检索结果-内蒙古大学图书馆

Anxiety and Depression Diagnosis Method Based on brain Networks and Convolutional Neural Networks

学校读者我要写书评

暂无评论

Anxiety and Depression Diagnosis Method Based on Brain Netwo...

Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

作者： Yunlong Xie Banghua Yang Xi Lu Minmin Zheng Cunxiu Fan Xiaoying Bi Shu zhou Yingjie Li School of Mechatronic Engineering and Automation Shanghai Key Laboratory of Power Station Automation Technology Research Center of Brain Computer Engineering Shanghai University China Department of Neurology Shanghai Changhai Hospital PR. China Shanghai institute for advanced communication and data science School of Communication and Information Engineering Shanghai University China

ISBN: (数字)9781728119908

ISBN: (纸本)9781728119915

At present, only professional doctors can use the professional scales to diagnose depression and anxiety in clinical practice. In recent years, the problems of detecting the presence of anxiety or depression using Electroencephalography (EEG) has received attention as a way to implement assistant diagnosis, and some researchers explored that there are differences in the degree of prefrontal lateralization and functional connectivity of brain networks between patients with anxiety and depression and normal people. In this paper, we proposed a new approach that combines functional connectivity of brain networks and convolutional neural networks (CNN) for EEG-based anxiety and depression recognition. EEG data are collected from subjects consisting ten healthy controls and ten patients with anxiety or depression. In this way, we achieved 67.67% classification accuracy. It points out the way to further explore the application of functional connectivity of brain networks and deep learning technology in EEG about patients with anxiety and depression.

关键词： Electroencephalography Electrodes brain modeling Feature extraction Task analysis Convolution Scalp

SVM-based deep stacking networks

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Wang, Jingyuan Feng, Kai Wu, Junjie MOE Engineering Research Center of Advanced Computer Application Technology School of Computer Science Engineering Beihang University Beijing100191 China Beijing Key Laboratory of Emergency Support Simulation Technologies for City Operations School of Economics and Management Beihang University Beijing100191 China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing100191 China

The deep network model, with the majority built on neural networks, has been proved to be a powerful framework to represent complex data for high performance machine learning. In recent years, more and more studies turn to nonneural network approaches to build diverse deep structures, and the Deep Stacking Network (DSN) model is one of such approaches that uses stacked easy-to-learn blocks to build a parameter-training-parallelizable deep network. In this paper, we propose a novel SVM-based Deep Stacking Network (SVM-DSN), which uses the DSN architecture to organize linear SVM classifiers for deep learning. A BP-like layer tuning scheme is also proposed to ensure holistic and local optimizations of stacked SVMs simultaneously. Some good math properties of SVM, such as the convex optimization, is introduced into the DSN framework by our model. From a global view, SVM-DSN can iteratively extract data representations layer by layer as a deep neural network but with parallelizability, and from a local view, each stacked SVM can converge to its optimal solution and obtain the support vectors, which compared with neural networks could lead to interesting improvements in anti-saturation and interpretability. Experimental results on both image and text data sets demonstrate the excellent performances of SVM-DSN compared with some competitive benchmark models. Copyright © 2019, The Authors. All rights reserved.

关键词： Convex optimization

Parameter-Efficient Fine-Tuning for Continual Learning: A Neural Tangent Kernel Perspective

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Liu, Jingren Ji, Zhong Yu, YunLong Cao, Jiale Pang, Yanwei Han, Jungong Li, Xuelong School of Electrical and Information Engineering Tianjin Key Laboratory of Brain-Inspired Intelligence Technology Tianjin University Tianjin300072 China Shanghai Artificial Intelligence Laboratory Shanghai200232 China College of Information Science and Electronic Engineering Zhejiang University Hangzhou310027 China Department of Computer Science The University of Sheffield United Kingdom China Telecom Corp Ltd 31 Jinrong Street Beijing100033 China

Parameter-efficient fine-tuning for continual learning (PEFT-CL) has shown promise in adapting pre-trained models to sequential tasks while mitigating catastrophic forgetting problem. However, understanding the mechanisms that dictate continual performance in this paradigm remains elusive. To tackle this complexity, we undertake a rigorous analysis of PEFT-CL dynamics to derive relevant metrics for continual scenarios using Neural Tangent Kernel (NTK) theory. With the aid of NTK as a mathematical analysis tool, we recast the challenge of test-time forgetting into the quantifiable generalization gaps during training, identifying three key factors that influence these gaps and the performance of PEFT-CL: training sample size, task-level feature orthogonality, and regularization. To address these challenges, we introduce NTK-CL, a novel framework that eliminates task-specific parameter storage while adaptively generating task-relevant features. Aligning with theoretical guidance, NTK-CL triples the feature representation of each sample, theoretically and empirically reducing the magnitude of both task-interplay and task-specific generalization gaps. Grounded in NTK analysis, our approach imposes an adaptive exponential moving average mechanism and constraints on task-level feature orthogonality, maintaining intra-task NTK forms while attenuating inter-task NTK forms. Ultimately, by fine-tuning optimizable parameters with appropriate regularization, NTK-CL achieves state-of-the-art performance on established PEFT-CL benchmarks. This work provides a theoretical foundation for understanding and improving PEFT-CL models, offering insights into the interplay between feature representation, task orthogonality, and generalization, contributing to the development of more efficient continual learning systems. Copyright © 2024, The Authors. All rights reserved.

