Spatial Adaptation Layer: Interpretable Domain Adaptation For Biosignal Sensor Array Applications
- URL: http://arxiv.org/abs/2409.08058v2
- Date: Wed, 29 Jan 2025 14:50:58 GMT
- Title: Spatial Adaptation Layer: Interpretable Domain Adaptation For Biosignal Sensor Array Applications
- Authors: Joao Pereira, Michael Alummoottil, Dimitrios Halatsis, Dario Farina,
- Abstract summary: We propose the Spatial Adaptation Layer (SAL), which can be applied to any biosignal array model.
We also introduce learnable baseline normalization (LBN) to reduce baseline fluctuations.
Tested on two HD-sEMG gesture recognition datasets, SAL and LBN outperformed standard fine-tuning on regular arrays.
- Score: 0.7499722271664147
- License:
- Abstract: Machine learning offers promising methods for processing signals recorded with wearable devices such as surface electromyography (sEMG) and electroencephalography (EEG). However, in these applications, despite high within-session performance, intersession performance is hindered by electrode shift, a known issue across modalities. Existing solutions often require large and expensive datasets and/or lack robustness and interpretability. Thus, we propose the Spatial Adaptation Layer (SAL), which can be applied to any biosignal array model and learns a parametrized affine transformation at the input between two recording sessions. We also introduce learnable baseline normalization (LBN) to reduce baseline fluctuations. Tested on two HD-sEMG gesture recognition datasets, SAL and LBN outperformed standard fine-tuning on regular arrays, achieving competitive performance even with a logistic regressor, with orders of magnitude less, physically interpretable parameters. Our ablation study showed that forearm circumferential translations account for the majority of performance improvements.
Related papers
- CEReBrO: Compact Encoder for Representations of Brain Oscillations Using Efficient Alternating Attention [53.539020807256904]
We introduce a Compact for Representations of Brain Oscillations using alternating attention (CEReBrO)
Our tokenization scheme represents EEG signals at a per-channel patch.
We propose an alternating attention mechanism that jointly models intra-channel temporal dynamics and inter-channel spatial correlations, achieving 2x speed improvement with 6x less memory required compared to standard self-attention.
arXiv Detail & Related papers (2025-01-18T21:44:38Z) - Graph Adapter of EEG Foundation Models for Parameter Efficient Fine Tuning [1.8946099300030472]
We propose EEG-GraphAdapter (EGA), a parameter-efficient fine-tuning (PEFT) approach designed to address these challenges.
EGA is integrated into a pre-trained temporal backbone model as a GNN-based module, freezing the backbone and allowing only the adapter to be fine-tuned.
Experimental evaluations on two healthcare-related downstream tasks-Major Depressive Disorder (MDD) and Abnormality Detection (TUAB)-show that EGA improves performance by up to 16.1% in F1-score compared with the backbone BENDR model.
arXiv Detail & Related papers (2024-11-25T07:30:52Z) - Automatic Classification of Sleep Stages from EEG Signals Using Riemannian Metrics and Transformer Networks [6.404789669795639]
In sleep medicine, assessing the evolution of a subject's sleep often involves the costly manual scoring of electroencephalographic (EEG) signals.
We present a novel way of integrating learned signal-wise features into said matrices without sacrificing their Symmetric Definite Positive (SPD) nature.
arXiv Detail & Related papers (2024-10-18T06:49:52Z) - Multi-Source and Test-Time Domain Adaptation on Multivariate Signals using Spatio-Temporal Monge Alignment [59.75420353684495]
Machine learning applications on signals such as computer vision or biomedical data often face challenges due to the variability that exists across hardware devices or session recordings.
In this work, we propose Spatio-Temporal Monge Alignment (STMA) to mitigate these variabilities.
We show that STMA leads to significant and consistent performance gains between datasets acquired with very different settings.
arXiv Detail & Related papers (2024-07-19T13:33:38Z) - Physics-informed and Unsupervised Riemannian Domain Adaptation for Machine Learning on Heterogeneous EEG Datasets [53.367212596352324]
We propose an unsupervised approach leveraging EEG signal physics.
We map EEG channels to fixed positions using field, source-free domain adaptation.
Our method demonstrates robust performance in brain-computer interface (BCI) tasks and potential biomarker applications.
arXiv Detail & Related papers (2024-03-07T16:17:33Z) - Tackling Electrode Shift In Gesture Recognition with HD-EMG Electrode
Subsets [0.8192907805418583]
We propose training on a collection of input channel subsets and augmenting our training distribution with data from different electrode locations.
Our method increases robustness against electrode shift and results in significantly higher intersession performance across subjects and classification algorithms.
arXiv Detail & Related papers (2024-01-05T12:13:00Z) - DGSD: Dynamical Graph Self-Distillation for EEG-Based Auditory Spatial
Attention Detection [49.196182908826565]
Auditory Attention Detection (AAD) aims to detect target speaker from brain signals in a multi-speaker environment.
Current approaches primarily rely on traditional convolutional neural network designed for processing Euclidean data like images.
This paper proposes a dynamical graph self-distillation (DGSD) approach for AAD, which does not require speech stimuli as input.
arXiv Detail & Related papers (2023-09-07T13:43:46Z) - Convolutional Monge Mapping Normalization for learning on sleep data [63.22081662149488]
We propose a new method called Convolutional Monge Mapping Normalization (CMMN)
CMMN consists in filtering the signals in order to adapt their power spectrum density (PSD) to a Wasserstein barycenter estimated on training data.
Numerical experiments on sleep EEG data show that CMMN leads to significant and consistent performance gains independent from the neural network architecture.
arXiv Detail & Related papers (2023-05-30T08:24:01Z) - Decision Forest Based EMG Signal Classification with Low Volume Dataset
Augmented with Random Variance Gaussian Noise [51.76329821186873]
We produce a model that can classify six different hand gestures with a limited number of samples that generalizes well to a wider audience.
We appeal to a set of more elementary methods such as the use of random bounds on a signal, but desire to show the power these methods can carry in an online setting.
arXiv Detail & Related papers (2022-06-29T23:22:18Z) - Adaptive Spike-Like Representation of EEG Signals for Sleep Stages
Scoring [6.644008481573341]
We propose an adaptive scheme to encode, filter and accumulate the input signals and the weight features by the half-Gaussian probabilities of signal intensities.
Experiments on the largest public dataset against state-of-the-art methods validate the effectiveness of our proposed method and reveal promising future directions.
arXiv Detail & Related papers (2022-04-02T11:21:49Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.