检索结果-内蒙古大学图书馆

Frequency-mixed Single-source Domain Generalization for Medical Image Segmentation

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Li, Heng Li, Haojin Zhao, Wei Fu, Huazhu Su, Xiuyun Hu, Yan Liu, Jiang Research Institute of Trustworthy Autonomous Systems Southern University of Science and Technology Shenzhen China Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China Medical Intelligence and Innovation Academy Southern University of Science and Technology Shenzhen China Southern University of Science and Technology Hospital Shenzhen China Institute of High Performance Computing Agency for Science Technology and Research Singapore Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation Southern University of Science and Technology Shenzhen China

The annotation scarcity of medical image segmentation poses challenges in collecting sufficient training data for deep learning models. Specifically, models trained on limited data may not generalize well to other unseen data domains, resulting in a domain shift issue. Consequently, domain generalization (DG) is developed to boost the performance of segmentation models on unseen domains. However, the DG setup requires multiple source domains, which impedes the efficient deployment of segmentation algorithms in clinical scenarios. To address this challenge and improve the segmentation model's generalizability, we propose a novel approach called the Frequency-mixed Single-source Domain Generalization method (FreeSDG). By analyzing the frequency's effect on domain discrepancy, FreeSDG leverages a mixed frequency spectrum to augment the single-source domain. Additionally, self-supervision is constructed in the domain augmentation to learn robust context-aware representations for the segmentation task. Experimental results on five datasets of three modalities demonstrate the effectiveness of the proposed algorithm. FreeSDG outperforms state-of-the-art methods and significantly improves the segmentation model's generalizability. Therefore, FreeSDG provides a promising solution for enhancing the generalization of medical image segmentation models, especially when annotated data is scarce. The code is available at https://***/liamheng/Non-IID Medical Image Segmentation. Copyright © 2023, The Authors. All rights reserved.

关键词： Deep learning

Spectralhomogeneitycross frequencies can be a quality metric for the large-scale resting EEGpreprocessing

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Hu, Shiang Ruan, Jie Langer, Nicolas Bosch-Bayard, Jorge Lv, Zhao Yao, Dezhong Valdes-Sosa, Pedro Antonio Anhui Province Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Anhui University 111 Jiulong Road Hefei230601 China Methods of Plasticity Research Department of Psychology University of Zurich Zurich Switzerland The Clinical Hospital of Chengdu Brain Science Institute MOE Key Lab for Neuroinformation School of Life Science and Technology University of Electronic Science and Technology of China Chengdu China Cuban Center for Neurocience La Habana Cuba

The brain projectsrequire the collectionof massiveelectrophysiologicaldata,aiming to the longitudinal, sectional,or populational neuroscience *** metrics automatically label the data after centralizedpreprocessing. However, although thewaveforms-basedmetricsarepartially useful, theymay be unreliable by neglecting the spectral profiles. Here, we detected the phenomenon of parallel log spectra(PaLOS)that thescalp EEG power in the log scale were parallel to each otherfrom 10% of 2549 HBNEEG. This phenomenon was reproduced in 8% of 412 PMDT EEG from 4 databases. We designed the PaLOSindex (PaLOSi) to indicate this phenomenon by decomposing the cross-spectraatdifferent frequenciesinto the common principal component spaces. We found that the PaLOS biophysically implied a prominently dominant dipolein the source spacewhich wasimplausible for the resting EEG. And it may be practically resulted from *** with the 1966 normative EEG cross-spectra, theHBN and the PMDT EEG with PaLOS presented generally much higherelectrode pairwise coherences and highersimilarity of coherence-based network patterns, which went against the known frequency dependent characteristic of coherence networks. We suggestthe PaLOSi should lay in the range of0.4-0.7 for large resting EEG quality assurance. Copyright © 2023, The Authors. All rights reserved.

