检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Feng, Xiaodong Shangguan, Haojiong Tang, Tao Wan, Xiaoliang Zhou, Tao Division of Science and Technology BNU-HKBU United International College Zhuhai519087 China School of Electrical and Computer Engineering Guangzhou Nanfang College Guangzhou510970 China Department of Mathematics Center for Computation and Technology Louisiana State University Baton Rouge70803 United States Institute of Computational Mathematics and Scientific/Engineering Computing Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing China

In this work, we present a hybrid numerical method for solving evolution partial differential equations (PDEs) by merging the time finite element method with deep neural networks. In contrast to the conventional deep learning-based formulation where the neural network is defined on a spatiotemporal domain, our methodology utilizes finite element basis functions in the time direction where the space-dependent coefficients are defined as the output of a neural network. We then apply the Galerkin or collocation projection in the time direction to obtain a system of PDEs for the space-dependent coefficients which is approximated in the framework of PINN. The advantages of such a hybrid formulation are twofold: statistical errors are avoided for the integral in the time direction, and the neural network’s output can be regarded as a set of reduced spatial basis functions. To further alleviate the difficulties from high dimensionality and low regularity, we have developed an adaptive sampling strategy that refines the training set. More specifically, we use an explicit density model to approximate the distribution induced by the PDE residual and then augment the training set with new time-dependent random samples given by the learned density model. The effectiveness and efficiency of our proposed method have been demonstrated through a series of numerical experiments. © 2024, CC BY.

关键词： Partial differential equations

来源：评论

学校读者我要写书评

暂无评论

Integrating LLM, EEG, and Eye-Tracking Biomarker Analysis for Word-Level neural State Classification in Semantic Inference Reading Comprehension

arXiv

引用

arXiv 2023年

作者： Zhang, Yuhong Li, Qin Nahata, Sujal Jamal, Tasnia Cheng, Shih-Kuen Cauwenberghs, Gert Jung, Tzyy-Ping The School of Engineering Brown University ProvidenceRI02912 United States Institute for Neural Computation University of California San Diego La Jolla CA92093 United States Department of Radiology and Biomedical Imaging Yale University New HavenCT06520 United States The Department of Bioengineering University of California Los Angeles Los AngelesCA90095 United States The Department of Computer Science and Engineering University of California San Diego La Jolla CA92093 United States The Department of Electrical and Computer Engineering University of California San Diego La Jolla CA92093 United States The Institute of Cognitive Neuroscience National Central University Taoyuan32001 Taiwan The Department of Bioengineering Institute for Neural Computation University of California San Diego La Jolla CA92093 United States The Institute for Neural Computation University of California San Diego La Jolla CA92093 United States

With the recent proliferation of large language models (LLMs), such as Generative Pre-trained Transformers (GPT), there has been a significant shift in exploring human and machine comprehension of semantic language meaning. This shift calls for interdisciplinary research that bridges cognitive science and natural language processing (NLP). This pilot study aims to provide insights into individuals’ neural states during a semantic relation reading-comprehension task. We propose jointly analyzing LLMs, eye-gaze, and electroencephalographic (EEG) data to study how the brain processes words with varying degrees of relevance to a keyword during reading. We also use a feature engineering approach to improve the fixation-related EEG data classification while participants read words with high versus low relevance to the keyword. The best validation accuracy in this word-level classification is over 60% across 12 subjects. Words of high relevance to the inference keyword had significantly more eye fixations per word: 1.0584 compared to 0.6576 when excluding no-fixation words, and 1.5126 compared to 1.4026 when including them. This study represents the first attempt to classify brain states at a word level using LLM knowledge. It provides valuable insights into human cognitive abilities and the realm of Artificial General Intelligence (AGI), and offers guidance for developing potential reading-assisted technologies. Copyright © 2023, The Authors. All rights reserved.