关键词：

A highly efficient clustering algorithm for analyzing gene sequences

学校读者我要写书评

暂无评论

A highly efficient clustering algorithm for analyzing gene s...

数学、计算机与生命科学交叉研究青年学者研讨会

作者： Dan Wei Qingshan Jiang Yanjie Wei Shengrui Wang Shenzhen Key Lab for High Performance Data Mining Shenzhen Institutes of Advanced TechnologyChinese Academy of SciencesShenzhenChina Shenzhen Key Lab for High Performance Data MiningShenzhen Institutes of Advanced TechnologyChinese Academy of SciencesShenzhenChina Department of Computer SciencesUniversity of SherbrookeSherbrookeQCCanada Cognitive Science Department & Fujian Key Laboratory of the Brain-like Intelligent Systems Xiamen UniversityXiamenChina

Efficient Combinatorial Optimization via Heat Diffusion

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Ma, Hengyuan Lu, Wenlian Feng, Jianfeng Institute of Science and Technology for Brain-inspired Intelligence Fudan University Shanghai200433 China Key Laboratory of Computational Neuroscience and Brain-Inspired Intelligence Fudan University Ministry of Education China School of Mathematical Sciences Fudan University No. 220 Handan Road Shanghai Shanghai200433 China Shanghai Center for Mathematical Sciences No. 220 Handan Road Shanghai Shanghai200433 China Shanghai Key Laboratory for Contemporary Applied Mathematics No. 220 Handan Road Shanghai Shanghai200433 China Key Laboratory of Mathematics for Nonlinear Science No. 220 Handan Road Shanghai Shanghai200433 China Department of Computer Science University of Warwick CoventryCV4 7AL United Kingdom

Combinatorial optimization problems are widespread but inherently challenging due to their discrete nature. The primary limitation of existing methods is that they can only access a small fraction of the solution space at each iteration, resulting in limited efficiency for searching the global optimal. To overcome this challenge, diverging from conventional efforts of expanding the solver’s search scope, we focus on enabling information to actively propagate to the solver through heat diffusion. By transforming the target function while preserving its optima, heat diffusion facilitates information flow from distant regions to the solver, providing more efficient navigation. Utilizing heat diffusion, we propose a framework for solving general combinatorial optimization problems. The proposed methodology demonstrates superior performance across a range of the most challenging and widely encountered combinatorial optimizations. Echoing recent advancements in harnessing thermodynamics for generative artificial intelligence, our study further reveals its significant potential in advancing combinatorial optimization. The codebase of our study is available in https://***/AwakerMhy/HeO. © 2024, CC BY.

关键词： Combinatorial optimization

Automated Detection of Epileptic Spikes and Seizures Incorporating a Novel Spatial Clustering Prior

学校读者我要写书评

暂无评论

Automated Detection of Epileptic Spikes and Seizures Incorpo...

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Hanyang Dong Shurong Sheng Xiongfei Wang Jia-Hong Gao Yi Sun Wanli Yang Kuntao Xiao Pengfei Teng Guoming Luan Zhao Lv School of Artificial Intelligence Anhui University Hefei China Anhui Province Key Laboratory of Biomedical Imaging and Intelligent Processing Institute of Artificial Intelligence Hefei Comprehensive National Science Center Hefei China Department of Neurosurgery Beijing Key Laboratory of Epilepsy Sanbo Brain Hospital Capital Medical University Beijing China McGovern Institute for Brain Research Peking University Beijing China Center for MRI Research Academy for Advanced Interdisciplinary Studies Peking University Beijing China Beijing City Key Lab for Medical Physics and Engineering Institute of Heavy Ion Physics School of Physics Peking University Beijing China Anhui Province Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Anhui University Hefei China

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

A Magnetoencephalography (MEG) time-series recording consists of multi-channel signals collected by superconducting sensors, with each signal’s intensity reflecting magnetic field changes over time at the sensor location. Automating epileptic MEG spike detection significantly reduces manual assessment time and effort, yielding substantial clinical benefits. Existing research addresses MEG spike detection by encoding neural network inputs with signals from all channel within a time segment, followed by classification. However, these methods overlook simultaneous spiking occurred from nearby sensors. We introduce a simple yet effective paradigm that first clusters MEG channels based on their sensor’s spatial position. Next, a novel convolutional input module is designed to integrate the spatial clustering and temporal changes of the signals. This module is fed into a custom MEEG-ResNet3D developed by the authors, which learns to extract relevant features and classify the input as a spike clip or not. Our method achieves an F1 score of 94.73% on a large real-world MEG dataset Sanbo-CMR collected from two centers, outperforming state-of-the-art approaches by 1.85%. Moreover, it demonstrates efficacy and stability in the Electroencephalographic (EEG) seizure detection task, yielding an improved weighted F1 score of 1.4% compared to current state-of-the-art techniques evaluated on TUSZ, whch is the largest EEG seizure dataset.

