检索结果-内蒙古大学图书馆

4th International Workshop on Human brain and Artificial Intelligence, HBAI 2024

作者： Cao, Siyuan Liang, Chuang Zhu, Qi Jiang, Rongtao Zhang, Daoqiang Calhoun, Vince D. Qi, Shile Department of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing China Key Laboratory of Brain-Machine Intelligence Technology Ministry of Education Nanjing University of Aeronautics and Astronautics Nanjing China MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Nanjing University of Aeronautics and Astronautics Nanjing China Georgia State University Georgia Institute of Technology Emory University AtlantaGA United States Department of Radiology and Biomedical Imaging Yale University New HavenCT United States

ISBN: (纸本)9789819640003

Multimodal fusion offers a complementary perspective for understanding brain function and structure. Nevertheless, most existing multimodal fusion methods are unsupervised and thus ignore the diagnostic information. Previous supervised fusion models stack subjects from different diagnostic groups into a single feature matrix, resulting in potential interference between diagnostic groups. In this study, we propose a group-specific multimodal fusion method, called Group-specific Multiset Canonical Correlation Analysis with Logistic Regression (GMCCALR) that can effectively leverage group specific information by incorporating a logistic regression term into mCCA and utilizing a group-specific fusion strategy. Results in human neuroimaging data show that GMCCALR provide higher diagnostic accuracy across several psychiatric disorders, including schizophrenia, schizoaffective disorder, bipolar disorder and autism spectrum disorder. We also show the identified disorder-specific multimodal patterns are replicable across multiple cohorts. Overall, results demonstrate the reliability and generalizability of the proposed GMCCALR approach and its efficacy for identifying multimodal co-varying diagnostic patterns for psychiatric disorders. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Logistic regression

来源：评论

学校读者我要写书评

暂无评论

Mocpso: A Multi-Objective Cooperative Particle Swarm Optimization Algorithm with Dual Search Strategies

SSRN

引用

SSRN 2023年

作者： Zhang, Yan Li, Bingdong Hong, Wenjing Zhou, Aimin School of Computer Science and Technology East China Normal University 3663 Zhongshan North Road Shanghai200062 China Shanghai Institute of AI for Education East China Normal University 3663 Zhongshan North Road Shanghai200062 China Guangdong Provincial Key Laboratory of Brain-Inspired Intelligent Computation Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China

Particle swarm optimization (PSO) is a popular meta-heuristic method for solving multi-objective optimization problems (MOPs) due to its simplicity and fast convergence. However, most PSOs suffer from limited local exploration and insufficient randomness on large-scale multi-objective optimization problems (LSMOPs), which can lead to poor results in high-dimensional spaces. To address these issues, this paper proposes MOCPSO, a Multi-Objective Cooperative Particle Swarm Optimization Algorithm with Dual Search Strategies. MOCPSO adopts a diversity search strategy (DSS) to increase disturbance and improve the local search range of particles, and a more convergent search strategy (CSS) to speed up particle convergence. Additionally, MOCPSO uses a three-category framework to effectively utilize both DSS and CSS. Experimental results on benchmark LSMOPs with 500, 1000, and 2000 decision variables demonstrate that MOCPSO outperforms existing state-of-the-art large-scale multi-objective evolutionary algorithms on most test instances. © 2023, The Authors. All rights reserved.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Enabling surrogate-assisted evolutionary reinforcement learning via policy embedding

arXiv

引用

arXiv 2023年

作者： Tang, Lan Li, Xiaxi Zhang, Jinyuan Li, Guiying Yang, Peng Tang, Ke Guangdong Provincial Key Laboratory of Brain-Inspired Intelligent Computation Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China Faculty of engineering Shenzhen MSU-BIT university Shenzhen518172 China Research Institute of Trustworthy Autonomous Systems Southern University of Science and Technology Shenzhen518055 China Department of Statistics and Data Science Southern University of Science and Technology Shenzhen518055 China

Evolutionary Reinforcement Learning (ERL) that applying Evolutionary Algorithms (EAs) to optimize the weight parameters of Deep Neural Network (DNN) based policies has been widely regarded as an alternative to traditional reinforcement learning methods. However, the evaluation of the iteratively generated population usually requires a large amount of computational time and can be prohibitively expensive, which may potentially restrict the applicability of ERL. Surrogate is often used to reduce the computational burden of evaluation in EAs. Unfortunately, in ERL, each individual of policy usually represents millions of weights parameters of DNN. This high-dimensional representation of policy has introduced a great challenge to the application of surrogates into ERL to speed up training. This paper proposes a PE-SAERL Framework to at the first time enable surrogate-assisted evolutionary reinforcement learning via policy embedding (PE). Empirical results on 5 Atari games show that the proposed method can perform more efficiently than the four state-of-the-art algorithms. The training process is accelerated up to 7x on tested games, comparing to its counterpart without the surrogate and PE. Copyright © 2023, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Light Radiation Simulation of Micro-LED Array for the Optical Neural interface Targeted Cerebral Cortex in Rhesus Monkey

Light Radiation Simulation of Micro-LED Array for the Optica...

