检索结果-内蒙古大学图书馆

16th Asian Conference on Computer Vision, ACCV 2022

作者： Su, Peng Liu, Rui Dong, Jing Yi, Pengfei Zhou, Dongsheng Key Laboratory of Advanced Design and Intelligent Computing Ministry of Education School of Software Engineering Dalian University Dalian China

ISBN: (纸本)9783031262838

Cross-modality person re-identification between visible and infrared images has become a research hotspot in the image retrieval field due to its potential application scenarios. Existing research usually designs loss functions around samples or sample centers, mainly focusing on reducing cross-modality discrepancy and intra-modality variations. However, the sample-based loss function is susceptible to outliers, and the center-based loss function is not compact enough between features. To address the above issues, we propose a novel loss function called Heterocentric Sample Loss. It optimizes both the sample features and the center of the sample features in the batch. In addition, we also propose a network structure combining spatial and channel features and a random channel enhancement method, which improves feature discrimination and robustness to color changes. Finally, we conduct extensive experiments on the SYSU-MM01 and RegDB datasets to demonstrate the superiority of the proposed method. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Infrared imaging

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

A transformer-based framework for temporal health event prediction with graph-enhanced representations

引用

Journal of Biomedical Informatics 2025年 166卷 104826页

作者： Liu, Tianci Liang, Lizhong Che, Chao Liu, Yunjiong Jin, Bo Key Laboratory of Advanced Design and Intelligent Computing Ministry of Education Dalian University Liaoning Dalian116622 China School of Software Engineering Dalian University Liaoning Dalian116622 China School of Computer Science and Engineering Sun Yat-Sen University Guangdong Guangzhou510006 China Affiliated Hospital of Guangdong Medical University Guangdong Zhanjiang524013 China The Marine Biomedical Research Institute School of Ocean and Tropical Medicine Guangdong Medical University Guangdong Zhanjiang524023 China School of Innovation and Entrepreneurship Dalian University of Technology Liaoning Dalian116024 China

Objective: Deep learning approaches have demonstrated significant potential in predicting temporal health events in recent years. However, existing methods have not fully leveraged the complex interactions among comorbidities and have overlooked imbalances and temporal irregularities in admission records. Methods: This study proposes GLT-Net, a deep learning approach that combines Graph Learning with Transformer framework to tackle these challenges. GLT-Net begins by constructing a patient association graph to generate unique representations for each individual. At the same time, the hierarchical structure of diagnosis codes is utilized to pre-train the diagnosis code embeddings. Subsequently, a comorbidity association matrix is created to illustrate the relationships between comorbidities, and graph neural networks are employed to enhance the feature representations of diagnosis codes. Finally, a Transformer-Encoder framework captures the dependencies in historical admission records by incorporating time information. Results: We demonstrate our approach on two tasks in temporal health event predcition. Experimental results on real-world datasets show that GLT-Net outperforms baseline models in forecasting temporal health events. Additionally, a case study demonstrates the effectiveness of GLT-Net in predicting health events. Conclusion: Understanding progression patterns over time, comorbidity associations, and patient characterization is essential for predicting temporal health events. Our study provides new insights and methods for a deeper understanding of patient health status and disease trends. Moreover, our model can be extended to other data sources, enhancing its versatility. © 2025 Elsevier Inc.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

An Improved Correlation-Based Just-in-Time Modeling Method Using Dynamic Partial Least Squares and Adaptive Local Domain Partition 29

An Improved Correlation-Based Just-in-Time Modeling Method U...

引用

第29届中国控制与决策会议

作者： Xiaolong Chen Zhizhong Mao Runda Jia Dong Xiao Xiaojun Wang College of Information Science & Engineering Northeastern University State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Key Laboratory of Advanced Design and Intelligent Computing Dalian university

ISBN: (纸本)9781509046584

This paper proposes an improved correlation-based just-in-time modeling method,referring to as the ICo JIT,for improving the prediction accuracy and real-time performance of the conventional correlation-based just-in-time(CoJIT) modeling *** achieve this objective,a novel adaptive local domain partition method has been developed based on the moving window technique and the fitting precision,which takes into account the input and output information simultaneously and has potentially the capabilities of obtaining the optimal local domain partition adaptively and capturing new process states by adding new local *** dynamic partial least squares and adaptive local domain partition method,multiple local domains and corresponding local models can be obtained during the offline operation *** online computation burden is reduced compared to CoJIT modeling *** addition,the proposed ICoJIT modeling method can efficiently deal with nonlinearity and time-varying behavior of processes as well as the CoJIT modeling *** effectiveness of the proposed method is demonstrated through a real industrial process dataset in sulfur recovery unit process.