关键词： Quality assurance

Hyperbolic variational graph neural network for modeling dynamic graphs

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Sun, Li Zhang, Zhongbao Zhang, Jiawei Wang, Feiyang Peng, Hao Su, Sen Yu, Philip S. State Key Laboratory of Networking and Switching Technology Beijing University of Posts and Telecommunications China IFM Lab Department of Computer Science Florida State University FL United States Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University China Department of Computer Science University of Illinois ChicagoIL United States

Learning representations for graphs plays a critical role in a wide spectrum of downstream applications. In this paper, we summarize the limitations of the prior works in three folds: representation space, modeling dynamics and modeling uncertainty. To bridge this gap, we propose to learn dynamic graph representation in hyperbolic space, for the first time, which aims to infer stochastic node representations. Working with hyperbolic space, we present a novel Hyperbolic Variational Graph Neural Network, referred to as HVGNN. In particular, to model the dynamics, we introduce a Temporal GNN (TGNN) based on a theoretically grounded time encoding approach. To model the uncertainty, we devise a hyperbolic graph variational autoencoder built upon the proposed TGNN to generate stochastic node representations of hyperbolic normal distributions. Furthermore, we introduce a reparameterisable sampling algorithm for the hyperbolic normal distribution to enable the gradient-based learning of HVGNN. Extensive experiments show that HVGNN outperforms state-of-the-art baselines on real-world datasets. © 2021, CC BY-NC-SA.

关键词： Normal distribution

Detection of trace metals in water by filamentand plasma-grating-induced breakdown spectroscopy

学校读者我要写书评

暂无评论

Advanced Photonics Nexus 2023年第1期2卷 70-79页

作者： Mengyun Hu Fangfang Li Shencheng Shi Yu Qiao Jinman Ge Xiaojun Li Heping Zeng East China Normal University State Key Laboratory of Precision SpectroscopyShanghaiChina Chongqing Institute of East China Normal University Chongqing Key Laboratory of Precision OpticsChongqingChina University of Shanghai for Science and Technology School of Optical-Electrical and Computer EngineeringEngineering Research Center of Optical Instrument and System(Ministry of Education)Shanghai Key Laboratory of Modern Optical SystemShanghaiChina China Academy of Space Technology(Xi’an) National Key Laboratory of Science and Technology on Space MicrowaveXi’anShaanxiChina Shanghai Research Center for Quantum Sciences ShanghaiChina Chongqing Institute for Brain and Intelligence Guangyang Bay LaboratoryChongqingChina

Filament-and plasma-grating-induced breakdown spectroscopy(F-GIBS)was demonstrated as an efficient technique for sensitive detection of metals in water,where plasma gratings were established through synchronized nonlinear interaction of two noncollinear filaments and an additional filament was generated with another fs laser beam propagating along their bisector.A water jet was constructed vertically to the three coplanar filaments,overcoming side effects from violent plasma explosion and bubble *** distinct regimes of different mechanisms were validated for nonlinear couplings of the third filament with plasma *** the third filament was temporally overlapped with the two noncollinear filaments in the interaction zone,all the three filaments participated in synchronous nonlinear interaction and plasma grating structures were altered by the addition of the third *** the third filament was positively or negatively delayed,the as-formed plasma gratings were elongated by the delayed third filament,or plasma gratings were formed in the presence of plasma expansion of the ahead third filament,*** F-GIBS for trace metal detection in water,significant spectral line enhancements were observed.

关键词： laser-induced breakdown spectroscopy filament and plasma-gratings induced breakdown spectroscopy filaments plasma gratings grating induced breakdown spectroscopy

BiKT: Unleashing the potential of GNNs via Bi-directional Knowledge Transfer

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zheng, Shuai Liu, Zhizhe Zhu, Zhenfeng Zhang, Xingxing Li, Jianxin Zhao, Yao The Institute of Information Science Beijing Jiaotong University Beijing100044 China The Beijing Key Laboratory of Advanced Information Science and Network Technology Beijing100044 China Qiyuan Lab Beijing China The Beijing Advanced Innovation Center for Big Data and Brain Computing School of Computer Science and Engineering Beihang University Beijing100083 China

