Liu Yu, Wei Yi, Li Chang, Cheng Juan, Song Rencheng, Chen Xun
IEEE J Biomed Health Inform. 2023 Mar;27(3):1319-1330. doi: 10.1109/JBHI.2022.3232514. Epub 2023 Mar 7.
In recent years, deep learning has gained widespread attention in electroencephalogram (EEG)-based emotion recognition. However, deep learning methods are usually time-consuming with a large amount of memory usage, which obstructs their practical usage on resource-constrained devices. In this paper, we propose a binary capsule network (Bi-CapsNet) for EEG emotion recognition with low computational cost and memory usage. The Bi-CapsNet binarizes 32-bit weights and activations to 1 b, and replaces floating-point operations with efficient bitwise operations. To address the issue of function discontinuity in backward propagation, we use a continuous function to approximate the binarization process. Two popular EEG emotion databases, namely, DEAP and DREAMER, are used for performance evaluation. In comparison to its full-precision counterpart, the Bi-CapsNet achieves a $>!25\times$reduction on the computational cost and a $>!5\times$ reduction on the memory usage, while with only a $< $1% drop on the recognition accuracy. Compared to some state-of-the-art EEG emotion recognition methods, the proposed method obtains more competitive performance. In addition, the Bi-CapsNet is implemented on a mobile phone via an open-source binary inference framework named Bolt, and it achieves an $\sim! 5\times$ inference acceleration in comparison to its full-precision counterpart.
近年来，深度学习在基于脑电图（EEG）的情绪识别中受到了广泛关注。然而，深度学习方法通常耗时且内存占用量大，这阻碍了它们在资源受限设备上的实际应用。在本文中，我们提出了一种用于EEG情绪识别的二进制胶囊网络（Bi-CapsNet），其计算成本和内存占用较低。Bi-CapsNet将32位权重和激活值二值化为1位，并使用高效的按位运算代替浮点运算。为了解决反向传播中函数不连续的问题，我们使用连续函数来近似二值化过程。使用两个流行的EEG情绪数据库，即DEAP和DREAMER，进行性能评估。与全精度对应模型相比，Bi-CapsNet的计算成本降低了25倍以上，内存占用降低了5倍以上，而识别准确率仅下降不到1%。与一些最新的EEG情绪识别方法相比，该方法具有更具竞争力的性能。此外，Bi-CapsNet通过一个名为Bolt的开源二进制推理框架在手机上实现，与全精度对应模型相比，其推理速度提高了约5倍。
