检索结果-内蒙古大学图书馆

arXiv 2020年

作者： Lyu, Kexin He, Fan Huang, Xiaolin Yang, Jie Chen, Liming Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University MOE Key Laboratory of System Control and Information Processing 800 Dongchuan Road Shanghai200240 China Institute of Medical Robotics Shanghai Jiao Tong University 800 Dongchuan Road Shanghai200240 China Ecole Centrale de Lyon France

Nowadays, more and more datasets are stored in a distributed way for the sake of memory storage or data privacy. The generalized eigenvalue problem (GEP) plays a vital role in a large family of high-dimensional statistical models. However, the existing distributed method for eigenvalue decomposition cannot be applied in GEP for the divergence of the empirical covariance matrix. Here we propose a general distributed GEP framework with one-shot communication for GEP. If the symmetric data covariance has repeated eigenvalues, e.g., in canonical component analysis, we further modify the method for better convergence. The theoretical analysis on approximation error is conducted and the relation to the divergence of the data covariance, the eigenvalues of the empirical data covariance, and the number of local servers is analyzed. Numerical experiments also show the effectiveness of the proposed algorithms. Copyright © 2020, The Authors. All rights reserved.

关键词： Eigenvalues and eigenfunctions

来源：评论

学校读者我要写书评

暂无评论

SMTC-CL: Continuous Learning via Selective Multi-Task Coordination for Adaptive Signal Classification

引用

IEEE Transactions on Cognitive Communications and Networking 2024年

作者： Hao, Xiaoyang Yang, Shuyuan Liu, Ruoyu Feng, Zhixi Peng, Tongqing Huang, Bincheng Xidian University Key Laboratory of Intelligent Perception and Image Understanding Ministry of Education School of Artificial Intelligence Xi'an710071 China Avic Xi'an Flight Automatic Control Research Institute China MeiTuan China China Electronics Technology Group Corporation Institute of Information Science and Technology China

Continuously adaptive signal classification in complex electromagnetic environments is a desired property of realistic intelligent systems. However, the limitation of most existing signal processing tasks and methods lies in their assumption of fixed categories and invariant distributions. In contrast, humans naturally acquire knowledge continuously from data streams, enhancing their capabilities through cross-task knowledge integration and learning from the past. Inspired by this, we propose a continuous learning (CL) method based on selective multi-task coordination (SMTC) to deal with ever-changing task categories and distributions in practical electromagnetic environments (denoted as SMTC-CL). Firstly, we propose a signal task distribution comparison (TDC) method that leverages intra-domain density and inter-domain divergence. TDC selectively activates multiple old tasks to collaboration with the current incremental new task. Secondly, we propose the SMTC method. By revisiting potential collaborative tasks from the past using TDC and formulating different selection strategies based on the context, continuous learners can achieve mutual benefits between past and current tasks in SMTC learning. SMTC can partially alleviate catastrophic forgetting and enable continuous learners to adapt to the changing electromagnetic environment. Based on the signal automatic modulation classification (AMC) and real-world specific emitter identification (SEI) datasets, extensive experimental results validate the effectiveness of our proposed method on a variety of CL scenarios, including varying signal task categories, distributions, and their combinations. © 2015 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Research Progress of Encoder-Decoder Network in image Fusion

SSRN

引用

SSRN 2023年

作者： Zhou, Tao Zhang, Xiangxiang Cheng, Qianru Li, Qi Lu, Huiling School of Computer Science and Engineering North Minzu University Yinchuan750021 China Key Laboratory of Image and Graphics Intelligent Processing of State Ethnic Affairs Commission North Minzu University Yinchuan750021 China School of Science Ningxia Medical University Yinchuan750004 China

