Figure - available via license: Creative Commons Attribution 3.0 Unported
Content may be subject to copyright.
Source publication
Internet television (IPTV) is rapidly gaining popularity and is being widely deployed in content delivery networks on the Internet. In order to proactively deliver optimum user quality of experience (QoE) for IPTV, service providers need to identify network bottlenecks in real time. In this paper, we develop psycho-acoustic-visual models that can p...
Citations
... They can also lead to application latency issues that degrade performance. Based on prior works in VRLE and other IoT applications [10], [11] we adopt the following definitions of various performance (3Q) factors: Quality of Application (QoA) -a measure of the application performance; Quality of Service (QoS) -a measure of network resources such as bandwidth and jitter; Quality of Experience (QoE) -a measure of the perceived satisfaction or annoyance of a user's experience [12]. Similarly, we adopt the definition of security -as a condition that ensures a VR system is able to perform critical application functions with the establishment of confidentiality, integrity, and availability [7]. ...
Social virtual reality learning environments (VRLEs) provide immersive experience to users with increased accessibility to remote learning. Lack of maintaining high-performance and secured data delivery in critical VRLE application domains (e.g., military training, manufacturing) can disrupt application functionality and induce cybersickness. In this paper, we present a novel rule-based 3QS-adaptation framework that performs risk and cost aware trade-off analysis to control cybersickness due to performance/security anomaly events during a VRLE session. Our framework implementation in a social VRLE viz., vSocial monitors performance/security anomaly events in network/session data. In the event of an anomaly, the framework features rule-based adaptations that are triggered by using various decision metrics. Based on our experimental results, we demonstrate the effectiveness of our rule-based 3QS-adaptation framework in reducing cybersickness levels, while maintaining application functionality. Using our key findings, we enlist suitable practices for addressing performance and security issues towards a more high-performing and robust social VRLE.
... They can also lead to application latency issues that degrade performance. Based on prior works in VRLE and other IoT applications [10], [11] we adopt the following definitions of various performance (3Q) factors: Quality of Application (QoA) -a measure of the application performance; Quality of Service (QoS) -a measure of network resources such as bandwidth and jitter; Quality of Experience (QoE) -a measure of the perceived satisfaction or annoyance of a user's experience [12]. Similarly, we adopt the definition of security -as a condition that ensures a VR system is able to perform critical application functions with the establishment of confidentiality, integrity, and availability [7]. ...
Social virtual reality learning environments (VRLEs) provide immersive experience to users with increased accessibility to remote learning. Lack of maintaining high-performance and secured data delivery in critical VRLE application domains (e.g., military training, manufacturing) can disrupt application functionality and induce cybersickness. In this paper, we present a novel rule-based 3QS-adaptation framework that performs risk and cost aware trade-off analysis to control cybersickness due to performance/security anomaly events during a VRLE session. Our framework implementation in a social VRLE viz., vSocial monitors performance/security anomaly events in network/session data. In the event of an anomaly, the framework features rule-based adaptations that are triggered by using various decision metrics. Based on our experimental results, we demonstrate the effectiveness of our rule-based 3QS-adaptation framework in reducing cybersickness levels, while maintaining application functionality. Using our key findings, we enlist suitable practices for addressing performance and security issues towards a more high-performing and robust social VRLE.
... Networking Protocol Selection in FANETs. The recognition of imagery taken from over-the-head cameras poses many challenging tasks compared with imagery taken by a fixed ground level camera because of low or high resolution imagery patterns [20,21]. Herein, a major challenging task involves handling the large intra-class variation in activities including variations in resolution scale, target (e.g., visual appearance, speed of motion) and environment (e.g., lighting condition, occlusion) [22]. ...
