检索结果-内蒙古大学图书馆

IEEE International Conference on Signal and Image Processing (ICSIP)

作者： Lu Ji Rui Liu Dongsheng Zhou Qiang Zhang Xiaopeng Wei Key Laboratory of Advanced Design and Intelligent Computing Ministry of Education School of Software Engineering Dalian University Dalian China School of Computer Science and Technology Dalian University of Technology Dalian China

ISBN: (数字)9781728168968

ISBN: (纸本)9781728168975

Human mocap (motion capture) data has been widely used in many fields. However, influenced by the occlusion and falling, missing of markers is inevitable in optical motion capture system. According to the temporal and spatial characteristics of mocap data, a missing data recovery method based on attention-based LSTM network (A-LSTM) and least-squares (LS) constraint is proposed in this paper. First, the LSTM is chosen as the basic network to estimate the position of the missing markers, in which an attention mechanism is introduced to learn the temporal continuity of human mocap data. Then, a space affine transformation based on least-squares fitting is adopted as the spatial constraint to refine the estimated positions, after which the restored error can be reduced significantly. Experiments show that the proposed A-LSTM+LS method is robust to the length of missing gap and the number of missing markers. Under the same conditions, our method achieves smaller restore error than the state of the art.

关键词： Legged locomotion Deep learning Image recognition Correlation Fitting Neural networks Image restoration

来源：评论

学校读者我要写书评

暂无评论

A Weighting Possibilistic Fuzzy C-Means Algorithm for Interval Granularity 17th

A Weighting Possibilistic Fuzzy C-Means Algorithm for Interv...

引用

17th CCF Conference on Computer Supported Cooperative Work and Social computing, ChineseCSCW 2022

作者： Tang, Yiming Xi, Lei Wu, Wenbin Wu, Xi Li, Shujie Chen, Rui Anhui Province Key Laboratory of Affective Computing and Advanced Intelligent Machine School of Computer and Information Hefei University of Technology Anhui Hefei230601 China Engineering Research Center of Safety Critical Industry Measure and Control Technology Ministry of Education Hefei University of Technology Anhui Hefei230601 China

ISBN: (纸本)9789819923847

Granular clustering is an emerging branch in the field of clustering. However, the existing granular clustering algorithms are still immature in terms of weight setting of granular data and noise resistance. In this study, a weighting possibilistic fuzzy c-means algorithm for interval granularity (WPFCM-IG) is proposed. To begin with, a new weight setting method for interval granular data is given. The principle of justifiable granularity is used as the evaluation criterion of granular data, and a weight is assigned to each granular data from two perspectives of coverage and specificity to measure the quality of the granular data. In addition, the idea of possibilistic clustering is introduced, which is helpful to improve the noise resistance. And, with the proposed weights of interval granular data, the influence of data with smaller weights on the clustering results can be reduced during the clustering process. Based upon these ideas, the WPFCM-IG algorithm is put forward, and its core idea, formula derivation and implementation process are described. Finally, the performance of the proposed algorithm is verified by comparison experiments on the artificial and UCI datasets. The experimental results show that the WPFCM-IG algorithm is better than other advanced algorithms in this field in terms of reconstruction error. Next, the WPFCM-IG algorithm is smoother than other algorithms on the collaborative relationship curve between the fuzzy coefficient and the reconstruction error, so WPFCM-IG can better optimize the fuzzy coefficient. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Fuzzy clustering

来源：评论

学校读者我要写书评

暂无评论

On Interval Perturbation of the ɑ-Symmetric Implicational Algorithm 2nd

On Interval Perturbation of the ɑ-Symmetric Implicational A...

