检索结果-内蒙古大学图书馆

Universal enzymatic numerical P systems with small number of enzymatic variables

Science China(information Sciences) 2018年第9期61卷 38-49页

作者： Zhiqiang ZHANG Tingfang WU ANDrei P■UN Linqiang PAN Key Laboratory of Image Information Processing and Intelligent Control of Education Ministry of China School of Automation Huazhong University of Science and Technology Department of Computer Science Faculty of Mathematics and Computer ScienceUniversity of Bucharest Bioinformatics Department National Institute of Research and Development for Biological Sciences School of Electric and Information Engineering Zhengzhou University of Light Industry

Numerical P systems(for short, NP systems) are distributed and parallel computing models inspired from the structure of living cells and economics. Enzymatic numerical P systems(for short, ENP systems) are a variant of NP systems, which have been successfully applied in designing and implementing controllers for mobile robots. Since ENP systems were proved to be Turing universal, there has been much work to simplify the universal systems, where the complexity parameters considered are the number of membranes, the degrees of polynomial production functions or the number of variables used in the *** the number of enzymatic variables, which is essential for ENP systems to reach universality, has not been investigated. Here we consider the problem of searching for the smallest number of enzymatic variables needed for universal ENP systems. We prove that for ENP systems as number acceptors working in the all-parallel or one-parallel mode, one enzymatic variable is sufficient to reach universality; while for the one-parallel ENP systems as number generators, two enzymatic variables are sufficient to reach *** results improve the best known results that the numbers of enzymatic variables are 13 and 52 for the all-parallel and one-parallel systems, respectively.

关键词： bio-inspired computing numerical P system mobile robot membrane controller universality

来源：评论

学校读者我要写书评

暂无评论

Realization of remote sensing image segmentation based on K-means clustering

Realization of remote sensing image segmentation based on K-...

引用

第二届材料科学应用与能源材料国际研讨会

作者： Yanhong Wang Denghui Li Yuying Wang Guangxi Key Lab of Wireless Wideband Communication & Signal Processing Institute Of Information Technology of Guilin University of Electronic Technology Key Laboratory of Cognitive Radio and Information Processing Ministry of Education(Guilin University of Electronic Technology) GUET School of Computer Science and Information Security of GUET

Segmentation of remote sensing image is the key technology of positioning ***,we transform the remote sensing image from RGB pace to lab ***,three centres are iterated by using K-means ***,in order to eliminate the influence,the closed operation of mathematical morphology is used to correct the segmented *** results show that it can segment the road from the remote sensing image in lab mode,by using K-means clustering ***,lab mode is more suitable for k-mean than other modes.

关键词： Realization of remote sensing image segmentation based on K-means clustering image

来源：评论

学校读者我要写书评

暂无评论

Synaptic learning with augmented spikes

arXiv

引用

arXiv 2020年

作者： Yu, Qiang Song, Shiming Ma, Chenxiang Pan, Linqiang Tan, Kay Chen Tianjin Key Laboratory of Cognitive Computing and Application College of Intelligence and Computing Tianjin University Tianjin China Key Laboratory of Image Information Processing and Intelligent Control Institute of Artificial Intelligence School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China The Department of Computer Science City University of Hong Kong Hong Kong

Traditional neuron models use analog values for information representation and computation, while all-or-nothing spikes are employed in the spiking ones. With a more brain-like processing paradigm, spiking neurons are more promising for improvements on efficiency and computational capability. They extend the computation of traditional neurons with an additional dimension of time carried by all-or-nothing spikes. Could one benefit from both the accuracy of analog values and the time-processing capability of spikes? In this paper, we introduce a concept of augmented spikes to carry complementary information with spike coefficients in addition to spike latencies. New augmented spiking neuron model and synaptic learning rules are proposed to process and learn patterns of augmented spikes. We provide systematic insight into the properties and characteristics of our methods, including classification of augmented spike patterns, learning capacity, construction of causality, feature detection, robustness and applicability to practical tasks such as acoustic and visual pattern recognition. The remarkable results highlight the effectiveness and potential merits of our methods. Importantly, our augmented approaches are versatile and can be easily generalized to other spike-based systems, contributing to a potential development for them including neuromorphic computing. Copyright © 2020, The Authors. All rights reserved.