Multi-Unmanned Aerial Vehicle (UAV) systems with high-resolution cameras have been found useful for operations such as smart city and disaster management. These systems feature Flying Ad-Hoc Networks (FANETs) that connect the computation edge with UAVs and a Ground Control Station (GCS) through air-to-ground wireless network links. Leveraging the edge/fog computation resources effectively with energy-latency-awareness, and handling intermittent failures of FANETs are the major challenges in supporting video processing applications. In this paper, we propose a novel “DroneCOCoNet” framework for drone video analytics that coordinates intelligent processing of large video datasets using edge computation offloading and performs network protocol selection based on resource-awareness. We present two edge computation offloading approaches, i.e., heuristic-based and reinforcement learning-based approaches. These approaches provide intelligent task sharing and co-ordination for dynamic offloading decision-making among UAVs. Our scheme handles the problem of computation offloading tasks in two separate ways: (i) heuristic decision-making process, and (ii) Markov decision process; wherein we aim to minimize the total computation costs as well as latency in the edge/fog resources while minimizing video processing times to meet application requirements. Our experimental results show that our heuristic-based offloading decision-making scheme enables lower scheduling time and energy consumption for low drone-to-ground server ratios. In comparison, our dynamic reinforcement learning-based decision-making approach increases the accuracy and saves overall time periodically. Notably, these results also hold in various other multi-UAV scenarios involving largely different numbers of detected objects in e.g., smart farming, transportation traffic flow monitoring and disaster response.
... Occlusion-awareness on Aerial Video Analytics. The overhead imagery recognition poses many challenging tasks than a xed ground level camera because of low resolution or high resolution imagery patterns [2]. Here a major challenging task involves handling the large intra-class variation in activities including variations in resolution scale, target (e.g., visual appearance, speed of motion) and environment (e.g., lighting condition, occlusion) [28]. ...
... The control provided a mean of creating transmission environments for good, medium and poor video qualities. The video was sent over a PPP link such that the traffic from PC-1 transmitted to PC-2 through NetEm server [32]. The selected video was a Big Buck Bunny [33] clip, duration 90 seconds and consisting of 1350 frames. ...
Video transmission over wireless computer networks is increasingly popular as new applications emerge and wireless networks become more widespread and reliable. An ability to quantify the quality of a video transmitted using a wireless computer network is important for determining network performance and its improvement. The process requires analysing the images making up the video from the point of view of noise and associated distortion as well as traffic parameters represented by packet delay, jitter and loss. In this study a modular fuzzy logic based system was developed to quantify the quality of video transmission over a wireless computer network. Peak signal to noise ratio, structural similarity index and image difference were used to represent the user's quality of experience (QoE) while packet delay, jitter and percentage packet loss ratio were used to represent traffic related quality of service (QoS). An overall measure of the video quality was obtained by combining QoE and QoS values. Systematic sampling was used to reduce the number of images processed and a novel scheme was devised whereby the images were partitioned to more sensitively localize distortions. To further validate the developed system, a subjective test involving 25 participants graded the quality of the received video. The image partitioning significantly improved the video quality evaluation. The subjective test results correlated with the developed fuzzy logic approach. The video quality assessment developed in this study was compared against a method that uses spatial efficient entropic differencing and consistent results were observed. The study indicated that the developed fuzzy logic approaches could accurately determine the quality of a wirelessly transmitted video.
... 130 In case of audio-video communication, predicted quality decreases with the increase of the jitter. 118,126 Packet loss Small increment in the packet loss rate causes lower MOS ratings of audio. 130 Analysis of different applications (ie, Skype, MSN Messenger, AIM) showed that the best Skype's audio quality can be achieved under different loss rates, whereas AIM performs the best in the nonloss and bandwidth limited scenarios. ...
... 131 In audio-video communication, predicted quality decreases with the increase of the packet loss levels. 118,126 In addition, lower audio quality results in less similarity between the perceived video and audio quality ratings. 132 Perceived difference in video quality follows the perception of audio quality, although the video quality was never altered. ...
... System IF Bitrate 20,23,31,34,36,37,44,45,48,51,67,97,98,105,108,112,124,129,142,146 32.787 Frame rate 23,45,49,52,[92][93][94][95][97][98][99][100][101]143 22.951 Content type 20,34,37,45,52,67,90,97,98,102,105,129,145,147 22.951 Packet loss 20,44,47,48,51,107,109,113,[123][124][125]130 20,23,26,29,31,32,34,36,37,44,[46][47][48][49][50][51][52]72,90,[92][93][94][95]97,98,[100][101][102]105,106,112,113,119,123,124,126,129,130,[142][143][144][145]148 70.492 ...
