检索结果-内蒙古大学图书馆

2024 4th International Conference on Artificial Intelligence and Industrial Technology Applications, AIITA 2024

作者： Yang, Duo Su, Yang Wu, Hongwei Yi, Pengfei Key Laboratory for Advanced Design and Intelligent Computing Ministry of Education School of Mechanical Engineering and Software Engineering Dalian University Dalian116622 China Olympic Circuit Technology Co. Ltd. Guangdong Jiangmen529700 China Co. Ltd. Dalian116622 China

Given the hurdles posed by existing techniques for identifying microscopic offsets in miniature printed circuit boards (PCBs), including their low accuracy and high iteration count, this study presents an innovative approach that measures micrometer offsets by utilizing the ORB feature-guided FREAK descriptor enhancement. It improves matching outcomes with a brute-force matcher and RANSAC via ORB feature extraction to guide FREAK descriptors for better feature uniqueness. A PCB small offset detection algorithm is developed with a homography matrix and a theoretical offset model. A novel distance threshold performance evaluation method for this suggested matching algorithm that objectively evaluates matching results is also proposed in this article. The proposed matching method outperforms alternative algorithms in precision and recall, according to its experiments. This research conducts simulation detection of PCB calibration bare boards and instance verification of real PCB boards by constructing a PCB tiny offset detection experimental system. The results show that micron-level detection precision can be achieved without iteration. © Published under licence by IOP Publishing Ltd.

关键词： Engineering education

来源：评论

学校读者我要写书评

暂无评论

Blockchain-based multi-role healthcare data sharing system 22

Blockchain-based multi-role healthcare data sharing system

引用

22nd IEEE International Conference on E-Health Networking, Application and Services, HEALTHCOM 2020

作者： Yu, Yao Li, Qirui Zhang, Qieshi Hu, Wenjian Liu, Shumei Key Laboratory of Intelligent Computing in Medical Image Ministry of Education Northeastern University Shenyang China School of Computer Science and Engineering Northeastern University Shenyang China Shenzhen Institutes of Advanced Technology Chinese Academy of Science Shenzhen China

ISBN: (纸本)9781728162676

Blockchain has unique advantages in data privacy protection and data integrity. We can solve many security problems, such as the single point of failure and data sharing in the current centralized system through blockchain approach. Existing studies have demonstrated that the application of blockchain in the medical system could improve the patient's medical experience. However, we found that the blockchain-based medical systems didn't consider the problems of long insurance claim cycle and complicated procedures. There are also very few healthcare systems that provide targeted sharing protocols for medical data and personal health data. In this paper, we propose a multi-role healthcare data sharing system framework based on blockchain. In this system, we reduce the storage cost through the collaborative storage of blockchain and IPFS. Then we design a smart contract on insurance to help patients achieve automatic insurance claim. In addition, we design two different sharing protocols to realize the fine management of personal data. The system analysis shows that our proposed blockchain-based multi-role healthcare data sharing system can effectively address the actual needs of users and has perfect performance in data storage, privacy protection, insurance claims and personal data management. © 2021 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Robotic Global Path-Planning Based Modified Genetic Algorithm and A* Algorithm

Robotic Global Path-Planning Based Modified Genetic Algorith...

引用

International Conference on Measuring Technology and Mechatronics Automation, ICMTMA

作者： Cen Zeng Qiang Zhang Xiaopeng Wei Key Laboratory of Advanced Design and Intelligent Computing Ministry of Education Dalian Dalian University China Dalian University of Technology Dalian Liaoning China

ISBN: (纸本)9781424490103

Global path planning for mobile robot using genetic algorithm and A* algorithm is investigated in this paper. The proposed algorithm includes three steps: the MAKLINK graph theory is adopted to establish the free space model of mobile robots firstly, then Dijkstra algorithm is utilized for finding a feasible collision-free path, finally the global optimal path of mobile robots is obtained based on the hybrid algorithm of A* algorithm and genetic algorithm. Experimental results indicate that the proposed algorithm has better performance than Dijkstra algorithm in term of both solution quality and computational time, and thus it is a viable approach to mobile robot global path planning.