引用

2nd International Conference on Artificial Intelligence Logic and Applications, AILA 2022

作者： Tang, Yiming Han, Jianghui Bao, Guangqing Chen, Rui Anhui Province Key Laboratory of Affective Computing and Advanced Intelligent Machine School of Computer and Information Hefei University of Technology Anhui Hefei230601 China Engineering Research Center of Safety Critical Industry Measure and Control Technology Ministry of Education Hefei University of Technology Anhui Hefei230601 China

ISBN: (纸本)9789811975097

Perturbation is an important property of fuzzy reasoning algorithms. It is an important task to estimate the upper and lower bounds of the output after a perturbation (such as an interval perturbation) is given to the input. In this study, the interval perturbation problem of a fuzzy reasoning algorithm, i.e., the ɑ-symmetric implicational algorithm, is researched systematically. For FMP (Fuzzy Modus Ponens) and FMT (Fuzzy Modus Tollens) problems of fuzzy reasoning, aiming at the case of a single rule, the estimation for the upper and lower bounds are obtained for the input interval disturbance, in which R-implications and (S, N)-implications are mainly employed. Then the stability is verified on account of the upper and lower bounds. Following that, for the multi-rule case, the upper and lower bounds of the output are also given, and the corresponding stability is validated. In conclusion, it is found that the ɑ-symmetric implicational algorithm has good stability. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Fuzzy inference

来源：评论

学校读者我要写书评

暂无评论

MFN: Explainable DNA triple helixes Stabilized design based on mCGR and flow network

MFN: Explainable DNA triple helixes Stabilized Design based ...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Xiaoru Wen Lijun Sun Lei Xie Yanfen Zheng Ben Cao Bin Wang Key Laboratory of Advanced Design and Intelligent Computing Ministry of Education School of Software Engineering Dalian University Dalian China School of Computer Science and Technology Dalian University of Technology Dalian China

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

DNA triple helix structure, as a highly specific gene targeting tool, enable gene regulation by precisely identifying and binding to target DNA sequences. However, the limits of design quality and efficiency affect their wide application in gene therapy. Therefore, in this paper, we propose an antiparallel DNA triple helixes design method-MFN based on matrix chaotic game representation (mCGR) and flow network. Leveraging the structural characteristics of DNA sequences, this method employs the mCGR algorithm to construct an initial matrix, generating a set of DNA sequences that conform to foundational constraints. Then, these sequences are mapped as stream network nodes to screen crosstalk structures by path search, and the whole process is observable and interpretable. Experimental results show that MFN significantly improves the design efficiency of triple helix structure and reduces crosstalk phenomenon. Wet experiments further verify the effectiveness of the method. In summary, MFN achieves an efficient and high-quality design of DNA triple helixes and provides a new idea for targeted gene therapy.

关键词： Scalability design methodology DNA Crosstalk Genomics Games Reliability engineering Regulation Gene therapy Bioinformatics

来源：评论

学校读者我要写书评

暂无评论

Positive-Unlabeled Learning with Field of View Consistency for Histology Image Segmentation 1

引用

13th International Conference on Frontier computing, FC 2023

作者： Jia, Xiaoqi Fu, Chong Hou, Jiaxin Qin, Wenjian School of Computer Science and Engineering Northeastern University Shenyang110819 China Key Laboratory of Intelligent Computing in Medical Image Ministry of Education Northeastern University Shenyang110819 China Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China Shenzhen College of Advanced Technology University of Chinese Academy of Sciences Shenzhen518055 China

ISBN: (数字)9789819993420

ISBN: (纸本)9789819993413

Histology image annotation is costly and time-consuming. Utilizing Positive and Unlabeled (PU) data for model training offers a more resource-efficient alternative. However, previous methods for PU learning suffer from the noise arising from label assignment to unlabeled data. We observe that predictions on noisy data lack consistency under data augmentation. In this paper, we present Field of View (FoV) consistency regularization for PU segmentation in histology images, which effectively reduces the noise influence by promoting consistent predictions across varying FoVs. Using only 20% of positive labels on the Glas Dataset, our approach outperforms previous methods, achieving a Dice score of 90.69%-almost reaching the fully supervised result of 93.30%. Source code is available at: https://***/lzaya/PU_with_FoV. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2024.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Compactness and Separateness Driven Fuzzy Clustering Validity Index Called TLW 18th

Compactness and Separateness Driven Fuzzy Clustering Validit...

