Search arXiv⌕ Search
Home/Archive/arXiv

arXiv · 2411.16165

Explainable MST-ECoGNet Decode Visual Information from ECoG Signal

Changqing JI
View original source ↗Read source document ↗Export metadata ↓

Abstract

In the application of brain-computer interface (BCI), we not only need to accurately decode brain signals,but also need to consider the explainability of the decoding process, which is related to the reliability of the model. In the process of designing a decoder or processing brain signals, we need to explain the discovered phenomena in physical or physiological way. An explainable model not only makes the signal processing process clearer and improves reliability, but also allows us to better understand brain activities and facilitate further exploration of the brain. In this paper, we systematically analyze the multi-classification dataset of visual brain signals ECoG, using a simple and highly explainable method to explore the ways in which ECoG carry visual information, then based on these findings, we propose a model called MST-ECoGNet that combines traditional mathematics and deep learning. The main contributions of this paper are: 1) found that ECoG time-frequency domain information carries visual information, provides important features for visual classification tasks. The mathematical method of MST (Modified S Transform) can effectively extract temporal-frequency domain information; 2) The spatial domain of ECoG signals also carries visual information, the unique spatial features are also important features for classification tasks; 3) The real and imaginary information in the time-frequency domain are complementary. The effective combination of the two is more helpful for classification tasks than using amplitude information alone; 4) Finally, compared with previous work, our model is smaller and has higher performance: for the object MonJ, the model size is reduced to 10.82% of base model, the accuracy is improved by 6.63%; for the object MonC, the model size is reduced to 8.78%, the accuracy is improved by 16.63%.

Explore related subjects

math.NAcs.NA

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Changqing JI. 2024-11-25. Explainable MST-ECoGNet Decode Visual Information from ECoG Signal. https://arxiv.org/abs/2411.16165

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

How many continuous measurements are needed to learn a vector?

One can recover vectors from $\mathbb{R}^m$ with arbitrary precision, using only $\lceil \log_2(m)\rceil +1$ continuous measurements that are chosen adaptively. This surprising result is explained and discussed, and we present applications to infinite-dimensional approximation problems.

math.NA↗
arXiv2026

IterativeCUR: Large Rank-Adaptive Approximation From a Small Recycled Sketch

The computation of accurate low-rank matrix approximations is central to improving the scalability of various techniques in machine learning, uncertainty quantification, and control. Traditionally, low-rank approximations are constructed using SVD-based approaches such as truncated SVD or Randomized SVD. Although these SVD approaches---especially Randomized SVD---have proven to be very computationally efficient, other low-rank approximation methods can offer even greater performance. One such approach is the CUR decomposition, which forms a low-rank approximation using direct row and column subsets of a matrix. Because CUR uses direct matrix subsets, it is also often better able to preserve native matrix structures like sparsity or non-negativity than SVD-based approaches and can facilitate data interpretation in many contexts. This paper introduces IterativeCUR, which draws on previous work in randomized numerical linear algebra to build a new algorithm that is highly competitive compared to prior work. IterativeCUR is adaptive in the sense that it takes as an input parameter the desired tolerance $ε$ and outputs (with arbitrarily high probability) an approximation of error bounded by $ε$, rather than requiring an a priori guess of the numerical rank. IterativeCUR typically runs significantly faster than both existing CUR algorithms and techniques such as Randomized SVD. Its asymptotic complexity is $\mathcal{O}(mn + (m+n)r^2)$ for an $m\times n$ matrix of output rank $r$. IterativeCUR relies on a single small sketch from the matrix that is successively downdated as the algorithm proceeds. We demonstrate through extensive experiments that IterativeCUR achieves up to $4\times$ speed-up over state-of-the-art pivoting-on-sketch approaches with no loss of accuracy, and up to $40\times$ speed-up over rank-adaptive randomized SVD approaches.

math.NA↗
arXiv2026

Multigrid with Linear Storage Complexity

As the discretization error for the solution of a partial differential equation (PDE) decreases, the precision required to store the corresponding coefficients naturally increases. Storing the solution's finite element coefficients explicitly requires $\mathcal O(n \log n)$ bits of storage, where $n$ is the number of degrees of freedom (DoFs). This paper presents a full multigrid method to compute the solution in a compressed format that reduces the storage complexity of the solution and intermediate vectors to $\mathcal O(n)$ bits. This reduction allows a matrix-free implementation to solve elliptic PDEs with an overall linear space complexity. For problems limited by the memory capacity of current supercomputers, we expect a memory footprint reduction of about an order of magnitude compared to state-of-the-art mixed-precision methods. We demonstrate the applicability of our algorithm by solving two model problems. Depending on the PDE and polynomial degree, but irrespective of the problem size, the solution vector on the finest grid requires between 4 and 12 bits per DoF, and the residual and correction require 3 to 6 bits each. Additional data is stored on the coarse grids with modestly increasing bit widths toward coarser grids.

math.NA↗