{"id":{"repo_id":"uwtsd","oai_identifier":"oai:repository.uwtsd.ac.uk:1226"},"canonical_url":"https://search.dev.ndltd.org/etd/uwtsd/oai:repository.uwtsd.ac.uk:1226","repository":{"repo_id":"uwtsd","name":"University of Wales Trinity Saint David","base_url":"https://repository.uwtsd.ac.uk/cgi/oai2"},"display":{"title":"A novel non-intrusive objective method to predict voice quality of service in LTE networks.","abstract":"This research aimed to introduce a novel approach for non-intrusive objective measurement of voice Quality of Service (QoS) in LTE networks. While achieving this aim, the thesis established a thorough knowledge of how voice traffic is handled in LTE networks, the LTE network architecture and its similarities and differences to its predecessors and traditional ground IP networks and most importantly those QoS affecting parameters which are exclusive to LTE environments. Mean Opinion Score (MOS) is the scoring system used to measure the QoS of voice traffic which can be measured subjectively (as originally intended). Subjective QoS measurement methods are costly and time-consuming, therefore, objective methods such as Perceptual Evaluation of Speech Quality (PESQ) were developed to address these limitations. These objective methods have a high correlation with subjective MOS scores. However, they either require individual calculation of many network parameters or have an intrusive nature that requires access to both the reference signal and the degraded signal for comparison by software. Therefore, the current objective methods are not suitable for application in real-time measurement and prediction scenarios. A major contribution of the research was identifying LTE-specific QoS affecting parameters. There is no previous work that combines these parameters to assess their impacts on QoS. The experiment was configured in a hardware in the loop environment. This configuration could serve as a platform for future research which requires simulation of voice traffic in LTE environments. The key contribution of this research is a novel non-intrusive objective method for QoS measurement and prediction using neural networks. A comparative analysis is presented that examines the performance of four neural network algorithms for non-intrusive measurement and prediction of voice quality over LTE networks. In conclusion, the Bayesian Regularization algorithm with 4 neurons in the hidden layer and sigmoid symmetric transfer function was identified as the best solution with a Mean Square Error (MSE) rate of 0.001 and regression value of 0.998 measured for the testing data set.","abstract_html":"This research aimed to introduce a novel approach for non-intrusive objective measurement of voice Quality of Service (QoS) in LTE networks. While achieving this aim, the thesis established a thorough knowledge of how voice traffic is handled in LTE networks, the LTE network architecture and its similarities and differences to its predecessors and traditional ground IP networks and most importantly those QoS affecting parameters which are exclusive to LTE environments. Mean Opinion Score (MOS) is the scoring system used to measure the QoS of voice traffic which can be measured subjectively (as originally intended). Subjective QoS measurement methods are costly and time-consuming, therefore, objective methods such as Perceptual Evaluation of Speech Quality (PESQ) were developed to address these limitations. These objective methods have a high correlation with subjective MOS scores. However, they either require individual calculation of many network parameters or have an intrusive nature that requires access to both the reference signal and the degraded signal for comparison by software. Therefore, the current objective methods are not suitable for application in real-time measurement and prediction scenarios. A major contribution of the research was identifying LTE-specific QoS affecting parameters. There is no previous work that combines these parameters to assess their impacts on QoS. The experiment was configured in a hardware in the loop environment. This configuration could serve as a platform for future research which requires simulation of voice traffic in LTE environments. The key contribution of this research is a novel non-intrusive objective method for QoS measurement and prediction using neural networks. A comparative analysis is presented that examines the performance of four neural network algorithms for non-intrusive measurement and prediction of voice quality over LTE networks. In conclusion, the Bayesian Regularization algorithm with 4 neurons in the hidden layer and sigmoid symmetric transfer function was identified as the best solution with a Mean Square Error (MSE) rate of 0.001 and regression value of 0.998 measured for the testing data set.","abstract_has_math":false,"creators":["Sedigh, Arya"],"institution":"University of Wales Trinity Saint David","degree_name":"phd","degree_level":"doctoral","degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2020,"date_issued":"2020-03","date_published":"2020-03","updated_at":"2026-07-24T05:52:50Z","subjects":["QA75 Cyfrifiaduron electronig"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier.grantnumber","label":"Dc Identifier Grantnumber","values":["UWTSD"],"render_values":[{"text":"UWTSD","href":null,"code":true}]}]},"links":{"outbound_url":"https://doi.org/10.82227/repository.uwtsd.ac.uk.00001226","outbound_label":"DOI","outbound_source":"dc:identifier.doi"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.sponsor","label":"Sponsor","values":["University of Wales Trinity Saint David"]},{"key":"dc:creator","label":"Author","values":["Sedigh, Arya"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2020-03-02"]},{"key":"dc:date.issued","label":"Date","values":["2020-03"]},{"key":"dc:publisher.commercial","label":"Dc Publisher Commercial","values":["University of Wales Trinity Saint David"]},{"key":"dc:publisher.department","label":"Dc Publisher Department","values":["Traethodau PhD","Institutes and Academies : Wales Institute for Science & Art (WISA) : Academic discipline : Applied Computing"]},{"key":"dc:publisher.institution","label":"Dc Publisher Institution","values":["University of Wales Trinity Saint David"]},{"key":"dc:relation.isreferencedby","label":"Dc Relation Isreferencedby","values":["https://repository.uwtsd.ac.uk/id/eprint/1226/"]},{"key":"dc:type","label":"Dc