Change search
Link to record
Permanent link

Direct link
BETA
Fiedler, Markus
Publications (10 of 196) Show all publications
Fiedler, M., Chapala, U. K. & Peteti, S. (2019). Modeling instantaneous quality of experience using machine learning of model trees. In: 2019 11th International Conference on Quality of Multimedia Experience, QoMEX 2019: . Paper presented at 11th International Conference on Quality of Multimedia Experience, QoMEX, Berlin, 5 June 2019 through 7 June 2019. Institute of Electrical and Electronics Engineers Inc.
Open this publication in new window or tab >>Modeling instantaneous quality of experience using machine learning of model trees
2019 (English)In: 2019 11th International Conference on Quality of Multimedia Experience, QoMEX 2019, Institute of Electrical and Electronics Engineers Inc. , 2019Conference paper, Published paper (Refereed)
Abstract [en]

For service providers and operators, successful root cause analysis is essential for satisfactory service provisioning. However, reasons for sudden trend changes of the instantaneous Quality of Experience (QoE) may not always be immediately visible from underlying service- or network-level monitoring data. Thus, there is the challenge to pinpoint such moments of change in provisioning, and model the impact on instantaneous QoE, as a lead in root cause analysis. This work investigates the potential of Machine Learning (ML) of deriving time-interval-based models for instantaneous QoE ratings, obtained from a set of publicly available rating traces. In particular, the paper demonstrates the capability of the ML algorithm M5P to model trends of instantaneous QoE through model trees, consisting of piecewise linear functions over time. It is shown how and to which extent these functions can be used to estimate moments of change. Furthermore, the model trees support earlier assumptions about exponential shapes of instantaneous QoE over time as reactions to sudden changes of provisioning, such as video freezes. © 2019 IEEE.

Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers Inc., 2019
Keywords
M5P algorithm, Mean Opinion Score (MOS), Root cause analysis, Time dependency, Video freezes, Forestry, Machine learning, Multimedia systems, Piecewise linear techniques, Trees (mathematics), Mean opinion scores, Piece-wise linear functions, Quality of experience (QoE), Service provider, Service provisioning, Time interval, Quality of service
National Category
Communication Systems Other Electrical Engineering, Electronic Engineering, Information Engineering
Identifiers
urn:nbn:se:bth-18604 (URN)10.1109/QoMEX.2019.8743250 (DOI)000482562000035 ()2-s2.0-85068689152 (Scopus ID)9781538682128 (ISBN)
Conference
11th International Conference on Quality of Multimedia Experience, QoMEX, Berlin, 5 June 2019 through 7 June 2019
Available from: 2019-09-10 Created: 2019-09-10 Last updated: 2019-09-13Bibliographically approved
Fiedler, M., Zepernick, H.-J. & Kelkkanen, V. (2019). Network-induced temporal disturbances in virtual reality applications. In: 2019 11th International Conference on Quality of Multimedia Experience, QoMEX 2019: . Paper presented at 11th International Conference on Quality of Multimedia Experience, QoMEX, Berlin, 5 June 2019 through 7 June 2019. Institute of Electrical and Electronics Engineers Inc.
Open this publication in new window or tab >>Network-induced temporal disturbances in virtual reality applications
2019 (English)In: 2019 11th International Conference on Quality of Multimedia Experience, QoMEX 2019, Institute of Electrical and Electronics Engineers Inc. , 2019Conference paper, Published paper (Refereed)
Abstract [en]

Virtual Reality (VR) applications put high demands on software and hardware in order to enable an immersive experience for the user and avoid causing simulator sickness. As soon as networks become part of the Motion-To-Photon (MTP) path between rendering and display, there is a risk for extraordinary delays that may impair Quality of Experience (QoE). This short paper provides an overview of latency measurements and models that are applicable to the MTP path, complemented by demands on user and network levels. It specifically reports on freeze duration measurements using a commercial TPCAST wireless VR solution, and identifies a corresponding stochastic model of the freeze length distribution, which may serve as disturbance model for VR QoE studies. © 2019 IEEE.

Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers Inc., 2019
Keywords
Application programs, Multimedia systems, Quality of service, Stochastic systems, Virtual reality, Disturbance modeling, High demand, Latency measurements, Length distributions, Network level, Quality of experience (QoE), Simulator sickness, Software and hardwares, Stochastic models
National Category
Communication Systems Other Electrical Engineering, Electronic Engineering, Information Engineering
Identifiers
urn:nbn:se:bth-18605 (URN)10.1109/QoMEX.2019.8743304 (DOI)000482562000056 ()2-s2.0-85068679022 (Scopus ID)9781538682128 (ISBN)
Conference
11th International Conference on Quality of Multimedia Experience, QoMEX, Berlin, 5 June 2019 through 7 June 2019
Funder
Knowledge Foundation, 20170056
Available from: 2019-09-10 Created: 2019-09-10 Last updated: 2019-09-13Bibliographically approved
Fiedler, M. (2019). Performance Analytics by Means of the M5P Machine Learning Algorithm. In: Proceedings of the 31st International Teletraffic Congress, ITC 2019: . Paper presented at 31st International Teletraffic Congress, ITC, Budapest, 27 August 2019 through 29 August 2019 (pp. 104-105). Institute of Electrical and Electronics Engineers Inc.
Open this publication in new window or tab >>Performance Analytics by Means of the M5P Machine Learning Algorithm
2019 (English)In: Proceedings of the 31st International Teletraffic Congress, ITC 2019, Institute of Electrical and Electronics Engineers Inc. , 2019, p. 104-105Conference paper, Published paper (Refereed)
Abstract [en]

Machine Learning (ML) has shown its capability to analyse, classify, and make predictions based on large data sets. Network performance analysis and evaluation focuses on finding and expressing qualitative, quantitative and formal relationships between performance-related parameters, with specific interest in asymptotic behaviours. This work introduces the notion of performance analytics as performance modeling with help of ML. In particular, it demonstrates the applicablibility of the ML algorithm M5P to such performance analytics, as the parameters of the generated model trees allow for identifying approximations together the applicable parameter sub-spaces in a straightforward approach. We present a set of examples with focus on post-analysis of analytically obtained performance results for asymptotic behaviour. © 2019 ITC Press.

Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers Inc., 2019
Keywords
approximation formulae, model tree, multivariate analysis, performance evaluation, Approximation algorithms, Asymptotic analysis, Classification (of information), Forestry, Learning algorithms, Multivariant analysis, Parameter estimation, Trees (mathematics), Asymptotic behaviour, Large datasets, Model trees, Multi variate analysis, Network performance analysis, Performance Model, Machine learning
National Category
Telecommunications
Identifiers
urn:nbn:se:bth-18937 (URN)10.1109/ITC31.2019.00023 (DOI)2-s2.0-85074777929 (Scopus ID)9780988304574 (ISBN)
Conference
31st International Teletraffic Congress, ITC, Budapest, 27 August 2019 through 29 August 2019
Note

Funding details: d-nr 2014-0032; Funding text 1: ACKNOWLEDGEMENTS The co-funding of the “BigData@BTH” project by the Swedish KKS Foundation (d-nr 2014-0032) is gratefully acknowledged.

Available from: 2019-11-21 Created: 2019-11-21 Last updated: 2019-11-21Bibliographically approved
Ickin, S., Vandikas, K. & Fiedler, M. (2019). Privacy Preserving QoE Modeling using Collaborative Learning. In: Proceedings of the Annual International Conference on Mobile Computing and Networking, MOBICOM: . Paper presented at 4th Workshop on QoE-Based Analysis and Management of Data Communication Networks, Internet-QoE 2019, co-located with MobiCom 2019, Los Cabos; Mexico, 21 October (pp. 13-18). Association for Computing Machinery
Open this publication in new window or tab >>Privacy Preserving QoE Modeling using Collaborative Learning
2019 (English)In: Proceedings of the Annual International Conference on Mobile Computing and Networking, MOBICOM, Association for Computing Machinery , 2019, p. 13-18Conference paper, Published paper (Refereed)
Abstract [en]

Machine Learning (ML) 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. © 2019 Association for Computing Machinery.