引用

18th CCF Conference on Computer Supported Cooperative Work and Social computing, ChineseCSCW 2023

作者： Tang, Yiming Wang, Xiang Li, Bing Hu, Xianghui Xie, Wenjun Anhui Province Key Laboratory of Affective Computing and Advanced Intelligent Machine School of Computer and Information Hefei University of Technology Anhui Hefei230601 China Engineering Research Center of Safety Critical Industry Measure and Control Technology Ministry of Education Hefei University of Technology Anhui Hefei230601 China

ISBN: (纸本)9789819996391

The design of validity index of fuzzy clustering has always been a historical problem in fuzzy clustering field. When the distribution of cluster centers is very close, it is difficult for the existing fuzzy clustering validity indexes to obtain a reasonable cluster number, and the separation mechanism of these indexes is too simple. In order to solve the above problems, we propose a novel fuzzy clustering validity index called TLW (Tang-Li-Wang) index. Firstly, compactness is expressed as the ratio of the membership weighted distance value to the sample variance of the dataset. Secondly, the sum of the maximum distance between cluster centers and the mean distance is used in separateness, and the sample variance of cluster centers is introduced, and the two are multiplied to describe the separateness. Thirdly, on the basis of considering compactness and separateness, the introduction of cluster number can alleviate the phenomenon that the index value may change monotonically with the increase of cluster number. Finally, the classical FCM (Fuzzy C-Mean) algorithm is used to conduct experiments on indexes. Comparative experiments and analyses were carried out on 17 typical datasets and 12 clustering validity indexes. From the experimental results of normal simple datasets and high-dimensional difficult datasets, the proposed index shows some advantages. All in all, these results verify that the proposed TLW index has better accuracy and stronger stability. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Fuzzy clustering

来源：评论

学校读者我要写书评

暂无评论

A Feature Reduction-Induced Subspace Multiple Kernel Fuzzy Clustering Algorithm 17th

A Feature Reduction-Induced Subspace Multiple Kernel Fuzzy C...

引用

17th CCF Conference on Computer Supported Cooperative Work and Social computing, ChineseCSCW 2022

作者： Tang, Yiming Li, Bing Pan, Zhifu Sun, Xiao Chen, Renhao Anhui Province Key Laboratory of Affective Computing and Advanced Intelligent Machine School of Computer and Information Hefei University of Technology Anhui Hefei230601 China Engineering Research Center of Safety Critical Industry Measure and Control Technology Ministry of Education Hefei University of Technology Anhui Hefei230601 China

ISBN: (纸本)9789819923847

High-dimensional data poses a great challenge to clustering, and subspace clustering algorithms have unique advantages when working with high-dimensional data. However, there are still some difficulties in adapting the nonlinear feature dimension, the selection and collaborative settings of kernel functions. Therefore, in this study, we come up with a feature reduction-induced subspace multiple kernel fuzzy clustering. Firstly, in order to solve the information loss caused by the nonlinear characteristics of the data, the multiple kernel clustering method is introduced, and some nonlinear features of the data are collaboratively mapped to the high-dimensional linear space, so as to better understand the characteristic information of the data. Secondly, due to the complexity of subspace and multiple kernel learning, we introduce the idea of feature reduction, and reduce the data dimension according to the importance of information, which can reduce the complexity of the algorithm on the one hand, and improve the role of important feature attributes in clustering on the other hand. Finally, the proposed RS-MKFC algorithm and the related 6 algorithms are compared on 6 ordinary datasets and 4 high-dimensional datasets, and it is found that the proposed algorithms are superior over the other 6 algorithms. At the same time, we discover the ability of RS-MKFC algorithm to screen important features as well as the function of feature reduction, and good results are achieved. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Fuzzy clustering

来源：评论

学校读者我要写书评

暂无评论

Extended Coprime Arrays with Sum-Difference Coarray for DOA Estimation 5

Extended Coprime Arrays with Sum-Difference Coarray for DOA ...