关键词： Neurons

来源：评论

学校读者我要写书评

暂无评论

Spectral-Spatial Weighted Sparse Nonnegative Tensor Factorization for Hyperspectral Unmixing

Spectral-Spatial Weighted Sparse Nonnegative Tensor Factoriz...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Shaoquan Zhang Guorong Zhang Chengzhi Deng Jun Li Shengqian Wang Jun Wang Antonio Plaza Jiangxi Province Key Laboratory of Water Information Cooperative Sensing and Intelligent Processing Nanchang Institute of Technology Nanchang China Guangdong Provincial Key Laboratory of Urbanization and Geo-simulation School of Geography and Planning Sun Yat-sen University Guangzhou China Hyperspectral Computing Laboratory Escuela Politécnica University of Extremadura Cáceres Spain

ISBN: (数字)9781728163741

ISBN: (纸本)9781728163758

Hyperspectral unmixing aims to decompose a hyperspectral image (HSI) into a collection of constituent materials, or end-members, and their corresponding abundance fractions. Recently, nonnegative tensor factorization (NTF)-based spectral unmixing methods have attracted significant attention owing to their outstanding performance when representing an HSI without any information loss. However, tensor factorization-based HSI methods do not fully exploit the spatial contextual information present in the scene. Besides, these approaches are sensitive to low signal-to-noise ratio (SNR) in HSIs. To address this limitation, we propose a new spectral-spatial weighted sparse nonnegative tensor factorization (SSWNTF) method to preserve the spatial details in the abundance maps via the spectral and spatial weighting factors. Our experiments with simulated data sets certified that the proposed method outperforms other advanced methods.

关键词： Hyperspectral imaging Tensors Signal to noise ratio Signal processing algorithms Matrix decomposition Sparse matrices Noise measurement

来源：评论

学校读者我要写书评

暂无评论

Tackling Instance-Dependent label Noise via a Universal Probabilistic Model

arXiv

引用

arXiv 2021年

作者： Wang, Qizhou Han, Bo Liu, Tongliang Niu, Gang Yang, Jian Gong, Chen Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of MoE School of Computer Science and Engineering Nanjing University of Science and Technology China Department of Computer Science Hong Kong Baptist University Hong Kong Trustworthy Machine Learning Lab School of Computer Science Faculty of Engineering The University of Sydney Australia Japan Department of Computing Hong Kong Polytechnic University Hong Kong

The drastic increase of data quantity often brings the severe decrease of data quality, such as incorrect label annotations, which poses a great challenge for robustly training Deep Neural Networks (DNNs). Existing learning methods with label noise either employ ad-hoc heuristics or restrict to specific noise assumptions. However, more general situations, such as instance-dependent label noise, have not been fully explored, as scarce studies focus on their label corruption process. By categorizing instances into confusing and unconfusing instances, this paper proposes a simple yet universal probabilistic model, which explicitly relates noisy labels to their instances. The resultant model can be realized by DNNs, where the training procedure is accomplished by employing an alternating optimization algorithm. Experiments on datasets with both synthetic and real-world label noise verify that the proposed method yields significant improvements on robustness over state-of-the-art counterparts. Copyright © 2021, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Motif Discovery via Convolutional Networks with K-mer Embedding 15th

Motif Discovery via Convolutional Networks with K-mer Embedd...

引用

15th International Conference on intelligent Computing, ICIC 2019

作者： Wang, Dailun Zhang, Qinhu Yuan, Chang-An Qin, Xiao Huang, Zhi-Kai Shang, Li Institute of Machine Learning and Systems Biology School of Electronics and Information Engineering Tongji University Shanghai China Science Computing and Intelligent Information Processing of GuangXi Higher Education Key Laboratory Nanning Normal University NanningGuangxi China College of Mechanical and Electrical Engineering Nanchang Institute of Technology NanchangJiangxi330099 China Department of Communication Technology College of Electronic Information Engineering Suzhou Vocational University SuzhouJiangsu215104 China

ISBN: (纸本)9783030269685

With the rapid development of deep learning, some discriminative motif discovery methods based on deep neural network are gradually becoming the mainstream, which also bringing huge improvement of prediction accuracy. In this paper, we propose a convolutional neural network based architecture (eCNN), combining embedding layer with GloVe. Firstly, eCNN divides each single sequence of ChIP-seq datasets into multiple subsequences called k-mers by a sliding window, and then encoding k-mers into a relatively low dimension vectors by GloVe, and finally scores each vector using multiple convolutional networks. The experiment shows that our architecture can get good results on the task of motif discovery. © 2019, Springer Nature Switzerland AG.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Leaf Recognition Based on Capsule Network 15th

Leaf Recognition Based on Capsule Network

引用

15th International Conference on intelligent Computing, ICIC 2019

作者： Zheng, Yang Yuan, Chang-An Shang, Li Huang, Zhi-Kai Institute of Machine Learning and Systems Biology School of Electronics and Information Engineering Tongji University Shanghai China Science Computing and Intelligent Information Processing of GuangXi Higher Education Key Laboratory Nanning Normal University NanningGuangxi China Department of Communication Technology College of Electronic Information Engineering Suzhou Vocational University SuzhouJiangsu215104 China College of Mechanical and Electrical Engineering Nanchang Institute of Technology NanchangJiangxi330099 China

ISBN: (纸本)9783030267629

Plant is an indispensable part of human life, so it is very important to identify and protect plants. Convolutional neural network is a commonly used neural network for image recognition. However, convolutional neural network has huge defects. In order to avoid the defects of convolutional neural network, this paper adopts a new type of neural network: capsule neural network to complete plant leaf recognition. The experiment shows that the capsule neural network has a more effective recognition rate than the common neural network in plant leaf recognition. © 2019, Springer Nature Switzerland AG.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Machine learning for diagnosis of coronary artery disease in computed tomography angiography:A survey