关键词： Soft sensor Correlation-based just-in-time modeling Partial least squares Local domain partition Moving window

来源：评论

学校读者我要写书评

暂无评论

3D Ear Shape Matching Using Joint -Entropy

引用

Journal of Computer Science & Technology 2015年第3期30卷 565-577页

作者：孙晓鹏李思慧韩枫魏小鹏 Institute of Computer Systems School of Computer and Information Technology Liaoning Normal University Dalian 116029 China Beijing Key Laboratory of Intelligent Telecommunications Software and Multimedia Beijing University of Posts and Telecommunications Beijing 100876 China School of Mechanical and Engineering Dalian University of Technology Dalian 116024 China Key Laboratory of Advanced Design and Intelligent Computing Dalian University Dalian 116622 China

In this article, we investigate the use of joint a-entropy for 3D ear matching by incorporating the local shape feature of 3D ears into the joint a-entropy. First, we extract a sut^cient number of key points from the 3D ear point cloud, and fit the neighborhood of each key point to a single-value quadric surface on product parameter regions. Second, we define the local shape feature vector of each key point as the sampling depth set on the parametric node of the quadric surface. Third, for every pair of gallery ear and probe ear, we construct the minimum spanning tree （MST） on their matched key points. Finally, we minimize the total edge weight of MST to estimate its joint a-entropy the smaller the entropy is, the more similar the ear pair is. We present several examples to demonstrate the advantages of our algorithm, including low time complexity, high recognition rate, and high robustness. To the best of our knowledge, it is the first time that, in computer graphics, the classical information theory of joint a-entropy is used to deal with 3D ear shape recognition.

关键词： joint a-entropy minimum spanning tree local shape feature ear matching ear recognition

来源：评论

学校读者我要写书评

暂无评论

designing Uncorrelated Address Constrain for DNA Storage by DMVO Algorithm

引用

IEEE/ACM Transactions on Computational Biology and Bioinformatics 2022年第2期19卷 866-877页

作者： Cao, Ben Ii, Xue Zhang, Xiaokang Wang, Bin Zhang, Qiang Wei, Xiaopeng Key Laboratory of Advanced Design and Intelligent Computing Ministry of Education Ministry of Education School of Software Engineering Dalian University Dalian116622 China School of Computer Science and Technology Dalian University of Technology Dalian116024 China

At present, huge amounts of data are being produced every second, a situation that will gradually overwhelm current storage technology. DNA is a storage medium that features high storage density and long-term stability and is now considered to be a feasible storage solution. Errors are easily made during the sequencing and synthesis of DNA, however. In order to reduce the error rate, novel uncorrelated address constrain are reported, and a Damping Multi-Verse Optimizer (DMVO)algorithm is proposed to construct a set of DNA coding, which is used as the non-payload. The DMVO algorithm exchanges objects through black/white holes in order to achieve a stable state and adds damping factors as disturbances. Compared with previous work, the coding set obtained by the DMVO algorithm is larger in size and of higher quality. The results of this study reveal that the size of the DNA storage coding set obtained by the DMVO algorithm increased by 4-16 percent, and the variance of the melting temperature decreased by 3-18 percent. © 2004-2012 IEEE.

关键词： Damping

来源：评论

学校读者我要写书评

暂无评论

Algorithm of Detecting and Filling Small Holes in Triangular Mesh Surface

引用

Computer Aided Drafting,design and Manufacturing 2014年第4期24卷 33-38页

作者： ZHOU Dong-sheng JIANG Chao DONG Jing LIU Rui Key Laboratory of Advanced Design and Intelligent Computing Ministry of Education Dalian University

In some scattered point cloud triangular mesh restoration algorithm, small triangular mesh holes problem will often affect the quality of the model. For small holes at the details, this paper propose a method for identifying and extracting hollow edge,and use a triangle growth way based on boundary edge angle to fill the empty void. First, according the relationship of the point, side and face of the triangle mesh model to identify the hole, then extracting the holes boundary edge and classifying it. Finally, using a triangle growth method based on holes boundary edge angle to fill each small holes separated from the boundary. Compared with other algorithm of filling holes, this method is high efficiency for small holes of smooth surface,and itimprovesthe quality of the triangular mesh model.

