Relationships between physiological signals and stress levels in the case of automated technology failure

Branstrom, Celeste; Jeong, Heejin; Park, Jaehyun; Lee, Byung-Cheol; Park, Jangwoon

doi:10.1007/s42454-019-00003-w

Cited by 6 publications

(4 citation statements)

References 15 publications

(16 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The general assumption of this study is that an AI failure and unreliability cause increased stress based on a low trust in AI system operations owing to unpredictable AI reactions. A connection between trust and stress was described in previous research [9], [33], where it was found that AI mistakes and unreliability cause a higher cognitive workload and mental stress with decreased user trust. In other words, if the AI system fails or is unreliable, then the operator stress increases and the trust level decreases.…”

Section: B Relationships Among Emotional State Perception and Ai Operation Of Usersmentioning

confidence: 74%

“…2) APPARATUS A previous program developed using Visual Studio C# (Visual Studio 2015, Microsoft Co., USA) was applied to conduct the experiment [33], [34]. The program included four different auto-proofreading sessions (i.e., sessions A, B, C, and D) [9]: Session A: A reliable auto-proofreading condition indicating a grammatical error with an underline and without providing a suggestion (word).…”

Section: B Experiments 2: English Proofreading Software Using Ai 1) Participantsmentioning

confidence: 99%

“…A connection between trust and stress existed when there were AI mistakes and unreliability. This aspect was explained through writing task performance using AI software [9], [10]. In case of AI system failures, the user's trust gradually decreases and their stress increases.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

User Stress in Artificial Intelligence: Modeling in Case of System Failure

et al. 2021

Self Cite

View full text Add to dashboard Cite

The uninterrupted operation of systems with artificial intelligence (AI) ensures high productivity and accuracy of the tasks performed. The physiological state of AI operators indicates a relation with an AI system failure event and can be measured through electrodermal activity. This study aims to model the stress levels of system operators based on system trustworthiness and physiological responses during a correct AI operation and its failure. Two groups of 18 and 19 participants took part in the experiments using two different types of software with elements of AI. The first group of participants used English proofreading software and the second group used drawing software as the AI tools. During the tasks, the electrodermal activities of the participants as a stress level indicator were measured. Based on the results obtained, the users' stress was determined and classified using logistic regression models with an accuracy of approximately 70%. The insights obtained can serve AI product developers in increasing the level of user trust and managing the anxiety and stress levels of AI operators.

show abstract

Section: B Relationships Among Emotional State Perception and Ai Operation Of Usersmentioning

confidence: 74%

Section: B Experiments 2: English Proofreading Software Using Ai 1) Participantsmentioning

confidence: 99%

See 1 more Smart Citation

User Stress in Artificial Intelligence: Modeling in Case of System Failure

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…The airbag control unit (ACU) can be improved with adaptive strategies depending on the actual occupant positions once the crash is going to occur (Depottey and Schneider 2007;Farmer and Jain 2003;Hall et al 2008, Schneider andRose 2010). So, future intelligent vehicles should be capable of monitoring also the inside scenario with physical and physiological measures (Branstrom et al 2019;Teo et al 2019).…”

Section: Introductionmentioning

confidence: 99%

A methodology for out of position occupant identification from pressure sensors embedded in a vehicle seat

Vergnano

Leali

2020

Hum.-Intell. Syst. Integr.

View full text Add to dashboard Cite

The airbag deployment against an out of position (OP) occupant is critical. The OP condition can be hardly expected during design, while a too close airbag deployment can cause serious injuries instead of mitigating the crash effects. An adaptive airbag system would be capable to adjust its deployment to the inside scenario. However, the integration between human passengers and intelligent vehicle requires the airbag control unit to be aware of the actual occupant(s) position. In the present research, a methodology for monitoring the occupant(s) position is developed and tested with a seat prototype. A layout of thin film sensors monitors the interface pressure between the occupant and the seat cover. An inertial measurement unit (IMU) monitors the accelerations of the vehicle, considered the reference moving platform. A microcontroller is programmed for pressure sensors calibration, IMU alignment with the vehicle reference system, signals processing, OP detection, and identification. Real driving experiments on a race track were performed in the correct position and in three different OPs. The comparison of the pressure center in longitudinal and transversal directions with the vehicle acceleration enables to identify the OPs.

show abstract

Development of a statistical model to classify driving stress levels using galvanic skin responses

Kim

Park

2020

Hum Ftrs & Erg Mfg Svc

View full text Add to dashboard Cite

Many studies have demonstrated the strong relationships between physiological responses and driving stress, but they have done little to build a model that could be used to identify a driver's stress accurately in real time. The objective of this study is to develop a model that accurately classifies driving stress by monitoring physiological responses—specifically galvanic skin response (GSR). GSR data were collected from nine drivers with licenses obtained in the US in real road driving situations with two stress conditions—rest period (low stress) and highway or city driving (high stress). The validation drive was performed by one driver with licenses obtained in South Korea in real long‐term road driving situations with two stress conditions—rural area (low stress) and highway or highway under construction (high stress). Those two conditions were used to build a binary logistic regression model to classify low stress or high stress based on a driver's measured hand GSR. The overall classification accuracy of the developed model was found to be 85.3%, and the accuracy of cross validation, with a testing dataset, was found to be 83.2%. A simple logit model was developed to identify drivers' stress by incorporating their GSR data. The developed model can be embedded in a wearable device equipped with GSR sensors for drivers to detect their stress level in real time.

show abstract

Relationships between physiological signals and stress levels in the case of automated technology failure

Cited by 6 publications

References 15 publications

User Stress in Artificial Intelligence: Modeling in Case of System Failure

User Stress in Artificial Intelligence: Modeling in Case of System Failure

A methodology for out of position occupant identification from pressure sensors embedded in a vehicle seat

Development of a statistical model to classify driving stress levels using galvanic skin responses

Contact Info

Product

Resources

About