@INPROCEEDINGS{7146546,
author={Herff, C. and Fortmann, O. and Chun-Yu Tse and Xiaoqin Cheng and Putze, F. and Heger, D. and Schultz, T.},
booktitle={Neural Engineering (NER), 2015 7th International IEEE/EMBS Conference on},
title={Hybrid fNIRS-EEG based discrimination of 5 levels of memory load},
year={2015},
pages={5-8},
url={https://www.csl.uni-bremen.de/cms/images/documents/publications/ner_2015_paper_cherff.pdf},
abstract={In this study, we show that both electroencephalograhy (EEG) and functional Near-Infrared Spectroscopy (fNIRS) can be used to discriminate between 5 levels of memory load. We induce memory load with the memory updating task, which is known to robustly generate memory load and allows us to define 5 different levels of load. Typical experiments only discriminate between low and high workload or up to a maximum of three classes. To the best of our knowledge, the memory updating task has not been used in combination with brain activity measurements before. Here, accuracies of up to 93% are achieved for the binary classification between very high and very low workload. On average, two levels of workload could be discriminated with 74% accuracy. Classification between the full five classes yielded 44% accuracy on average. Despite the fact that EEG results consistently outperformed the results obtained with fNIRS, we could show that the feature-level fusion of both modalities increased robustness of classification results. A reliable discrimination between different levels of memory load could be used to adapt user interfaces or present the right amount of information to a learner.},
keywords={cognition;electroencephalography;feature extraction;infrared spectroscopy;medical signal processing;neurophysiology;sensor fusion;signal classification;user interfaces;5-level memory load discrimination;binary classification accuracy;brain activity measurements;classification robustness;electroencephalograhy;feature-level fusion;five-class classification accuracy;functional near-infrared spectroscopy;high memory workload discrimination;hybrid fNIRS-EEG based discrimination;low memory workload discrimination;memory load generation;memory updating task;three-class workload discrimination;two-level workload discrimination accuracy;user interface;Accuracy;Brain;Electrodes;Electroencephalography;Feature extraction;Robustness;Spectroscopy},
doi={10.1109/NER.2015.7146546},
month={April},}