引用

International Winter Workshop on brain-computer interface (BCI)

作者： Lusheng Liu Wenlei Zhang Bo Wen Minjie Wang Aiping Wang Jing Zhang Yuan Zhang Song Le Haifeng Jiang Rongwei Zhai Lihua Zhang Xiaoyang Kang Shanghai Engineering Research Center of AI & Robotics MOE Frontiers Center for Brain Science State Key Laboratory of Medical Neurobiology Institute of AI & Robotics Laboratory for Neural Interface and Brain Computer Interface Engineering Research Center of AI & Robotics Ministry of Education Institute of Meta-Medical Academy for Engineering & Technology Fudan University Shanghai China Ji Hua Laboratory Foshan Guangdong Province China Yiwu Research Institute of Fudan University Chengbei Road Yiwu City Zhejiang China Research Center for Intelligent Sensing Zhejiang Lab Hangzhou China Shanghai Mental Health Center Shanghai China Jiao Tong University School of Medicine Shanghai China Lingang Laboratory Shanghai China

The advanced technology of optogenetics has greatly promoted the development of neuroscience. To further optimize the optical neural interface, understanding the propagation process of light in neural tissues is essential for neuroscience research on the application of LED in optogenetics. In this work, we use TracePro software to build geometric models and simulate LED devices. The Rhesus monkey brain model is established to simulate the neural tissue to analyze the irradiance distribution at a specific location, to obtain the effective lighting range. In addition, we analyzed the influencing factors of the illumination range of the implanted light source device. We believe that the distance between devices should be $1.1 \sim1.2$ times of the light range of the simulation result when the devices fit the brain.

关键词： Neuroscience Shape Simulation Lighting Implants Light emitting diodes Optogenetics

来源：评论

学校读者我要写书评

暂无评论

Highly sensitive mid-infrared upconversion detection based on external-cavity pump enhancement

引用

Advanced Photonics Nexus 2024年第4期3卷 28-35页

作者： Xiaohan Liu Kun Huang Wen Zhang Ben Sun Jianan Fang Yan Liang 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 Shanxi University Collaborative Innovation Center of Extreme OpticsTaiyuanChina University of Shanghai for Science and Technology School of Optical Electrical and Computer EngineeringShanghaiChina Shanghai Research Center for Quantum Sciences ShanghaiChina Chongqing Institute for Brain and Intelligence Guangyang Bay LaboratoryChongqingChina

Sensitive mid-infrared(MIR)detection is in high demand in various applications,ranging from remote sensing,infrared surveillance,and environmental monitoring to industrial *** others,upconversion infrared detectors have recently attracted increasing attention due to their advantageous features of high sensitivity,fast response,and room-temperature ***,it remains challenging to realize high-performance passive MIR sensing due to the stringent requirement of high-power continuouswave ***,we propose and implement a high-efficiency and low-noise MIR upconversion detection system based on pumping enhancement via a low-loss optical ***,a singlelongitudinal-mode pump at 1064 nm is significantly enhanced by a factor of 36,thus allowing for a peak conversion efficiency of up to 22%at an intracavity average power of 55 *** corresponding noise equivalent power is achieved as low as 0.3 fW∕Hz^(1∕2),which indicates at least a 10-fold improvement over previous ***,the involved single-frequency pumping would facilitate high-fidelity spectral mapping,which is particularly attractive for high-precision MIR upconversion spectroscopy in photonstarved scenarios.

关键词： infrared detection single-photon detection upconversion detection

来源：评论

学校读者我要写书评

暂无评论

Learning Representation for Clustering via Prototype Scattering and Positive Sampling

arXiv

引用

arXiv 2021年

作者： Huang, Zhizhong Chen, Jie Zhang, Junping Shan, Hongming The Shanghai Key Lab of Intelligent Information Processing The School of Computer Science Fudan University Shanghai200433 China Institute of Science and Technology for Brain-inspired Intelligence MOE Frontiers Center for Brain Science Key Laboratory of Computational Neuroscience and Brain-Inspired Intelligence Fudan University Shanghai200433 China Shanghai Center for Brain Science and Brain-inspired Technology Shanghai201210 China

