Search research articles

关于 JoVE

概览领导团队博客 JoVE 帮助中心

作者

出版流程编辑委员会范围与政策同行评审常见问题投稿

图书馆员

用户评价订阅访问资源图书馆顾问委员会常见问题

研究

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments 存档

教育

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual 教师资源中心教师网站

使用条款与条件

相关概念视频

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序

Same author

Therapeutic Potential of Cymbopogon citratus in Hepatotoxicity: A Review of Its Phytochemical and Pharmacological Properties.

Current topics in medicinal chemistry·2026

Same author

Lymphatic Drug Delivery System and Lipid-based Nanoformulations: Savior to Save for Patients Receiving Highly Hepatotoxic Drugs.

Current drug metabolism·2026

Same author

Seamless integration for enhanced seizure prediction using HybridConvMobileNet on Typhoon HIL.

Scientific reports·2025

Same author

Design and pharmacological assessment of naproxen-ibuprofen linked NSAIDs as selective COX-2 modulators in inflammatory pathways.

Inflammopharmacology·2025

Same author

Influenza strains in focus: global approaches to the diagnosis, treatment, and control of H1N1, H3N2, H7N9, and H9N2.

Pathogens and global health·2025

Same author

Advancements in Autoimmune Hemolytic Anemia (AIHA) treatment: Exploring emerging therapies.

Leukemia research·2025

Search research articles

相关实验视频

Updated: Jan 11, 2026

Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding

Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding

Published on: July 26, 2013

量子增强的EEG分类器向大脑控制的轮椅导航方向发展.

Prabhat Kumar Upadhyay¹, Kumar Avinash Chandra¹

¹Department of Electrical & Electronics Engineering, Birla Institute of Technology, Mesra, Ranchi, Jharkhand, India.

|November 9, 2025

概括

这项研究引入了一种量子增强的CNN-LSTM模型,用于分类电脑图信号,实现大脑-计算机接口的高精度. 这种新的方法增强了用于轮椅等辅助技术的机动图像解码.

科学领域:

神经科学是一个神经科学.
计算机科学计算机科学
量子计算是一种量子计算.

背景情况:

大脑-计算机接口 (BCI) 能够实现辅助技术,但由于噪音和可变性,在精确的脑电图 (EEG) 信号分类方面面临挑战.
运动图像 (MI) 的分类对于控制诸如脑控制轮椅之类的设备至关重要.

研究的目的:

开发一种混合量子增强CNN-LSTM模型 (HQeCL) 以改进基于EEG的MI分类.
整合各种EEG特征 (频率,空间,非线性) 和量子启发的技术,以进行可靠的分类.

主要方法:

提出了一个混合模型 (HQeCL),将卷积神经网络 (CNN) 和长短期记忆 (LSTM) 与模拟的量子聚合层相结合.
综合功率光谱密度 (PSD),共同空间模式 (CSP) 和量子,用于全面的特征提取.
在8通道MI数据集上使用离开一个主体的交叉验证 (LOSO) 进行评估.

主要成果:

实现了高性能指标:92.1%±5.9准确度,93.1%±6.2精度,91.9%±1.3回忆,92.5%±1.3F1得分,以及科恩的 κ=0.89±0.02.
超越了CSP-LDA,ShallowConvNet和CNN-LSTM等现有方法的性能,证明了与QuEEG.Net具有竞争力的结果.
除研究证实了量子聚合 (精度为0.7%) 和UMAP对特征减少的好处.

关键词:

大脑与计算机接口 (BCI)卷积神经网络 (CNN) 是一种神经网络.电脑电图 (EEG) 是一种电脑电图.长时间短期记忆 (LSTM)运动图像 (MI)量子计算是一种量子计算.

更多相关视频

WheelCon: A Wheel Control-Based Gaming Platform for Studying Human Sensorimotor Control

WheelCon: A Wheel Control-Based Gaming Platform for Studying Human Sensorimotor Control

Published on: August 15, 2020

Brain-Computer Interface-controlled Upper Limb Robotic System for Enhancing Daily Activities in Stroke Patients

Brain-Computer Interface-controlled Upper Limb Robotic System for Enhancing Daily Activities in Stroke Patients

Published on: April 18, 2025

相关实验视频

Last Updated: Jan 11, 2026

Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding

Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding

Published on: July 26, 2013

WheelCon: A Wheel Control-Based Gaming Platform for Studying Human Sensorimotor Control

WheelCon: A Wheel Control-Based Gaming Platform for Studying Human Sensorimotor Control

Published on: August 15, 2020

Brain-Computer Interface-controlled Upper Limb Robotic System for Enhancing Daily Activities in Stroke Patients

Brain-Computer Interface-controlled Upper Limb Robotic System for Enhancing Daily Activities in Stroke Patients

Published on: April 18, 2025

证明了0.12M参数,270.2M FLOP和77.6ms推理延迟的计算效率.

结论:

HQeCL模型为基于EEG的运动图像解码提供了一种量子灵感,高效和高性能解决方案.
该方法在模拟中显示了近实时的可行性,推进了先进的大脑控制辅助技术的潜力.
对于硬件实现,需要进行进一步的研究,才能充分实现这一BCI进步的潜力.