A Simple Channel Compression Method for Brain Signal Decoding on Classification Task

TL;DR

This paper introduces a simple learnable channel compression method for ECoG signals in brain-computer interfaces, significantly reducing model size and training resources while improving classification performance.

Contribution

It proposes a novel, straightforward channel compression technique using a learnable matrix, enhancing efficiency and accuracy in brain signal decoding.

Findings

Reduced GPU memory usage by over 68%.

Increased training speed by up to 4.65 times.

Achieved state-of-the-art accuracy on the dataset.

Abstract

In the application of brain-computer interface (BCI), while pursuing accurate decoding of brain signals, we also need consider the computational efficiency of BCI devices. ECoG signals are multi-channel temporal signals which is collected using a high-density electrode array at a high sampling frequency. The data between channels has a high similarity or redundancy in the temporal domain. The redundancy of data not only reduces the computational efficiency of the model, but also overwhelms the extraction of effective features, resulting in a decrease in performance. How to efficiently utilize ECoG multi-channel signals is one of the research topics. Effective channel screening or compression can greatly reduce the model size, thereby improving computational efficiency, this would be a good direction to solve the problem. Based on previous work [1], this paper proposes a very simple channel compression method, which uses a learnable matrix to perform matrix multiplication on the original channels, that is, assigning weights to the channels and then linearly add them up. This effectively reduces the number of final channels. In the experiment, we used the vision-based ECoG multi-classification dataset owned by our laboratory to test the proposed channel selection (compression) method. We found that the new method can compress the original 128-channel ECoG signal to 32 channels (of which subject MonJ is compressed to 8 channels), greatly reducing the size of the model. The demand for GPU memory resources during model training is reduced by about 68.57%, 84.33% for each subject respectively; the model training speed also increased up around 3.82, 4.65 times of the original speed for each subject respectively. More importantly, the performance of the model has improved by about 1.10% compared with our previous work, reached the SOTA level of our unique visual based ECoG dataset