检索结果-内蒙古大学图书馆

Uncertainty estimation by boosting with Gaussian process for expensive optimization problems

Applied Soft Computing 2025年 180卷

作者： Hanhua Zou Sanyou Zeng Changhe Li Ruwang Jiao Fei Zhao School of Mechanical Engineering and Electronic Information China University of Geosciences Wuhan China School of Artificial Intelligence Anhui University of Science & Technology Hefei China School of Future Science and Engineering Soochow University Suzhou China National Key Laboratory of Blind Signal Processing Chengdu China

In surrogate-assisted evolutionary algorithms (SAEAs), uncertainty measures the confidence level of the predicted fitness and plays an important role in selecting candidate points for expensive evaluation, as evaluating those with a large degree of uncertainty can enhance the exploration ability of algorithms and significantly improve model reliability. Gaussian process (GP) gains great popularity with a predictive variance to estimate uncertainty. However, the performance of GP-assisted SAEAs is still limited with weakened predictions and underutilized uncertainty. In this paper, we propose a novel SAEA that leverages a boosting ensemble with GP as the base learner to enhance optimization performance. First, GP is leveraged to boost a weak learner that captures global trends, refining its prediction in guiding the search. Then, the uncertainty provided by GP is integrated into boosting ensemble model to estimate its overall ensemble uncertainty, enhancing the model reliability and promoting the exploration capabilities. Moreover, a mechanism study is performed through standardized residual and a distance-based metric to have deep insights into search behaviors, demonstrating that the migrated uncertainty basically covers the statistical boundary of Gaussian distribution and contributes to exploitation and exploration trade-off. Experimental results across multiple benchmark problems and an antenna design problem demonstrate that the proposed method significantly enhanced GP-assisted SAEAs in statistical results of the best fitness value and convergence profile without increasing too much running time, particularly in high-dimensional problems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhanced Fixed-Interval Smoothing for Markovian Switching Systems

Enhanced Fixed-Interval Smoothing for Markovian Switching Sy...

引用

International Conference on Information Fusion

作者： Xi Li Yi Liu Le Yang Lyudmila Mihaylova Bing Deng State Key Lab of Complex Electromagnetic Environment Effects on Electronics and Information Systems National University of Defense Technology Changsha China University of Canterbury Christchurch NZ University of Sheffield Sheffield UK National Key Lab of Science and Technology on Blind Signal Processing Chengdu China

ISBN: (纸本)9781665414272

This paper considers the problem of fixed-interval smoothing for Markovian switching systems with multiple linear state-space models. An enhanced algorithm that is capable of accurately approximating the Bayesian optimal smoother is proposed. It utilizes the exact expression for the quotient of two Gaussian densities to help solve the backward-time recursive equations of Bayesian smoothing, and computes the joint posterior of the state vector and model index. The proposed algorithm only involves the approximation of each model-matched state posterior, which is a Gaussian mixture, with a single Gaussian density for maintaining computational tractability in retrodiction. The validity of the newly developed smoother is verified using a simulated maneuvering target tracking task.

关键词： Time-frequency analysis Smoothing methods Target tracking Switching systems Time difference of arrival Computational modeling Approximation algorithms

来源：评论

学校读者我要写书评

暂无评论

Active learning for spam email classification 2

Active learning for spam email classification

引用

2nd International Conference on Algorithms, Computing and Artificial Intelligence, ACAI 2019

作者： Chen, Zheng Tao, Ruiwen Wu, Xiaoyang Wei, Zhimin Luo, Xiao School of Information and Software Engineering University of Electronic Science and Technology of China China National Key Laboratory of Science and Technology on Blind Signal Processing Chengdu Sichuan China

ISBN: (纸本)9781450372619

Deep learning has yielded state-of-the-art performance on text classification tasks. In this paper, a new neural network based on Long-Short-Term-Memory model is applied to classify spam emails. Using deep learning method to classify spam emails requires large amounts of labeled data. To solve this problem, active learning method is used to reduce labeling cost and increase model adaptability. In this paper, it is found that the new model performs better than standard CNNs and RNNs on email classification task, and active learning methods can match state-of-the-art performance with just 10% of the labeled data. © 2019 ACM.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

An Information Quantity-Based Uncertainty Measure to Incomplete Numerical Systems 1

引用

9th International Conference on Fuzzy Information and Engineering, ICFIE 2017

作者： Guo, Xin Xiang, Yingzhuo Shu, Lan School of Mathematical Sciences University of Electronic Science and Technology of China Chengdu611731 China National Key Laboratory of Science and Technology on Blind Signal Processing Chengdu610041 China

