检索结果-内蒙古大学图书馆

Cross Languages One-Versus-All Speech Emotion Classifier 1

2nd International Conference on Neural computing for advanced Applications, NCAA 2021

作者： Liu, Xiangrui Bin, Junchi Li, Huakang Key Laboratory of Urban Land Resources Monitoring and Simulation Ministry of Natural Resources Shenzhen China School of Engineering University of British Columbia Kelowna Canada School of Artificial Intelligence and Advanced Computing Xi’an Jiaotong-Liverpool University Suzhou China Suzhou Privacy Technology Co. Ltd. Suzhou China

ISBN: (数字)9789811651885

ISBN: (纸本)9789811651878

Speech emotion recognition (SER) is a task that cannot be accomplished solely depending on linguistic models due to the presence of figures of speech. For a more accurate prediction of emotions, researchers adopted acoustic modelling. The complexity of SER can be attributed to a variety of acoustic features, the similarities among certain emotions, etc. In this paper, we proposed a framework named Cross Languages One-Versus-All Speech Emotion Classifier (CLOVASEC) that identifies speeches’ emotions for both Chinese and English. Acoustic features were preprocessed by Synthetic Minority Oversampling Technique (SMOTE) to diminish the impact of an imbalanced dataset then by Principal component analysis (PCA) to reduce the dimension. The features were fed into a classifier that was made up of eight sub-classifiers and each sub-classifier was tasked to differentiate one class from the other seven classes. The framework outperformed regular classifiers significantly on The Chinese Natural Audio-Visual Emotion Database (CHEAVD) and an English dataset from Deng. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Interfacial thermal conductance between TiO2 nanoparticle and water: A molecular dynamics study

arXiv

引用

arXiv 2021年

作者： Roodbari, Mahdi Abbasi, Mohsen Arabha, Saeed Gharedaghi, Ayla Rajabpour, Ali Advanced Simulation and Computing Laboratory Imam Khomeini International University Qazvin Iran Departmant of Mechanical Engineering Tarbiat Modares University Tehran Iran Tehran Iran

The interfacial thermal conductance (Kapitza conductance) between a TiO2 nanoparticle and water is investigated using transient non-equilibrium molecular dynamics. It is found that Kapitza conductance of TiO2 nanoparticles is one order of magnitude greater than other conventional nanoparticles such as gold, silver, silicon, platinum and also carbon nanotubes and graphene flakes. This difference can be explained by comparing the contribution of electrostatic interactions between the partially charged titanium and oxygen atoms and water atoms to the van der Waals interactions, which increases the cooling time by about 10 times. The effects of diameter and temperature of nanoparticle, surface wettability on the interfacial thermal conductance are also investigated. The results showed that by increasing the diameter of the nanoparticle from 4 to 9 nm, Kapitza conductance decreased slightly. Also, increasing the temperature of the heated nanoparticle from 400 K to 600 K led to thermal conductance enhancement. It has been found that increasing the coupling strength of Lennard-Jones (LJ) potential from 0.5 to 4 caused the increment of the Kapitza conductance about 20%. It is also shown that a continuum model which its input is provided by molecular dynamics can be a suitable approximation to describe the thermal relaxation of a nanoparticle in a liquid medium. Copyright © 2021, The Authors. All rights reserved.

关键词： TiO2 nanoparticles

来源：评论

学校读者我要写书评

暂无评论

A Novel Method for Detection of ECG with Deep Learning 7

A Novel Method for Detection of ECG with Deep Learning

引用

7th International Conference on Computer and Communications, ICCC 2021

作者： Wang, Haiyan Zhou, Yanjie Zhou, Bing Wang, Zongmin State Key Laboratory of Mathematical Engineering and Advanced Computing Zhengzhou China Simulation Experiment Centre Zhengzhou University of Aeronautics Zhengzhou China Collaborative Innovation Centre For Internet Healthcare Zhengzhou University Zhengzhou China School of Management Engineering Zhengzhou University Zhengzhou China School of Information Engineering Zhengzhou University Zhengzhou China