关键词： computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Efficient Self-Learning Evolutionary neural Architecture Search

SSRN

引用

SSRN 2023年

作者： Qiu, Zhengzhong Bi, Wei Xu, Dong Guo, Hua Ge, Hongwei Liang, Yanchun Lee, Heow Pueh Wu, Chunguo Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education College of Computer Science and Technology Jilin University Jilin Changchun130012 China YGSOFT INC Guangdong Zhuhai519085 China Department of Electrical Engineering and Computer Science Informatics Institute Christopher S. Bond Life Sciences Center University of Missouri ColumbiaMO65211 United States College of Computer Science and Technology Dalian University of Technology Liaoning Dalian116081 China School of Computer Science Zhuhai College of Science and Technology Guangdong Zhuhai519041 China Department of Mechanical Engineering National University of Singapore 9 Engineering Drive 1 117575 Singapore

The evolutionary algorithm has become a major method for neural architecture search recently. However, the fixed probability distribution adopted by the traditional evolutionary algorithm makes the algorithm unable to control the increase or decrease of the individual architecture size and thus cannot guarantee the lightweight and inference efficiency of the candidate architecture. In addition, the existing approaches cannot learn the optimal sampling probability distribution relevant to the specific problem from the empirical information accumulated through the search process. What’s more, the algorithm needs to evaluate the performance of all the individual architectures, which requires huge computing resources and time overhead. To overcome these problems and challenges, an Efficient Self-learning Evolutionary neural Architecture Search method, called ESE-NAS, is presented in this paper. Firstly, we propose a Model Size Control module, which generates the probability distribution for sampling the type of mutation operators according to the current model size, so as to control both the node number of network architecture and the sparsity of links, therefore ensuring that neural architectures can remain compact and efficient as they evolve. Thereafter, a Mutation Candidate Credit Assignment method is proposed, which enables the algorithm to dynamically adjust the probability distribution for available types of node operations and directed links according to the empirical information from individuals’ performance evaluation, which can guide the evolutionary direction of neural architecture and shorten the first hitting time of the optimal architecture. Finally, a neural architecture performance predictor is formulated, and the accuracy of each individual architecture is predicted by using the simplified input features, to further improve the efficiency of neural architecture search. Experiments show that the ESE-NAS method proposed in this paper can learn a highly i

关键词： Evolutionary algorithms

来源：评论

学校读者我要写书评

暂无评论

Estimating distinguishability measures on quantum computers

引用

Physical Review A 2023年第1期108卷 012409-012409页

作者： Soorya Rethinasamy Rochisha Agarwal Kunal Sharma Mark M. Wilde Hearne Institute for Theoretical Physics Department of Physics and Astronomy and Center for Computation and Technology Louisiana State University Baton Rouge Louisiana 70803 USA School of Applied and Engineering Physics Cornell University Ithaca New York 14850 USA Department of Physics Indian Institute of Technology Roorkee Roorkee Uttarakhand 247667 India School of Electrical and Computer Engineering Cornell University Ithaca New York 14850 USA Joint Center for Quantum Information and Computer Science University of Maryland College Park Maryland 20742 USA IBM Quantum IBM T. J. Watson Research Center Yorktown Heights New York 10598 USA

The performance of a quantum information processing protocol is ultimately judged by distinguishability measures that quantify how distinguishable the actual result of the protocol is from the ideal case. The most prominent distinguishability measures are those based on the fidelity and trace distance, due to their physical interpretations. In this paper we propose and review several algorithms for estimating distinguishability measures based on trace distance and fidelity. The algorithms can be used for distinguishing quantum states, channels, and strategies (the last also known in the literature as “quantum combs”). The fidelity-based algorithms offer physical interpretations of these distinguishability measures in terms of the maximum probability with which a single prover (or competing provers) can convince a verifier to accept the outcome of an associated computation. We simulate many of these algorithms by using a variational approach with parameterized quantum circuits. We find that the simulations converge well in both the noiseless and noisy scenarios for all examples considered. Furthermore, the noisy simulations exhibit a parameter noise resilience. Finally, we establish a strong relationship between various quantum computational complexity classes and distance estimation problems.