A B S T R A C Timage fusion is a research hotspot in the field of computer vision, which obtains complementary information from the different modal images and then presents it in a comprehensive, highly information-cohesive fused image. Encoder-decoder networks are an important technical method in the field of image fusion. This paper reviewed the research status and development of the Encoder-decoder networks in the field of image fusion from the following aspects: Firstly, the18 image fusion-related datasets and the 22 open-source codes of deep learning-based image fusion are summarized. Secondly, the model structure of encoder-decoder networks and the basic principles for image fusion based on the encoder-decoder network are described. Thirdly, encoder-decoder networks fusion models are summarized into 4 aspects: Convolutional Auto-encoder network(CAE Net), Sparse Auto-encoder network(SAE Net), U-shape Encoder-decoder network(U-net) and Variational Auto-encoder network(VAE Net),in U-net, there are 5 types: U-net incorporating residual connection mechanism (Res U-net), U-net incorporating dense connection mechanism (Dens U-net), U-net incorporating multiscale connection mechanism (MS U-net), U-net incorporating attention mechanism (Att U-net) and U-shaped Encoder-decoder networks(U-net) combined with Generative Adversarial Network(GAN U-net). Fourthly, the existing image fusion evaluation metrics are summarized from both subjective and objective aspects. Fifthly, the application of Encoder-decoder network in 5 kinds of image fusion, such as multi-exposure image fusion, multi-focus image fusion, infrared and visible image fusion, medical image fusion and remote sensing image fusion are summarized. Finally, there is a discussion of the main challenges faced by encoder-decoder networks in the image fusion domain and an outlook on future directions. This paper systematically analyzed the application of encoder-decoder networks in the image fusion areas, which has posi

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Multiple-atlas-based automatic sementation of hippocampus for lateralization in temporal lobe epilepsy

Multiple-atlas-based automatic sementation of hippocampus fo...

引用

IEEE International Symposium on Biomedical Imaging

作者： Alireza Akhondi-Asl Kourosh Jafari-Khouzani Hamid Soltanian-Zadeh Image Analysis Laboratory Department of Diagnostic Radiology Henry Ford Health System Detroit MI USA School of Cognitive Sciences Institute of Studies in Theoretical Physics and Mathematics Tehran Iran Control and Intelligent Processing Center of Excellence School of Electrical and Computer Engineering University of Tehran Tehran Iran

ISBN: (纸本)9781424441259

We introduce a 3D segmentation framework which uses principal shapes. The probabilistic energy function of the method is defined based on intensity, tissue type, and location information of the structures using a multiple atlas method. For intensity information, nonparametric probability density function is used which considers intensity relation of different structures. To find a local minimum of the energy function, a two-step optimization strategy is used. In the first step, shape parameters are optimized based on the analytic derivatives of the energy function. In the second step, shapes of the structures are fine-tuned using a level set method. The proposed method is shown to be superior to some popular methods in the literature using a dataset of 64 patients with mesial temporal lobe epilepsy. In addition, the method can be used for lateralization with accuracy close to that of manual segmentation.

关键词： Hippocampus Temporal lobe Epilepsy image segmentation Principal component analysis Shape control Probability density function Level set Skull Algorithm design and analysis

来源：评论

学校读者我要写书评

暂无评论

T-TIME: Test-Time Information Maximization Ensemble for Plug-and-Play BCIs

arXiv

引用

arXiv 2024年

作者： Li, Siyang Wang, Ziwei Luo, Hanbin Ding, Lieyun Wu, Dongrui Ministry of Education Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China Shenzhen Huazhong University of Science and Technology Research Institute Shenzhen China Henan Key Laboratory of Brain Science and Brain Computer Interface Technology School of Electrical and Information Engineering Zhengzhou University China School of Civil and Hydraulic Engineering Huazhong University of Science and Technology Wuhan430074 China

Objective: An electroencephalogram (EEG)-based brain-computer interface (BCI) enables direct communication between the human brain and a computer. Due to individual differences and non-stationarity of EEG signals, such BCIs usually require a subject-specific calibration session before each use, which is time-consuming and user-unfriendly. Transfer learning (TL) has been proposed to shorten or eliminate this calibration, but existing TL approaches mainly consider offline settings, where all unlabeled EEG trials from the new user are available. Methods: This paper proposes Test-Time Information Maximization Ensemble (T-TIME) to accommodate the most challenging online TL scenario, where unlabeled EEG data from the new user arrive in a stream, and immediate classification is performed. T-TIME initializes multiple classifiers from the aligned source data. When an unlabeled test EEG trial arrives, T-TIME first predicts its labels using ensemble learning, and then updates each classifier by conditional entropy minimization and adaptive marginal distribution regularization. Our code is publicized. Results: Extensive experiments on three public motor imagery based BCI datasets demonstrated that T-TIME outperformed about 20 classical and state-of-the-art TL approaches. Significance: To our knowledge, this is the first work on test time adaptation for calibration-free EEG-based BCIs, making plug-and-play BCIs possible. © 2024, CC BY.