ISBN: (纸本)9781665409506

With the rapid development of machine learning and deep learning, ECG intelligent detection models lean more heavily on the labeled data. However, the development of ECG annotation cannot satisfy the development of an intelligent detection model because of its high complexity and heavy workload. Developing a model with low dependence on labeled data becomes the core for solving the ECG intelligent detection. To overcome this limitation, this paper proposes a deep active learning (DAL) model for ECG intelligent detection, which combines high-performance deep learning (DL) with active learning (AL) that is less dependent on labeled data. Experimental results show that the proposed method can achieve high performance with the support of a small amount of labeled data. The proposed method could be adopted for data annotation, which achieves a high-quality data annotation and avoids useless annotation. © 2021 IEEE.

关键词： Electrocardiograms

来源：评论

学校读者我要写书评

暂无评论

Improving quantum thermal transistors through feedback-controlled baths

APL Quantum

引用

APL Quantum 2024年第3期1卷

作者： Uthpala N. Ekanayake Sarath D. Gunapala Malin Premaratne Advanced Computing and Simulation Laboratory (AχL) Department of Electrical and Computer Systems Engineering Monash University Clayton Victoria 3800 Australia Jet Propulsion Laboratory California Institute of Technology Pasadena California 91109 USA

In recent years, integrating quantum feedback mechanisms into thermal machines has gained attention due to its benefits in manipulating the system states and energy flows. This is particularly advantageous for quantum thermal transistors in preserving their inherent quantum properties as they lose the purity of the system states due to decoherence and relaxation from interactions with thermal baths, within the subsystems, and monitoring. In the literature, studies have demonstrated that preserving quantum coherence can enhance the performance of quantum thermal machines, improving their efficiency. In our paper, we present a model that proposes engineering baths to be equipped with detectors and a controller to enable feedback in a quantum thermal transistor that emulates a role played by a feedback resistor in an electronic transistor. We use the framework of quantum feedback control via weak monitoring. We modify the system evolution trajectories by using a weak monitoring record from a detector. By taking the ensemble average of these trajectories, we unveil the evolution of the system density matrix that corresponds to the Markovian dynamics of the transistor. This type of feedback introduces minimal perturbation to the system and, once tuned, enhances the system coherence that would otherwise degrade due to bath interactions. Furthermore, there will be no change in the relaxation times. The probabilities of population terms remain unchanged. We treat this an enhancement in the operational characteristics of the quantum thermal transistor as it maintains its quantum features with an added benefit of improved amplification capabilities.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhanced thermal rectification in coupled qutrit–qubit quantum thermal diode

APL Quantum

引用

APL Quantum 2024年第4期1卷

作者： Anuradhi Rajapaksha Sarath D. Gunapala Malin Premaratne Advanced Computing and Simulation Laboratory(AχL) Department of Electrical and Computer Systems Engineering Monash University Clayton Victoria 3800 Australia Jet Propulsion Laboratory California Institute of Technology Pasadena California 91109 USA

We present a quantum thermal diode model based on a coupled qutrit–qubit system designed to control heat flow between two thermal baths with unprecedented efficiency. This differs from previous models in terms of the asymmetry introduced by spin particles and their interaction. By exploiting the interactions between degenerate states within the coupled qutrit–qubit system, our model demonstrates diode-like behavior that is both robust and energy-efficient. Utilizing the frameworks of open quantum systems and the quantum Markovian master equation, with the Born and rotating wave approximations, we comprehensively analyze the system’s behavior. Numerical simulations reveal significant thermal rectification across a wide temperature range, positioning our model as a groundbreaking solution for nanoscale heat management. In addition, we employ state transition diagrams to elucidate the transition rate characteristics that underpin the diode behavior. Finally, we explore the potential for physical implementation using superconducting circuits, highlighting the practical relevance of our design.