Place, publisher, year, edition, pages
Association for Computing Machinery, 2019
Keywords
Distributed Learning, Federated Learning, QoE, Convolutional codes, Data communication systems, Data privacy, Machine learning, Collaborative learning, Learning mechanism, Machine learning models, Quality of experience (QoE), Sensitive informations, Sequential manners, Quality of service
National Category
Computer Sciences
Identifiers
urn:nbn:se:bth-18936 (URN)10.1145/3349611.3355548 (DOI)2-s2.0-85074785270 (Scopus ID)9781450369275 (ISBN)
Conference
4th Workshop on QoE-Based Analysis and Management of Data Communication Networks, Internet-QoE 2019, co-located with MobiCom 2019, Los Cabos; Mexico, 21 October
Available from: 2019-11-21 Created: 2019-11-21 Last updated: 2019-11-21Bibliographically approved
Minhas, T. N., Nawaz, O., Fiedler, M. & Khatibi, S. (2019). The Effects of Additional Factors on Subjective Quality Assessments. In: 2nd International Conference on Advancements in Computational Sciences, ICACS 2019: . Paper presented at 2nd International Conference on Advancements in Computational Sciences, ICACS, Lahore, 18 February 2019 through 20 February 2019 (pp. 120-124). Institute of Electrical and Electronics Engineers Inc., Article ID 8689138.
Open this publication in new window or tab >>The Effects of Additional Factors on Subjective Quality Assessments
2019 (English)In: 2nd International Conference on Advancements in Computational Sciences, ICACS 2019, Institute of Electrical and Electronics Engineers Inc. , 2019, p. 120-124, article id 8689138Conference paper, Published paper (Refereed)
Abstract [en]

In Quality of Experience, the users' degrees of delight or annoyance are quantized by direct human interaction via subjective quality assessments. There are many factors that may influence the users' responses, and standards have been laid down to strictly control the monitoring conditions. In this paper, we analyze limitations of Mean Opinion Score (MOS) assessment to portray the influence of additional factors on user behavior while assessing multimedia content. We show that the frequency of watching online video content as well as the user delight with the content play a significant role in her final feedback. Our study emphasizes the need to use additional metrics along with MOS for content ratings to obtain a more accurate measure of the user experience. © 2019 The University of Lahore.

Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers Inc., 2019
Keywords
Multimedia communication, Quality of Experience, User Perception, Multimedia systems, Quality of service, Content ratings, Human interactions, Mean opinion scores, Multi-media communications, Multimedia contents, Quality of experience (QoE), Subjective quality assessments, User perceptions, Behavioral research
National Category
Other Electrical Engineering, Electronic Engineering, Information Engineering
Identifiers
urn:nbn:se:bth-17906 (URN)10.23919/ICACS.2019.8689138 (DOI)000470736000018 ()2-s2.0-85065105387 (Scopus ID)9789699721014 (ISBN)
Conference
2nd International Conference on Advancements in Computational Sciences, ICACS, Lahore, 18 February 2019 through 20 February 2019
Available from: 2019-05-21 Created: 2019-05-21 Last updated: 2019-06-27Bibliographically approved
Fiedler, M., Moller, S., Reichl, P. & Xie, M. (2018). A Glance at the Dagstuhl Manifesto 'QoE Vadis?'. In: 2018 10th International Conference on Quality of Multimedia Experience, QoMEX 2018: . Paper presented at 10th International Conference on Quality of Multimedia Experience, QoMEX 2018, 29 May 2018 through 1 June 2018, Sardinia, Italy. Institute of Electrical and Electronics Engineers Inc., Article ID 8463374.
Open this publication in new window or tab >>A Glance at the Dagstuhl Manifesto 'QoE Vadis?'
2018 (English)In: 2018 10th International Conference on Quality of Multimedia Experience, QoMEX 2018, Institute of Electrical and Electronics Engineers Inc. , 2018, article id 8463374Conference paper, Published paper (Refereed)
Abstract [en]