Based on the message-passing paradigm, there has been an amount of research proposing diverse and impressive feature propagation mechanisms to improve the performance of GNNs. However, less focus has been put on feature transformation, another major operation of the message-passing framework. In this paper, we first empirically investigate the performance of the feature transformation operation in several typical GNNs. Unexpectedly, we notice that GNNs do not completely free up the power of the inherent feature transformation operation. By this observation, we propose the Bi-directional Knowledge Transfer (BiKT), a plug-and-play approach to unleash the potential of the feature transformation operations without modifying the original architecture. Taking the feature transformation operation as a derived representation learning model that shares parameters with the original GNN, the direct prediction by this model provides a topological-agnostic knowledge feedback that can further instruct the learning of GNN and the feature transformations therein. On this basis, BiKT not only allows us to acquire knowledge from both the GNN and its derived model but promotes each other by injecting the knowledge into the other. In addition, a theoretical analysis is further provided to demonstrate that BiKT improves the generalization bound of the GNNs from the perspective of domain adaption. An extensive group of experiments on up to 7 datasets with 5 typical GNNs demonstrates that BiKT brings up to 0.5% - 4% performance gain over the original GNN, which means a boosted GNN is obtained. Meanwhile, the derived model also shows a powerful performance to compete with or even surpass the original GNN, enabling us to flexibly apply it independently to some other specific downstream tasks. Copyright © 2023, The Authors. All rights reserved.

关键词： Message passing

A novel data quality assessment framework for vehicular network testbeds 12

学校读者我要写书评

暂无评论

A novel data quality assessment framework for vehicular netw...

12th EAI International Conference on Testbeds and Research Infrastructures for the Development of Networks and Communities, TRIDENTCOM 2017

作者： Tian, Daxin Zhu, Yukai Zhou, Jianshan Duan, Xuting Wang, Yunpeng Song, Jeungeun Rong, Hui Guo, Peng Beihang University Beijing Advanced Innovation Center for Big Data and Brain Computing XueYuan Road No.37 Beijing100191 China China Automotive Technology and Research Center Automotive Engineering Research Institute East Xianfeng Road No.68 Tianjin300300 China Beihang University Beijing Key Laboratory for Cooperative Vehicle Infrastructure Systems and Safety Control School of Transportation Science and Engineering XueYuan Road No.37 Beijing100191 China Jiangsu Province Collaborative Innovation Center of Modern Urban Traffic Technologies Si Pai Lou. 2 Nanjing210096 China School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China

ISBN: (纸本)9781631901577

Big data technique is considered as a powerful tool to exploit all the potential of the Internet of Things and the smart cities. The development of internet of Vehicles (IoV) and wireless communication technologies have boosted diverse applications related to smart cities and Cyber-Physical Systems, but the data quality of vehicular sensors is an important issue due to the high-speed mobile wireless communication environment and physical sensor noise. This paper presents our experiences for big data analytics based on a vehicular network testbed, in terms of sensors data management, multi-dimension data fusion and data quality assessment for the vehicular sensor data. The proposed data quality assessment framework consist of feature extraction based on multi-sensor data fusion and multi-level wavelet transform, as well as a semi-supervised learning based classification algorithm. The comparison experiment shows that the proposed framework and approaches can extract feasible features and solve the unbalanced label problems, which achieve a better assessment effect. Copyright © 2018 EAI.

关键词： Smart city

How do the resting EEG preprocessing states affect the outcomes of postprocessing?

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Hu, Shiang Ruan, Jie Hou, Juan Valdes-Sosa, Pedro Antonio Lv, Zhao Anhui Province Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Anhui University 11 Jiulong Road Hefei230601 China Department of Psychology School of Philosophy Anhui University Hefei230601 China The Clinical Hospital of Chengdu Brain Science Institute MOE Key Lab for Neuroinformation School of Life Science and Technology University of Electronic Science and Technology of China Chengdu China Cuban Center for Neurocience La Habana Cuba