关键词： triangular mesh holes detection holes filling

来源：评论

学校读者我要写书评

暂无评论

An Improved Virtual Spherical Lights Approach for Glossy Illumination

引用

Computer Aided Drafting,design and Manufacturing 2015年第1期25卷 74-80页

作者： DONG Jing WANG Lan BAI Shuang-xue Key Laboratory of Advanced Design and Intelligent Computing (Dalian University) Ministry of Education

Based on a virtual spherical light source method, this paper presents an improved virtual spherical lights approach for glossy illumination by modifying a reflection render equation. First, in order to keep primitive spherical lights, it uses non-zero solid angle integration instead of a geometric item of traditional Instant Radiosity arithmetic. Second, the formula mode for the light energy allocation of VSLs is improved by the energy distribution, in which the radius of sphere is replaced by the radius of inscribed circle generated by the tangent to the non-zero solid angle of cone. Third, the similar function of judging two point visibility takes place of a cosine term in the approximate equations of the VSLs. Experiments show that blurring or disappearing phenomenon that appear in part of right-angle surface scene is avoided.

关键词： virtual spherical lights glossy rendering global illumination rendering

来源：评论

学校读者我要写书评

暂无评论

View-dependent fast real-time generating algorithm for large-scale terrain

引用

Procedia Earth and Planetary Science 2009年第1期1卷 1147-1151页

作者： Jin, Hai-liang Lu, Xiao-ping Liu, Hui-jie Key Laboratory of Mine Spatial Information Technologies State Bureau of Surveying and Mapping Henan Polytechnic University Jiaozuo 454000 China Key Laboratory of Advanced Design and Intelligent Computing Dalian University Dalian 116622 China

In order to eliminate the popping effect of switching among levels of detail and to increase the frame rates with high image quality during the fly-through of large-scale terrain, this paper put forward a new bottom-up modeling strategy, which constructed simplified terrain triangle mesh globally and updated mesh nodes dynamically. Employed hybrid culling technique based on blocks and triangle faces and simplified computing method for screen-space errors to select appropriate terrain nodes rapidly. Then updated the Delaunay terrain mesh by adding nodes, deleting nodes and modifying locally. At the same time achieved self-adaptive control for screen-space error tolerance during the terrain fly-through. Results of simulation experiments demonstrate that the algorithm eliminates popping effect effectively, and has a higher frame rate compared with other algorithms. So it is particularly suitable for close-distance fly-through simulation of large-scale terrain. © 2009.

关键词： Landforms Image quality Visualization Bottom up modeling computing methods Delaunay Error tolerance Frame rate High image quality Large scale terrain Levels of detail Mesh nodes Other algorithms Real time visualization Self adaptive control Simulation experiments Terrain meshes Triangle mesh View dependent

来源：评论

学校读者我要写书评

暂无评论

Image encryption algorithm based on DNA sequences for the big image

Image encryption algorithm based on DNA sequences for the bi...

引用

International Conference on Multimedia Information Networking and Security

作者： Zhou, Shihua Zhang, Qiang Wei, Xiaopeng School of Mechanical Engineering Dalian University of Technology Dalian China Key Laboratory of Advanced Design and Intelligent Computing Dalian University Ministry of Education Dalian China

ISBN: (纸本)9780769542584

With the fast development of Internet technology and information processing technology, the image is commonly transmitted via the Internet. People enjoy the convenience and shortcut, but people have to face to the obsession that the important image information in transmission is easily intercepted by unknown persons or hackers. In order to enhance the image information security, image encryption becomes an important research direction. An image encryption algorithm based on DNA sequences for the big image is presented in this paper. The main purpose of this algorithm is to reduce the big image encryption time. This algorithm is implemented by using the natural DNA sequences as main keys. The first part is the process of pixel scrambling. The original image is confused in the light of the scrambling sequence is generated by the DNA sequence. The second part is the process of pixel replacement. The pixel gray values of the new image and the one of the three encryption templates are generated by the other DNA sequence are XORed bit-by-bit in turn. The experimental result demonstrates that the image encryption algorithm is feasible and simple. Through performance analysis, this algorithm is robust against all kinds of attacks and owns higher security. © 2010 IEEE.

关键词： DNA sequences

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：