This short paper presents the recently published Dagstuhl Manifesto 'QoE Vadis?'. The Manifesto is the result of a set of three Dagstuhl Seminars and one Dagstuhl Perspectives Workshop, aimed at shaping understanding, development and application of the Quality of Experience (QoE) notion and concept. Its task is to convey the current status, promising developments and future projections for different stakeholders. The latter are summarised in a set of eleven recommendations to academia, industry and funding organisations. © 2018 IEEE.

Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers Inc., 2018
Keywords
Business Aspects, Multimedia, Quality Feedback, Quality Management, Quality of Experience, Recommendations, Socioeconomic Aspects, User Experience
National Category
Other Electrical Engineering, Electronic Engineering, Information Engineering
Identifiers
urn:nbn:se:bth-17147 (URN)10.1109/QoMEX.2018.8463374 (DOI)2-s2.0-85054407120 (Scopus ID)9781538626054 (ISBN)
Conference
10th International Conference on Quality of Multimedia Experience, QoMEX 2018, 29 May 2018 through 1 June 2018, Sardinia, Italy
Available from: 2018-10-19 Created: 2018-10-19 Last updated: 2018-10-19Bibliographically approved
Kelkkanen, V. & Fiedler, M. (2018). A Test-bed for Studies of Temporal Data Delivery Issues in a TPCAST Wireless Virtual Reality Set-up. In: 2018 28TH INTERNATIONAL TELECOMMUNICATION NETWORKS AND APPLICATIONS CONFERENCE (ITNAC): . Paper presented at 28th International Telecommunication Networks and Applications Conference (ITNAC),Sydney, NOV 21-23 (pp. 404-406). IEEE
Open this publication in new window or tab >>A Test-bed for Studies of Temporal Data Delivery Issues in a TPCAST Wireless Virtual Reality Set-up
2018 (English)In: 2018 28TH INTERNATIONAL TELECOMMUNICATION NETWORKS AND APPLICATIONS CONFERENCE (ITNAC), IEEE , 2018, p. 404-406Conference paper, Published paper (Refereed)
Abstract [en]

Virtual Reality (VR) is becoming increasingly popular, and wireless cable replacements unleash the user of VR Head Mounted Displays (HMD) from the rendering desktop computer. However, the price to pay for additional freedom of movement is a higher sensitivity of the wireless solution to temporal disturbances of both video frame and input traffic delivery, as compared to its wired counterpart. This paper reports on the development of a test-bed to be used for studying temporal delivery issues of both video frames and input traffic in a wireless VR environment, here using TPCAST with a HTC Vive headset. We provide a solution for monitoring and recording of traces of (1) video frame freezes as observed on the wireless VR headset, and (2) input traffic from the headset and hand controls to the rendering computer. So far, the test-bed illustrates the resilience of the underlying WirelesslID technology and TCP connections that carry the input traffic, and will be used in future studies of Quality of Experience (QoE) in wireless desktop VR.

Place, publisher, year, edition, pages
IEEE, 2018
Keywords
Virtual Reality, Quality of Experience, Video Freezes: Wireless, Head-Mounted Display, Monitoring, Recording: Tools
National Category
Communication Systems Telecommunications
Identifiers
urn:nbn:se:bth-17729 (URN)000459862300074 ()978-1-5386-7177-1 (ISBN)
Conference
28th International Telecommunication Networks and Applications Conference (ITNAC),Sydney, NOV 21-23
Available from: 2019-03-21 Created: 2019-03-21 Last updated: 2019-03-25Bibliographically approved
Kelkkanen, V. & Fiedler, M. (2018). Coefficient of Throughput Variation as Indication of Playback Freezes in Streamed Omnidirectional Videos. In: 2018 28TH INTERNATIONAL TELECOMMUNICATION NETWORKS AND APPLICATIONS CONFERENCE (ITNAC): . Paper presented at 28th International Telecommunication Networks and Applications Conference (ITNAC), Sydney, NOV 21-23 (pp. 392-397). IEEE
Open this publication in new window or tab >>Coefficient of Throughput Variation as Indication of Playback Freezes in Streamed Omnidirectional Videos
2018 (English)In: 2018 28TH INTERNATIONAL TELECOMMUNICATION NETWORKS AND APPLICATIONS CONFERENCE (ITNAC), IEEE , 2018, p. 392-397Conference paper, Published paper (Refereed)
Abstract [en]