关键词： Machine learning Quantum algorithms Quantum channels Quantum computation Quantum information theory

来源：评论

学校读者我要写书评

暂无评论

PDMATLAB2D: A Peridynamics MATLAB Two-dimensional Code

引用

Journal of Peridynamics and Nonlocal Modeling 2024年第1期6卷 149-205页

作者： Seleson, Pablo Pasetto, Marco John, Yohan Trageser, Jeremy Reeve, Samuel Temple Computer Science and Mathematics Division Oak Ridge National Laboratory P.O. Box 2008 MS-6013 Oak Ridge 37831-6013 TN United States Department of Mechanical and Aerospace Engineering University of California San Diego 9500 Gilman Drive La Jolla 92093 CA United States George W. Woodruff School of Mechanical Engineering Georgia Institute of Technology 801 Ferst Dr Atlanta 30332 GA United States Center for Control Dynamical Systems and Computation University of California at Santa Barbara Harold Frank Hall Room 5119 Santa Barbara 93106 CA United States Engineering Sciences Center Sandia National Laboratories P.O. Box 5800 MS-1322 Albuquerque 87185-1322 NM United States Computational Sciences and Engineering Division Oak Ridge National Laboratory P.O. Box 2008 MS-6085 Oak Ridge 37831-6085 TN United States

PDMATLAB2D is a meshfree peridynamics implementation in MATLAB suitable for simulation of two-dimensional fracture problems. The purpose of this code is twofold. First, it provides an entry-level peridynamics computational tool for educational and training purposes. Second, it serves as an accessible and easily modifiable computational tool for peridynamics researchers who would like to adapt the code for a multitude of peridynamics simulation scenarios. The current version of the code implements a bond-based brittle elastic peridynamic model and a critical stretch criterion for bond breaking. However, the code is designed to be extendable for other peridynamic models and computational features. In this paper, we provide an overview of the code structure and functions with illustrative examples. Due to the integrated computation and postprocessing MATLAB capabilities, PDMATLAB2D can serve as an effective testbed for testing new constitutive models and advanced numerical features for peridynamics computations. © UT-Battelle, LLC, under exclusive licence to Springer Nature Switzerland AG 2024. corrected publication 2024.

关键词： Fracture Meshfree Peridynamics Two-dimensional

来源：评论

学校读者我要写书评

暂无评论

Exploiting the Intrinsic Neighborhood Semantic Structure for Domain Adaptation in EEG-based Emotion Recognition

引用

IEEE Transactions on Affective Computing 2025年

作者： Yang, Yi Wang, Ze Song, Yu Jia, Ziyu Wang, Boyu Jung, Tzyy-Ping Wan, Feng Macau University of Science and Technology Macao Centre for Mathematical Sciences Respiratory Disease AI Laboratory on Epidemic Intelligence and Medical Big Data Instrument Applications Faculty of Innovation Engineering 999078 China Tianjin University of Technology School of Electrical Engineering and Automation Tianjin Key Laboratory of New Energy Power Conversion Transmission and Intelligent Control Tianjin300384 China Chinese Academy of Sciences Beijing Key Laboratory of Brainnetome and Brain-Computer Interface and Brainnetome Center Institute of Automation Beijing100045 China Western University Department of Computer Science Brain Mind Institute LondonONN6A 3K7 Canada University of California at San Diego Swartz Center for Computational Neuroscience Institute for Neural Computation La Jolla CA92093 United States University of Macau Department of Electrical and Computer Engineering Faculty of Science and Technology China University of Macau Centre for Cognitive and Brain Sciences Centre for Artificial Intelligence and Robotics Institute of Collaborative Innovation 999078 China

