National Center of Artificial Intelligence (NCAI), School of Mechanical and Manufacturing Engineering (SMME), National University of Sciences and Technology (NUST), Islamabad, 44000, Pakistan.
Department of Mechatronics Engineering, College of Electrical and Mechanical Engineering, National University of Sciences and Technology (NUST), Islamabad, 44000, Pakistan.
Sci Rep. 2022 Feb 24;12(1):3198. doi: 10.1038/s41598-022-06805-4.
The brain-computer interface (BCI) provides an alternate means of communication between the brain and external devices by recognizing the brain activities and translating them into external commands. The functional Near-Infrared Spectroscopy (fNIRS) is becoming popular as a non-invasive modality for brain activity detection. The recent trends show that deep learning has significantly enhanced the performance of the BCI systems. But the inherent bottleneck for deep learning (in the domain of BCI) is the requirement of the vast amount of training data, lengthy recalibrating time, and expensive computational resources for training deep networks. Building a high-quality, large-scale annotated dataset for deep learning-based BCI systems is exceptionally tedious, complex, and expensive. This study investigates the novel application of transfer learning for fNIRS-based BCI to solve three objective functions (concerns), i.e., the problem of insufficient training data, reduced training time, and increased accuracy. We applied symmetric homogeneous feature-based transfer learning on convolutional neural network (CNN) designed explicitly for fNIRS data collected from twenty-six (26) participants performing the n-back task. The results suggested that the proposed method achieves the maximum saturated accuracy sooner and outperformed the traditional CNN model on averaged accuracy by 25.58% in the exact duration of training time, reducing the training time, recalibrating time, and computational resources.
脑机接口 (BCI) 通过识别大脑活动并将其转化为外部命令，为大脑和外部设备之间提供了一种替代的通信方式。功能近红外光谱 (fNIRS) 作为一种非侵入式的大脑活动检测方式越来越受欢迎。最近的趋势表明，深度学习显著提高了 BCI 系统的性能。但是，深度学习（在 BCI 领域）的固有瓶颈是需要大量的训练数据、冗长的重新校准时间以及昂贵的计算资源来训练深度网络。为基于深度学习的 BCI 系统构建高质量、大规模的标注数据集非常繁琐、复杂且昂贵。本研究探讨了迁移学习在基于 fNIRS 的 BCI 中的新应用，以解决三个目标函数（关注点），即训练数据不足、训练时间减少和准确性提高的问题。我们在卷积神经网络 (CNN) 上应用了对称同形特征迁移学习，该网络是专门为从 26 名参与者执行 n-back 任务时采集的 fNIRS 数据设计的。结果表明，与传统的 CNN 模型相比，该方法在更短的训练时间内达到了最大饱和精度，平均准确率提高了 25.58%，减少了训练时间、重新校准时间和计算资源。