ISBN: (数字)9783030027773

ISBN: (纸本)9783030027766

The uncertainty measure plays an important role in the analysis of data. At present, many uncertain measures for incomplete information systems or incomplete decision systems have been developed. However, these measures are mainly aimed at discrete valued information systems, but they are not suitable for real valued data sets. In this paper, we mainly study the uncertainty measurement method of incomplete numerical information systems. By introducing neighborhood tolerant rough sets model, each concept has a neighborhood tolerant subset called neighborhood tolerance granule. Neighborhood tolerance information quantity uncertainty measure is proposed. We then prove that it satisfies non-negativity and monotonicity, giving maximum and minimum values. On this basis, the concept of neighborhood-tolerance joint quantity and neighborhood-tolerance condition quantity is proposed, and the relation between them and neighborhood tolerance information is discussed. Theoretical analysis and experimental results show that, in incomplete numerical information systems, the uncertainty measures we propose are performed better than the neighborhood-tolerance approximation accuracy measure in some case. © 2019, Springer Nature Switzerland AG.

关键词： Information systems

来源：评论

学校读者我要写书评

暂无评论

A signal Synchronization and Pilot-Aided DOA Estimation Method in the presence of Interferences

A Signal Synchronization and Pilot-Aided DOA Estimation Meth...

引用

International Conference on Computer and Communications (ICCC)

作者： Lanxin Wei Siye Wang Wenbo Xu Dong Li Kun Yang Network and Wireless Communication Lab Beijing University of Posts and Telecommunications Beijing China National Key Laboratory of Science and Technology on Blind Signal Processing Shanghai China

ISBN: (数字)9781728186351

ISBN: (纸本)9781728186368

Direction of arrival (DOA) estimation is a fundamental problem in signal processing. The super-resolution spatial spectrum estimation algorithm based on feature decomposition, such as multiple signal classification (MUSIC) and estimating signal parameter via rotational invariance techniques (ESPRIT), has a good performance in high signal-to-interference plus noise ratio (SINR) environment and single interference. However, strong interferences will make DOA estimation error. And the number of angles that can be estimated by these methods is limited by the freedom of the antenna. The existence of multiple interferences will affect accuracy of DOA estimation. To address this problem, in this paper, we propose a novel dual-channel synchronization architecture and a Piloted-Aided DOA estimation method. We improve the matching performance by dual channel synchronization. A new matched filter is designed by using the idea of filter truncation, which reduces the computational resource cost. And a new DOA estimation method is proposed, which can estimate the angle of target signal in the environment of low SINR and multiple interferences. Experiments were performed to verify the performance of the proposed design. Results show that this architecture can greatly reduce the computational complexity. And the method successfully gets the direction of target signal in low SINR environment.

关键词： Direction-of-arrival estimation Estimation signal processing algorithms Interference Computer architecture Synchronization signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Reduced-complexity Transmit Antenna Selection for Spatial Modulation

Reduced-complexity Transmit Antenna Selection for Spatial Mo...

引用

International Conference on Communication technology (ICCT)

作者： Ruotong Zhu Hao Chen Yue Xiao Xinrong Ji Wenqi Tang Yan Zhao UESTC Chengdu China School of Information and Communication Engineering UESTC Chengdu China National Key Laboratory of Science and Technology on Blind Signal Processing Chengdu China

ISBN: (数字)9781728181417

ISBN: (纸本)9781728181424

In this paper, a novel transmit antenna selection (TAS) scheme is conceived for spatial modulation multiple-input multiple-output (SM-MIMO) systems, in order to reduce the search complexity. Compared to the existing TAS schemes, the proposed scheme shows a similar performance to optimal one with lower complexity, by exploring an efficient pruning algorithm for tree search based on a combined criterion. Simulation result indicates that the proposed scheme is capable of balancing the transmission performance and search complexity.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Convergence Analysis of Whale Optimization Algorithm

引用

Journal of Physics: Conference Series 2021年第1期1757卷

作者： Wentao Feng National Key Laboratory of Science and Technology on Blind Signal Processing Chengdu Sichuan 610041 China

The whale optimization algorithm (WOA) has been widely used in different applications. It has simple control parameters and novel population updating mechanism. However, there is few theoretical analysis of WOA and the convergence property of WOA is ambiguity. This paper analyzes the convergence property of WOA by using the Markov chain of the stochastic process theory. The Markov chain model of the WOA algorithm is established. The one step transition probabilities and convergence properties of different population updating mechanisms in WOA are given. It's proved that the convergence property of WOA is determined by its shrinking encircling mechanism. Finally, three algorithms with different population updating mechanisms are tested with thirteen benchmark functions on accuracy and convergence speed. The simulation results on benchmark functions verify the validity of the theoretical analysis of WOA.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Parallax attention for unsupervised stereo correspondence learning

arXiv

引用

arXiv 2020年

作者： Wang, Longguang Guo, Yulan Wang, Yingqian Liang, Zhengfa Lin, Zaiping Yang, Jungang An, Wei China The School of Electronics and Communication Engineering Sun Yat-Sen University Guangzhou510275 China The National Key Laboratory of Science and Technology on Blind Signal Processing China