关键词： Calibration

来源：评论

学校读者我要写书评

暂无评论

Differential Private Discrete Noise Adding Mechanism: Conditions, Properties and Optimization

arXiv

引用

arXiv 2022年

作者： Qin, Shuying He, Jianping Fang, Chongrong Lam, James The Dept. of Automation Shanghai Jiao Tong University The Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai China The Dept. of Mechanical Engineering The University of Hong Kong Pokfulam Road Hong Kong

Differential privacy is a standard framework to quantify the privacy loss in the data anonymization process. To preserve differential privacy, a random noise adding mechanism is widely adopted, where the trade-off between data privacy level and data utility is of great concern. The privacy and utility properties for the continuous noise adding mechanism have been well studied. However, the related works are insufficient for the discrete random mechanism on discretely distributed data, e.g., traffic data, health records. This paper focuses on the discrete random noise adding mechanisms. We study the basic differential privacy conditions and properties for the general discrete random mechanisms, as well as the trade-off between data privacy and data utility. Specifically, we derive a sufficient and necessary condition for discrete ∊-differential privacy and a sufficient condition for discrete (∊, δ)-differential privacy, with the numerical estimation of differential privacy parameters. These conditions can be applied to analyze the differential privacy properties for the discrete noise adding mechanisms with various kinds of noises. Then, with the differential privacy guarantees, we propose an optimal discrete ∊-differential private noise adding mechanism under the utility-maximization framework, where the utility is characterized by the similarity of the statistical properties between the mechanism's input and output. For this setup, we find that the class of the discrete noise probability distributions in the optimal mechanism is Staircase-shaped. Copyright © 2022, The Authors. All rights reserved.

关键词： Probability distributions

来源：评论

学校读者我要写书评

暂无评论

Prediction of piRNA-mRNA interactions based on an interactive inference network

Prediction of piRNA-mRNA interactions based on an interactiv...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Yajun Liu Ru Li Aimin Li Rong Fei Xie Guo Fang-Xiang Wu Shaanxi Key Laboratory for Network Computing and Security Technology Xi'an University of Technology Xi'an China Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing Xi'an University of Technology Xi'an China Department of Computer Science Department of Mechanical Engineering Division of Biomedical Engineering University of Saskatchewan Saskatoon Canada

As the largest class of small non-coding RNAs, piRNAs primarily present in the reproductive cells of mammals, which influence post-transcriptional processes of mRNAs in multiple ways. Effective methods for predicting piRNA and mRNA target relationships can help identify piRNA functions, investigate the possibility of piRNAs as biomarkers and therapeutic targets. In this study, we propose a computational approach for classifying the relationships of piRNA-mRNA pairs based on an interactive inference network (IIN). First, we gather piRNA-mRNA target data, collect sequence data by position alignment, and construct a benchmark dataset. Furthermore, a reliable negative set is constructed by positive-unlabeled learning. Finally, we view a piRNA and a mRNA sequence as a premise and hypothesis sentence, respectively, and IIN model is used to predict the relationship between them. The experiments demonstrate that our method effectively characterizes piRNA-mRNA interaction and could be beneficial for researchers to investigate piRNA functions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Constrained optimization of nonparametric entropy-based segmentation of brain structures

Constrained optimization of nonparametric entropy-based segm...

引用

IEEE International Symposium on Biomedical Imaging

作者： Alireza Akhondi Asl Hamid Soltanian-Zadeh School of Cognitive Sciences Institute of Studies in Theoretical Physics and Mathematics Tehran Iran Control and Intelligent Processing Center of Excellence (CIPCE) School of Electrical and Computer Engineering University of Tehran Tehran Iran Image Analysis Laboratory Radiology Department Henry Ford Health System Detroit MI USA

We propose a constrained, three-dimensional, nonparametric, entropy-based, coupled, multi-shape approach to segment subcortical brain structures from magnetic resonance images (MRI). The proposed method uses PCA to develop shape models that capture structural variability. It integrates geometrical relationship between different structures into the algorithm by coupling them (limiting their independent deformations). On the other hand, to allow variations among coupled structures, it registers each structure separately when building the shape models. It defines an entropy-based energy function, which is minimized using quasi-Newton algorithm. To this end, probability density functions (pdf) are estimated iteratively using nonparametric Parzen window method. In the optimization algorithm, constraints are used to improve segmentation quality. These constraints are extracted from training data. Sample results are given for the segmentation of caudate, hippocampus, and putamen, illustrating highly superior performance of the proposed method compared to the most similar methods in the literature.

