检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Liu, Yuanyuan Long, Chengjiang Zhang, Zhaoxuan Liu, Bokai Zhang, Qiang Yin, Baocai Yang, Xin The Department of Electronic Information and Electrical Engineering Dalian University of Technology Dalian116024 China Meta Reality Labs BurlingameCA94010 United States The Key Lab of Advanced Design and Intelligent Computing Dalian University Ministry of Education Dalian116622 China The Beijing Key Laboratory of Multimedia and Intelligent Software Technology Beijing Institute of Artificial Intelligence Faculty of Information Technology Beijing University of Technology Beijing100124 China

3D scene graph generation (SGG) has been of high interest in computer vision. Although the accuracy of 3D SGG on coarse classification and single relation label has been gradually improved, the performance of existing works is still far from being perfect for fine-grained and multi-label situations. In this paper, we propose a framework fully exploring contextual information for the 3D SGG task, which attempts to satisfy the requirements of fine-grained entity class, multiple relation labels, and high accuracy simultaneously. Our proposed approach is composed of a Graph Feature Extraction module and a Graph Contextual Reasoning module, achieving appropriate information-redundancy feature extraction, structured organization, and hierarchical inferring. Our approach achieves superior or competitive performance over previous methods on the 3DSSG dataset, especially on the relationship prediction sub-task. Copyright © 2022, The Authors. All rights reserved.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Aspect-Level Sentiment Classification of Chinese Patient Comments Based on Pre-trained Sentiment Embedding

Aspect-Level Sentiment Classification of Chinese Patient Com...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Yongxue Shan Zhaoqian Zhong Chao Che Bo Jin Xiaopeng Wei Key Laboratory of Advanced Design and Intelligent Computing Ministry of Education Dalian University Dalian China School of Innovation and Entrepreneurship Dalian University of Technology Dalian China School of Computer Science and Technology Dalian University of Technology Dalian China

ISBN: (纸本)9781665429825

With the development of information technology, online health care service platforms have collected a large amount of patient comment information. Through fine-grained sentiment classification of this information, we can provide references for patients to seek medical treatment and help doctors understand their work. Therefore, we proposed a model that integrated pre-trained emotional information and semantic information at the word and character level for aspect-level sentiment classification. Specifically, we employed adversarial learning for training sentiment word embeddings and the two-layer bidirectional long short-term memory network to extract the sentiment embedding of the entire sentence in a specific aspect. We also combined the pre-trained sentiment feature vector with the structured semantic information by linear weighting and the multi-head self-attention mechanism, enabling the model to pay more attention to the information most relevant to a given aspect category. We performed experiments on the Chinese patient comments data set constructed by our research team and the proposed model outperformed the state-of-the-art methods, which proved the effectiveness of the proposed model for aspect-level sentiment classification of Chinese patient comments.

关键词： Training Biological system modeling Conferences Semantics Bit error rate Medical treatment Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Modelling and analysis of haemoglobin catalytic reaction kinetic system

引用

Mathematical & Computer Modelling of Dynamical Systems 2020年第4期26卷 306-321页

作者： Liu, Yanhong Lv, Hui Wang, Bin Yang, Deyun Zhang, Qiang Key Laboratory of Advanced Design and Intelligent Computing Ministry of Education School of Software Dalian University Dalian China Department of Information Science and Technology Taishan University Taian China

In order to study whether haemoglobin (Hb) can replace peroxidase and has good catalytic properties. The key to exploring the characteristics of Hb peroxidase is to establish a suitable kinetic model, which is studied in this paper. First, according to the Hb catalytic reaction, a nonlinear system is established and improved. It is proved that the established system is in line with the practical significance. The stability of the original system is judged by analysing the stability of the simplified system. Then, considering the effect of time delay on Hb catalytic reaction, a nonlinear time-delay catalytic reaction system is obtained. For convenient application, the system is linearized using Taylor's formula, and the dynamic characteristics of Hopf bifurcation are analysed. The response diagrams of three system are plotted by setting perturbation parameters, and their variations are observed to analyse the differences among them. The results show that the nonlinear time-delay system can better describe the characteristics of the catalytic reaction. [ABSTRACT FROM AUTHOR]

关键词： central manifold theorem haemoglobin Hopf bifurcation Nonlinear system model time delay

来源：评论

学校读者我要写书评

暂无评论

End-to-end speech emotion recognition based on one-dimensional convolutional neural network 2019

End-to-end speech emotion recognition based on one-dimension...

