Investigating the generalizability of EEG-based cognitive load estimation across visualizations

Viral Parekh; C. V. Jawahar; Ramanathan Subramanian; Maneesh Bilalpur; Stefan Winkler; Shravan Kumar

doi:10.1145/3281151.3281160

Investigating the generalizability of EEG-based cognitive load estimation across visualizations

Viral Parekh, C. V. Jawahar, Ramanathan Subramanian, Maneesh Bilalpur, Stefan Winkler, Shravan Kumar

Research output: A Conference proceeding or a Chapter in Book › Conference contribution › peer-review

2 Citations (Scopus)

Abstract

We examine if EEG-based cognitive load (CL) estimation is generalizable across the character, spatial pattern, bar graph and pie chart-based visualizations for the n-back task. CL is estimated via two recent approaches: (a) Deep convolutional neural network [2], and (b) Proximal support vector machines [15]. Experiments reveal that CL estimation suffers across visualizations calling for for effective machine learning techniques to benchmark visual interface usability for a given analytic task.

Original language	English
Title of host publication	ICMI '18: Proceedings of the 20th International Conference on Multimodal Interaction
Pages	1-5
Number of pages	5
DOIs	https://doi.org/10.1145/3281151.3281160
Publication status	Published - 16 Oct 2018
Externally published	Yes
Event	20th International Conference on Multimodal Interaction, ICMI 2018 - Boulder, United States Duration: 16 Oct 2018 → 20 Oct 2018

Conference

Conference	20th International Conference on Multimodal Interaction, ICMI 2018
Country/Territory	United States
City	Boulder
Period	16/10/18 → 20/10/18

Access to Document

10.1145/3281151.3281160

https://arxiv.org/pdf/1809.04507.pdf

Cite this

@inproceedings{5130ec8162ef4e4e88e1374f81ad9440,

title = "Investigating the generalizability of EEG-based cognitive load estimation across visualizations",

abstract = "We examine if EEG-based cognitive load (CL) estimation is generalizable across the character, spatial pattern, bar graph and pie chart-based visualizations for the n-back task. CL is estimated via two recent approaches: (a) Deep convolutional neural network [2], and (b) Proximal support vector machines [15]. Experiments reveal that CL estimation suffers across visualizations calling for for effective machine learning techniques to benchmark visual interface usability for a given analytic task.",

keywords = "Cognitive Load Estimation, Convolutional Neural Network, EEG, Generalization, Proximal SVMs, Visual Interfaces",

author = "Viral Parekh and Jawahar, {C. V.} and Ramanathan Subramanian and Maneesh Bilalpur and Stefan Winkler and Shravan Kumar",

note = "Publisher Copyright: Copyright {\textcopyright} 2018 ACM ISBN. Copyright: Copyright 2019 Elsevier B.V., All rights reserved.; 20th International Conference on Multimodal Interaction, ICMI 2018 ; Conference date: 16-10-2018 Through 20-10-2018",

year = "2018",

month = oct,

day = "16",

doi = "10.1145/3281151.3281160",

language = "English",

pages = "1--5",

booktitle = "ICMI '18: Proceedings of the 20th International Conference on Multimodal Interaction",

}

Parekh, V, Jawahar, CV, Subramanian, R, Bilalpur, M, Winkler, S & Kumar, S 2018, Investigating the generalizability of EEG-based cognitive load estimation across visualizations. in ICMI '18: Proceedings of the 20th International Conference on Multimodal Interaction. pp. 1-5, 20th International Conference on Multimodal Interaction, ICMI 2018, Boulder, United States, 16/10/18. https://doi.org/10.1145/3281151.3281160

TY - GEN

T1 - Investigating the generalizability of EEG-based cognitive load estimation across visualizations

AU - Parekh, Viral

AU - Jawahar, C. V.

AU - Subramanian, Ramanathan

AU - Bilalpur, Maneesh

AU - Winkler, Stefan

AU - Kumar, Shravan

PY - 2018/10/16

Y1 - 2018/10/16

N2 - We examine if EEG-based cognitive load (CL) estimation is generalizable across the character, spatial pattern, bar graph and pie chart-based visualizations for the n-back task. CL is estimated via two recent approaches: (a) Deep convolutional neural network [2], and (b) Proximal support vector machines [15]. Experiments reveal that CL estimation suffers across visualizations calling for for effective machine learning techniques to benchmark visual interface usability for a given analytic task.

AB - We examine if EEG-based cognitive load (CL) estimation is generalizable across the character, spatial pattern, bar graph and pie chart-based visualizations for the n-back task. CL is estimated via two recent approaches: (a) Deep convolutional neural network [2], and (b) Proximal support vector machines [15]. Experiments reveal that CL estimation suffers across visualizations calling for for effective machine learning techniques to benchmark visual interface usability for a given analytic task.

KW - Cognitive Load Estimation

KW - Convolutional Neural Network

KW - EEG

KW - Generalization

KW - Proximal SVMs

KW - Visual Interfaces

UR - http://www.scopus.com/inward/record.url?scp=85057391913&partnerID=8YFLogxK

U2 - 10.1145/3281151.3281160

DO - 10.1145/3281151.3281160

M3 - Conference contribution

AN - SCOPUS:85057391913

SP - 1

EP - 5

BT - ICMI '18: Proceedings of the 20th International Conference on Multimodal Interaction

T2 - 20th International Conference on Multimodal Interaction, ICMI 2018

Y2 - 16 October 2018 through 20 October 2018

ER -

Investigating the generalizability of EEG-based cognitive load estimation across visualizations

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this