Khan M N Afzal, Zahour Nada, Tariq Usman, Masri Ghinwa, Almadani Ismat F, Al-Nashah Hasan
Department of Electrical Engineering, American University of Sharjah, Sharjah 26666, United Arab Emirates.
Biosciences and Bioengineering Graduate Program, American University of Sharjah, Sharjah 26666, United Arab Emirates.
Sensors (Basel). 2025 Jan 13;25(2):428. doi: 10.3390/s25020428.
Accurately identifying and discriminating between different brain states is a major emphasis of functional brain imaging research. Various machine learning techniques play an important role in this regard. However, when working with a small number of study participants, the lack of sufficient data and achieving meaningful classification results remain a challenge. In this study, we employ a classification strategy to explore stress and its impact on spatial activation patterns and brain connectivity caused by the Stroop color-word task (SCWT). To improve our results and increase our dataset, we use data augmentation with a deep convolutional generative adversarial network (DCGAN). The study is carried out at two separate times of day (morning and evening) and involves 21 healthy participants. Additionally, we introduce binaural beats (BBs) stimulation to investigate its potential for stress reduction. The morning session includes a control phase with 10 SCWT trials, whereas the afternoon session is divided into three phases: stress, mitigation (with 16 Hz BB stimulation), and post-mitigation, each with 10 SCWT trials. For a comprehensive evaluation, the acquired fNIRS data are classified using a variety of machine-learning approaches. Linear discriminant analysis (LDA) showed a maximum accuracy of 60%, whereas non-augmented data classified by a convolutional neural network (CNN) provided the highest classification accuracy of 73%. Notably, after augmenting the data with DCGAN, the classification accuracy increases dramatically to 96%. In the time series data, statistically significant differences were noticed in the data before and after BB stimulation, which showed an improvement in the brain state, in line with the classification results. These findings illustrate the ability to detect changes in brain states with high accuracy using fNIRS, underline the need for larger datasets, and demonstrate that data augmentation can significantly help when data are scarce in the case of brain signals.
准确识别和区分不同的脑状态是功能性脑成像研究的一个主要重点。各种机器学习技术在这方面发挥着重要作用。然而，在研究参与者数量较少的情况下，缺乏足够的数据以及获得有意义的分类结果仍然是一个挑战。在本研究中，我们采用一种分类策略来探索压力及其对由Stroop颜色-文字任务（SCWT）引起的空间激活模式和脑连接性的影响。为了改善我们的结果并增加我们的数据集，我们使用深度卷积生成对抗网络（DCGAN）进行数据增强。该研究在一天中的两个不同时间（上午和晚上）进行，涉及21名健康参与者。此外，我们引入双耳节拍（BBs）刺激来研究其减轻压力的潜力。上午的实验包括一个有10次SCWT试验的对照阶段，而下午的实验分为三个阶段：压力阶段、缓解阶段（16赫兹BB刺激）和缓解后阶段，每个阶段都有10次SCWT试验。为了进行全面评估，使用多种机器学习方法对采集到的功能近红外光谱（fNIRS）数据进行分类。线性判别分析（LDA）显示最高准确率为60%，而由卷积神经网络（CNN）对未增强数据进行分类时提供的最高分类准确率为73%。值得注意的是，在用DCGAN增强数据后，分类准确率大幅提高到96%。在时间序列数据中，在BB刺激前后的数据中发现了具有统计学意义的差异，这表明脑状态有所改善，与分类结果一致。这些发现说明了使用fNIRS能够高精度地检测脑状态的变化，强调了对更大数据集的需求，并证明了在脑信号数据稀缺的情况下，数据增强可以显著提供帮助。
