Models of user experience quality in computer information systems
This paper introduces a unified, scalable, and context-aware framework for evaluating user experience quality (QuE) in computer information systems by proposing the Enhanced Perceived Quality of User Experience (EPQuE) metric. Unlike traditional Quality of Service (QoS) or subjective Quality of Exp...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Ukrainian National Forestry University
2025-06-01
|
| Series: | Науковий вісник НЛТУ України |
| Subjects: | |
| Online Access: | https://nv.nltu.edu.ua/index.php/journal/article/view/2787 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | This paper introduces a unified, scalable, and context-aware framework for evaluating user experience quality (QuE) in computer information systems by proposing the Enhanced Perceived Quality of User Experience (EPQuE) metric. Unlike traditional Quality of Service (QoS) or subjective Quality of Experience (QoE) models alone, EPQuE integrates technical and perceptual factors through an adaptive algorithmic pipeline. The model incorporates three synergistic components: a Fuzzy Inference System (FIS) to interpret imprecise or ambiguous user feedback; Multi-Criteria Decision Analysis (MCDA), used to normalize and prioritize heterogeneous parameters in real time; a regression-based machine learning model for dynamic adjustment of input weights based on contextual variations. The methodology was validated in a real-world teledentistry scenario, involving remote consultations with elderly patients, where it achieved a 91 % accuracy rate in identifying high-risk sessions – outperforming baseline QoS- or QoE-only models by 34 %. Consequently, EPQuE enables intelligent service monitoring and real-time personalization by linking engineering-level metrics such as bandwidth, latency, and packet loss with perceptual indicators like emotional comfort and user engagement. Furthermore, the model was successfully tested in additional use cases, including augmented reality applications and smart home environments, demonstrating its flexibility and scalability. The benefits of this study include the development of a robust computational pipeline capable of bridging the gap between human-centered assessments and objective technical indicators, supporting proactive service adaptation, and enabling data-driven decisions in dynamic digital ecosystems. As a result, the EPQuE framework lays the foundation for future research in adaptive quality assessment, intelligent resource optimization, and the design of next-generation user-centric service infrastructures.
|
|---|---|
| ISSN: | 1994-7836 2519-2477 |