Adaptive Interface Personalization through Real-Time Cognitive

Load Detection

Wadhah Ahmed Muthanna Abdullah1,* Aygul Z. Ibatova2

1 Saint Petersburg State University, Saint Petersburg, Russia

2 Tyumen Industrial University, Russia

Received: December 04, 2025 Revised: January 30, 2026 Accepted: February 28, 2026 ⋆ Corresponding author

ABSTRACT

High-stakes computer work often requires users to interpret dense visual information while responding to timesensitive

events. Static interfaces can become counterproductive in such conditions because the amount of information

presented to the user does not change when mental demand rises. This paper presents an adaptive interface

personalization approach that detects cognitive load from pupillometry, heart-rate variability, gaze behaviour, and

interaction traces, then selects a transparent interface response. The proposed approach does not simply reduce

screen content; it chooses between full, highlighted, simplified, and critical-only modes while preserving user control

and explanation cues. A feature-level experimental analysis was conducted using a multimodal workload table

structured around public cognitive-load datasets and high-stakes monitoring tasks. The results show that pupil

expansion, lower HRV, response delay, gaze dispersion, and screen density jointly indicate rising cognitive load. The

adaptation policy reduced predicted interaction errors and shortened response latency in high-load windows while

maintaining explanation support for user trust. The findings suggest that cognitive-load detection should be treated

as a personalization service rather than a hidden automation layer.

Keywords: Adaptive interfaces Cognitive load detection Pupillometry Heart-rate variability Transparent personalization

1. PROBLEM FRAMING

Air traffic coordination, clinical monitoring, emergency response,

and industrial supervision place users in front of

interfaces that are visually dense and temporally demanding.

In these settings, usability is not only a matter of arranging

buttons or choosing a clear font. It is also a matter of whether

the interface can recognize when the user is overloaded and

adjust the amount, order, and salience of information. A

static display may be appropriate during routine monitoring

but harmful when alarms, conflicting cues, and time pressure

appear simultaneously.

Physiological workload sensing offers a practical path toward

this type of adaptation. Pupillometry is sensitive to mental

effort and attention, while HRV reflects autonomic regulation

and strain [1]. Recent datasets and reviews have shown that

multimodal cognitive-load assessment can combine wearable,

ocular, behavioural, and interaction features in realistic tasks

[2-4]. The challenge is no longer whether cognitive load can

be measured at all, but how the estimate should be used inside

an adaptive interface without undermining user trust.

Trust is central because personalization changes what the

user sees. If a system hides secondary panels or simplifies a

medical monitoring screen without explanation, the user may

suspect that important information is being removed. HCI

trust research therefore suggests that adaptive systems should