... , (3.1) em que os parâmetros 1 a 7 são otimizados pelo método iterativo LM (LEVENBERG, 1944;MARQUARDT, 1963;MORÉ, 1977) relatado na literatura em diversos trabalhos relacionados à avaliação de qualidade de imagem e vídeo que o empregam na solução de problemas de mínimos quadrados RIES et al., 2006;ZEPERNICK, 2007a;KEIMEL et al., 2009;BRANDÃO;QUELUZ, 2010;SHAHID et al., 2011;CALYAM et al., 2012;KIPLI et al., 2012). ...
A pesquisa e o desenvolvimento de métodos sem referência para avaliação de qualidade de vídeos submetidos a distorções e perdas de pacotes em transmissões pela Internet, redes sem fio e em TV Digital é um campo de pesquisa incipiente e promissor no campo de pesquisa em vídeo digital. O objetivo desta linha de pesquisa é estabelecer a melhor correlação possível entre a percepção (subjetiva) do Sistema Visual Humano e os métodos objetivos de avaliação de vídeo. Este projeto propõe o desenvolvimento de métodos para avaliação objetiva de qualidade de vídeo sem referência baseados em características
espaço-temporais, segundo duas abordagens: a primeira recorre a um modelo analítico sigmoidal com solução de mínimos quadrados pelo método de Levenberg-Marquardt e a segunda abordagem usa uma rede neural artificial Single-Hidden Layer Feedforward Neural Network com aprendizado baseado em uma versão estendida do algoritmo Extreme Learning Machine, a qual busca, iterativamente, os melhores parâmetros da rede neural artificial, segundo um simples critério de parada. Como resultados esperados, acredita-se na ampliação das contribuições defendidas pelo coordenador em trajetória como pes-
quisador, continuando com a produção e publicação de novos resultados no campo de avaliação de qualidade de vídeo, enquanto docente da Universidade Federal de Santa Catarina (UFSC). Além de desenvolver atividades de ensino, pesquisa e extensão junto à
UFSC, o coordenador deste projeto se dispõe a orientar alunos de graduação e de pós-graduação. Assim, almeja-se que este projeto possa contribuir para o fortalecimento e consolidação dessa linha de pesquisa na UFSC.
... A similar testbed experiment was conducted through the Distributed Passive Measurement Infrastructure (DPMI) constituting a server, a client, the Linux Traffic Controller (TC) shaper, two measurement points (M2 and M3), a measurement area controller and the consumer station for data (Shaikh et al., 2010). Other testbed experiment studies often involved volunteered participants of different age groups to collect data in a controlled environment with a high level of control to enable the estimation/prediction of the perceived QoE for different internet applications (the likes of web browsing, video and VOIP applications (Alreshoodi & Woods, 2013;Aroussi & Mellouk, 2016;Calyam et al., 2012;Charonyktakis et al., 2016;Calyam et al., 2012;DeMoor et al., 2010;Fiedler et al. 2010;Geerts et al., 2010;Li et al., 2016;Menkovski et al., 2009;Rugelj et al., 2014;Spetebroot et al., 2015) Similarly, as seen in Table 2, most of the studies focused on a specific application or service, because the authors tended to make the contextual factors as fixed as possible for a certain QoS parameter which is a variable of the system QoE influence factor. To overcome this drawback, a deterministic mathematical model (DQX) was proposed by . ...