关键词：

来源：评论

学校读者我要写书评

暂无评论

CrTe2 as a two-dimensional material for topological magnetism in complex heterobilayers

arXiv

引用

arXiv 2023年

作者： Abuawwad, Nihad dos Santos Dias, Manuel Abusara, Hazem Lounis, Samir Peter Grünberg Institut Institute for Advanced Simulation Forschungszentrum Jülich & JARA Jülich52425 Germany Faculty of Physics University of Duisburg-Essen CENIDE Duisburg47053 Germany Department of Physics Birzeit University PO Box 14 Palestine Birzeit Palestine Scientific Computing Department STFC Daresbury Laboratory WarringtonWA4 4AD United Kingdom

The discovery of two-dimensional (2D) van der Waals magnetic materials and their heterostructures provided an exciting platform for emerging phenomena with intriguing implications in information technology. Here, based on a multiscale modelling approach that combines first-principles calculations and a Heisenberg model, we demonstrate that interfacing a CrTe2 layer with various Te-based layers enables the control of the magnetic exchange and Dzyaloshinskii-Moriya interactions as well as the magnetic anisotropy energy of the whole heterobilayer, and thereby the emergence of topological magnetic phases such as skyrmions and antiferromagnetic Néel merons. The latter are novel particles in the world of topological magnetism since they arise in a frustrated Néel magnetic environment and manifest as multiples of intertwined hexamer-textures. Our findings pave a promising road for proximity-induced engineering of both ferromagnetic and long-sought antiferromagnetic chiral objects in the very same 2D material, which is appealing for new information technology devices employing quantum materials. © 2023, CC BY.

关键词： Tellurium compounds

来源：评论

学校读者我要写书评

暂无评论

Electrical engineering of topological magnetism in two-dimensional heterobilayers

arXiv

引用

arXiv 2023年

作者： Abuawwad, Nihad dos Santos Dias, Manuel Abusara, Hazem Lounis, Samir Peter Grünberg Institut Institute for Advanced Simulation Forschungszentrum Jülich JARA Jülich52425 Germany Faculty of Physics University of Duisburg-Essen and CENIDE Duisburg47053 Germany Department of Physics Birzeit University PO Box 14 Birzeit Palestine Scientific Computing Department STFC Daresbury Laboratory WarringtonWA4 4AD United Kingdom

The emergence of topological magnetism in two-dimensional (2D) van der Waals (vdW) magnetic materials promoted 2D heterostructures as key building-blocks of devices for information technology based on topological concepts. Here, we demonstrate the all-electric switching of the topological nature of individual magnetic objects emerging in 2D vdW heterobillayers. We show from the first principles that an external electric field modifies the vdW gap between CrTe 2 and (Rh, Ti)Te2 layers and alters the underlying magnetic interactions. This enables switching between ferromagnetic skyrmions and meron pairs in the CrTe2/RhTe2 heterobilayer while it enhances the stability of frustrated antiferromagnetic merons in the CrTe2/TiTe2 heterobilayer. We envision that the electrical engineering of distinct topological magnetic solitons in a single device could pave the way for novel energy-efficient mechanisms to store and transmit information with applications in spintronics. © 2023, CC BY.

关键词： Electric fields

来源：评论

学校读者我要写书评

暂无评论

Semantic segmentation of track image based on deep neural network

引用

The Journal of China Universities of Posts and Telecommunications 2020年第5期27卷 23-33页

作者： Wang Zhaoying Zhou Junhua Liao Zhonghua Zhai Xiang Zhang Lianping School of Electronic Engineering Beijing University of Posts and TelecommunicationsBeijing 100876China Beijing Complex Product Advanced Manufacturing Kngineering Research Center Beijing Simulation CenterBeijing 100854China State Key Laboratory of Intelligent Manufacturing System Technology Beijing Institute of Electronic System EngineeringBeijing 100854China Alibaba Cloud Computing Beijing 100020China

In this paper,deep learning technology was utilited to solve the railway track recognition in intrusion detection *** railway track recognition can be viewed as semantic segmentation task which extends image processing to pixel level *** encoder-decoder architecture DeepLabv3+model was applied in this work due to its good performance in semantic segmentation *** images of the railway track collected from the video surveillance of the train cab were used as experiment dataset in this work,the following improvements were made to the *** first aspect deals with over-fitting problem due to the limited amount of training *** augmentation and transfer learning are applied consequently to rich the diversity of data and enhance model robustness during the training ***,different gradient descent methods are compared to obtain the optimal optimizer for training model *** third problem relates to data sample imbalance,cross entropy(CE)loss is replaced by focal loss(FL)to address the issue of serious imbalance between positive and negative *** of the improved DeepLabv3+model with above solutions is demonstrated by experiment results with different system parameters.