关键词： Convolution Magnetic sensors Neural networks Magnetoencephalography Manuals Feature extraction Electroencephalography Encoding Recording Magnetic fields

A ratiometric fluorescent probe for imaging of palladium

学校读者我要写书评

暂无评论

A ratiometric fluorescent probe for imaging of palladium

中国化学会第十届全国发光分析学术研讨会

作者： Yamin Li Xiaoling Zhang Baocun Zhu Hongying Jia Juan Xue Weihong Tan Key Laboratory of Cluster Science of Ministry of Education Department of chemistry School of Science Beijing Institute of Technology Beijing People''s Republic of China Beijing National Laboratory for Molecular Sciences State Key Laboratory for Structural Chemistry of Unstable and Stable Species Institute of Chemistry Chinese Academy of Sciences Beijing 100190People''s Republic of China Department of Chemistry and Department of Physiology and Functional Genomics Shands Cancer Center and Center for Research at the Bio/nano Interface UF Genetics Institute and McKnight Brain Institute University of Florida Gainesville Florida 32611-7200 USA

Data-Driven Low-Carbon Smart Mobility Framework: A Case Study on Electric Vehicle Charging Services

学校读者我要写书评

暂无评论

SSRN

SSRN 2024年

作者： Xie, Hongbin Zhang, Haoran Song, Xuan Shi, Zhuoran Song, Ge Peng, Jinquan Xie, Yi Wang, Zhongyi Shenzhen China Shenzhen China Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China School of Urban Planning and Design Peking University No.2199 Lishui Road Nanshan District Guangdong Shenzhen518055 China Huawei Technologies CO. Ltd. Shenzhen China

In order to further reduce environmental pollution, many countries around the world are advocating and implementing the policies of "carbon peaking" and "carbon neutralization". Low-carbon Smart Mobility (LSM) is an innovative and environmentally-friendly transportation development model proposed over the last few years. By effectively integrating transportation resources and providing comfortable and intelligent transportation services, LSM can improve people's acceptance and utilization of electric transportation and public transportation, so as to reduce greenhouse gas emissions. At present, the development of LSM is still in its infancy, and most researches on LSM focus on the integration at the service level, without sufficient effective collection and analysis of various traffic data generated by massive traffic equipments at the bottom layer, so there is a lack of traffic value-added services based on data analysis. To solve the problem above, we proposes a novel construction scheme of building a data-driven Low-carbon Smart Mobility system. The scheme mainly realizes the interconnection of traffic equipment and the collection of traffic data in the whole transportation system by introducing Internet of Things (IoT) technology. On the basis of this, it further realizes the analysis and decision-making of massive traffic data by using cutting-edge science and technology such as big data, artificial intelligence, large language models (LLM), cloud computing and blockchain, so as to provide users with more environmentally-friendly, intelligent, convenient and comfortable transportation services, accelerate the development of urban green transportation, and ultimately achieve the goals of "carbon peak" and "carbon neutralization" as soon as possible. At the end of this article, we conducted a numerical experiment that demonstrates a case of scheduling decision in data-driven management for an automotive charging battery supply chain, thereby illustrating the feas

关键词： Internet of things

CLDG: Contrastive Learning on Dynamic Graphs

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Xu, Yiming Shi, Bin Ma, Teng Dong, Bo Zhou, Haoyi Zheng, Qinghua Department of Computer Science and Technology Xi’an Jiaotong University China Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering Xi’an Jiaotong University China Department of Distance Education Xi’an Jiaotong University China School of Software Beihang University China Advanced Innovation Center for Big Data and Brain Computing Beihang University China

The graph with complex annotations is the most potent data type, whose constantly evolving motivates further exploration of the unsupervised dynamic graph representation. One of the representative paradigms is graph contrastive learning. It constructs self-supervised signals by maximizing the mutual information between the statistic graph’s augmentation views. However, the semantics and labels may change within the augmentation process, causing a significant performance drop in downstream tasks. This drawback becomes greatly magnified on dynamic graphs. To address this problem, we designed a simple yet effective framework named CLDG. Firstly, we elaborate that dynamic graphs have temporal translation invariance at different levels. Then, we proposed a sampling layer to extract the temporally-persistent signals. It will encourage the node to maintain consistent local and global representations, i.e., temporal translation invariance under the timespan views. The extensive experiments demonstrate the effectiveness and efficiency of the method on seven datasets by outperforming eight unsupervised state-of-the-art baselines and showing competitiveness against four semi-supervised methods. Compared with the existing dynamic graph method, the number of model parameters and training time is reduced by an average of 2,001.86 times and 130.31 times on seven datasets, respectively. The code and data are available at: https://***/yimingxu24/CLDG. © 2024, CC BY.

关键词： Contrastive Learning