Feasibility and pragmatics of classifying working memory load with an electroencephalograph

Grimes, David B.; Tan, Desney; Hudson, Scott E.; Shenoy, Pradeep; Rao, Rajesh P. N.

doi:10.1145/1357054.1357187

Cited by 166 publications

(152 citation statements)

References 32 publications

(31 reference statements)

Supporting

Mentioning

136

Contrasting

Order By: Relevance

“…Kramer linked an increase in beta and decreases in alpha and theta to an increase in task engagement [30]. Several studies also used EEG devices to classify mental tasks or states of cognitive load [21,32].…”

Section: Biometric Sensorsmentioning

confidence: 99%

Interruptibility of Software Developers and its Prediction Using Psycho-Physiological Sensors

Züger

Fritz

2015

Proceedings of the 33rd Annual ACM Conference on Human Factors in Computing Systems

View full text Add to dashboard Cite

Interruptions of knowledge workers are common and can cause a high cost if they happen at inopportune moments. With recent advances in psycho-physiological sensors and their link to cognitive and emotional states, we are interested whether such sensors might be used to measure interruptibility of a knowledge worker. In a lab and a field study with a total of twenty software developers, we examined the use of psycho-physiological sensors in a real-world context. The results show that a Naive Bayes classifier based on psychophysiological features can be used to automatically assess states of a knowledge worker's interruptibility with high accuracy in the lab as well as in the field. Our results demonstrate the potential of these sensors to avoid expensive interruptions in a real-world context. Based on brief interviews, we further discuss the usage of such an interruptibility measure and interruption support for software developers. Interruptibility of Software Developers and its Prediction Using Psycho-Physiological SensorsManuela Züger and Thomas Fritz Department of Informatics University of Zurich, Switzerland {zueger, fritz}@ifi.uzh.ch ABSTRACTInterruptions of knowledge workers are common and can cause a high cost if they happen at inopportune moments. With recent advances in psycho-physiological sensors and their link to cognitive and emotional states, we are interested whether such sensors might be used to measure interruptibility of a knowledge worker. In a lab and a field study with a total of twenty software developers, we examined the use of psycho-physiological sensors in a real-world context. The results show that a Naïve Bayes classifier based on psychophysiological features can be used to automatically assess states of a knowledge worker's interruptibility with high accuracy in the lab as well as in the field. Our results demonstrate the potential of these sensors to avoid expensive interruptions in a real-world context. Based on brief interviews, we further discuss the usage of such an interruptibility measure and interruption support for software developers.

show abstract

Section: Biometric Sensorsmentioning

confidence: 99%

Interruptibility of Software Developers and its Prediction Using Psycho-Physiological Sensors

Züger

Fritz

2015

Proceedings of the 33rd Annual ACM Conference on Human Factors in Computing Systems

View full text Add to dashboard Cite

show abstract

“…Except for 'X' in the 0-back task, letters were randomly selected from English consonants. Vowels were excluded to reduce the likeliness of participants developing chunking strategies which reduce mental effort, as suggested in [6].…”

Section: Experimental Design and Taskmentioning

confidence: 99%

Measuring workload using a combination of electroencephalography and near infrared spectroscopy

Coffey

Brouwer²,

Erp³

2012

Proceedings of the Human Factors and Ergonomics Society Annual

View full text Add to dashboard Cite

The ability to continuously monitor workload in a real-world environment would have important implications for the offline design of human machine interfaces as well as the real-time online improvement of interaction between humans and machines. The present study explored the usefulness of combining electroencephalography (EEG) with the newer technique of near infrared spectroscopy (NIRS), under data acquisition and processing conditions that could be applied to real-time usage, for example as an input to adaptive automation. Eight EEG channels (Cz, Pz, FCz, Fz, C3, C4, F3, and F4) and three NIRS channels over the left forehead were acquired simultaneously, during repetitions of blocks of three difficulty conditions of the N-back task. The resulting data were separated into five-second windows and binary classifications on condition were performed on bandpower-derived features for EEG, and average hemoglobin levels for NIRS. Each type of data was classified independently, and in combination. In general, EEG could be used to reliably classify workload condition for most subjects, whereas the NIRS signal was less helpful and did not contribute to classification accuracies when combined with EEG. Implications and future directions are discussed.

show abstract

“…Brain-Computer Interaction techniques (BCI) have been researched recently in order to provide interaction possibilities, e.g., for physically handicapped people [4]. Grimes et al [2] advanced the field by investigating brain waves and how to classify working memory load with the help of an EEG devices. Scherer et al [7] introduced an EEG-controlled Virtual Keyboard.…”

Section: Related Workmentioning

confidence: 99%

EEG-Based Measurement of Subjective Parameters in Evaluations

Cernea

Olech

Ebert

et al. 2011

Communications in Computer and Information Science

View full text Add to dashboard Cite

Abstract.Evaluating new approaches, be it new interaction techniques, new applications or even new hardware, is an important task, which has to be done to ensure both usability and user satisfaction. The drawback of evaluating subjective parameters is that this can be relatively time consuming, and the outcome is possibly quite imprecise. Considering the recent release of costefficient commercial EEG headsets, we propose the utilization of electroencephalographic (EEG) devices for evaluation purposes. The goal of our research is to evaluate if a commercial EEG headset can provide cutting-edge support during user studies and evaluations. Our results are encouraging and suggest that wireless EEG technology is a viable alternative for measuring subjectivity in evaluation scenarios.

show abstract

Feasibility and pragmatics of classifying working memory load with an electroencephalograph

Cited by 166 publications

References 32 publications

Interruptibility of Software Developers and its Prediction Using Psycho-Physiological Sensors

Interruptibility of Software Developers and its Prediction Using Psycho-Physiological Sensors

Measuring workload using a combination of electroencephalography and near infrared spectroscopy

EEG-Based Measurement of Subjective Parameters in Evaluations

Contact Info

Product

Resources

About