检索结果-内蒙古大学图书馆

Reversible Data Hiding Based on DNA computing

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

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

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

Improved Modular Convolution Neural Network for Human Pose Estimation 12th

Improved Modular Convolution Neural Network for Human Pose E...

引用

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

作者： Zhang, Zhengxuan Dong, Jing Zhou, Dongsheng Fang, Xiaoyong Wei, Xiaopeng Key Laboratory of Advanced Design and Intelligent Computing Dalian University Ministry of Education Dalian116622 China School of Computer Science and Technology Dalian University of Technology Dalian1160243 China Research Institute of Human Factors and Safety Engineering Hunan Institute of Technology HengyangHunan Province421002 China

ISBN: (纸本)9783030237110

Human pose estimation in image is an important branch of computer vision and graphics research. In this paper, an improved modular convolution neural network is proposed to solve the problem of human pose estimation in static 2D images. A cascaded three-stage full convolutional network (FCN) can learn the non-linear mapping from image feature space to human pose space in an end-to-end way. In order to improve the accuracy of predicting joints, the method of multi-feature source fusion is adopted to improve the estimation process of the human body posture. The first two stages of the network focus on learning local image features and joints neighborhood pixel features, and these features are merged in the third stage of the network. Finally, the coordinates of human joints are obtained by regression of the merged features. In our experiments, using the strict PCP criteria on the full body pose dataset LSP, the average prediction accuracy of our method is 79.3%. In addition, using the PCKh standard on the upper body pose dataset FLIC, our method achieves an average prediction accuracy of 93% without additional training. © 2019, Springer Nature Switzerland AG.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

design, Analyze, and Simulation of a Bionic Swept-Back Wing Scheme with Force Amplification Mechanism 3

Design, Analyze, and Simulation of a Bionic Swept-Back Wing ...

引用

3rd International Symposium on Aerospace Engineering and Systems, ISAES 2024

作者： Wu, Jiangpeng Du, Huixiang Ma, Xinmeng Li, Manhong Zhao, Libin Hu, Ning Shenyang Aircraft Design and Research Institute Shenyang China School of Mechanical Engineering Hebei University of Technology Tianjin China Key Laboratory of Advanced Intelligent Protective Equipment Technology Ministry of Education Hebei University of Technology Tianjin China

ISBN: (纸本)9798350350418

Compared with traditional aircraft, the variant aircraft can change the shape of its fuselage or wing to adapt to the needs of different flight conditions. Among them, the variable swept-back wing can provide excellent aerodynamic characteristics for the morphing aircraft by adjusting the swept back angle of the wing. Aiming at the problem of the existing variable swept-back wings encroach on the belly space. Based on the principles of mechanism and bionics, this paper innovatively puts forward a design scheme of wing root bending variable swept-wing without encroaching on the belly space and designs a force amplification mechanism, which is reasonable according to the principle of virtual work. It is verified to be able to amplify the force by 130% through a set of eigenvalues. It provides certain references for the design of the variable swept-back wing. © 2024 IEEE.

关键词： Eigenvalues and eigenfunctions

来源：评论

学校读者我要写书评

暂无评论

The Effect of the Number of Sensor Coils on Sensitivity in Electromagnetic Tomography 4

The Effect of the Number of Sensor Coils on Sensitivity in E...

引用

4th International Symposium on Image computing and Digital Medicine, ISICDM 2020

作者： Xu, Siqi Zhao, Qian Li, Liu Li, Nan Tan, Wenjun College of Physical Science and Technology Shenyang Normal University Shenyang China Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen China Key Laboratory of Intelligent Computing in Medical Image Ministry of Education Northeastern University Shenyang China

ISBN: (纸本)9781450389686

Electromagnetic tomography (EMT) is a process tomography based on the principle of electromagnetic induction. It has the advantages of non-intrusive, non-contact and low harm. In the process of image reconstruction, the sensitivity matrix reflects the influence of tiny disturbance on the measured value, which is an important index of image quality. Base on the traditional "O"sensor array structure in this article, Comsol Multiphysics finite element simulation software is used to divide the measured field into several tiny elements. A simulated perturbation method is used to investigate the effect of the number of EMT sensors' midline coils on sensitivity. The sensitivity matrix of sensor arrays with 4 coils ,8 coils ,12 coils ,16 coils and 20 coils is compared by using the method of separation variables. The sensitivity matrix of different coils is imaged by Matlab software. Through comparative analysis, it is concluded that the sensitivity band shape of the coil in the same position is same in different models. All of them are distributed along the arc type between the excitation and detection coils, which presents the middle strong and gradually weakens to the outside. With the increase of the number of coils, the sensitivity band is widened, but the sensitivity value of the central part is slightly weakened. According to this characteristic, it lays a foundation for the practical application of EMT technology and image reconstruction. © 2020 Owner/Author.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Palmprint recognition using fusion of contourlet and dual-tree complex wavelet features

引用

ICIC Express Letters, Part B: Applications 2013年第4期4卷 937-942页

作者： Zhang, Jianxin Liu, Jianyang Zheng, Xiaojun Zhang, Qiang Key Lab of Advanced Design and Intelligent Computing Ministry of Education Dalian University No. 10 Xuefu Ave Jinzhou Xinqu Dalian 116622 China

The palm-lines, including principal lines, wrinkles and ridges with different resolutions and directions, are beneficial to discriminate between two different palms. In this paper, we present a novel palmprint recognition algorithm using the fusion of palmprint contourlet transform (CT) and dual-tree complex wavelet transform (DT-CWT) features. The CT is a nice choice to palmprint recognition due to its contours/curves extraction and multidirectional decomposition capability. However, the limitation of CT is that a small translation in input palmprint may cause large changes of the output coefficients. The DT-CWT, which exhibits approximate shift invariance, is an effective complement to the CT. Thus, we employ CT and DT-CWT to extract the palmprint feature, and then examine them for their individual and combined recognition performances on score levels. Based on the fusion approach, the average EER (1.30%), FAR100 (1.45%) and FAR1000 (2.35%) are achieved on the public PolyU Palmprint Database. The comparative experiment results illuminate that the fusion of CT and DT-CWT is effective to palmprint recognition. © 2013 ISSN 2185-2766.

关键词： Palmprint recognition

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：