Decision Deferral in a Human-AI Joint Face-Matching Task: Effects on Human Performance and Trust

2021 ◽  
Vol 65 (1) ◽  
pp. 638-642
Author(s):  
Pouria Salehi ◽  
Erin K. Chiou ◽  
Michelle Mancenido ◽  
Ahmadreza Mosallanezhad ◽  
Myke C. Cohen ◽  
...  
Keyword(s):  
Human Performance ◽  
Rate Sensitivity ◽  
Matching Task ◽  
Work Systems ◽  
Security Screening ◽  
Task Effects ◽  
Human Agent ◽  
Face Matching ◽  
Ethical And Legal Considerations ◽  
Process Component

This study investigates how human performance and trust are affected by the decision deferral rates of an AI-enabled decision support system in a high criticality domain such as security screening, where ethical and legal considerations prevent full automation. In such domains, deferring cases to a human agent becomes an essential process component. However, the systemic consequences of the rate of deferrals on human performance are unknown. In this study, a face-matching task with an automated face verification system was designed to investigate the effects of varying deferral rates. Results show that higher deferral rates are associated with higher sensitivity and higher workload, but lower throughput and lower trust in the AI. We conclude that deferral rates can affect performance and trust perceptions. The tradeoffs between deferral rate, sensitivity, throughput, and trust need to be considered in designing effective human-AI work systems.

scholarly journals Auditory Working Memory Load Impairs Visual Ventral Stream Processing: Toward a Unified Model of Attentional Load

2010 ◽  
Vol 22 (3) ◽  
pp. 437-446 ◽  
Author(s):  
Jane Klemen ◽  
Christian Büchel ◽  
Mira Bühler ◽  
Mareike M. Menz ◽  
Michael Rose
Keyword(s):  
Working Memory ◽  
Cognitive Control ◽  
Cognitive Load ◽  
Human Performance ◽  
Memory Load ◽  
Matching Task ◽  
Load Theory ◽  
Attentional Load ◽  
Relevant Task ◽  
Task Irrelevant

Attentional interference between tasks performed in parallel is known to have strong and often undesired effects. As yet, however, the mechanisms by which interference operates remain elusive. A better knowledge of these processes may facilitate our understanding of the effects of attention on human performance and the debilitating consequences that disruptions to attention can have. According to the load theory of cognitive control, processing of task-irrelevant stimuli is increased by attending in parallel to a relevant task with high cognitive demands. This is due to the relevant task engaging cognitive control resources that are, hence, unavailable to inhibit the processing of task-irrelevant stimuli. However, it has also been demonstrated that a variety of types of load (perceptual and emotional) can result in a reduction of the processing of task-irrelevant stimuli, suggesting a uniform effect of increased load irrespective of the type of load. In the present study, we concurrently presented a relevant auditory matching task [n-back working memory (WM)] of low or high cognitive load (1-back or 2-back WM) and task-irrelevant images at one of three object visibility levels (0%, 50%, or 100%). fMRI activation during the processing of the task-irrelevant visual stimuli was measured in the lateral occipital cortex and found to be reduced under high, compared to low, WM load. In combination with previous findings, this result is suggestive of a more generalized load theory, whereby cognitive load, as well as other types of load (e.g., perceptual), can result in a reduction of the processing of task-irrelevant stimuli, in line with a uniform effect of increased load irrespective of the type of load.

scholarly journals EEG recording during an emotional face-matching task in children of mothers with interpersonal violence-related posttraumatic stress disorder

2019 ◽  
Vol 283 ◽  
pp. 34-44
Author(s):  
Virginie C. Perizzolo ◽  
Cristina Berchio ◽  
Dominik A. Moser ◽  
Cristina Puro Gomez ◽  
Marylène Vital ◽  
...  
Keyword(s):  
Posttraumatic Stress Disorder ◽  
Posttraumatic Stress ◽  
Interpersonal Violence ◽  
Stress Disorder ◽  
Matching Task ◽  
Face Matching ◽  
Emotional Face

scholarly journals A grey area: How does image hue affect unfamiliar face matching?