... A similar testbed experiment was conducted through the Distributed Passive Measurement Infrastructure (DPMI) constituting a server, a client, the Linux Traffic Controller (TC) shaper, two measurement points (M2 and M3), a measurement area controller and the consumer station for data (Shaikh et al., 2010). Other testbed experiment studies often involved volunteered participants of different age groups to collect data in a controlled environment with a high level of control to enable the estimation/prediction of the perceived QoE for different internet applications (the likes of web browsing, video and VOIP applications (Alreshoodi & Woods, 2013;Aroussi & Mellouk, 2016;Calyam et al., 2012;Charonyktakis et al., 2016;Calyam et al., 2012;DeMoor et al., 2010;Fiedler et al. 2010;Geerts et al., 2010;Li et al., 2016;Menkovski et al., 2009;Rugelj et al., 2014;Spetebroot et al., 2015) Similarly, as seen in Table 2, most of the studies focused on a specific application or service, because the authors tended to make the contextual factors as fixed as possible for a certain QoS parameter which is a variable of the system QoE influence factor. To overcome this drawback, a deterministic mathematical model (DQX) was proposed by . ...
... However, evidence has shown experimentally that there is a need to quantify QoE of different mobile internet applications in relation to time and location al., 2016;Calyam et al., 2012;DeMoor et al., 2010;;Li et al., 2016;Menkovski et al., 2009;Rugelj et al., the studies focused on a specific application or service, contextual factors as fixed as possible for a certain QoS tem QoE influence factor. To overcome this drawback, a ) was proposed by (Barakovic & Skorin-Kapov, 2015;Reichl et al., 2015;. ...
The increase in the usage of different mobile internet applications can cause deterioration in the mobile network performance. Such deterioration often declines the performance of the mobile network services that can influence the mobile Internet user's experience, which can make the internet users switch between different mobile network operators to get good user experience. In this case, the success of mobile network operators primarily depends on the ability to ensure good quality of experience (QoE), which is a measure of users' perceived quality of mobile Internet service. Traditionally, QoE is usually examined in laboratory experiments to enable a fixed contextual factor among the participants even though the results derived from these laboratory experiments presented an estimated mean opinion score representing perceived QoE. The use of user experience dataset involving time and location gathered from the mobile network traffic for modelling perceived QoE is still limited in the literature. The mobile Internet user experience dataset involving the time and location constituted in the mobile network can be used by the mobile network operators to make data-driven decisions to deal with disruptions observed in the network performance and provide an optimal solution based on the insights derived from the user experience data. Therefore, this paper proposed a framework for modelling mobile network QoE using the big data analytics approach. The proposed framework describes the process of estimating or predicting perceived QoE based on the datasets obtained or gathered from the mobile network to enable the mobile network operators effectively to manage the network performance and provide the users a satisfactory mobile Internet QoE.
... A similar testbed experiment was conducted through the Distributed Passive Measurement Infrastructure (DPMI) constituting a server, a client, the Linux Traffic Controller (TC) shaper, two measurement points (M2 and M3), a measurement area controller and the consumer station for data (Shaikh et al., 2010). Other testbed experiment studies often involved volunteered participants of different age groups to collect data in a controlled environment with a high level of control to enable the estimation/prediction of the perceived QoE for different internet applications (the likes of web browsing, video and VOIP applications (Alreshoodi & Woods, 2013;Aroussi & Mellouk, 2016;Calyam et al., 2012;Charonyktakis et al., 2016;Calyam et al., 2012;DeMoor et al., 2010;Fiedler et al. 2010;Geerts et al., 2010;Li et al., 2016;Menkovski et al., 2009;Rugelj et al., 2014;Spetebroot et al., 2015) Similarly, as seen in Table 2, most of the studies focused on a specific application or service, because the authors tended to make the contextual factors as fixed as possible for a certain QoS parameter which is a variable of the system QoE influence factor. To overcome this drawback, a deterministic mathematical model (DQX) was proposed by . ...
