检索结果-内蒙古大学图书馆

1st EAI International Conference on Artificial Intelligence for communications and Networks, AICON 2019

作者： Ye, Liang Li, Yue Dong, Wenjing Seppänen, Tapio Alasaarela, Esko Department of Information and Communication Engineering Harbin Institute of Technology Harbin150080 China Health and Wellness Measurement Research Group OPEM Unit University of Oulu Oulu90014 Finland Key Laboratory of Police Wireless Digital Communication Ministry of Public Security Harbin150080 China Electrical Engineering School Heilongjiang University Harbin150080 China Physiological Signal Analysis Team University of Oulu Oulu90014 Finland

ISBN: (纸本)9783030229702

Bullying in campus has attracted more and more attention in recent years. By analyzing typical campus bullying events, it can be found that the victims often use the words "help" and some other appealing or begging words, that is to say, by using the artificial intelligence of speech recognition, we can find the occurrence of campus bullying events in time, and take measures to avoid further harm. The main purpose of this study is to help the guardians discover the occurrence of campus bullying in time by real-time monitoring of the keywords of campus bullying, and take corresponding measures in the first time to minimize the harm of campus bullying. On the basis of Sunplus MCU and speech recognition technology, by using the MFCC acoustic features and an efficient DTW classifier, we were able to realize the detection of common vocabulary of campus bullying for the specific human voice. After repeated experiments, and finally combining the voice signal processing functions of Sunplus MCU, the recognition procedure of specific isolated words was completed. On the basis of realizing the isolated word detection of specific human voice, we got an average accuracy of 99% of appealing words for the dedicated speaker and the misrecognition rate of other words and other speakers was very low. © ICST Institute for Computer Sciences, Social Informatics and Telecommunications engineering 2019 Published by Springer Nature Switzerland AG 2019. All Rights Reserved.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Comparison of Different Machine Learning Methods to Forecast Air Quality Index 6th

Comparison of Different Machine Learning Methods to Forecast...

引用

6th International Conference on Frontier Computing, FC 2018

作者： Liu, Bo Shi, Chao Li, Jianqiang Li, Yong Lang, Jianlei Gu, Rentao Beijing Advanced Innovation Center for Future Internet Technology Beijing University of Technology Beijing100124 China Faculty of Information Technology School of Software Engineering Beijing University of Technology Beijing100124 China Key Laboratory of Beijing on Regional Air Pollution Control Beijing University of Technology Beijing100124 China College of Environmental and Energy Engineering Beijing University of Technology Beijing100124 China Beijing Laboratory of Advanced Information Networks School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing100876 China

ISBN: (纸本)9789811336478

In recent years, more and more people have been plagued by respiratory diseases. The air quality, which is characterized by inhalable particles and fine particles, has attracted increasing attention. Accurately monitor and forecast the quality of air could not only help the government conduct interventions to alleviate the air pollution earlier, but also alert relevant people who suffer from respiratory diseases. In order to develop effective Air Quality Index (AQI) prediction models, this paper compared the performance of different Machine Learning (ML) methods and feature selection methods. First the air quality data in Beijing from 2016 to 2017 were collected. Then Multi-Linear Regression (MLR), Random forest Regression (RFR), BP Neural Network (BPNN) and Support Vector Regression (SVR) algorithm were trained on 10-fold cross validation. Correlation coefficient (R), mean absolute error (MAE) and root mean square error (RMSE) were used as evaluation metrics. The experimental results showed that the performance of SVR and BPNN were similarly well. MLR had the worst performance, which was possibly caused by a small feature dimension, and RFR had higher accuracy and better generalization capability than the other models, probably because the algorithm of regression tree in random forest included the interaction of variables. © 2019, Springer Nature Singapore Pte Ltd.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Tunable Fiber Laser Based on Cascaded Grating Combing with Sagnac Loop

引用

Faguang Xuebao/Chinese Journal of Luminescence 2019年第3期40卷 357-365页

作者： Zhao, Xiao-Li Zhang, Yu-Min Zhuang, Wei Song, Yan-Ming Luo, Fei Meng, Fan-Yong Beijing Engineering Research Center of Optoelectronic Information and Instruments Beijing Information Science & Technology University Beijing100016 China School of Instrument Science and Opto-electronics Engineering Hefei University of Technology Hefei230009 China Key Laboratory of Modern Measurement Control Technology Ministry of Education Beijing100192 China Beijing Key Laboratory of Optoelectronics Measurement Technology Beijing Information Science & Technology University Beijing100192 China

A tunable single-dual wavelength erbium-doped fiber laser is proposed and demonstrated. The finer filtering is generated by compound filtering effect which is produced by cascaded fiber Bragg gratings(Cascaded FBGs) combined with Sagnac loop, the birefringence effect is introduced by adjusting polarization controller(PC) in Sagnac loop, and then the tunable fiber laser is obtained. Based on the coupled mode theory and transmission matrix, the characteristics of the structure are analyzed, experimental system is established, and the correctness of theoretical analysis is verified. The experimental results show that, by adjusting PC, the adjustable laser range is about 1 555.644~1 556.112 nm, the wavelength spacing of dual-wavelength is about 0.108~0.452 nm, the side mode suppression ratio (SMSR) of single- and dual-wavelength is more than 40 dB. In the stability test, the maximum wavelength drift of single- and dual-wavelength fiber laser is less than 0.008 nm. The proposed method has the advantages of simple structure, convenient tuning, easy implementation and high fineness, which can be applied in fields such as dense wavelength division multiplexing(DWDM) and all-optical communication systems. © 2019, Science Press. All right reserved.

