materials to date,to the best of our *** addition,the SHG anisotropy ratio can be harnessed from 0.12 to 45(375 times)by varying the excitation wavelength due to the dispersion ofχ^(2)*** an illustrative example,we further demonstrate polarized SHG imaging for potential applications in crystal orientation identification and polarization-dependent spatial *** findings in 2D PdPSe are promising for nonlinear nanophotonic and optoelectronic applications.

关键词： materials anisotropy nonlinear

来源：评论

学校读者我要写书评

暂无评论

Dependence of thermodynamic quantities at freeze-out on pseudorapidity and collision energy in p-p collisions at LHC energies

引用

Chinese physics C 2024年第10期48卷 235-246页

作者： Murad Badshah Yahia A.H.Obaidat Haifa I.Alrebdi M.Waqas Muhammad Ajaz Refka Ghodhbani Department of Physics Abdul Wali Khan University MardanMardan 23200Pakistan Department of Physics College of ScienceUniversity of BishaBisha 61922Saudi Arabia Department of Physics College of SciencePrincess Nourah bint Abdulrahman UniversityRiyadh 11671Saudi Arabia School of Mathematics Physics and Optoelectronic EngineeringHubei University of Automotive TechnologyShiyan 442002China Department of Computer Sciences Faculty of Computing and Information TechnologyNorthern Border UniversityRafhaSaudi Arabia

The transverse momentum distributions of charged hadrons produced in proton-proton collisions at center-of-mass energies(√s)of 0.9 TeV and 2.36 TeV,as measured by the CMS detector at the Large Hadron Collider(LHC),have been analyzed within various pseudorapidity classes utilizing the thermodynamically consistent Tsallis *** fitting procedure resulted in the key parameters,namely,effective temperature(T),non-extensivity parameter(q),and kinetic freezeout volume(V).Additionally,the mean transverse momentum()and initial temperature(T_(i))of the particle source are determined through the fit function and string percolation method,*** alternative method is employed to calculate the kinetic freezeout temperature(T_(0))and transverse flow velocity(β_(T))from ***,thermodynamic quantities at the freezeout,including energy density(ε),particle density(n),entropy density(s),pressure(P),and squared speed of sound(C_(s)^(2)),are computed using the extracted T and *** is also observed that,with a decrease in pseudorapidity,all thermodynamic quantities except V and q *** trend is attributed to greater energy transfer along the mid pseudorapidity.q increases towards higher values of pseudorapidity,indicating that particles close to the beam axis are far from ***,V remains nearly independent of *** excitation function of these parameters(q)shows a direct(inverse)correlation with collision *** ε,n,s,and P show a strong dependence on collision energies at low *** verification of the thermodynamic inequality ε≥3P suggests the formation of a highly dense droplet-like Quark-Gluon Plasma(QGP).Additionally,the inequality T_(i)>T>T_(0)is explicitly confirmed,aligning with the evolution of the produced fireball.

关键词： charged hadrons tsallis statistics effective temperature non-extensivity parameter pseudorapidity kinetic freeze-out stage multiple freeze-out scenario QGP QCD matter squared speed of sound

来源：评论

学校读者我要写书评

暂无评论

Emotion classification of Chinese text using improved NEZHA model

Emotion classification of Chinese text using improved NEZHA ...

引用

2024 International Conference on Algorithms, High Performance Computing, and Artificial Intelligence, AHPCAI 2024

作者： Yang, Hao Kuang, Lei Liang, Chengjing Lin, Xuyi Guangdong Preschool Normal College in Maoming School of Computer Science Guangdong Maoming525000 China China University of Geosciences School of Computer Science Hubei Wuhan430074 China Guangdong University of Technology School of Physics and Optoeletronic Engineering Guangdong Guangzhou510006 China

