Physiological Noise Filtering in Functional Near-Infrared Spectroscopy Signals Using Wavelet Transform and Long-Short Term Memory Networks

Abstract

Activated channels of functional near-infrared spectroscopy are typically identified using the desired hemodynamic response function (dHRF) generated by a trial period. However, this approach is not possible for an unknown trial period. In this paper, an innovative method not using the dHRF is proposed, which extracts fluctuating signals during the resting state using maximal overlap discrete wavelet transform, identifies low-frequency wavelets corresponding to physiological noise, trains them using long-short term memory networks, and predicts/subtracts them during the task session. The motivation for prediction is to maintain the phase information of physiological noise at the start time of a task, which is possible because the signal is extended from the resting state to the task session. This technique decomposes the resting state data into nine wavelets and uses the fifth to ninth wavelets for learning and prediction. In the eighth wavelet, the prediction error difference between the with and without dHRF from the 15-s prediction window appeared to be the largest. Considering the difficulty in removing physiological noise when the activation period is near the physiological noise, the proposed method can be an alternative solution when the conventional method is not applicable. In passive brain-computer interfaces, estimating the brain signal starting time is necessary.

Spectroscopic assessment of flavor-related chemical compounds in fresh tea shoots using deep learning

“…7). To qualitatively identify patterns, encompassing both local and global aspects, and to isolate local patterns within the branch layers of reflectance and transmittance, a high-pass filter was employed in this study [43,44]. The high-pass filter adopts a fast Fourier transform that can enhance the minor contribution or local aspect by capturing the high frequency in the feature importance [35].…”

Fcg-Former: Identification of Functional Groups in FTIR Spectra Using Enhanced Transformer-Based Model

“…In recent years, transformer models have emerged as the cornerstone of various machine learning applications, revolutionizing the field with their remarkable capabilities in handling diverse data types such as signals, images, speech, and text . The transformer architecture, initially introduced for natural language processing tasks, has showcased exceptional performance across various domains, including translation, , time series forecasting, − and signal classification. − Overview of the existing landscape of machine learning models for functional group characterization, traditional models, such as 1D-CNNs, recurrent neural networks (RNNs), and long short-term memory, have historically dominated functional group analysis tasks. ,,,− Despite these achievements, there remains a noticeable gap in the literature regarding the application of transformer models to chemical spectra signals, particularly in the functional group characterization data sets.…”