Assessment System Using Gaze and Brain Activity for Cheating Detection

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current assessment systems face challenges in detecting cheating, particularly in low-supervision environments, where candidates may engage in identity fraud, use unauthorized resources, or exhibit attention deficiencies, compromising the integrity of certifications and qualifications.

Innovation Solution

A method and system that monitor user attributes such as attention levels through gaze detection, brain electrical activity, and other physiological measures to identify attention deficiency events, classifying actions as potential cheating or learning deficiencies, and providing alerts to prevent and address such issues.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If live monitoring is provided during assessments, then cheating detection capability is improved, but operational cost and complexity increase

Engineering Contradiction:

Improvecheating detection capabilityVSAvoidoperational complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The assessment system performs self-monitoring through automated detection of attention levels, physiological signals, and behavioral patterns. The system independently identifies cheating attempts without requiring external human monitors, thereby maintaining high detection capability while reducing operational complexity and costs.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent replaces mechanical human monitoring with electronic and optical detection systems. Sensors capture physiological signals (heart rate, galvanic skin response, pupil dilation) and behavioral data (gaze direction, head position) which are then analyzed by algorithms to detect cheating, substituting the mechanical system of human supervisors with an automated electronic monitoring system.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Measurement precision

If multiple monitoring attributes are tracked simultaneously, then detection accuracy is improved, but data processing complexity increases

Engineering Contradiction:

Improvedetection accuracyVSAvoiddata processing complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The system merges multiple monitoring attributes including gaze detection, head position tracking, physiological signal monitoring (heart rate, galvanic skin response), and behavioral pattern analysis into a unified detection framework. By combining these diverse data streams and analyzing them collectively, the system achieves high detection accuracy while managing processing complexity through integrated analysis algorithms.

Inventive Principle:

Principle #5Merging (Combining)

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

The system effectively reduces the need for live monitoring, deters cheating, and ensures the integrity of assessments by accurately detecting attention levels and alerting authorities to potential cheating, thereby saving costs and maintaining certification validity.

Implementation Method 1

A method and system that monitor user attributes such as attention levels through gaze detection

Methodology Applied

Scientific EffectGaze detection:

Implementation Method 2

The attention level of the user is determined with the identified at least one attribute... The at least one attribute may include brain electrical activity detection

Methodology Applied

Scientific EffectBrain electrical activity detection:

Data Source

PatentUS9763613B2System and method for data anomaly detection process in assessments

Publication Date: 2017.09.19 QUESTIONMARK COMPUTING

AI summary

A method, computer program product, and computer system for identifying at least one attribute of a user. An attention level of the user is determined with the identified at least one attribute. The attention level of the user is analyzed. An action of the user is classified as an attention deficiency event using the analyzed attention level of the user.