关键词： Mobile robots Path planning Gallium Genetic algorithms Encoding Algorithm design and analysis

来源：评论

学校读者我要写书评

暂无评论

Impulsive Control of Heterogeneous Multi-agent Systems with Saturation Constraint and Time Delay

Impulsive Control of Heterogeneous Multi-agent Systems with ...

引用

2024 China Automation Congress, CAC 2024

作者： Jiao, Ranran Li, Bo Chen, Xiangyong Jiang, Xiaowei School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control Intelligent Automation of Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan China School of Finance Anhui University of Finance and Economics Bengbu China Key Laboratory of Complex systems and Intelligent Computing in Universities of Shandong Linyi University Linyi China

ISBN: (纸本)9798350368604

This paper addresses the problem of leader-following consensus in heterogeneous multi-agent systems (HMAS) with input saturation and communication delay. Given the practical differences between leader and follower dimensions, we design virtual leaders to address this problem by allowing actual leaders and followers to communicate with virtual leaders separately, thus enabling indirect communication between actual leaders and followers. Additionally, the control protocol proposed in this paper takes into account the effects of input saturation and time delay that exist in real communication. At last, a simulation example is presented to demonstrate the effectiveness of the designed control protocol. © 2024 IEEE.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Speech emotion recognition using mixed model

引用

ICIC Express Letters 2011年第6期5卷 1987-1994页

作者： Zhao, Lasheng Wei, Xiaopeng Zhang, Qiang Key Laboratory of Advanced Design and Intelligent Computing Ministry of Education Dalian University Dalian Economic Technological Development Zone No. 10 Xuefu Ave Dalian 116622 China

Speech emotion recognition is one of the latest challenges in human-compu-ter interaction. By the comprehensive use of Gaussian mixture model (GMM) and genetic algorithm (GA) techniques, etc., a mixed speech emotion recognition model is presented based on different emotion feature set and multiple classiers combination. First, the different set of features is extracted respectively according to the different speech model, and then, individual classier is designed for each set of features using GMM. Finally, speech emotion is recognized by the combined classier based on GA. Experimental results show that the proposed method can obtain much better performance than the individual classier. © 2011 ISSN 1881-803X.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Reversible Data Hiding Based on DNA computing

引用

Computational Intelligence and Neuroscience 2017年第20170101期2017卷 7276084-7276084页

作者： Wang, Bin Xie, Yingjie Zhou, Shihua Zhou, Changjun Zheng, Xuedong Key Laboratory of Advanced Design and Intelligent Computing Dalian University Ministry of Education Dalian116622 China Applied Technology College Dalian Ocean University Dalian116300 China

Biocomputing, especially DNA, computing has got great development. It is widely used in information security. In this paper, a novel algorithm of reversible data hiding based on DNA computing is proposed. Inspired by the algorithm of histogram modification, which is a classical algorithm for reversible data hiding, we combine it with DNA computing to realize this algorithm based on biological technology. Compared with previous results, our experimental results have significantly improved the ER (Embedding Rate). Furthermore, some PSNR (peak signal-to-noise ratios) of test images are also improved. Experimental results show that it is suitable for protecting the copyright of cover image in DNA-based information security. © 2017 Bin Wang et al.

关键词： Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

A new image encryption algorithm based on encryption template

引用

Journal of Information and Computational Science 2010年第8期7卷 1661-1667页

作者： Zhou, Shihua Zhang, Qiang Wei, Xiaopeng School of Mechanical Engineering Dalian University of Technology Dalian 116024 China Key Laboratory of Advanced Design and Intelligent Computing Dalian University Ministry of Education Dalian 116622 China

In order to enhance the image information security, image encryption becomes an important research direction. A new image encryption algorithm based on encryption template is presented in this paper. This algorithm is implemented by using the natural DNA sequences as main keys and the new defined encryption template as main tool to fully exert the special advantages. Firstly, the original image is confused in the light of the chaotic sequence is generated by Logistic Mapping. Secondly, the encryption template is generated by the new given definition in which DNA sequences and chaos game representation are used. Thirdly, the pixel gray values of the new image and the ones of the encryption template are XORed bit-by-bit. 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. Copyright © 2010 Binary Information Press.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

Contact-based motion graph and its application in locomotion synthesis for virtual actors