... A similar testbed experiment was conducted through the Distributed Passive Measurement Infrastructure (DPMI) constituting a server, a client, the Linux Traffic Controller (TC) shaper, two measurement points (M2 and M3), a measurement area controller and the consumer station for data (Shaikh et al., 2010). Other testbed experiment studies often involved volunteered participants of different age groups to collect data in a controlled environment with a high level of control to enable the estimation/prediction of the perceived QoE for different internet applications (the likes of web browsing, video and VOIP applications (Alreshoodi & Woods, 2013;Aroussi & Mellouk, 2016;Calyam et al., 2012;Charonyktakis et al., 2016;Calyam et al., 2012;DeMoor et al., 2010;Fiedler et al. 2010;Geerts et al., 2010;Li et al., 2016;Menkovski et al., 2009;Rugelj et al., 2014;Spetebroot et al., 2015) Similarly, as seen in Table 2, most of the studies focused on a specific application or service, because the authors tended to make the contextual factors as fixed as possible for a certain QoS parameter which is a variable of the system QoE influence factor. To overcome this drawback, a deterministic mathematical model (DQX) was proposed by . ...
... However, evidence has shown experimentally that there is a need to quantify QoE of different mobile internet applications in relation to time and location al., 2016;Calyam et al., 2012;DeMoor et al., 2010;;Li et al., 2016;Menkovski et al., 2009;Rugelj et al., the studies focused on a specific application or service, contextual factors as fixed as possible for a certain QoS tem QoE influence factor. To overcome this drawback, a ) was proposed by (Barakovic & Skorin-Kapov, 2015;Reichl et al., 2015;. ...
The increase in the usage of different mobile internet applications can cause deterioration in the mobile network performance. Such deterioration often declines the performance of the mobile network services that can influence the mobile Internet user’s experience, which can make the internet users switch between different mobile network operators to get good user experience. In this case, the success of mobile network operators primarily depends on the ability to ensure good quality of experience (QoE), which is a measure of users’ perceived quality of mobile Internet service. Traditionally, QoE is usually examined in laboratory experiments to enable a fixed contextual factor among the participants even though the results derived from these laboratory experiments presented an estimated mean opinion score representing perceived QoE. The use of user experience dataset involving time and location gathered from the mobile network traffic for modelling perceived QoE is still limited in the literature. The mobile Internet user experience dataset involving the time and location constituted in the mobile network can be used by the mobile network operators to make data-driven decisions to deal with disruptions observed in the network performance and provide an optimal solution based on the insights derived from the user experience data. Therefore, this paper proposed a framework for modelling mobile network QoE using the big data analytics approach. The proposed framework describes the process of estimating or predicting perceived QoE based on the datasets obtained or gathered from the mobile network to enable the mobile network operators effectively to manage the network performance and provide the users a satisfactory mobile Internet QoE.
... The various QoS factors used are execution time, response time, latency, throughput and capacity. The correlation between certain factors of QoUE used in this paper and QoS can be found in [5] [7].These factors are found to have impact in both stand-alone web services and services that are composed of other web services. In order to reason about the QoS and QoUE factors of web services, a model is required for capturing the description of these from the user perspective. ...
... The earlier work entitled WSrep [7] framework in which the service reputation is modelled based on the user's response. It uses the subjective and objective views of historical behaviour of service owners and applies these for obtaining the reputation value for the service. ...
Service Oriented Architecture (SOA) approaches are presently getting to be appropriate to embedded devices that feature embedded processing and communication. As a result these services get the ability to be hosted on high end machines to wireless resource constrained devices and on any physical object supported with communication ability. This creates the Internet of Services (IoS) environment. Services from multiple owners can be assembled into a composite service irrespective of their specific Quality of Service (QoS) and related properties for implementing a complex business process. In this context service consumer comes against the problem of selecting best service and for which providing QoS relevant guarantees leads to many challenging issues. One among them is determining a feasible service composition that fulfils a set of conditions while maintaining a good Quality of User Experience (QoUE). The last goal suggests the requirement to enforce an extra optimality prerequisite on the feasibility problem. In this paper, an optimization strategy oriented to efficient composite service selection for IoS model is designed through use of Particle Swarm Optimization (PSO) technique. Furthermore, prior to optimization, the services are assured of rich QoUE, especially trustworthiness in terms of reputation. The proposed work evaluates QoUE using the fuzzy based inference algorithm for identifying QoUE satisfied composite service. Experimental evaluation on a set of real world web services demonstrates the effectiveness of our proposed methodology.
