Assessing user mental workload for smartphone applications with built-in sensors

Liang Wang; Tao Gu; Alex X. Liu; Hengzhi Yao; Xianping Tao; Jian Lu

doi:10.1109/MPRV.2018.2873851

Assessing user mental workload for smartphone applications with built-in sensors

Liang Wang, Tao Gu, Alex X. Liu, Hengzhi Yao, Xianping Tao, Jian Lu

Research output: Contribution to journal › Article › peer-review

6 Citations (Scopus)

Abstract

This work proposes a novel three-dimensional model to represent users' mental workload when using smartphone applications. We validate this model by studying the factors' perceptual independence and interactions using data collected from 22 participants. By analyzing the correlations between the factors of mental workload and tap strength captured by smartphones' built-in sensors, we discover tap strength is significantly affected by and can potentially be used to infer the hidden states of mental workload. We build a prototype system and show the effectiveness of assessing mental workload using tap strength without additional human or device costs in both laboratory and real-world settings.

Original language	English
Pages (from-to)	59-70
Number of pages	12
Journal	IEEE Pervasive Computing
Volume	18
Issue number	1
DOIs	https://doi.org/10.1109/MPRV.2018.2873851
Publication status	Published - Jan 2019
Externally published	Yes

Keywords

Smart phones
Solid modeling
Data models
Sensors
Computer applications

Access to Document

10.1109/MPRV.2018.2873851

Cite this

@article{9a176e41a822473ebf8ce14542fabeb2,

title = "Assessing user mental workload for smartphone applications with built-in sensors",

abstract = "This work proposes a novel three-dimensional model to represent users' mental workload when using smartphone applications. We validate this model by studying the factors' perceptual independence and interactions using data collected from 22 participants. By analyzing the correlations between the factors of mental workload and tap strength captured by smartphones' built-in sensors, we discover tap strength is significantly affected by and can potentially be used to infer the hidden states of mental workload. We build a prototype system and show the effectiveness of assessing mental workload using tap strength without additional human or device costs in both laboratory and real-world settings.",

keywords = "Smart phones, Solid modeling, Data models, Sensors, Computer applications",

author = "Liang Wang and Tao Gu and Liu, {Alex X.} and Hengzhi Yao and Xianping Tao and Jian Lu",

year = "2019",

month = jan,

doi = "10.1109/MPRV.2018.2873851",

language = "English",

volume = "18",

pages = "59--70",

journal = "IEEE Pervasive Computing",

issn = "1536-1268",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

number = "1",

}

TY - JOUR

T1 - Assessing user mental workload for smartphone applications with built-in sensors

AU - Wang, Liang

AU - Gu, Tao

AU - Liu, Alex X.

AU - Yao, Hengzhi

AU - Tao, Xianping

AU - Lu, Jian

PY - 2019/1

Y1 - 2019/1

N2 - This work proposes a novel three-dimensional model to represent users' mental workload when using smartphone applications. We validate this model by studying the factors' perceptual independence and interactions using data collected from 22 participants. By analyzing the correlations between the factors of mental workload and tap strength captured by smartphones' built-in sensors, we discover tap strength is significantly affected by and can potentially be used to infer the hidden states of mental workload. We build a prototype system and show the effectiveness of assessing mental workload using tap strength without additional human or device costs in both laboratory and real-world settings.

AB - This work proposes a novel three-dimensional model to represent users' mental workload when using smartphone applications. We validate this model by studying the factors' perceptual independence and interactions using data collected from 22 participants. By analyzing the correlations between the factors of mental workload and tap strength captured by smartphones' built-in sensors, we discover tap strength is significantly affected by and can potentially be used to infer the hidden states of mental workload. We build a prototype system and show the effectiveness of assessing mental workload using tap strength without additional human or device costs in both laboratory and real-world settings.

KW - Smart phones

KW - Solid modeling

KW - Data models

KW - Sensors

KW - Computer applications

UR - http://www.scopus.com/inward/record.url?scp=85065394555&partnerID=8YFLogxK

UR - http://purl.org/au-research/grants/arc/DP180103932

U2 - 10.1109/MPRV.2018.2873851

DO - 10.1109/MPRV.2018.2873851

M3 - Article

SN - 1536-1268

VL - 18

SP - 59

EP - 70

JO - IEEE Pervasive Computing

JF - IEEE Pervasive Computing

IS - 1

ER -

Assessing user mental workload for smartphone applications with built-in sensors

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this