引用

International Journal of Industrial and Systems Engineering 2015年第1期20卷 58-68页

作者： Wei, Xiaopeng Yi, Pengfei Zhang, Qiang School of Mechanical and Engineering Dalian University of Technology Dalian116024 China Key Laboratory of Advanced Design and Intelligent Computing Ministry of Education Dalian University Dalian116622 China

To generate foot-skate free locomotion along user defined path for virtual actors, a novel data structure of contact-based motion graph is proposed. At first, sample motions are divided to contact clips according to the number of feet in contact with the ground. Then a directed graph can be built by producing nodes and basic edges based on these clips. After generating edges between nodes from different samples by linear interpolation, the contact-based motion graph can be defined as a strongly connected component of this graph. Applying synthesis strategy designed for nodes and edges, a path on contact-based motion graph can be converted to a smooth foot-skate free motion moving along the given path. The following experiments show the effectiveness of this method. Copyright © 2015 Inderscience Enterprises Ltd.

关键词： Directed graphs

来源：评论

学校读者我要写书评

暂无评论

A novel and fast chaotic cryptosystem for image encryption

引用

Journal of Computational and Theoretical Nanoscience 2014年第3期11卷 731-738页

作者： Wang, Bin Wei, Xiaopeng Zhang, Qiang School of Mechanical and Engineering Dalian University of Technology Dalian 116024 China Key Laboratory of Advanced Design and Intelligent Computing Dalian University Ministry of Education Dalian 116622 China

In recent years, there has been growing interesting in image encryption based on chaotic systems. In order to improve the effect of encryption, a large amount of operations are implemented in the most chaos-based cryptosystems. However, the runtime of chaos-based cryptosystems would be increased with the rise of operations. In this paper, a novel algorithm is proposed to generate cipher key for the permutation-diffusion architecture. The cipher key not only relates to the plain-image, but also the generated time of cipher key is shorter than the conventional method. On the premise of security, a novel and fast permutation-diffusion architecture based on chaotic systems and variable control conditions is proposed. For the sake of increasing the key space and enhancing the security of proposed architecture, variable control conditions used in this cryptosystem as the parameter and initial value of same chaotic system are generated from the cipher key related to the plain-image. So the proposed algorithm can effectively resist the most attacks against permutation-diffusion architectures. Finally, theoretical analyses and numerical experimental results show that the proposed chaos-based cryptosystem possesses high security and sound time of image encryption, which is suitable for protecting the image information Copyright © 2014 American Scientific Publishers.

关键词： Chaotic systems

来源：评论

学校读者我要写书评

暂无评论

DCET-Net: Dual-Stream Convolution Expanded Transformer for Breast Cancer Histopathological Image Classification

DCET-Net: Dual-Stream Convolution Expanded Transformer for B...

引用

2021 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2021

作者： Zou, Ying Chen, Shannan Sun, Qiule Liu, Bin Zhang, Jianxin Dalian University Key Lab of Advanced Design and Intelligent Computing Ministry of Education Dalian China Dalian University of Technology School of Information and Communication Engineering Dalian China Dalian China Dalian Minzu University School of Computer Science and Engineering Dalian China

ISBN: (纸本)9781665401265

Researches on breast cancer histopathological image classification have achieved a great breakthrough using deep backbones of Convolutional Neural Networks (CNNs) in recent years. However, due to the inductive bias of locality, CNNs are unable to effectively extract the global feature information of breast cancer histopathological images, limiting the improvement of the classification results. To overcome this shortcoming, this paper reasonably introduces an extra backbone stream of a pure transformer, which consists of a self-attention mechanism to capture global receptive fields of histopathological images, thereby compensating the locality characteristic of CNNs backbone. Based on two backbone streams of CNN and transformer, a dual-stream network called DCET-Net is proposed, which considers local features and global ones simultaneously, and progressively combines them from these two streams to form the final representations for classification. DCET-Net is extensively evaluated on the representative BreakHis histopathological image dataset, and experimental results demonstrate that it is highly competitive with the state-of-the-art CNN methods in breast cancer histopathological image classification task. © 2021 IEEE.

关键词： Convolutional neural networks

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：