Existing deep clustering methods rely on either contrastive or non-contrastive representation learning for downstream clustering task. Contrastive-based methods thanks to negative pairs learn uniform representations for clustering, in which negative pairs, however, may inevitably lead to the class collision issue and consequently compromise the clustering performance. Non-contrastive-based methods, on the other hand, avoid class collision issue, but the resulting non-uniform representations may cause the collapse of clustering. To enjoy the strengths of both worlds, this paper presents a novel end-to-end deep clustering method with prototype scattering and positive sampling, termed ProPos. Specifically, we first maximize the distance between prototypical representations, named prototype scattering loss, which improves the uniformity of representations. Second, we align one augmented view of instance with the sampled neighbors of another view—assumed to be truly positive pair in the embedding space—to improve the within-cluster compactness, termed positive sampling alignment. The strengths of ProPos are avoidable class collision issue, uniform representations, well-separated clusters, and within-cluster compactness. By optimizing ProPos in an end-to-end expectation-maximization framework, extensive experimental results demonstrate that ProPos achieves competing performance on moderate-scale clustering benchmark datasets and establishes new state-of-the-art performance on large-scale datasets. Copyright © 2021, The Authors. All rights reserved.

关键词： Cluster analysis

来源：评论

学校读者我要写书评

暂无评论

Manipulation of Phase Transitions and Electrical Properties of Ba 1-XSr xTiO 3 Thin Films Through Orientation Engineering

SSRN

引用

SSRN 2023年

作者： Lin, Jiamin Guo, Xiangwei Li, Cheng Hong, Zijian Wu, Yongjun Huang, Yuhui School of Materials Science and Engineering State Key Laboratory of Silicon and Advanced Semiconductor Materials Cyrus Tang Center for Sensor Materials and Applications Zhejiang University Hangzhou310027 China Zhejiang Brain-computer Interface Institute Hangzhou311100 China Institute of Advanced Semiconductors & Zhejiang Provincial Key Laboratory of Power Semiconductor Materials and Devices Hangzhou Innovation Center Zhejiang University Zhejiang Hangzhou311200 China

This study investigates the influence of epitaxial orientation on the phase structures and electrical properties of Barium Strontium Titanate ( Ba1-XSrxTiO3 , BST) thin films by employing a thermodynamic model. A comprehensive analysis is conducted, including the construction of strain-concentration and temperature-strain phase diagrams for (001)-, (110)-, and (111)-oriented BST thin films. The results demonstrate that BST thin films with high-index (110) and (111) orientations have a greater tendency to stabilize the low-symmetry ferroelectric phase compared to the low-index (001) orientation. Subsequently, the impact of epitaxial orientation on the piezoelectric and electrocaloric properties is explored based on the constructed phase diagrams. Significantly, enhanced piezoelectric and electrocaloric effects closely related to the epitaxial orientation are observed at the different phase boundaries for BST thin films. These findings have profound implications for future experimental investigations and the design of devices incorporating BST thin films with precise epitaxial orientations and innovative functionalities. © 2023, The Authors. All rights reserved.

关键词： Phase diagrams

来源：评论

学校读者我要写书评

暂无评论

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

arXiv

引用

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

来源：评论

学校读者我要写书评

暂无评论

A Framework Based on Generational and Environmental Response Strategies for Dynamic Multi-objective Optimization

arXiv

引用

arXiv 2022年

作者： Li, Qingya Liu, Xiangzhi Wang, Fuqiang Wang, Shuai Zhang, Peng Wu, Xiaoming Guangdong Provincial Key Laboratory of Brain-Inspired Intelligent Computation Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China Shandong Provincial Key Laboratory of Computer Networks Shandong China Heze Branch Qilu University of Technology Shandong Academy of Sciences Biological Engineering Technology Innovation Center of Shandong Province Shandong China

Due to the dynamics and uncertainty of the dynamic multi-objective optimization problems (DMOPs), it is difficult for algorithms to find a satisfactory solution set before the next environmental change, especially for some complex environments. One reason may be that the information in the environmental static stage can not be used well in the traditional framework. In this paper, a novel framework based on generational and environmental response strategies (FGERS) is proposed, in which response strategies are run both in the environmental change stage and the environmental static stage to obtain population evolution information of those both stages. Unlike in the traditional framework, response strategies are only run in the environmental change stage. For simplicity, the feed-forward center point strategy was chosen to be the response strategy in the novel dynamic framework (FGERS-CPS). FGERS-CPS is not only to predict change trend of the optimum solution set in the environmental change stage, but to predict the evolution trend of the population after several generations in the environmental static stage. Together with the feed-forward center point strategy, a simple memory strategy and adaptive diversity maintenance strategy were used to form the complete FGERS-CPS. On 13 DMOPs with various characteristics, FGERS-CPS was compared with four classical response strategies in the traditional framework. Experimental results show that FGERS-CPS is effective for DMOPs. Copyright © 2022, The Authors. All rights reserved.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

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

arXiv

引用

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

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：