引用

3rd International Conference on Innovation in Artificial Intelligence, ICIAI 2019

作者： Gao, Mengna Zhang, Qiang Dong, Jing Yang, Deyun Zhou, Dongsheng Key Laboratory of Advanced Design and Intelligent Computing Ministry of Education Dalian University Dalian116024 China School of Information Science and Technology Taishan University Tai'an Shandong Province271000 China Key Laboratory of Advanced Design and Intelligent Computing Ministry of Education Dalian University Dalian116024 China

ISBN: (纸本)9781450361286

Real-time speech emotion recognition has always been a problem. To this end, we proposed an end-to-end speech emotion recognition model based on one-dimensional convolutional neural network, which contains only three convolution layers, two pooling layers and one full-connected layer. Through Adam optimization algorithm and back propagation mechanism, more discriminative features can be extracted continuously. Our model is quite simple in structure and easy to quickly complete the emotional classification task. Compared with traditional methods, there is no need to carry out the complex process of manually extracting features, and the model can automatically learn the emotional features from raw speech signals. In the emotional recognition experiments with EMODB, CASIA, IEMOCAP, and CHEAVD four speech databases, relatively high recognition rates were obtained. Experiments show that the proposed algorithm is of great benefit to the implementation of real-time speech emotion recognition. © 2019 ACM

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Attention-Guided Second-Order Pooling Convolutional Networks

Attention-Guided Second-Order Pooling Convolutional Networks

引用

IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Shannan Chen Qiule Sun Cunhua Li Jianxin Zhang Qiang Zhang Key Lab of Advanced Design and Intelligent Computing Dalian University China Faculty of Electronic Information and Electrical Engineering Dalian University of Technology China School of Computer Engineering Jiangsu Ocean University China School of Computer Science and Engineering Dalian Minzu University China

Recently, channel attention-guided convolutional networks (ConvNets) have shown great advance on visual recognition tasks. However, they mainly exploit coarse first-order statistics to characterize holistic image and rarely focus on long-range feature dependencies, which limits the representation power in a certain. To handle above limitations, this paper proposes a novel attention-guided second-order pooling convolutional network (ASP-Net). ASP-Net introduces bilinear pooling that captures pairwise feature interactions to model second-order statistics. Meanwhile, it explicitly collects long-range dependencies via non-local operations, thus providing a global view in lower layers. Then, the second-order statistics and non-local context features are fused to obtain the enhanced representation for predicting channel-wise attention map and scaling convolution features. Experiment results on three commonly used datasets illuminate that ASP-Net outperforms its counterparts and achieves competitive performance.

关键词： Convolutional codes Visualization Convolution Conferences Network architecture Acoustics Task analysis

来源：评论

学校读者我要写书评

暂无评论

A method of terminology alignment in Historical Books based on the correspondence between Pivot language and position

引用

Journal of Physics: Conference Series 2021年第1期1883卷

作者： Xingchen Xie Xiaoting Wu Xiaopeng Wei Chao Che Key Laboratory of Advanced Design and Intelligent Computing Dalian University Dalian Liaoning 116622 China

In view of the most difficult problem of terminology translation in the translation of historical books, this paper extracts term translation pairs from bilingual parallel corpus as a reference to improve the quality and efficiency of the translation of historical books. However, the small size of the corpus of historical books leads to poor word alignment, which brings a large number of errors to term alignment. At the same time, the special grammar of ancient Chinese will also affect term alignment. In order to solve the above two problems, this paper proposes a method of term alignment of historical books based on pivot language and position correspondence. This method introduces modern Chinese as the pivot language, makes use of the position correspondence between modern Chinese and English terms in sentences, and uses the sliding window method to generate candidate term pairs, which avoids the influence of word alignment errors on term alignment. In addition, if we first align to modern Chinese, the ancient Chinese terminology will complete the omitted characters in modern Chinese and replace the false characters, so as to avoid the influence of the special usage in ancient Chinese on the term alignment. The experimental results in Historical Records show that the accuracy of this method is slightly better than that of the method based on word alignment, which verifies the effectiveness of this method without word alignment.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Protein Embedding Model for Drug Molecular Screening

A Protein Embedding Model for Drug Molecular Screening

引用

International Conference on Big Data and Smart computing (BIGCOMP)

作者： Chao Che Min Zhu Yongjun Zhu Qiang Zhang Dongsheng Zhou Bin Wang Key Laboratory of Advanced Design and Intelligent Computing Ministry of Education Dalian University Dalian China Department of Library and Information Science Sungkyunkwan University Seoul Republic of Korea

ISBN: (数字)9781728160344

ISBN: (纸本)9781728160351

Application of machine learning method in new drug development can greatly shorten the process of experimental discovery and reduce the risk of clinical failure. However, the feature extraction of proteins sequence is very difficult due to the large dimension. To this end, we propose a Protein Embedding Model(PEM) for drug molecular screening to predict the interaction between proteins and small molecules. Specifically, PEM first classifies 20 kinds of amino acids into 6 categories to reduce the dimension and learns the representation of protein borrowing the idea of word embedding. Then the model uses multiple imputation to fill the physical and chemical properties of small molecule compounds. Finally, the model uses LightGBM model to predict the affinity value Ki between proteins and small molecules. Experiments show that the model can effectively extract the features of proteins and small molecules and outperforms other traditional methods on the data provided by a drug discovery and development company.

