检索结果-南通市图书馆

An autoencoder-based feature level fusion for speech emotion recognition

Digital Communications and Networks 2024年第5期10卷 1341-1351页

作者： Peng Shixin Chen Kai tian tian Chen Jingying National Engineering Research Center for E-Learning National Engineering Laboratory for Educational Big DataCentral China Normal University

Although speech emotion recognition is challenging,it has broad application prospects in human-computer *** a system that can accurately and stably recognize emotions from human languages can provide a better user ***,the current unimodal emotion feature representations are not distinctive enough to accomplish the recognition,and they do not effectively simulate the inter-modality dynamics in speech emotion recognition *** paper proposes a multimodal method that utilizes both audio and semantic content for speech emotion *** proposed method consists of three parts:two high-level feature extractors for text and audio modalities,and an autoencoder-based feature *** audio modality,we propose a structure called Temporal Global Feature Extractor(TGFE) to extract the high-level features of the timefrequency domain relationship from the original speech *** that text lacks frequency information,we use only a Bidirectional Long Short-Term Memory network(BLSTM) and attention mechanism to simulate an intra-modal *** these steps have been accomplished,the high-level text and audio features are sent to the autoencoder in parallel to learn their shared representation for final emotion *** conducted extensive experiments on three public benchmark datasets to evaluate our *** results on Interactive Emotional Motion Capture(IEMOCAP) and Multimodal EmotionLines Dataset(MELD) outperform the existing ***,the results of CMU Multi-modal Opinion-level Sentiment Intensity(CMU-MOSI) are ***,experimental results show that compared to unimodal information and autoencoderbased feature level fusion,the joint multimodal information(audio and text) improves the overall performance and can achieve greater accuracy than simple feature concatenation.

关键词： Attention mechanism Autoencoder Bimodal fusion Emotion recognition

来源：

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

“屈原赋二十五篇”到刘向《楚辞》成书的“聚合之势”考论——兼说今本《楚辞》篇次的来源之二

引用

三峡大学学报（人文社会科学版） 2025年第1期47卷 18-23,116页

作者：谢天鹏湖南理工学院中国语言文学学院湖南岳阳414006

从屈原《离骚》化用自己《抽思》《涉江》《天问》《远游》《思美人》《惜往日》诸篇,以及宋玉、贾谊、司马迁、东方朔或化用或论及屈作分别达今存七卷中之五卷、六卷、四卷、五卷等情况看,一个共25篇的“屈原集”很可能早已存在,甚至... 详细信息

从屈原《离骚》化用自己《抽思》《涉江》《天问》《远游》《思美人》《惜往日》诸篇,以及宋玉、贾谊、司马迁、东方朔或化用或论及屈作分别达今存七卷中之五卷、六卷、四卷、五卷等情况看,一个共25篇的“屈原集”很可能早已存在,甚至就是屈原自己所编。再从司马迁《屈原列传》、东方朔《七谏》看,今存《楚辞》中宋玉等人的拟屈之作也已围绕着屈原及其作品形成了一个“关系网”。因此,刘向编《楚辞》应是基于这样一个“屈原集”加“关系网”,合并、落实、调适而成的。就其“调适”而言,他主要受了司马迁影响,一是依循“时间”标准排列篇次,二是依据“悲其志”主旨进行再选拔;此外,他还引入了“代屈原设言”的写作标准。

关键词：屈原《楚辞》司马迁刘向

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Multivariable Intelligent Decoupling Control System and its Application

引用

自动化学报 2005年第1期31卷 123-131页

作者： tian-YouCHAI HengYUE NationalEngineeringandTechnologyResearchCenterforMetallurgicIndustryAutomation NortheasternUniversityShenyang110004P.R.China

Many industrial processes have compositive complexities including multivariable, strong coupling, nonlinearity, time-variant and operating condition variations. Combining multivariable adaptive decoupling control with neural networks, this paper presents a multivariable neural networkbased decoupling control algorithm. This control algorithm is integrated with distributed control technique and intelligent control technique, and a three-leveled intelligent decoupling control system consisting of basic control level, coordinating control level, and management and decision level is developed. The configuration and function of the control system are discussed in detail. This system has been successfully applied in ball mill pulverizing systems of 200MW power units, and remarkable benefits have been obtained.

