1 University of Belgrade, The Mihajlo Pupin Institute, Volgina 15, 11060 Belgrade, Serbia.
2 School of Electrical Engineering, University of Belgrade, Bulevar kralja Aleksandra 73, P. O. Box 3554, 11120 Belgrade, Serbia.
Int J Neural Syst. 2017 Aug;27(5):1750008. doi: 10.1142/S0129065717500083. Epub 2016 Sep 30.
In recent years, simulation of the human electroencephalogram (EEG) data found its important role in medical domain and neuropsychology. In this paper, a novel approach to simulation of two cross-correlated EEG signals is proposed. The proposed method is based on the principles of artificial neural networks (ANN). Contrary to the existing EEG data simulators, the ANN-based approach was leveraged solely on the experimentally acquired EEG data. More precisely, measured EEG data were utilized to optimize the simulator which consisted of two ANN models (each model responsible for generation of one EEG sequence). In order to acquire the EEG recordings, the measurement campaign was carried out on a healthy awake adult having no cognitive, physical or mental load. For the evaluation of the proposed approach, comprehensive quantitative and qualitative statistical analysis was performed considering probability distribution, correlation properties and spectral characteristics of generated EEG processes. The obtained results clearly indicated the satisfactory agreement with the measurement data.
近年来，人类脑电图（EEG）数据的模拟在医学和神经心理学领域发挥了重要作用。本文提出了一种新的模拟两个交叉相关 EEG 信号的方法。该方法基于人工神经网络（ANN）的原理。与现有的 EEG 数据模拟器不同，基于 ANN 的方法仅利用实验获得的 EEG 数据。更准确地说，测量的 EEG 数据用于优化模拟器，该模拟器由两个 ANN 模型（每个模型负责生成一个 EEG 序列）组成。为了获取 EEG 记录，在没有认知、身体或精神负荷的健康清醒成年人身上进行了测量活动。为了评估所提出的方法，考虑生成的 EEG 过程的概率分布、相关特性和频谱特性，进行了全面的定量和定性统计分析。所得到的结果清楚地表明与测量数据具有令人满意的一致性。