ISBN: (纸本)9781510685840

In this study, we enhance emotion classification for Chinese text by modifying the NEZHA model and evaluating various architectures. We developed and evaluated six distinct classifiers. Using the SMP2020-EWECT and ChnSentiCorp datasets, we assessed the models based on accuracy, F1 score, and loss. The DeepFeatureFusionClassifier and DeepFeatureRegClassifier emerged as the most effective models, with the DeepFeatureFusionClassifier achieving the highest performance on the ChnSentiCorp dataset and the DeepFeatureRegClassifier excelling on the SMP2020-EWECT dataset. The study highlights the effectiveness of advanced model architectures and multi-fold cross-validation on enhancing emotion classification accuracy and robustness. © 2024 SPIE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Applying machine learning techniques to predict laminar burning velocity for ammonia/hydrogen/air mixtures

引用

Energy and AI 2023年第3期13卷 207-218页

作者： Cihat Emre Ustun Mohammad Reza Herfatmanesh Agustin Valera-Medina Amin Paykani School of Physics Engineering and Computer ScienceUniversity of HertfordshireHatfieldAL109ABUnited Kingdom College of Physical Sciences and Engineering Cardiff UniversityCardiffCF243AAUnited Kingdom

Ammonia utilisation in internal combustion engines has attracted wide interest due to the current trend toward decarbonisation,as ammonia is a zero-carbon fuel with different combustion properties to *** laminar burning velocity(LBV)is a fundamental property of fuels with a significant effect on the combustion processes and accurate calculations and measurements of the LBV over a wide range of fuel blends,pressures and flow conditions is a time-consuming,complicated *** main goal of the current study is to predict the LBV of NH_(3)/H_(2)/air mixtures using a hybrid machine learning(ML)approach based on a training dataset consisting of both the experimental LBV values and additional data obtained from numerical simulations with a detailed kinetic *** ML model training data is collected from existing experimental LBV in the literature for NH_(3)/H_(2)/air ***,synthetic data is generated using one-dimensional(1D)simulations to reduce data inhomogeneity and increase accuracy of the ML *** total,24 different ML algorithms are tested to find the best model both for the experimental and the hybrid *** results suggest that both Gaussian Process Regression(GPR)and Neural Networks(NNs)can be utilised to predict LBV of NH_(3)/H_(2)/air mixtures with reasonable *** hybrid ML model achieved a coefficient of determination of R^(2)=***,hybrid ML model hyperparameters are optimised to achieve a coefficient of determination of R^(2)=*** was also found that ML can speed up LBV computation from 9500 to 27000 times compared to 1D simulations with a reduced mechanism.

关键词： Machine learning Ammonia Hydrogen Laminar burning velocity Combustion

来源：评论

学校读者我要写书评

暂无评论

Design of a large-range rotary microgripper with freeform geometries using a genetic algorithm

引用

Microsystems & Nanoengineering 2022年第1期8卷 59-72页

作者： Chen Wang Yuan Wang Weidong Fang Xiaoxiao Song Aojie Quan Michiel Gidts Hemin Zhang Huafeng Liu Jian Bai Sina Sadeghpour Michael Kraft College of Optical Science and Engineering Zhejiang UniversityHangzhouChina Department of Electrical Engineering and Computer Science University of LiegeLiegeBelgium ESAT-MNS University of LeuvenLeuvenBelgium PGMF and School of Physics Huazhong University of Science and TechnologyWuhanChina

This paper describes a novel electrostatically actuated microgripper with freeform geometries designed by a genetic *** new semiautomated design methodology is capable of designing near-optimal MEMS devices that are robust to fabrication *** use of freeform geometries designed by a genetic algorithm significantly improves the performance of the *** experiment shows that the designed microgripper has a large displacement(91.5μm)with a low actuation voltage(47.5 V),which agrees well with the *** microgripper has a large actuation displacement and can handle micro-objects with a size from 10 to 100μm.A grasping experiment on human hair with a diameter of 77μm was performed to prove the functionality of the *** result confirmed the superior performance of the new design methodology enabling freeform *** design method can also be extended to the design of many other MEMS devices.

关键词： handle algorithm. algorithm

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：