Simple But Effective: Rethinking the Ability of Deep Learning in fNIRS to Exclude Abnormal Input (2402.18112v2)
Abstract: Functional near-infrared spectroscopy (fNIRS) is a non-invasive technique for monitoring brain activity. To better understand the brain, researchers often use deep learning to address the classification challenges of fNIRS data. Our study shows that while current networks in fNIRS are highly accurate for predictions within their training distribution, they falter at identifying and excluding abnormal data which is out-of-distribution, affecting their reliability. We propose integrating metric learning and supervised methods into fNIRS research to improve networks capability in identifying and excluding out-of-distribution outliers. This method is simple yet effective. In our experiments, it significantly enhances the performance of various networks in fNIRS, particularly transformer-based one, which shows the great improvement in reliability. We will make our experiment data available on GitHub.
- fnirs-based brain-computer interfaces: a review. Frontiers in human neuroscience, 9:3, 2015.
- Frans F Jöbsis. Noninvasive, infrared monitoring of cerebral and myocardial oxygen sufficiency and circulatory parameters. Science, 198(4323):1264–1267, 1977.
- Deep learning in fnirs: a review. Neurophotonics, 9(4):041411–041411, 2022.
- A brief review on the history of human functional near-infrared spectroscopy (fnirs) development and fields of application. Neuroimage, 63(2):921–935, 2012.
- The origin of extracellular fields and currents—eeg, ecog, lfp and spikes. Nature reviews neuroscience, 13(6):407–420, 2012.
- Nikos K Logothetis. What we can do and what we cannot do with fmri. Nature, 453(7197):869–878, 2008.
- Open access dataset for eeg+ nirs single-trial classification. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 25(10):1735–1745, 2016.
- Classification of schizophrenia using general linear model and support vector machine via fnirs. Physical and Engineering Sciences in Medicine, 43:1151–1160, 2020.
- Domain adaptation for robust workload level alignment between sessions and subjects using fnirs. Journal of Biomedical Optics, 26(2):022908–022908, 2021.
- A novel multimodal approach for hybrid brain–computer interface. IEEE Access, 8:89909–89918, 2020.
- Pain assessment based on fnirs using bi-lstm rnns. In 2021 10th International IEEE/EMBS Conference on Neural Engineering (NER), pages 399–402. IEEE, 2021.
- Transformer model for functional near-infrared spectroscopy classification. IEEE Journal of Biomedical and Health Informatics, 26(6):2559–2569, 2022.
- Rethinking delayed hemodynamic responses for fnirs classification. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2023.
- A baseline for detecting misclassified and out-of-distribution examples in neural networks. arXiv preprint arXiv:1610.02136, 2016.
- Enhancing the reliability of out-of-distribution image detection in neural networks. arXiv preprint arXiv:1706.02690, 2017.
- Training confidence-calibrated classifiers for detecting out-of-distribution samples. arXiv preprint arXiv:1711.09325, 2017.
- Metric learning for novelty and anomaly detection. arXiv preprint arXiv:1808.05492, 2018.
- Self-supervised learning for generalizable out-of-distribution detection. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 34, pages 5216–5223, 2020.
- Open-access fnirs dataset for classification of unilateral finger-and foot-tapping. Electronics, 8(12):1486, 2019.
- System for long-term measurement of cerebral blood and tissue oxygenation on newborn infants by near infra-red transillumination. Medical and Biological Engineering and Computing, 26:289–294, 1988.
- Standardized description of the feature extraction process to transform raw data into meaningful information for enhancing data reuse: Consensus study. JMIR Medical Informatics, 10(10):e38936, 2022.