In-Ear SpO2 for Classification of Cognitive Workload

被引：4

作者：

Davies, Harry J. ^{[1
]}

Williams, Ian ^{[2
]}

Hammour, Ghena ^{[2
]}

Yarici, Metin ^{[2
]}

Stacey, Michael J. ^{[3
]}

Seemungal, Barry M. ^{[4
]}

Mandic, Danilo P. ^{[2
]}

机构：

[1] Imperial Coll London, Dept Elect Engn, London SW7 2AZ, England

[2] Imperial Coll London, Dept Elect & Elect Engn, London SW7 2AZ, England

[3] Royal Ctr Def Med, Acad Dept Mil Med, Birmingham B15 2WB, England

[4] Imperial Coll London, Dept Med, London SW7 2AZ, England

来源：

IEEE TRANSACTIONS ON COGNITIVE AND DEVELOPMENTAL SYSTEMS | 2023年 / 15卷 / 02期

基金：

英国工程与自然科学研究理事会;

关键词：

Index Terms-Biomedical engineering; biomedical signal pro-cessing; brain-computer interfaces; cognitive processes; pho-toplethysmography; pulse oximeter; random forests; wearable health monitoring systems; TRANSIENT INCREASE; OXYGEN; PERFORMANCE;

D O I：

10.1109/TCDS.2022.3196841

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

The brain is the most metabolically active organ in the body, which increases its metabolic activity and, thus, oxygen consumption, with increasing cognitive demand. This motivates us to question whether the increased cognitive workload may be measurable through changes in blood oxygen saturation. To this end, we explore the feasibility of cognitive workload tracking based on in-ear SpO(2) measurements, which are known to be both robust and exhibit minimal delay. We consider a cognitive workload assessment based on an N-back task with a randomized order. It is shown that the 2-back and 3-back tasks (high cognitive workload) yield either the lowest median absolute SpO(2) or largest median decrease in SpO(2) in all of the subjects, indicating a measurable and statistically significant decrease in blood oxygen in response to the increased cognitive workload. This makes it possible to classify the four N-back task categories, over 5-s epochs, with a mean accuracy of 90.6%, using features derived from in-ear pulse oximetry, including SpO(2), pulse rate, and respiration rate. These findings suggest that in-ear SpO(2) measurements provide sufficient information for the reliable classification of cognitive workload over short time windows, which promises a new avenue for real-time cognitive workload tracking.

引用

页码：950 / 958

页数：9

共 40 条

[31] Signal processing methods for pulse oximetry [J].

Rusch, TL ;

Sankar, R ;

Scharf, JE .

COMPUTERS IN BIOLOGY AND MEDICINE, 1996, 26 (02) :143-159

[32] Cognitive performance, hyperoxia, and heart rate following oxygen administration in healthy young adults [J].

Scholey, AB ;

Moss, MC ;

Neave, N ;

Wesnes, K .

PHYSIOLOGY & BEHAVIOR, 1999, 67 (05) :783-789

[33] SpO2 values in acute medical admissions breathing air-Implications for the British Thoracic Society guideline for emergency oxygen use in adult patients? [J].

Smith, Gary B. ;

Prytherch, David R. ;

Watson, Duncan ;

Forde, Val ;

Windsor, Alastair ;

Schmidt, Paul E. ;

Featherstone, Peter I. ;

Higgins, Bernie ;

Meredith, Paul .

RESUSCITATION, 2012, 83 (10) :1201-1205

[34] Classification of a Driver's cognitive workload levels using artificial neural network on ECG signals [J].

Tjolleng, Amir ;

Jung, Kihyo ;

Hong, Wongi ;

Lee, Wonsup ;

Lee, Baekhee ;

You, Heecheon ;

Son, Joonwoo ;

Park, Seikwon .

APPLIED ERGONOMICS, 2017, 59 :326-332

[35]

Tsunashima Hitoshi, 2009, Comput Intell Neurosci, P164958, DOI 10.1155/2009/164958

[36] Resolving Ambiguities in the LF/HF Ratio: LF-HF Scatter Plots for the Categorization of Mental and Physical Stress from HRV [J].

von Rosenberg, Wilhelm ;

Chanwimalueang, Theerasak ;

Adjei, Tricia ;

Jaffer, Usman ;

Goverdovsky, Valentin ;

Mandic, Danilo P. .

FRONTIERS IN PHYSIOLOGY, 2017, 8

[37] A data-driven framework for learners' cognitive load detection using ECG-PPG physiological feature fusion and XGBoost classification [J].

Wang, Chixiang ;

Guo, Junqi .

2018 INTERNATIONAL CONFERENCE ON IDENTIFICATION, INFORMATION AND KNOWLEDGE IN THE INTERNET OF THINGS, 2019, 147 :338-348

[38]

Wang R, 2018, IEEE INT C INT ROBOT, P3060, DOI 10.1109/IROS.2018.8594305

[39] Pattern Recognition of Momentary Mental Workload Based on Multi-Channel Electrophysiological Data and Ensemble Convolutional Neural Networks [J].

Zhang, Jianhua ;

Li, Sunan ;

Wang, Rubin .

FRONTIERS IN NEUROSCIENCE, 2017, 11

[40]

Zhu J, 2009, STAT INTERFACE, V2, P349

← 1 2 3 4 →