关键词：神经网络去耦合控制智能去耦合控制系统煤粉碎系统多变量系统应用

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Development of a compact DOI-TOF detector module for high-performance PET systems

引用

Nuclear Science and Techniques 2017年第4期28卷 1-7页

作者： Qing-Yang Wei tian-Peng Xu tian-tian Dai Shi Wang Ya-Qiang Liu Yu Gu tian-Yu Ma School of Automatic and Electrical Engineering University of Science and Technology Beijing Beijing 100083 China Department of Engineering Physics Tsinghua UniversityBeijing 100084 China Key Laboratory of Particle and Radiation Imaging (Tsinghua University) Ministry of Education Beijing 100084 China Department of Radiation Oncology China-Japan Friendship Hospital Beijing 100029 China

To increase spatial resolution and signal-to-noise ratio in PET imaging,we present in this paper the design and performance evaluation of a PET detector module combining both depth-of-interaction(DOI) and time-offlight(TOF) *** detector module consists of a staggered dual-layer LYSO block with2 mm × 2 mm × 7 mm ***-compatible SiPM sensors(MicroFJ-30035-TSV,SensL) are assembled into an 8× 8 *** signals from both fast and slow outputs are read out by a 128-channel ASIC *** test its performance,a flood histogram is acquired with a ^(22)Na point source on top of the detector,and the energy resolution and the coincidence resolving time(CRT) value for each individual crystal are *** flood histogram shows excellent crystal separation in both *** average energy resolution at 511 keV is 14.0 and 12.7%at the bottom and top layers,*** average CRT of a single crystal is 635 and 565 ps at the bottom and top layers,*** conclusion,the compact DOI-TOF PET detector module is of excellent crystal identification capability,good energy resolution and reasonable time resolution and has promising application prospective in clinical TOF PET,PET/MRI,and brain PET systems.

关键词： Positron emission tomography SiPM Depth of interaction (DOI) Time-of-flight (TOF)

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Design of process and control scheme for cyclohexanol production from cyclohexene using reactive distillation

引用

Chinese Journal of Chemical Engineering 2021年第12期34卷 96-105页

作者： Mingyuan Hu Hui tian College of Chemistry and Chemical Engineering Yantai UniversityYantai 264005China Collaborative Innovation Center of Comprehensive Utilization of Light Hydrocarbon Resource Yantai UniversityYantai 264005China

Cyclohexanol is a commonly used organic ***,the most promising industrial process for synthesizing cyclohexanol,by cyclohexene hydration,suffers from a low conversion rate and difficult *** this paper,a three-column process for catalytic distillation applicable in the hydration of cyclohexene to cyclohexanol was established to solve *** with Aspen Plus shows that the process has good advantages,the conversion of cyclohexene reached 99.3%,and the product purity was>99.2%.The stable operation of the distillation system requires a good control *** design of the control scheme is very ***,at present,the reactive distillation process for cyclohexene hydration is under investigation experimentally and by steady-state ***,three different plant-wide control schemes were established(CS1,CS2,CS3) and the position of temperature sensitive stage was selected by using sensitivity analysis method and singular value decomposition *** Tyreus-Luyben empirical tuning method was used to tune the controller ***,Aspen Dynamics simulation software was used to evaluate the performance of the three control *** introducing ΔF±20% and χ_(ENE)±5%,comparison the changes in product purity and yield of the three different control *** comparison,we can see that the control scheme CS3 has the best performance.

关键词： Cyclohexene hydration Catalytic distillation Control schemes Dynamic Simulation

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Effect of Thermal Radiation Heat Transfer on the Temperature Measurement by the Thermocouple in Premixed Laminar Flames

引用

Journal of Thermal Science 2022年第2期31卷 541-551页

作者： JIN Kairu tian Zhenyu Institute of Engineering Thermophysics Chinese Academy of SciencesBeijing 100190China University of Chinese Academy of Sciences Beijing 100049China

In the past 30 years,the effect of thermal radiation and convection heat transfer,which are predominant at high temperature and can affect the measurement accuracy of thermocouple,were not fully considered in the field of laminar flame *** this work,the effect of thermal radiation heat transfer was newly calculated by determining the spectral irradiation heat flux from the whole space to thermocouple and the radiation heat loss from thermocouple junction to *** reveals that the thermocouple itself maintains at high temperature,resulting serious thermal radiation heat loss,which can be compensated via receiving energy from convection-transferred heat as well as thermal radiation emitted by flame and burner *** method was applied to correct the temperatures measured by thermocouple in rich nitromethane flame as *** results indicate that the radiation heat loss plays a dominant role,while the radiations emitted by flame and burner surface account for minor contribution with the percentage of 20.78%at the height above burner(HAB)of 0.4 mm,3.63%at HAB of 2.0 mm and even smaller at higher *** correction states that the maximum temperature error is 117.60 K,where the effect of thermal radiation emitted by flame and burner surface is less than 1.75 ***,it is provably reasonable and feasible to concentrate on the radiation heat loss and ignore the effect of thermal radiation emitted by flame and burner in real combustion processes.