Type","values":["Gosodiad"]},{"key":"dc:type.qualificationlevel","label":"Dc Type Qualificationlevel","values":["doctoral"]},{"key":"dc:type.qualificationname","label":"Dc Type Qualificationname","values":["phd"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["QA75 Cyfrifiaduron electronig"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.doi","label":"DOI","values":["10.82227/repository.uwtsd.ac.uk.00001226"]},{"key":"dc:identifier.grantnumber","label":"Dc Identifier Grantnumber","values":["UWTSD"]},{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://repository.uwtsd.ac.uk/id/eprint/1226/1/Sedigh%2C%20Arya%20%282018%20%29%20A%20novel%20non-intrusive.pdf"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["This research aimed to introduce a novel approach for non-intrusive objective measurement of voice Quality of Service (QoS) in LTE networks. While achieving this aim, the thesis established a thorough knowledge of how voice traffic is handled in LTE networks, the LTE network architecture and its similarities and differences to its predecessors and traditional ground IP networks and most importantly those QoS affecting parameters which are exclusive to LTE environments. Mean Opinion Score (MOS) is the scoring system used to measure the QoS of voice traffic which can be measured subjectively (as originally intended). Subjective QoS measurement methods are costly and time-consuming, therefore, objective methods such as Perceptual Evaluation of Speech Quality (PESQ) were developed to address these limitations. These objective methods have a high correlation with subjective MOS scores. However, they either require individual calculation of many network parameters or have an intrusive nature that requires access to both the reference signal and the degraded signal for comparison by software. Therefore, the current objective methods are not suitable for application in real-time measurement and prediction scenarios. A major contribution of the research was identifying LTE-specific QoS affecting parameters. There is no previous work that combines these parameters to assess their impacts on QoS. The experiment was configured in a hardware in the loop environment. This configuration could serve as a platform for future research which requires simulation of voice traffic in LTE environments. The key contribution of this research is a novel non-intrusive objective method for QoS measurement and prediction using neural networks. A comparative analysis is presented that examines the performance of four neural network algorithms for non-intrusive measurement and prediction of voice quality over LTE networks. In conclusion, the Bayesian Regularization algorithm with 4 neurons in the hidden layer and sigmoid symmetric transfer function was identified as the best solution with a Mean Square Error (MSE) rate of 0.001 and regression value of 0.998 measured for the testing data set."]},{"key":"dc:format","label":"Dc Format","values":["text"]},{"key":"dc:title","label":"Title","values":["A novel non-intrusive objective method to predict voice quality of service in LTE networks."]}]}],"canonical_facts":{"dc:contributor.sponsor":["University of Wales Trinity Saint David"],"dc:creator":["Sedigh, Arya"],"dc:date":["2020-03-02"],"dc:date.issued":["2020-03"],"dc:description.abstract":["This research aimed to introduce a novel approach for non-intrusive objective measurement of voice Quality of Service (QoS) in LTE networks. While achieving this aim, the thesis established a thorough knowledge of how voice traffic is handled in LTE networks, the LTE network architecture and its similarities and differences to its predecessors and traditional ground IP networks and most importantly those QoS affecting parameters which are exclusive to LTE environments. Mean Opinion Score (MOS) is the scoring system used to measure the QoS of voice traffic which can be measured subjectively (as originally intended). Subjective QoS measurement methods are costly and time-consuming, therefore, objective methods such as Perceptual Evaluation of Speech Quality (PESQ) were developed to address these limitations. These objective methods have a high correlation with subjective MOS scores. However, they either require individual calculation of many network parameters or have an intrusive nature that requires access to both the reference signal and the degraded signal for comparison by software. Therefore, the current objective methods are not suitable for application in real-time measurement and prediction scenarios. A major contribution of the research was identifying LTE-specific QoS affecting parameters. There is no previous work that combines these parameters to assess their impacts on QoS. The experiment was configured in a hardware in the loop environment. This configuration could serve as a platform for future research which requires simulation of voice traffic in LTE environments. The key contribution of this research is a novel non-intrusive objective method for QoS measurement and prediction using neural networks. A comparative analysis is presented that examines the performance of four neural network algorithms for non-intrusive measurement and prediction of voice quality over LTE networks. In conclusion, the Bayesian Regularization algorithm with 4 neurons in the hidden layer and sigmoid symmetric transfer function was identified as the best solution with a Mean Square Error (MSE) rate of 0.001 and regression value of 0.998 measured for the testing data set."],"dc:format":["text"],"dc:identifier.doi":["10.82227/repository.uwtsd.ac.uk.00001226"],"dc:identifier.grantnumber":["UWTSD"],"dc:identifier.uri":["https://repository.uwtsd.ac.uk/id/eprint/1226/1/Sedigh%2C%20Arya%20%282018%20%29%20A%20novel%20non-intrusive.pdf"],"dc:publisher.commercial":["University of Wales Trinity Saint David"],"dc:publisher.department":["Traethodau PhD","Institutes and Academies : Wales Institute for Science & Art (WISA) : Academic discipline : Applied Computing"],"dc:publisher.institution":["University of Wales Trinity Saint David"],"dc:relation.isreferencedby":["https://repository.uwtsd.ac.uk/id/eprint/1226/"],"dc:subject":["QA75 Cyfrifiaduron electronig"],"dc:title":["A novel non-intrusive objective method to predict voice quality of service in LTE networks."],"dc:type":["Gosodiad"],"dc:type.qualificationlevel":["doctoral"],"dc:type.qualificationname":["phd"]},"updated_at":"2026-07-24T05:52:50Z"}