关键词： Amino acids Feature extraction Drugs Protein sequence Chemicals Compounds

来源：评论

学校读者我要写书评

暂无评论

Speech Emotion Recognition Based on Image Enhancement 14

Speech Emotion Recognition Based on Image Enhancement

引用

14th IEEE International Conference on intelligent Systems and Knowledge Engineering, ISKE 2019

作者： Wang, Dongyan Dong, Jing Zhou, Dongsheng Wei, Xiaopeng Zhang, Qiang Ministry of Education Dalian University Key Laboratory of Advanced Design and Intelligent Computing Dalian China Dalian University of Technology School of Computer Science and Technology Dalian China

ISBN: (纸本)9781728123486

The performance of an emotion recognition system is determined by the quality of emotional features. In this paper, we propose a feature optimization algorithm based on image enhancement and present a convolutional recurrent model to realize emotional recognition of natural speech. For three-dimensional (3-D) log-Mel spectrum and 3-D spectrogram features, the fast gamma transformation with an adaptive threshold is adopted for feature enhancement to make full use of the dynamic characteristics of non-stationary speech signals. Meanwhile, the model combining Convolutional Neural Network (CNN) with the rectangular kernels and Long Short-Term Memory (LSTM) is used to complete speech emotion recognition tasks. Experiments are carried out on two public emotional datasets, and results demonstrate the good generalization ability and recognition performance of our proposed model. © 2019 IEEE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

A molecular device: A DNA molecular lock driven by the nicking enzymes

引用

Computational and structural biotechnology journal 2020年 18卷 2107-2116页

作者： Xiaokang Zhang Qiang Zhang Yuan Liu Bin Wang Shihua Zhou Key Laboratory of Advanced Design and Intelligent Computing Ministry of Education School of Software Engineering Dalian University Dalian 116622 China. School of Computer Science and Technology Dalian University of Technology Dalian 116024 China.

As people are placing more and more importance on information security, how to realize the protection of information has become a hotspot of current research. As a security device, DNA molecular locks have great potential to realize information protection at the molecular level. However, building a highly secure molecular lock is still a serious challenge. Therefore, taking advantage of the DNA strand displacement and enzyme control technology, we constructed a molecular lock with a self-destructive mechanism. This molecular lock is mainly composed of logic circuits and takes nicking enzymes as inputs. To build this molecular lock, we first constructed a series of cascade circuits, including a YES-YES cascade circuit and a YES-AND cascade circuit. Then, an Inhibit logic gate was constructed to explore the inhibitory properties between different combinations of two nicking enzymes. Finally, using the characteristics of mutual inhibition between several enzymes, a DNA molecular lock driven by three nicking enzymes was constructed. In this molecular device, only the correct sequence of nicking enzymes can be input to ensure the normal operation of the molecular lock. Once the wrong password is entered, the device will be destroyed and cannot be recovered, which effectively prevents intruders from cracking the lock through exhaustive methods. The molecular lock has the function of simulating an electronic keyboard, which can realize the protection of information at the molecular level, and provides a new implementation method for building more advanced and complex molecular devices.

关键词： DNA Information Security Molecular Lock Nicking Enzyme

来源：评论

学校读者我要写书评

暂无评论

Humanoid Robot Control Based on Deep Learning 12th

Humanoid Robot Control Based on Deep Learning

引用

12th International Conference on e-Learning and Games, Edutainment 2018

作者： Guo, Bin Yi, Pengfei Zhou, Dongsheng Wei, Xiaopeng Key Laboratory of Advanced Design and Intelligent Computing Dalian University Ministry of Education Dalian116622 China College of Computer Science and Technology Dalian University of Technology Dalian1160243 China

ISBN: (纸本)9783030237110

The direct control of humanoid robot by human motion is an important aspect of current research. Most of these methods are based on additional equipments, such as Kinect, which are usually not equipped on robot. In order to avoid using these external equipments, we explored a robot controlling method only using the low-resolution camera on robot. Firstly, a stacked hourglass network is employed to obtain the accurate 2D heatmap containing positions of human joints from RGB image captured by camera on robot. Then, 3D human poses including coordinates of human body joints are estimated from 2D heatmaps by a method aiming to reconstruct 3D human poses from 2D poses. Finally, the rotation angles of robot are computed according to these 3D coordinates and are transmitted to the robot to reconstruct the original human pose. Using the NAO robot as an example, the experimental results show that the humanoid robot can imitate motions of different human actors in different scenes well while applying our method. © 2019, Springer Nature Switzerland AG.

关键词： Anthropomorphic robots

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：