2018 ◽  
Author(s):  
Anna K Bobak ◽  
Viktoria Roumenova Mileva ◽  
Peter Hancock
Keyword(s):  
Matching Task ◽  
Mixed Condition ◽  
Face Matching ◽  
Matching Test ◽  
Unfamiliar Face Matching ◽  
Unfamiliar Face ◽  
Matching Performance ◽  
Small Decline ◽  
Clear Shift

The role of image colour in face identification has received little attention in research despite the importance of identifying people from photographs in identity documents (IDs). Here, in two experiments, we investigated whether colour congruency of two photographs shown side by side affects face matching accuracy. Participants were presented with two images from the Models Face Matching Test (Experiment 1) and a newly devised matching task incorporating female faces (Experiment 2) and asked to decide whether they show the same person, or two different people. The photographs were either both in colour, both in grayscale, or mixed (one in grayscale and one in colour). Participants were more likely to accept a pair of images as a “match”, i.e. same person, in the mixed condition, regardless of whether the identity of the pair was the same or not. This demonstrates a clear shift in bias between “congruent” colour conditions and the mixed trials. In addition, there was a small decline in accuracy in the mixed condition, relative to when the images were presented in colour. Our study provides the first evidence that the hue of document photographs matters for face matching performance. This finding has important implications for the design and regulation of photographic ID worldwide.

scholarly journals Unfamiliar Face Matching With Driving Licence and Passport Photographs

Perception ◽  
2019 ◽  
Vol 48 (2) ◽  
pp. 175-184 ◽  
Author(s):  
Robin S. S. Kramer ◽  
Sophie Mohamed ◽  
Sarah C. Hardy
Keyword(s):  
High Resolution ◽  
Ecological Validity ◽  
Current Work ◽  
Sorting Task ◽  
Matching Task ◽  
Performance Levels ◽  
Driving Licence ◽  
Face Matching ◽  
Unfamiliar Face Matching ◽  
Unfamiliar Face

Matching two different images of an unfamiliar face is difficult, although we rely on this process every day when proving our identity. Although previous work with laboratory photosets has shown that performance is error-prone, few studies have focussed on how accurately people carry out this matching task using photographs taken from official forms of identification. In Experiment 1, participants matched high-resolution, colour face photos with current UK driving licence photos of the same group of people in a sorting task. Averaging 19 mistaken pairings out of 30, our results showed that this task was both difficult and error-prone. In Experiment 2, high-resolution photographs were paired with either driving licence or passport photographs in a typical pairwise matching paradigm. We found no difference in performance levels for the two types of ID image, with both producing unacceptable levels of accuracy (around 75%–79% correct). The current work benefits from increased ecological validity and provides a clear demonstration that these forms of official identification are ineffective and alternatives should be considered.

scholarly journals Exploring the Effect of Communication Patterns and Transparency on Performance in a Human-Robot Team

2019 ◽  
Vol 63 (1) ◽  
pp. 160-164 ◽  
Author(s):  
Shan G. Lakhmani ◽  
Julia L. Wright ◽  
Michael R. Schwartz ◽  
Daniel Barber
Keyword(s):  
Information Sharing ◽  
Team Performance ◽  
Human Performance ◽  
Target Identification ◽  
Communication Patterns ◽  
Human Robot Interaction ◽  
Communication Pattern ◽  
Identification Task ◽  
Robot Interaction ◽  
Human Agent

Human-robot interaction requires communication, however what form this communication should take to facilitate effective team performance is still undetermined. One notion is that effective human-agent communications can be achieved by combining transparent information-sharing techniques with specific communication patterns. This study examines how transparency and a robot’s communication patterns interact to affect human performance in a human-robot teaming task. Participants’ performance in a target identification task was affected by the robot’s communication pattern. Participants missed identifying more targets when they worked with a bidirectionally communicating robot than when they were working with a unidirectionally communicating one. Furthermore, working with a bidirectionally communicating robot led to fewer correct identifications than working with a unidirectionally communicating robot, but only when the robot provided less transparency information. The implications these findings have for future robot interface designs are discussed.

scholarly journals Enhanced Matching of Children’s Faces in “Super-Recognisers” But Not High-Contact Controls

i-Perception ◽  
2020 ◽  
Vol 11 (4) ◽  
pp. 204166952094442
Author(s):  
Sarah Bate ◽  
Rachel Bennetts ◽  
Ebony Murray ◽  
Emma Portch
Keyword(s):  
Face Recognition ◽  
Young Children ◽  
Real World ◽  
Matching Task ◽  
Control Groups ◽  
Age Bias ◽  
Face Matching ◽  
Contact Control ◽  
Additional Exposure