A large portion of today's network traffic consists of streamed video of large variety, such as films, television shows, live-streamed games and recently omnidirectional videos. A common way of delivering video is by using Dynamic Adaptive Streaming over HTTP (DASH), or recently with encrypted HTTPS. Encrypted video streams disable the use of Quality of Service (QoS) systems that rely on knowledge of application-dependent data, such as video resolution and bit-rate. This could make it difficult for a party providing bandwidth to efficiently allocate resources and estimate customer satisfaction. An application-independent way of measuring video stream quality could be of interest for such a party. In this paper, we investigate encrypted streaming of omni-directional video via YouTube to a smartphone in a Google Cardboard VR-headset. We monitored such sessions, delivered via both WiFi and mobile networks, at different times of day, implying different levels of congestion, and characterised the network traffic by using the Coefficient of Throughput Variation (CoTV) as statistic. We observe that this statistic shows to be able to indicate whether a stream is stable or unstable, in terms of potential video playback freezes, when the DASH delivery strategy is used.

Place, publisher, year, edition, pages
IEEE, 2018
Keywords
Virtual Reality, 360-videos, video streaming, Quality of Experience, video freezes, throughput statistics
National Category
Communication Systems Telecommunications
Identifiers
urn:nbn:se:bth-17728 (URN)000459862300072 ()978-1-5386-7177-1 (ISBN)
Conference
28th International Telecommunication Networks and Applications Conference (ITNAC), Sydney, NOV 21-23
Available from: 2019-03-21 Created: 2019-03-21 Last updated: 2019-03-25Bibliographically approved
Eivazzadeh, S., Sanmartin Berglund, J., Larsson, T., Fiedler, M. & Anderberg, P. (2018). Most Influential Qualities in Creating Satisfaction Among the Users of Health Information Systems: A Study in Seven EU Countries. JMIR Medical Informatics, 6(4), 3-21
Open this publication in new window or tab >>Most Influential Qualities in Creating Satisfaction Among the Users of Health Information Systems: A Study in Seven EU Countries
Show others...
2018 (English)In: JMIR Medical Informatics, Vol. 6, no 4, p. 3-21Article in journal (Refereed) Published
Abstract [en]

Background:

Several models suggest how the qualities of a product or service influence user satisfaction. Models, such as the Customer Satisfaction Index (CSI), Technology Acceptance Model (TAM), and Delone and McLean Information Systems Success (D&M IS), demonstrate those relations and have been used in the context of health information systems.

Objective:

We want to investigate which qualities foster greater satisfaction among patient and professional users. In addition, we are interested in knowing to what extent improvement in those qualities can explain user satisfaction and if this makes user satisfaction a proxy indicator of those qualities.

Methods:

The Unified eValuation using ONtology (UVON) method was utilised to construct an ontology of the required qualities for seven e-health applications being developed in the FI-STAR project, a European Union (EU) project in e-health. The e-health applications were deployed across seven EU countries. The ontology included and unified the required qualities of those systems together with the aspects suggested by the Model for ASsessment of Telemedicine applications (MAST) evaluation framework. Two similar questionnaires, for 87 patient users and 31 health professional users, were elicited from the ontology. In the questionnaires, user was asked if the system has improved the specified qualities and if the user was satisfied with the system. The results were analysed using Kendall correlation coefficients matrices, incorporating the quality and satisfaction aspects. For the next step, two Partial Least Squares Structural Equation Modelling (PLS-SEM) path models were developed using the quality and satisfaction measure variables and the latent construct variables that were suggested by the UVON method.