关键词： Constraint optimization Brain Iterative algorithms image segmentation Shape Couplings Magnetic resonance Magnetic resonance imaging Principal component analysis Buildings

来源：评论

学校读者我要写书评

暂无评论

Multi-Wavelength Narrow Linewidth Random Fiber Laser Based on Fiber Bragg Grating Fabry-Perot Filter

Multi-Wavelength Narrow Linewidth Random Fiber Laser Based o...

引用

International Conference on Information Science and Technology (ICIST)

作者： Sokliep Pheng Luo Xiaonan Zhongshuai Wang Yijie Zhu Zetao Jiang School of Information and Communication Guilin University of Electronic Technology Guilin China Guangxi Key Laboratory of Intelligent Processing of Computer Image and Graphics Guilin University of Electronic Technology Guilin China School of Computer Science and Information Security Guilin University of Electronic Technology Guilin China

ISBN: (数字)9781728155586

ISBN: (纸本)9781728155593

Recently, multi-wavelength narrow linewidth random fiber laser has very interested for every researcher in this field, because of their useful advantages application, such as high-resolution spectroscopy and fiber optic sensing. In this paper, the standard single-mode fiber is used to form a half-opened cavity structure for generating the narrow linewidth random fiber laser and used the FBG-FP as a filter to form the narrow linewidth RFL into multi-wavelength. Firstly, we used the Rayleigh scattering that processed as well as in a standard single-mode fiber to provide random distribution feedback at the same time while using erbium-doped fiber (EDF) to provide the gain or amplification for achieving a broadband random laser output. Then, FBG-FP is added to the half-open cavity random laser structure. The multi-wavelength and narrow linewidth RFL can be achieved when the broadband RFL goes through the FBG-FP. In this paper we have generated the multi-wavelength narrow linewidth random fiber laser which has more than 10 wavelengths and the 3dB bandwidth is less than 0.01 nm and the mode separation of each wavelength is 0.04nm.

关键词： Fiber gratings Erbium-doped fiber lasers Optical fiber couplers Optical fiber amplifiers

来源：评论

学校读者我要写书评

暂无评论

Forget less,count better:a domain-incremental self-distillation learning benchmark for lifelong crowd counting

引用

Frontiers of Information Technology & Electronic Engineering 2023年第2期24卷 187-202页

作者： Jiaqi GAO Jingqi LI Hongming SHAN Yanyun QU James ZWANG Fei-Yue WANG Junping ZHANG Shanghai Key Laboratory of Intelligent Information Processing School of Computer ScienceFudan UniversityShanghai 200433China Institute of Science and Technology for Brain-inspired Intelligence Fudan UniversityShanghai 200433China Shanghai Center for Brain Science and Brain-inspired Technology Shanghai 201210China School of Information Science and Technology Xiamen UniversityXiamen 361005China College of Information Sciences and Technology the Pennsylvania State UniversityUniversity ParkPA 16802USA State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China

Crowd counting has important applications in public safety and pandemic control.A robust and practical crowd counting system has to be capable of continuously learning with the newly incoming domain data in real-world scenarios instead of fitting one domain ***-the-shelf methods have some drawbacks when handling multiple domains:(1)the models will achieve limited performance(even drop dramatically)among old domains after training images from new domains due to the discrepancies in intrinsic data distributions from various domains,which is called catastrophic forgetting;(2)the well-trained model in a specific domain achieves imperfect performance among other unseen domains because of domain shift;(3)it leads to linearly increasing storage overhead,either mixing all the data for training or simply training dozens of separate models for different domains when new ones are *** overcome these issues,we investigate a new crowd counting task in incremental domain training setting called lifelong crowd *** goal is to alleviate catastrophic forgetting and improve the generalization ability using a single model updated by the incremental ***,we propose a self-distillation learning framework as a benchmark(forget less,count better,or FLCB)for lifelong crowd counting,which helps the model leverage previous meaningful knowledge in a sustainable manner for better crowd counting to mitigate the forgetting when new data arrive.A new quantitative metric,normalized Backward Transfer(nBwT),is developed to evaluate the forgetting degree of the model in the lifelong learning *** experimental results demonstrate the superiority of our proposed benchmark in achieving a low catastrophic forgetting degree and strong generalization ability.

关键词： Crowd counting Knowledge distillation Lifelong learning

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：