相关实验视频

Updated: Jul 25, 2025

P300-Based Brain-Computer Interface Speller Performance Estimation with Classifier-Based Latency Estimation

P300-Based Brain-Computer Interface Speller Performance Estimation with Classifier-Based Latency Estimation

Published on: September 8, 2023

阶级不平衡不应该让你失去平衡:选择正确的分类器和性能指标,以帮助大脑解码不平衡数据

Philipp Thölke¹, Yorguin-Jose Mantilla-Ramos², Hamza Abdelhedi³

¹Cognitive and Computational Neuroscience Laboratory (CoCo Lab), University of Montreal, 2900, boul. Edouard-Montpetit, Montreal, H3T 1J4, Quebec, Canada; Institute of Cognitive Science, Osnabrück University, Neuer Graben 29/Schloss, Osnabrück, 49074, Lower Saxony, Germany.

|June 29, 2023

概括

神经科学中的机器学习 (ML) 面临着不平衡数据集的挑战. 这项研究揭示了标准准确度指标可能具有误导性,建议平衡准确度可用于ML应用中的可靠性能评估.

科学领域:

神经科学是一个神经科学.
机器学习机器学习
数据科学数据科学数据科学

背景情况:

机器学习 (ML) 在认知,计算和临床神经科学中至关重要.
不平衡的数据集是ML中常见的挑战,如果不解决,可能会导致严重后果.

研究的目的:

为神经科学中的阶级不平衡问题提供教学评估.
用模拟和真实大脑数据 (EEG,MEG,fMRI) 来说明数据不平衡对ML模型性能的影响.

主要方法:

在模拟和脑成像数据集中的数据不平衡比率的系统操纵.
评估分类指标,包括准确性 (Acc),接收器操作特征 (ROC) 曲线下的面积 (AUC) 和平衡准确性 (BAcc).
评估随机森林 (RF) 的稳定性,分层交叉验证和超参数优化.

主要成果:

标准准确性 (Acc) 度量在不平衡的数据集上产生了误导性的高性能,因为它不考虑少数类的性能.
平衡精度 (BAcc) 和AUC为不平衡数据提供了更可靠的性能评估.
随机森林 (RF) 证明了稳定性,分层交叉验证/超参数优化有助于解决数据不平衡.

结论:

对于旨在最大限度地减少分类错误的神经科学ML应用,建议使用平衡精度 (BAcc) 来进行可靠的性能评估.
在平衡数据上,BAcc相当于标准Acc,并扩展到多类设置.
为神经科学界提供建议和开源代码,以解决不平衡的数据.

关键词:

平衡的准确性均衡的准确性大脑解码的解码阶级不平衡造成的不平衡分类分类分类分类.电脑电图 (电脑电图) 是一种脑电图.机器学习机器学习磁性脑电图 (MEG) 是一种磁性脑电图.绩效指标是指性能指标.

更多相关视频

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

Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations

Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations

Published on: February 15, 2017

相关概念视频

Classification of Signals

Classification of Signals

In signal processing, signals are classified based on various characteristics: continuous-time versus discrete-time, periodic versus aperiodic, analog versus digital, and causal versus noncausal. Each category highlights distinct properties crucial for understanding and manipulating signals.
A continuous-time signal holds a value at every instant in time, representing information seamlessly. In contrast, a discrete-time signal holds values only at specific moments, often denoted as x(n), where...