Results:

Most of the quality aspects grouped by the UVON method are highly correlated. Strong correlations in each group suggest that the grouped qualities can be measures which reflect a latent quality construct. The PLS-SEM path analysis for the patients reveals that the effectiveness, safety, and efficiency of treatment provided by the system are the most influential qualities in achieving and predicting user satisfaction. For the professional users, effectiveness and affordability are the most influential. The parameters of the PLS-SEM that are calculated allow for the measurement of a user satisfaction index similar to CSI for similar health information systems.

Conclusions:

For both patients and professionals, the effectiveness of systems highly contributes to their satisfaction. Patients care about improvements in safety and efficiency, while professionals care about improvements in the affordability of treatments with health information systems. User satisfaction is reflected more in the users' evaluation of system output and fulfilment of expectations, but slightly less in how far the system is from ideal. Investigating satisfaction scores can be a simple, fast way to infer if the system has improved the abovementioned qualities in treatment and care.

Place, publisher, year, edition, pages
JMIR Publications, 2018
Keywords
Health Information Systems, Telemedicine, Evaluation Studies as Topic, Consumer Behavior, Treatment Outcome, Safety, Efficiency, Health Care Costs, Ontology Engineering, Equation Models
National Category
Other Health Sciences
Identifiers
urn:nbn:se:bth-16998 (URN)10.2196/11252 (DOI)000454162600001 ()
Projects
MD3S
Note

Open access

Available from: 2018-09-13 Created: 2018-09-13 Last updated: 2019-10-29Bibliographically approved
Lagerspetz, E., Flores, H., Mäkitalo, N., Hui, P., Nurmi, P., Tarkoma, S., . . . Quercia, D. (2018). Pervasive Communities in the Internet of People. In: 2018 IEEE International Conference on Pervasive Computing and Communications Workshops, PerCom Workshops 2018: . Paper presented at 2018 IEEE International Conference on Pervasive Computing and Communications Workshops, PerCom Workshops 2018, 19 March 2018 through 23 March 2018 (pp. 40-45). Institute of Electrical and Electronics Engineers Inc., Article ID 8480273.
Open this publication in new window or tab >>Pervasive Communities in the Internet of People
Show others...
2018 (English)In: 2018 IEEE International Conference on Pervasive Computing and Communications Workshops, PerCom Workshops 2018, Institute of Electrical and Electronics Engineers Inc. , 2018, p. 40-45, article id 8480273Conference paper, Published paper (Refereed)
Abstract [en]

The Internet has traditionally been a device-oriented architecture where devices with IP addresses are first-class citizens, able to serve and consume content or services, and their owners take part in the interaction only through those devices. The Internet of People (IoP) is a recent paradigm where devices become proxies of their users, and can act on their behalf. To realize IoP, new policies and rules for how devices can take actions are required. The role of context information grows as devices act autonomously based on the environment and existing social relationships between their owners. In addition, the social profiles of device owners determine e.g. how altruistic or resourceconserving they are in collaborative computing scenarios. In this paper we focus on community formation in IoP, a prerequisite for enabling collaborative scenarios, and discuss main challenges and propose potential solutions. © 2018 IEEE.

Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers Inc., 2018
Keywords
Computer programming, Computer science, Context information, IP addresss, Social profiles, Social relationships, Ubiquitous computing
National Category
Communication Systems Media and Communication Technology
Identifiers
urn:nbn:se:bth-17347 (URN)10.1109/PERCOMW.2018.8480273 (DOI)2-s2.0-85056482134 (Scopus ID)9781538632277 (ISBN)
Conference
2018 IEEE International Conference on Pervasive Computing and Communications Workshops, PerCom Workshops 2018, 19 March 2018 through 23 March 2018
Available from: 2018-11-29 Created: 2018-11-29 Last updated: 2018-11-29Bibliographically approved
Organisations

Search in DiVA

Show all publications