Plenty of artifact removal tools and pipelines have been developed to correct the EEG recordings and discover the values below the waveforms. Without visual inspection from the experts, it is susceptible to derive improper preprocessing states, like the insufficient preprocessed EEG (IPE), and the excessive preprocessed EEG (EPE). However, little is known about the impacts of IPE or EPE on the postprocessing in the frequency, spatial and temporal domains, particularly as to the spectra and the functional connectivity (FC) analysis. Here, the clean EEG (CE) was synthesized as the ground truth based on the New-York head model and the multivariate autoregressive model. Later, the IPE and the EPE were simulated by injecting the Gaussian noise and losing the brain activities, respectively. Then, the impacts on postprocessing were quantified by the deviation caused by the IPE or EPE from the CE as to the 4 temporal statistics, the multichannel power, the cross spectra, the dispersion of source imaging, and the properties of scalp EEG network. Lastly, the association analysis was performed between the PaLOSi metric and the varying trends of postprocessing with the evolution of preprocessing states. As results, compared with CE, it was found that: 1) the temporal statistics under IPE and EPE deviated greatly with more noise injected or more brain activities discarded;2) the IPE power was higher but the EPE power was lower, and the IPE power was almost parallel to that of CE cross all frequencies, while the power difference between the EPE and the CE decreased with higher frequencies;the cross spectra of IPE generally deviated more greatly than the EPE, except for the beta band;3) derived from the 7 Coupling measures, the IPE network had lower transmission efficiency and worse integration ability, while the EPE network had high transmission efficiency and better integration ability. 4) the source activation under IPE distributed more dispersedly with greater strength while t

关键词： Quality control

A Distributed Privacy-Preserving Learning Dynamics in General Social Networks

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Tao, Youming Chen, Shuzhen Li, Feng Yu, Dongxiao Yu, Jiguo Sheng, Hao School of Computer Science and Technology Shandong University Qingdao266237 China Big Data Institute Qilu University of Technology Jinan250353 China State Key Laboratory of Software Development Environment School of Computer Science and Engineering Beihang University Beijing100191 China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing100191 China

In this paper, we study a distributed privacy-preserving learning problem in social networks with general topology. The agents can communicate with each other over the network, which may result in privacy disclosure, since the trustworthiness of the agents cannot be guaranteed. Given a set of options which yield unknown stochastic rewards, each agent is required to learn the best one, aiming at maximizing the resulting expected average cumulative reward. To serve the above goal, we propose a four-staged distributed algorithm which efficiently exploits the collaboration among the agents while preserving the local privacy for each of them. In particular, our algorithm proceeds iteratively, and in every round, each agent i) randomly perturbs its adoption for the privacy-preserving purpose, ii) disseminates the perturbed adoption over the social network in a nearly uniform manner through random walking, iii) selects an option by referring to the perturbed suggestions received from its peers, and iv) decides whether or not to adopt the selected option as preference according to its latest reward feedback. Through solid theoretical analysis, we quantify the trade-off among the number of agents (or communication overhead), privacy preserving and learning utility. We also perform extensive simulations to verify the efficacy of our proposed social learning algorithm. Copyright © 2020, The Authors. All rights reserved.

关键词： Iterative methods

Reinforcement Learning with Dual-Observation for General Video Game Playing

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Hu, Chengpeng Wang, Ziqi Shu, Tianye Tong, Hao Togelius, Julian Yao, Xin Liu, Jialin Southern University of Science and Technology Shenzhen518055 China The Guangdong Provincial Key Laboratory of Brain-Inspired Intelligent Computation Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China The University of Birmingham BirminghamB15 2TT United Kingdom The New York University New York11201 United States

Reinforcement learning algorithms have performed well in playing challenging board and video games. More and more studies focus on improving the generalisation ability of reinforcement learning algorithms. The General Video Game AI Learning Competition aims to develop agents capable of learning to play different game levels that were unseen during training. This paper summarises the five years' General Video Game AI Learning Competition editions. At each edition, three new games were designed. The training and test levels were designed separately in the first three editions. Since 2020, three test levels of each game were generated by perturbing or combining two training levels. Then, we present a novel reinforcement learning technique with dual-observation for general video game playing, assuming that it is more likely to observe similar local information in different levels rather than global information. Instead of directly inputting a single, raw pixel-based screenshot of the current game screen, our proposed general technique takes the encoded, transformed global and local observations of the game screen as two simultaneous inputs, aiming at learning local information for playing new levels. Our proposed technique is implemented with three state-of-the-art reinforcement learning algorithms and tested on the game set of the 2020 General Video Game AI Learning Competition. Ablation studies show the outstanding performance of using encoded, transformed global and local observations as input. Copyright © 2020, The Authors. All rights reserved.

关键词： Reinforcement learning