Markus Fiedler

Alexander Raake, Markus Fiedler, Katrin Schoenenberg et al.

The paper presents a conceptual, multidimensional approach to understand the technological factors that are assumed to or even have been proven to contribute to what has been coined as Zoom Fatigue (ZF) or more generally Videoconferencing Fatigue (VCF). With the advent of the Covid-19 pandemic, the usage of VC services has drastically increased, leading to more and more reports about the ZF or VCF phenomenon. The paper is motivated by the fact that some of the media outlets initially starting the debate on what Zoom fatigue is and how it can be avoided, as well as some of the scientific papers addressing the topic, contain assumptions that are rather hypothetical and insufficiently underpinned by scientific evidence. Most of these works are acknowledge the lacking evidence and partly suggest directions for future research. This paper intends to deepen the survey of VC-technology-related literature and to provide more existing evidence, where possible, while reviewing some of the already provided support or evidence for certain causal hypotheses. The technological factors dimension and its identified sub-dimensions presented in this paper are embedded within a more holistic four-dimensional conceptual factors model describing the causes for ZF or VCF. The paper describing this overall conceptual model is written by the same group of authors and currently under revision for an Open Access Journal publication. The present paper expands on the technological factors dimension descriptions provided in the overall model paper and provides more detailed analyzes and concepts associated with how VC technology may affect users' perception, cognitive load, interaction and communication, possibly leading to stress, exhaustion and fatigue. The paper currently is a living document which will be expanded further with regard to the evidence for or against the impact of certain technological factors.

Tobias Hossfeld, Poul E. Heegaard, Martin Varela et al.

In the context of QoE management, network and service providers commonly rely on models that map system QoS conditions (e.g., system response time, paket loss, etc.) to estimated end user QoE values. Observable QoS conditions in the system may be assumed to follow a certain distribution, meaning that different end users will experience different conditions. On the other hand, drawing from the results of subjective user studies, we know that user diversity leads to distributions of user scores for any given test conditions (in this case referring to the QoS parameters of interest). Our previous studies have shown that to correctly derive various QoE metrics (e.g., Mean Opinion Score (MOS), quantiles, probability of users rating "good or better", etc.) in a system under given conditions, there is a need to consider rating distributions obtained from user studies, which are often times not available. In this paper we extend these findings to show how to approximate user rating distributions given a QoS-to-MOS mapping function and second order statistics. Such a user rating distribution may then be combined with a QoS distribution observed in a system to finally derive corresponding distributions of QoE scores. We provide two examples to illustrate this process: 1) analytical results using a Web QoE model relating waiting times to QoE, and 2) numerical results using measurements relating packet losses to video stall pattern, which are in turn mapped to QoE estimates. The results in this paper provide a solution to the problem of understanding the QoE distribution in a system, in cases where the necessary data is not directly available in the form of models going beyond the MOS, or where the full details of subjective experiments are not available.

Selim Ickin, Markus Fiedler, Konstantinos Vandikas

The development of QoE models by means of Machine Learning (ML) is challenging, amongst others due to small-size datasets, lack of diversity in user profiles in the source domain, and too much diversity in the target domains of QoE models. Furthermore, datasets can be hard to share between research entities, as the machine learning models and the collected user data from the user studies may be IPR- or GDPR-sensitive. This makes a decentralized learning-based framework appealing for sharing and aggregating learned knowledge in-between the local models that map the obtained metrics to the user QoE, such as Mean Opinion Scores (MOS). In this paper, we present a transfer learning-based ML model training approach, which allows decentralized local models to share generic indicators on MOS to learn a generic base model, and then customize the generic base model further using additional features that are unique to those specific localized (and potentially sensitive) QoE nodes. We show that the proposed approach is agnostic to specific ML algorithms, stacked upon each other, as it does not necessitate the collaborating localized nodes to run the same ML algorithm. Our reproducible results reveal the advantages of stacking various generic and specific models with corresponding weight factors. Moreover, we identify the optimal combination of algorithms and weight factors for the corresponding localized QoE nodes.

Selim Ickin, Konstantinos Vandikas, Markus Fiedler

Machine Learning based Quality of Experience (QoE) models potentially suffer from over-fitting due to limitations including low data volume, and limited participant profiles. This prevents models from becoming generic. Consequently, these trained models may under-perform when tested outside the experimented population. One reason for the limited datasets, which we refer in this paper as small QoE data lakes, is due to the fact that often these datasets potentially contain user sensitive information and are only collected throughout expensive user studies with special user consent. Thus, sharing of datasets amongst researchers is often not allowed. In recent years, privacy preserving machine learning models have become important and so have techniques that enable model training without sharing datasets but instead relying on secure communication protocols. Following this trend, in this paper, we present Round-Robin based Collaborative Machine Learning model training, where the model is trained in a sequential manner amongst the collaborated partner nodes. We benchmark this work using our customized Federated Learning mechanism as well as conventional Centralized and Isolated Learning methods.