# fNIRSAtlas: A Large-Scale Benchmark for Functional Near-Infrared Spectroscopy Classification

DevFeed: [fNIRSAtlas: A Large-Scale Benchmark for Functional Near-Infrared Spectroscopy Classification](<https://devfeed.tech/articles/fnirsatlas-a-large-scale-benchmark-for-functional-near-infrared-spectroscopy-classification-125131.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.10082>)

Author: Kalle M\\"akel\\"a, Tuukka Ruotsalo

Published: 2026-11-10T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Benchmark](<https://devfeed.tech/topics/benchmark.md>)

Tags: [arithmetic](<https://devfeed.tech/tags/arithmetic.md>), [automated](<https://devfeed.tech/tags/automated.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [brain](<https://devfeed.tech/tags/brain.md>), [classification](<https://devfeed.tech/tags/classification.md>), [code](<https://devfeed.tech/tags/code.md>), [collections](<https://devfeed.tech/tags/collections.md>), [comparison](<https://devfeed.tech/tags/comparison.md>), [cross](<https://devfeed.tech/tags/cross.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [data](<https://devfeed.tech/tags/data.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [decoding](<https://devfeed.tech/tags/decoding.md>), [deep](<https://devfeed.tech/tags/deep.md>), [deep-learning](<https://devfeed.tech/tags/deep-learning.md>), [emotion](<https://devfeed.tech/tags/emotion.md>), [functional](<https://devfeed.tech/tags/functional.md>), [infrared](<https://devfeed.tech/tags/infrared.md>), [large](<https://devfeed.tech/tags/large.md>), [scale](<https://devfeed.tech/tags/scale.md>), [spectroscopy](<https://devfeed.tech/tags/spectroscopy.md>)

## AI overview

fNIRSAtlas combines 23 classification tasks from 19 public fNIRS data collections, covering motor, cognitive, and emotion paradigms, in an automated pipeline from raw data to evaluation. It standardizes both cross-subject and within-subject tasks to enable reproducible comparisons and evaluates baseline methods from fNIRS, neuroimaging, and time-series machine learning. The reported results vary substantially by task; methods tested on limited data, especially deep learning approaches, often do not generalize beyond their original evaluation. The benchmark is presented as open and extensible, though the supplied abstract gives no task-level scores or details about individual methods.

## Source excerpt

arXiv:2611.10082v1 Announce Type: new Abstract: Functional near-infrared spectroscopy (fNIRS) is a promising modality for brain-computer interfaces and cognitive state decoding, but progress in machine learning for fNIRS has been limited by small, isolated datasets and inconsistent evaluation protocols. We introduce fNIRSAtlas, the largest open benchmark for fNIRS classification to date, comprising 23 classification tasks from 19 public data collections, spanning diverse experimental paradigms, including motor execution, motor imagery, mental arithmetic, working memory, and emotion recognition. fNIRSAtlas provides a fully automated pipeline from raw data to evaluation and defines standardized benchmark tasks for both cross-subject and within-subject classification, ensuring reproducible comparison of methods. We evaluate a variety of baseline models from fNIRS and related neuroimaging and time-series machine learning literature on the benchmark. Our results demonstrate that performance varies substantially across tasks and that methods validated on limited data -- especially deep learning approaches -- often fail to generalize beyond their original evaluation. fNIRSAtlas serves as an extensible, open, and reproducible benchmark to support more robust and cumulative progress in machine learning for fNIRS data. Our code and data can be found at https://fnirsatlas.github.io.