Due to the inherent non-stationarity and individual differences present in electroencephalogram (EEG) signals, developing a generalizable model that performs well on new subjects is challenging in EEG-based emotion recognition. Most existing domain adaptation (DA) methods typically mitigate these discrepancies by aligning the marginal distributions of domain feature representations. However, when there is a significant difference in the class-conditional distribution between domain features and labels, the domain-invariant features learned by aligning marginal distributions may have limited discriminative ability for unlabeled target instances or even prove counterproductive. To address this issue, we propose a Neighborhood Semantic Aware Learning-based Dynamic Graph Attention Convolution (NSAL-DGAT) approach that learns target semantic information by considering the inter-domain semantic topological structure, thereby improving classifier adaptation for target instances. Specifically, the proposed NSAL framework is designed to capitalize on the insight that after domain feature alignment, some target samples and their neighboring source samples exhibit similar semantics. By leveraging the neighborhood topological structure, we extract and incorporate semantic target features to train a more transferable classifier. Besides, we implement an entropy weighting mechanism to emphasize representative target semantic information, encouraging target instances to prioritize high-confidence individuals within the source neighborhood. We have conducted extensive experiments on the public SEED dataset and our collected the Hearing-Impaired EEG Dataset (HIED). The experimental results underscore the efficacy of our proposed NSAL-DGAT approach, showcasing state-of-the-art accuracy in subject-dependent as well as subject-independent scenarios. The source code is available at https://***/YYingDL/NSAL-DGAT. © 2010-2012 IEEE.

关键词： Speech analysis

来源：评论

学校读者我要写书评

暂无评论

Route Control of Four-rotor UAV based on Brain-computer Interface in Virtual Reality 12

Route Control of Four-rotor UAV based on Brain-Computer Inte...

引用

12th International Conference on CYBER Technology in Automation, Control, and Intelligent Systems, CYBER 2022

作者： Niu, Lan Bin, Jianxiong Wang, Junkongshuai Zhan, Gege Jiang, Haifeng Dong, Zhiyan Zhang, Lihua Kang, Xiaoyang Moe Frontiers Center for Brain Science State Key Laboratory of Medical Neurobiology Institute of Ai and Robotics Academy for Engineering and Technology Fudan University Laboratory for Neural Interface and Brain Computer Interface Engineering Research Center of Ai and Robotics Ministry of Education Shanghai Engineering Research Center of Ai and Robotics Shanghai200433 China Ji Hua Laboratory Guangdong Province Foshan China Shanghai Mental Center Shanghai Jiao Tong University School of Medicine Shanghai China Yiwu Research Institute of Fudan University Chengbei Road Zhejiang Province Yiwu City China Research Center for Intelligent Sensing Zhejiang Lab Hangzhou China

ISBN: (数字)9781665472678

ISBN: (纸本)9781665472678

This article presented an experiment to determine the effect of dynamic 3D vision-evoked modules on the performance of the system we designed to steer a four-rotor unmanned aerial vehicle (UAV). Nowadays, UAV system is widely used in various industries, and UAV control has always been a focus of research. The Brain-computer Interface (BCI) system was based on the well-known steady-state visually evoked potentials (SSVEP). The specificity of the interface was the integration of dynamic 3D paradigms in virtual reality. In order to achieve a more immersive and interactive scene, VR scenes were moving synchronously with the UAV. Users can achieve remote control of four-rotor UAV through virtual scenarios. Ten subjects participated in the experiment and operated the UAV to complete a specific track. The dynamic paradigm based on the experimenter's feedback may indeed affect their attention, we proposed an effective solution to overcome this problem. The detailed results of these experiments were reported in this paper and we discussed the possible causes of performance loss under such conditions. © 2022 IEEE.

关键词： Brain computer interface

来源：评论

学校读者我要写书评

暂无评论

Non-Invasive Brain-computer Interfaces: a New Perspective on the Assessment and Classification of Individuals with Methamphetamine Addiction

引用

SN Comprehensive Clinical Medicine 2023年第1期5卷 1-12页

作者： Zhan, Gege Su, Haolong Wang, Pengchao Wang, Junkongshuai Jiang, Haifeng Zhang, Lihua Kang, Xiaoyang Laboratory for Neural Interface and Brain Computer Interface Engineering Research Center of AI & Robotics Ministry of Education Shanghai Engineering Research Center of AI & Robotics MOE Frontiers Center for Brain Science State Key Laboratory of Medical Neurobiology Institute of AI & Robotics Academy for Engineering & Technology Fudan University Shanghai China Shanghai Mental Center Shanghai Jiao Tong University School of Medicine Shanghai China CAS Center for Excellence in Brain Science and Intelligence Technology (CEBSIT) Chinese Academy of Sciences Shanghai China Ji Hua Laboratory Foshan Guangdong Province China Yiwu Research Institute of Fudan University Yiwu City China