关键词： railway track recognition convolutional neural networks semantic segmentation DeepLabv3+

来源：评论

学校读者我要写书评

暂无评论

Magnetic superexchange couplings in Sr2IrO4

引用

Physical Review B 2021年第12期104卷 125116-125116页

作者： Guoren Zhang Eva Pavarini Key Laboratory of Materials Physics Institute of Solid State Physics HFIPS Chinese Academy of Sciences Hefei 230031 People's Republic of China Institute for Advanced Simulation Forschungszentrum Jülich 52425 Jülich Germany JARA High-Performance Computing 52056 Aachen Germany

We investigate the magnetic couplings in Sr2IrO4 in the Mott-insulating picture, combining density-functional theory, dynamical mean-field theory, and many-body perturbation theory. We first determine the form of the jeff=1/2 pseudospin via the local-density-approximation + dynamical mean-field theory approach. Next we study the magnetic interactions in the strong-to-intermediate coupling regime. To this end, we calculate the superexchange pseudospin tensors Γ1, Γ2, and Γ3 up to fourth order and analyze their dependence on the screened Coulomb interaction integrals U and J. We show that, due to term cancellations, the experimental nearest-neighbor coupling Γ1 is reasonably well reproduced for a whole range of realistic (U,J) values. We show that increasing the Hund's rule coupling J (within the window of realistic values) can lead to large fourth-order contributions, which could explain the ferromagnetic next-nearest-neighbor coupling Γ2 extracted from the spin-wave dispersion. This regime is characterized by a sizable ring exchange K. For (U,J) values that yield a Mott insulator with a half-filled jeff=1/2 state, however, fourth-order terms remain minor even if the gap is small. For no realistic parameters, we find a sizable next-next-nearest-neighbor coupling Γ3∼|Γ2|. Possible implications are discussed.

关键词： Exchange interaction Magnetism Spin-orbit coupling Iridates Mott insulators Strongly correlated systems Dynamical mean field theory Quantum Monte Carlo

来源：评论

学校读者我要写书评

暂无评论

Augmenting photoluminescence of monolayer MoS_(2) using high order modes in a metal dimer-on-film nanocavity

引用

Photonics Research 2021年第4期9卷 501-506页

作者： Shiyin Cao Liping Hou Qifa Wang Chenyang Li Weixing Yu Xuetao Gan Kaihui Liu Malin Premaratne Fajun Xiao Jianlin Zhao MOE Key Laboratory of Material Physics and Chemistry under Extraordinary Conditions and Shaanxi Key Laboratory of Optical Information TechnologySchool of Physical Science and TechnologyNorthwestern Polytechnical UniversityXi’an 710129China Key Laboratory of Spectral Imaging Technology of Chinese Academy of Sciences Xi’an 710119China State Key Laboratory for Mesoscopic Physics Collaborative Innovation Centre of Quantum MatterSchool of PhysicsPeking UniversityBeijing 100871China Advanced Computing and Simulation Laboratory(AχL) Department of Electrical and Computer Systems EngineeringMonash UniversityClaytonVIC 3800Australia

Plasmonic particle-on-film nanocavities,supporting gap modes with ultra-small volume,provide a great solution to boost light–matter interactions at the *** this work,we report on the photoluminescence(PL)enhancement of monolayer MoS_(2) using high order modes of an Au nanosphere dimer-on-film nanocavity(DoFN).The high order plasmon modes,consisting of two bonding quadrupoles in the dimer and their images in the Au film,are revealed by combining the polarization-resolved scattering spectra with the numerical *** integrating the monolayer MoS_(2) into the DoFN,these high order modes are used to enhance PL intensity through simultaneously boosting the absorption and emission processes,producing a 1350-fold enhancement *** opens an avenue to enhance the light–matter interaction with high order plasmon modes and may find applications in future optoelectronics and nanophotonics devices.

关键词： cavity high integrating

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：