引用

5th IEEE International Conference on Electronic Information and Communication Technology, ICEICT 2022

作者： Xin, Wei Xu, Lin Gao, Jincheng Li, Yingsong Huang, Zhixiang College of Information and Communication Engineering Harbin Engineering University Harbin150001 China Wuhan Second Ship Design and Research Institute Wuhan China Zhaojin Mining Industry Co. Ltd. Zhaoyuan China Anhui University Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education China

ISBN: (数字)9781665472111

ISBN: (纸本)9781665472111

A modified coprime array (CA) with a name of extended CA (ECA) is presented and constructed to reduce over-lapping sensors between sum and difference coarray using conventional CA (CCA) to get a sum-difference coarray with high degrees- of-freedoms (DOFs). The devised ECA is to shift a sub array of CCA to reduce redundancy and then to flip part of shifted sub array around zero point that is regarded as symmetric center. The onstructed ECA expands the inter-element separations with lower mutual coupling. Numerical simulation are provided to verify superiority of the devised ECA. © 2022 IEEE.

关键词： Direction of arrival

来源：评论

学校读者我要写书评

暂无评论

Four-Analog Computation Based on DNA Strand Displacement

引用

ACS omega 2017年第8期2卷 4143-4160页

作者： Chengye Zou Xiaopeng Wei Qiang Zhang Chanjuan Liu Changjun Zhou Yuan Liu Faculty of Electronic Information and Electrical Engineering Dalian University of Technology Dalian 116024 China. Key Laboratory of Advanced and Intelligent Computing Dalian University Ministry of Education Dalian 116622 China.

DNA strand displacement plays an important role in biological computations. The inherent advantages of parallelism, high storability, and cascading have resulted in increased functional circuit realization of DNA strand displacement on the nanoscale. Herein, we propose an analog computation with minus based on DNA strand displacement. The addition, subtraction, multiplication, and division gates as elementary gates could realize analog computation with minus. The advantages of this proposal are the analog computation with negative value and division computation. In this article, we provide the designs and principles of these elementary gates and demonstrate gate performance by simulation. Furthermore, to show the cascade property of gates, we computed a polynomial as an example by these gates.

关键词： Equilibrium Genetics Circuits Addition reactions Reaction rates

来源：评论

学校读者我要写书评

暂无评论

Reversible data hiding in encrypted images with Two-MSB prediction 10

Reversible data hiding in encrypted images with Two-MSB pred...

引用

10th IEEE International Workshop on Information Forensics and Security, WIFS 2018

作者： Puyang, Yi Yin, Zhaoxia Qian, Zhenxing Key Laboratory of Intelligent Computing Signal Processing Ministry of Education Anhui University Hefei230601 China Department of Computer Science Purdue University West lafayette47906 United States Shanghai Institute for Advanced Communication and Data Science School of Communication and Information Engineering Shanghai University Shanghai200072 China

ISBN: (纸本)9781538665367

In recent years, reversible data hiding in encrypted images (RDHEI) that embeds additional data into the encrypted image content has received more and more attention. In previous RDHEI methods, there is no one considering the correlation between neighboring pixels. In this paper, to better explore the correlation between neighbor pixels, a novel reversible data hiding method in encrypted images with two-MSB (MSB and second MSB) prediction is proposed. After analyzing the original image content and detecting all the possible prediction errors, we encrypt the original image content using the bitwise exclusive-or (XOR) operation and highlight prediction error based on the error location binary map. Finally, all available pixels are embedded with additional data by two-MSB substitution. In our method, reversibility, separability and error-free data extraction are realized. The experimental results show that the proposed method providing a higher embedding rate and better quality of directly decrypted image compared with other start-of-the-art methods. © 2018 IEEE.

关键词： Pixels

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：