关键词： Dense wavelength division multiplexing

来源：评论

学校读者我要写书评

暂无评论

Study on Fast Response of Semiconductor Laser Driven by Impulse Current

引用

Journal of Physics: Conference Series 2020年第1期1607卷

作者： Shi Qing Shi Gentai Zhang Tao Xing Zhongmin Department of Measurement Technology and Control Engineering School of Mechanical Engineering Sichuan University Chengdu 610065 China

A simulation model based on single-mode rate equations of semiconductor laser and its typical parameters shows that, the photon stimulated emission rate at the early turn-on time of the semiconductor laser is increased with the increase of the injection current, and the corresponding rise time is reduced with the increase of injection current. However, for an output power is fixed semiconductor laser, increasing the injection current to reduce the rise time of the transmitted pulse leads to increase in temperature of semiconductor laser. We show that adding an impulse current in the front of the normal luminous pulse current can reduce the rise time of the transmitted pulse and ensure the stable output of the semiconductor laser. This method is verified by simulation and an experiment using PLTB450B semiconductor laser. The simulation and test results show that for an output power is fixed semiconductor laser, the rise time of the transmitted pulse can be reduced significantly by adding impulse current.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Contrast enhancement of illumination layer image using optimized subsection-based histogram equalization

引用

International Journal of Performability engineering 2018年第11期14卷 2624-2632页

作者： Wang, Yongxin Diao, Ming Wu, Haibin School of Information and Communication Engineering Harbin Engineering University Harbin150080 China Higher Educational Key Laboratory for Measuring and Control Technology and Instrumentation of Heilongjiang Province Harbin University of Science and Technology Harbin150080 China

A key problem of underwater image sharpening is to improve image contrast while retaining image detail. The retinex model is used to obtain the illumination and detail layer images. The histogram of the illumination layer image is divided into under-exposure subsection and over-exposure subsection by using the maximum interclass variance method, and the histogram subsections are equalized separately. The above process of histogram dividing and equalization is repeated until the difference between adjacent thresholds for dividing histogram subsections reaches its optimal value. This enhances the contrast of the illumination layer image. As a result, our contrast enhancement method of illumination layer image using optimized histogram subsection based histogram equalization is formed. Furthermore, by multiplying the enhanced contrast of illumination layer image with the original detail layer image, the contrast of underwater image is enhanced and its original details are retained. Some evaluations, e.g. information entropy and mean structure similarity, are examined to show that the underwater image quality is improved appropriately. © 2018 Totem Publisher, Inc. All rights reserved.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

3D facial geometry recovery from a depth view with attention guided generative adversarial network

arXiv

引用

arXiv 2020年

作者： Cai, Xiaoxu Yu, Hui Lou, Jianwen Zhang, Xuguang Li, Gongfa Dong, Junyu School of Creative Technologies University of Portsmouth PortsmouthPO1 2DJ United Kingdom School of Communication Engineering Hangzhou Dianzi University Hangzhou310018 China Key Laboratory of Metallurgical Equipment and Control Technology Ministry of Education Wuhan University of Science and Technology Wuhan430081 China College of Information Science and Engineering Ocean University of China Qingdao266100 China

We present to recover the complete 3D facial geometry from a single depth view by proposing an Attention Guided Generative Adversarial Networks (AGGAN). In contrast to existing work which normally requires two or more depth views to recover a full 3D facial geometry, the proposed AGGAN is able to generate a dense 3D voxel grid of the face from a single unconstrained depth view. Specifically, AGGAN encodes the 3D facial geometry within a voxel space and utilizes an attention-guided GAN to model the ill-posed 2.5D depth-3D mapping. Multiple loss functions, which enforce the 3D facial geometry consistency, together with a prior distribution of facial surface points in voxel space are incorporated to guide the training process. Both qualitative and quantitative comparisons show that AGGAN recovers a more complete and smoother 3D facial shape, with the capability to handle a much wider range of view angles and resist to noise in the depth view than conventional methods. Copyright © 2020, The Authors. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Speech Interactive Emotion Recognition System Based on Random Forest

Speech Interactive Emotion Recognition System Based on Rando...