Methamphetamine addiction is a brain disease that causes abnormalities in the structure and function of the brain. EEG, a common signal acquired based on the noninvasive brain-computer interface, can reflect the altered brain activity associated with methamphetamine addiction. EEG-based analysis methods provide a perspective to explore the neural mechanisms of methamphetamine addiction and the effects on brain activity. This paper reports the results of a review of EEG-based assessment and classification of methamphetamine addiction. Current methods commonly used in EEG-based methamphetamine addiction research include traditional resting-state EEG analysis, brain network analysis, and analysis of event-related potentials. A small number of studies have classified methamphetamine addiction and healthy individuals based on resting state EEG features or event-related potentials. EEG is one of the common tools used to examine the effects of methamphetamine on brain function. In follow-up studies, new methods for analyzing resting-state EEG and event-related potentials may help to investigate the neural mechanisms of methamphetamine addiction.

关键词：

来源：评论

学校读者我要写书评

暂无评论

TagVibra: push the limit of RFID-based vibration sensing

TagVibra: push the limit of RFID-based vibration sensing

引用

International Conference on Big Data Computing and Communications (BIGCOM)

作者： Jian Li Ping Li Biaokai Zhu Chong Dong Chao Gong Zhao Lv Anhui Province Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Anhui University Hefei China Anhui Engineering Research Center for Intelligent Applications and Security of Industrial Internet Anhui University of Technology Ma’anshan China Shanxi Police College Taiyuan China

RFID-based mechanical vibration detection is considered a promising method for many Internet of Things (IoT) applications. However, existing methods are affected by ambient interference and leakage from the reader signature, which makes it difficult to obtain high-precision detection results. To overcome this limitation, this paper introduces TagVibra, a high-precision non-contact vibration sensing system based on RFID technology. By leveraging the nonlinear effect inside the tag and the modulation mechanism of RFID, TagVibra can achieve sub-millimeter level vibration detection accuracy. We implement TagVibra on our Universal Software Radio Peripheral (USRP) platform and evaluate its performance via experiments. The experimental results show that TagVibra can detect vibration with amplitude as low as 0.3mm, and the average estimation error below 0.7Hz when the vibration frequency is 100Hz.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Efficient Light Propagation Algorithm using Quantum computers

arXiv

引用

arXiv 2023年

作者： Cholsuk, Chanaprom Davani, Siavash Conlon, Lorcán O. Vogl, Tobias Eilenberger, Falk Abbe Center of Photonics Institute of Applied Physics Friedrich Schiller University Jena Jena07745 Germany Department of Computer Engineering School of Computation Information and Technology Technical University of Munich Munich80333 Germany Max Planck School of Photonics Jena07745 Germany Centre for Quantum Computation and Communication Technology Department of Quantum Science Australian National University CanberraACT2601 Australia Fraunhofer Institute for Applied Optics and Precision Engineering IOF Jena07745 Germany

Quantum algorithms can potentially overcome the boundary of computationally hard problems. One of the cornerstones in modern optics is the beam propagation algorithm, facilitating the calculation of how waves with a particular dispersion relation propagate in time and space. This algorithm solves the wave propagation equation by Fourier transformation, multiplication with a transfer function, and subsequent back transformation. This transfer function is determined from the respective dispersion relation, which can often be expanded as a polynomial. In the case of paraxial wave propagation in free space or picosecond pulse propagation, this expansion can be truncated after the quadratic term. The classical solution to the wave propagation requires O(NlogN) computation steps, where N is the number of points into which the wave function is discretized. Here, we show that the propagation can be performed as a quantum algorithm with O((logN)2) single-controlled phase gates, indicating exponentially reduced computational complexity. We herein demonstrate this quantum beam propagation method (QBPM) and perform such propagation in both one- and two-dimensional systems for the double-slit experiment and Gaussian beam propagation. We highlight the importance of the selection of suitable observables to retain the quantum advantage in the face of the statistical nature of the quantum measurement process, which leads to sampling errors that do not exist in classical solutions. Copyright © 2023, The Authors. All rights reserved.

关键词： Wave functions

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：