引用

Artificial Intelligence in Medical Imaging 2020年第1期1卷 31-39页

作者： Feng-Jun Zhao Si-Qi Fan Jing-Fang Ren Karen M von Deneen Xiao-Wei He Xue-Li Chen School of Information Science and Technology Northwest UniversityXi’an 710069Shaanxi ProvinceChina Xi’an Key Lab of Radiomics and Intelligent Perception Northwest UniversityXi’an 710069Shaanxi ProvinceChina Engineering Research Center of Molecular and Neuro Imaging Ministry of EducationSchool of Life Science and TechnologyXidian UniversityXi’an 710126Shaanxi ProvinceChina

Coronary artery disease(CAD)has become a major illness endangering human *** mainly manifests as atherosclerotic plaques,especially vulnerable plaques without obvious symptoms in the early *** a rupture occurs,it will lead to severe coronary stenosis,which in turn may trigger a major adverse cardiovascular *** tomography angiography(CTA)has become a standard diagnostic tool for early screening of coronary plaque and stenosis due to its advantages in high resolution,noninvasiveness,and three-dimensional ***,manual examination of CTA images by radiologists has been proven to be tedious and time-consuming,which might also lead to intra-and interobserver ***,many machine learning algorithms have enabled the(semi-)automatic diagnosis of CAD by extracting quantitative features from CTA *** paper provides a survey of these machine learning algorithms for the diagnosis of CAD in CTA images,including coronary artery extraction,coronary plaque detection,vulnerable plaque identification,and coronary stenosis *** included articles were published within this decade and are found in the Web of *** wish to give readers a glimpse of the current status,challenges,and perspectives of these machine learning-based analysis methods for automatic CAD diagnosis.

关键词： Machine learning Deep learning Coronary artery disease Atherosclerotic plaque Vulnerability Stenosis Segmentation Computed tomography angiography

来源：评论

学校读者我要写书评

暂无评论

Trust-based distributed kalman filter estimation fusion under malicious cyber attacks 21

Trust-based distributed kalman filter estimation fusion unde...

引用

21st IEEE International Conference on High Performance Computing and Communications, 17th IEEE International Conference on Smart City and 5th IEEE International Conference on Data Science and Systems, HPCC/SmartCity/DSS 2019

作者： Chen, Yanping Ma, Long Xia, Hong Gao, Cong Wang, Zhongmin Yu, Zhong School of Computer Science AND Technology Xi'an University of Posts and Telecommunications Xi'an710121 China Shananxi Key Laboratory of Network Data Analysis and Intelligent Processing Xi'an University of Posts and Telecommunications Xi'an710121 China School of Communications and Information Engineering Xi'an University of Posts and Telecommunications Xi'an710121 China

ISBN: (纸本)9781728120584

We consider distributed Kalman filter for dynamic state estimation over wireless sensor networks. It is promising but challenging when network is under cyber attacks. Since the information exchange between nodes, the malicious attacks quickly spread across the entire network, which causing large measurement errors and even to the collapse of sensor networks. Aiming at the malicious network attack, a trust-based distributed processing frame is proposed. Which allows neighbor nodes to exchange information, and a series of trusted nodes are found using truth discovery. As a demonstration, distributed Cooperative Localization is considered, and numerical results are provided to evaluate the performance of the proposed approach by considering random, false data injection and replay attacks. © 2019 IEEE.

关键词： Kalman filters

来源：评论

学校读者我要写书评

暂无评论

A recurrent Gaussian process regression model with composite kernel for industrial process quality prediction

A recurrent Gaussian process regression model with composite...

引用

2019 International Conference on Networking and Network Applications, NaNA 2019

作者： Chen, Yanping Gao, Cong Yang, Weihui Wang, Zhongmin Yu, Zhong Xia, Hong School of Computer Science and Technology Xi'An University of Posts and Telecommunications Xi'an710121 China Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Xi'An University of Posts and Telecommunications Xi'an710121 China School of Communication and Information Engineering Xi'An University of Posts and Telecommunications Xi'an710121 China

ISBN: (纸本)9781728126296

With the blooming development of Industry 4.0, the management of industrial processes has drawn a lot of research attention. We employed the Gaussian process regression model to predict the key indicators of an industrial process. To facilitate the description of the data characteristics in an industrial process, the kernel function is reconstructed with respect to different kinds of data. We propose a novel structure based on the Gaussian process regression model which incorporates the previously predicted values into the input data of subsequent prediction. A series of contrastive experiments are conducted on the Tennessee Eastman process simulator. Experimental results show that the proposed method possesses a higher prediction accuracy than several notable prediction methods. © 2019 IEEE.

关键词： Forecasting

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：