关键词： thermal radiation heat transfer temperature error premixed laminar flame

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Face Age Estimation Based on CSLBP and Lightweight Convolutional Neural Network

引用

Computers, Materials & Continua 2021年第11期69卷 2203-2216页

作者： Yang Wang Ying tian Ou tian School of Computer Science and Software Engineering University of Science&Technology LiaoningAnshan114051China Medical and Health Sciences University of WollongongNSW2522Australia

As the use of facial attributes continues to expand,research into facial age estimation is also *** face images are easily affected by factors including illumination and occlusion,the age estimation of faces is a challenging *** paper proposes a face age estimation algorithm based on lightweight convolutional neural network in view of the complexity of the environment and the limitations of device computing *** face age estimation based on Soft Stagewise Regression Network(SSR-Net)and facial images,this paper employs the Center Symmetric Local Binary Pattern(CSLBP)method to obtain the feature image and then combines the face image and the feature image as network input *** feature images to the convolutional neural network can improve the accuracy as well as increase the network model *** experimental results on IMDB-WIKI and MORPH 2 datasets show that the lightweight convolutional neural network method proposed in this paper reduces model complexity and increases the accuracy of face age estimations.

关键词： Face age estimation lightweight convolutional neural network CSLBP SSR-Net

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Robust adaptive radar beamforming based on iterative training sample selection using kurtosis of generalized inner product statistics

引用

Journal of Systems Engineering and Electronics 2024年第1期35卷 24-30页

作者： tian Jing ZHANG Wei School of Information and Electronics Beijing Institute of TechnologyBeijing 100081China National Key Laboratory of Electromagnetic Space Security Chengdu 610036China

In engineering application,there is only one adaptive weights estimated by most of traditional early warning radars for adaptive interference suppression in a pulse reputation interval(PRI).Therefore,if the training samples used to calculate the weight vector does not contain the jamming,then the jamming cannot be removed by adaptive spatial *** the weight vector is constantly updated in the range dimension,the training data may contain target echo signals,resulting in signal cancellation *** cope with the situation that the training samples are contaminated by target signal,an iterative training sample selection method based on non-homogeneous detector(NHD)is proposed in this paper for updating the weight vector in entire range *** principle is presented,and the validity is proven by simulation results.

关键词： adaptive radar beamforming training sample selection non-homogeneous detector electronic jamming jamming suppression

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Deep learning augmented microscopy: a faster, wider view, higher resolution autofluorescenceharmonic microscopy

引用

Light(Science & Applications) 2022年第5期11卷 746-747页

作者： Lei tian Department of Electrical and Computer Engineering Boston UniversityBostonMA 02215USA Department of Biomedical Engineering Boston UniversityBostonMA 02215USA

Deep learning enables bypassing the tradeoffs between imaging speed,field of view,and spatial resolution in autofluorescence-harmonic microscopy.

关键词： harmonic Deep faster

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Distributed entanglement generation from asynchronously excited qubits

引用

Frontiers of physics 2022年第4期17卷 107-113页

作者： tian-tian Huan Rigui Zhou Hou Ian Institute of Applied Physics and Materials Engineering University of MacaoMacaoChina College of Mathematics and Computer Science Chifeng UniversityChifeng 024000China College of Information Engineering Shanghai Maritime UniversityShanghai 201306China

The generation of GHZ states calls for simultaneous excitation of multiple *** peculiarity of such states is reflected in their nonzero distributed entanglement which is not contained in other entangled *** study the optimal way to excite three superconducting qubits through a common cavity resonator in a circuit such that the generation of distributed entanglement among them could be obtained at the highest degree in a time-controllable way.A non-negative measure quantifying this entanglement is derived as a time function of the quadripartite system *** find that this measure does not stay static but obtains the same maximum *** the qubit-resonator couplings are allowed to vary,its peak value is enhanced monotonically by increasing the greatest coupling strength to one of the *** period of its peak to peak revival maximizes when the couplings become inhomogeneous,thus qubit excitation becoming asynchronous,at a relative ratio of *** study demonstrates the role of asynchronous excitations for time-controlling multi-qubit systems,in particular in extending entanglement time.

关键词： dynamic entanglement asynchronous excitation

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

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：