引用

International Wireless communications and Mobile Computing Conference, IWCMC

作者： Susu Yan Liang Ye Shuai Han Tian Han Yue Li Esko Alasaarela School of Software and Micro Electronics Harbin University of Science and Technology Harbin China Key Laboratory of Police Wireless Digital Communication Ministry of Public Security P.R.C. Harbin China Harbin Institute of Technology Harbin China Health and Wellness Measurement research group OPEM unit University of Oulu Oulu Finland Electrical Engineering School Heilongjiang University Harbin China

ISBN: (数字)9781728131290

ISBN: (纸本)9781728131306

In daily life, speech is the main medium of human communication, and interpersonal communication is emotional. People hope that the computer can give a response based on the emotions contained in the voice. In this paper, we build a Wechat program of speech emotion recognition system, which is based on a random forest classifier. Firstly, the system preprocesses the collected speech signals in order to reduce noise. Secondly, 16 acoustic features are extracted from the pre-processed speech signals. The system obtains the emotional features of speech by applying 12 statistical functions to the original acoustic features. The emotional classification of Berlin Speech Emotion Database uses two classifiers: the Random Forest Classifier and the Support Vector Machine. The recognition accuracy of the SVM classifier is 83%. The accuracy of the random forest classifier is 89%. Finally, the random forest classifier is used to build the speech emotion recognition system.

关键词： Feature extraction Support vector machines Forestry Emotion recognition Speech recognition Classification algorithms Databases

来源：评论

学校读者我要写书评

暂无评论

Coherent H ∞ control for Markovian jump linear quantum systems

引用

IFAC-PapersOnLine 2020年第2期53卷 269-274页

作者： Yanan Liu Daoyi Dong Ian R. Petersen Qing Gao Steven X. Ding Hidehiro Yonezawa School of Engineering and Information Technology University of New South Wales Canberra ACT 2600 Australia Center for Quantum Computation and Communication Technology Australian Research Council Canberra ACT 2600 Australia Institute for Automatic Control and Complex Systems (AKS) University of Duisburg-Essen. 47057 Duisburg Germany Research School of Electrical Energy and Materials Engineering The Australian National University Canberra ACT 2601 Australia School of Automation Science and Electrical Engineering State Key Laboratory of Software Development Environment Beijing and also with Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing 100191 China

The purpose of this paper is to design a coherent feedback controller for a Markovian jump linear quantum system suffering from a fault signal. The control objective is to bound the effect of the disturbance input on the output for the time-varying quantum system. We prove the relation between the H ∞ control problem, the dissipation properties, and the solutions of Riccati differential equations, by which the H ∞ controller of the Markovian jump linear quantum system is given by the solutions of Linear Matrix Inequalities (LMIs).

关键词： Coherent quantum feedback H∞ control fault-tolerant control Markovian jump linear quantum systems

来源：评论

学校读者我要写书评

暂无评论

Corrigendum to ‘Dodecahydrododecaborate anion cluster-reduced nano-Au-decorated graphene oxide for 100% hydrogenation of nitroaromatics’[Colloid Interface Sci. Commun. 50 (2022) 100672]

引用

Colloid and Interface Science communications 2023年 55卷

作者： Yuwen Wang Xue Zhao Jianbing Chen Shuxing Zhou Xianxi Zhang Xinzhong Wang Thomas Wågberg Guangzhi Hu School of Electronic Communication Technology Shenzhen Institute of Information Technology Shenzhen 518172 China School of Materials and Energy Institute for Ecological Research and Pollution Control of Plateau Lakes Yunnan University Kunming 650504 China Research Academy of Non-metallic Mining Industry Development Materials and Environmental Engineering College Chizhou University Chizhou 247000 China Hubei Key Laboratory of Low Dimensional Optoelectronic Materials and Devices Hubei University of Arts and Science Xiangyang 441053 China School of Chemistry and Chemical Engineering Liaocheng University Liaocheng 252000 China Department of Physics Umeå University Umeå 901 87 Sweden

来源：评论

学校读者我要写书评

暂无评论

Research on the Influence of Non-Conductor on the Weight Function of Electromagnetic Flowmeter

引用

Journal of Physics: Conference Series 2021年第3期1952卷

作者： Xuejing Li Lijun Sun Shanghai Institute of Measurement and Testing Technology Shanghai 201203 China Shanghai Key Laboratory of On-line Testing and Control Technology Shanghai 201203 China School of Electrical and Information Engineering Tianjin University Tianjin 300072 China.

The demand for multiphase flow measurement is widespread in petrochemical and other fields. Due to its small size, easy maintenance, and no moving parts, electromagnetic flowmeters are widely used in single fluid measurement. With the increasing application of traditional electromagnetic flowmeters in petrochemical and other fields, the problems of traditional electromagnetic flowmeters in multiphase flow measurement applications have been discovered. How to optimize the structure of the electromagnetic flowmeter and how to improve the measurement accuracy has become a new research focus. On the basis of a large number of literature studies, this research is based on the finite element method, and systematically studies the influence of multiphase flow on the weight function of electromagnetic flowmeters. Firstly, modeling the existence of non-conductive objects in the electromagnetic flowmeter. Secondly, analyze the weight function characteristics of the non-conductive objects on the electromagnetic flowmeter from two angles of different radii and different positions. The conclusions of this study can provide a certain reference basis for the electromagnetic flowmeter in the measurement of multiphase flow.

关键词：

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：