Mota Mariana R F, Silva Pedro H L, Luz Eduardo J S, Moreira Gladston J P, Schons Thiago, Moraes Lauro A G, Menotti David
Department of Computing, Universidade Federal de Ouro Preto, Ouro Preto, Minas Gerais, Brazil.
Department of Informatics, Universidade Federal do Paraná, Curitiba, Paraná, Brazil.
PeerJ Comput Sci. 2021 May 19;7:e549. doi: 10.7717/peerj-cs.549. eCollection 2021.
Due to the application of vital signs in expert systems, new approaches have emerged, and vital signals have been gaining space in biometrics. One of these signals is the electroencephalogram (EEG). The motor task in which a subject is doing, or even thinking, influences the pattern of brain waves and disturb the signal acquired. In this work, biometrics with the EEG signal from a cross-task perspective are explored. Based on deep convolutional networks (CNN) and Squeeze-and-Excitation Blocks, a novel method is developed to produce a deep EEG signal descriptor to assess the impact of the motor task in EEG signal on biometric verification. The Physionet EEG Motor Movement/Imagery Dataset is used here for method evaluation, which has 64 EEG channels from 109 subjects performing different tasks. Since the volume of data provided by the dataset is not large enough to effectively train a Deep CNN model, it is also proposed a data augmentation technique to achieve better performance. An evaluation protocol is proposed to assess the robustness regarding the number of EEG channels and also to enforce train and test sets without individual overlapping. A new state-of-the-art result is achieved for the cross-task scenario (EER of 0.1%) and the Squeeze-and-Excitation based networks overcome the simple CNN architecture in three out of four cross-individual scenarios.
由于生命体征在专家系统中的应用，出现了新的方法，生命信号在生物识别领域也越来越受关注。其中一种信号就是脑电图（EEG）。受试者正在进行的运动任务，甚至是其思考过程，都会影响脑电波模式并干扰所采集的信号。在这项工作中，从跨任务的角度对基于EEG信号的生物识别进行了探索。基于深度卷积网络（CNN）和挤压激励模块，开发了一种新颖的方法来生成深度EEG信号描述符，以评估EEG信号中的运动任务对生物特征验证的影响。这里使用Physionet EEG运动/想象数据集进行方法评估，该数据集包含109名执行不同任务的受试者的64个EEG通道。由于数据集提供的数据量不足以有效训练深度CNN模型，因此还提出了一种数据增强技术以获得更好的性能。提出了一种评估协议，以评估关于EEG通道数量的鲁棒性，并确保训练集和测试集没有个体重叠。在跨任务场景中取得了新的最优结果（等效错误率为0.1%），并且在四分之三的跨个体场景中，基于挤压激励的网络优于简单的CNN架构。