Face matching is notoriously error-prone, and some work suggests additional difficulty when matching the faces of children. It is possible that individuals with natural proficiencies in adult face matching (“super-recognisers” [SRs]) will also excel at the matching of children’s faces, although other work implicates facilitations in typical perceivers who have high levels of contact with young children (e.g., nursery teachers). This study compared the performance of both of these groups on adult and child face matching to a group of low-contact controls. High- and low-contact control groups performed at a remarkably similar level in both tasks, whereas facilitations for adult and child face matching were observed in some (but not all) SRs. As a group, the SRs performed better in the adult compared with the child task, demonstrating an extended own-age bias compared with controls. These findings suggest that additional exposure to children’s faces does not assist the performance in a face matching task, and the mechanisms underpinning superior recognition of adult faces can also facilitate the child face recognition. Real-world security organisations should therefore seek individuals with general facilitations in face matching for both adult and child face matching tasks.

Simulating Human Performance of Task Sharing: Modeling Task Delay and Delegation of Authority

2017 ◽  
Vol 61 (1) ◽  
pp. 786-790
Author(s):  
Douglas W. Lee ◽  
Daniel W. Fitzick ◽  
Ellen J. Bass
Keyword(s):  
Case Studies ◽  
Human Performance ◽  
Autonomous Agents ◽  
Task Sharing ◽  
Dynamic Allocation ◽  
Air Traffic Controller ◽  
Agent Model ◽  
Delegation Of Authority ◽  
Human Agent ◽  
Operational Concept

In systems that support dynamic allocation of work across human and autonomous agents, analyzing the implications of task sharing can support operational concept development. Computational tools should address not only the taskwork but also the teamwork emerging from the allocation. This paper describes a computational human agent model that manages work by executing or delaying the execution of the task, or by delegating activities to other agents. The agent considers its capacity and strategies for delegation to coordinate with other agents. Using a framework for simulating multiple types of agents, case studies apply this computational human agent model to the evaluation of a concept of operation that distributes work across an air traffic controller capable of delegating and flight deck crews. The case studies show how capacity changes agent utilization and delegation strategies redistribute taskwork across multiple agents while creating teamwork demands.

scholarly journals Hand-movement profiles in a tactual—tactual matching task: Effects of spatial factors and laterality

1994 ◽  
Vol 56 (3) ◽  
pp. 347-355 ◽  
Author(s):  
Joël Fagot ◽  
Agnès Lacreuse ◽  
Jacques Vauclair
Keyword(s):  
Hand Movement ◽  
Matching Task ◽  
Spatial Factors ◽  
Task Effects

scholarly journals Making a Spectacle of Yourself: The Effect of Glasses and Sunglasses on Face Perception

Perception ◽  
2019 ◽  
Vol 48 (6) ◽  
pp. 461-470 ◽  
Author(s):  
Daisy L. Graham ◽  
Kay L. Ritchie
Keyword(s):  
Face Perception ◽  
The Other ◽  
Matching Task ◽  
Match Trial ◽  
Social Traits ◽  
Face Matching ◽  
Trial Performance

We investigated the effect of wearing glasses and sunglasses on the perception of social traits from faces and on face matching. Participants rated images of people wearing no glasses, glasses and sunglasses on three social traits (trustworthiness, competence and attractiveness). Wearing sunglasses reduced ratings of trustworthiness. Participants also performed a matching task (telling whether two images show the same person or not) with pairs of images both wearing no glasses, glasses or sunglasses, and all combinations of eyewear. Incongruent eyewear conditions (e.g., one image wearing glasses and the other wearing sunglasses, etc.) reduced performance. Further analysis comparing performance on congruent and incongruent eyewear trials showed that our effects were driven by match trial performance, where differences in eyewear decreased accuracy. For same-eyewear-condition pairs, performance was poorer for pairs of images both wearing sunglasses than no glasses. Our results extend and update previous research on the effect of eyewear on face perception.

Sign in / Sign up

Export Citation Format

Share Document