Stereo image pairs encode 3D scene cues into stereo correspondences between the left and right images. To exploit 3D cues within stereo images, recent CNN based methods commonly use cost volume techniques to capture stereo correspondence over large disparities. However, since disparities can vary significantly for stereo cameras with different baselines, focal lengths and resolutions, the fixed maximum disparity used in cost volume techniques hinders them to handle different stereo image pairs with large disparity variations. In this paper, we propose a generic parallax-attention mechanism (PAM) to capture stereo correspondence regardless of disparity variations. Our PAM integrates epipolar constraints with attention mechanism to calculate feature similarities along the epipolar line to capture stereo correspondence. Based on our PAM, we propose a parallax-attention stereo matching network (PASMnet) and a parallax-attention stereo image super-resolution network (PASSRnet) for stereo matching and stereo image super-resolution tasks. Moreover, we introduce a new and large-scale dataset named Flickr1024 for stereo image super-resolution. Experimental results show that our PAM is generic and can effectively learn stereo correspondence under large disparity variations in an unsupervised manner. Comparative results show that our PASMnet and PASSRnet achieve the state-of-the-art performance. Copyright © 2020, The Authors. All rights reserved.

关键词： Stereo image processing

来源：评论

学校读者我要写书评

暂无评论

Experimental study of mode distortion induced by stimulated Raman scattering in high-power fiber amplifiers

引用

Photonics Research 2020年第4期8卷 595-600页

作者： QIUHUI CHU QIANG SHU ZENG CHEN FENGYUN LI DONGLIN YAN CHAO GUO HONGHUAN LIN JIANJUN WANG FENG JING CHUANXIANG TANG RUMAO TAO Research Center of Laser Fusion China Academy of Engineering PhysicsMianyang 621900China Key Laboratory of Particle&Radiation Imaging(Tsinghua University) Ministry of EducationDepartment of Engineering PhysicsTsinghua UniversityBeijing 100084China National Key Laboratory of Science and Technology on Blind Signal Processing Chengdu 610000China

The experimental investigation of mode distortion induced by stimulated Raman scattering(SRS)in a high-power fiber amplifier,which includes the evolutions of optical spectra,spatial beam profiles,and time-frequency characteristics,has been carried out in ***-frequency characteristics have been studied for the first time,to the best of our knowledge,by using a low-speed camera and high-speed photodiode traces,which revealed that temporal-frequency characteristics of SRS-induced mode distortion are different from traditional dynamic mode instability(MI).The experimental results show that the output beam profile remains stable before the mode distortion occurs and fluctuates obviously after the onset of SRS-induced MI but on a time scale of seconds,which is much lower than that of Yb-gain-induced MI featuring millisecond-level beam profile *** also shows that the mode distortion became measurable in company with the onset of inter-mode four-wave mixing(IM-FWM)when the ratio of Raman light reaches 3%;further,the beam quality factor M2degrades gradually from 1.4 to 2.1 as the ratio of Raman light *** mode distortion is accompanied by an obvious temperature increase of the output passive fiber,which further confirms that the mode distortion originates from *** cause of the mode distortion induced by SRS has been explained in the context of core-pumped SRS effect,and the investigation on the accompanying IM-FWM effect indicates that the main content of the SRSinduced high-order mode is the LP21 mode.

关键词： Experimental mode distortion stimulated Raman scattering in high-power fiber amplifiers Raman

来源：评论

学校读者我要写书评

暂无评论

Speech Language Classification Algorithm Based on Multiple-instance Learning with Negative Sample Cleaning

Speech Language Classification Algorithm Based on Multiple-i...

引用

IEEE Joint International Information technology and Artificial Intelligence Conference (ITAIC)

作者： Jianyi Zhang Wei Xu Jiaqi Yao Jikun Yan Xin Huang College of Information System Engineering PLA Strategic Support Force Information Engineering University Zhengzhou China National Key Laboratory of Science and Technology on Blind Signal Processing Chengdu China

ISBN: (数字)9781728152448

ISBN: (纸本)9781728152455

Speech language classification is an important direction in the field of machine learning. In order to further improve the effect of speech classification, this paper propose a new speech language classification algorithm based on multiple-instance learning with negative instance cleaning, namely NUMI-Biased SVM algorithm. Firstly, extract MFCC features from speech files, regarding each file as an instance bag, and every speech frame as an instance. Secondly, adopt PU learning algorithm to clean negative instances in positive bags to reduce their impact on classification. Finally, multiple-instance learning algorithm is used to classify the speech files. Experiments show that, compared with the SVM algorithm and multiple-instance SVM algorithm, NUMI-Biased-SVM has achieved significant improvement in classification performance.

关键词： Support vector machines Machine learning algorithms Feature extraction Telephone sets Cleaning Classification algorithms Mel frequency cepstral coefficient

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：