User QoE Research Articles

Raising the Bar: Improved Fingerprinting Attacks and Defenses for Video Streaming Traffic

Despite the clear dominance of video streaming traffic on the Internet and the significant ramifications of disclosure of which videos users are streaming, video fingerprinting has received relatively little attention compared to other traffic analysis domains. Existing attacks are tailored to undefended traffic and mostly rely on a few manually crafted features. Meanwhile, potential defenses are ad hoc, often impractical, and typically only mentioned briefly. Drawing from progress made on website fingerprinting, we aim to improve current standards for attacks and defenses for video streaming traffic while highlighting a critical and underexplored issue on today's Internet. We show that directional and timing-based attacks that leverage CNNs are competitive with state-of-the-art video fingerprinting attacks, in many cases with far less training data. We also provide the first extensive study of potential defenses, which considers performance against attacks, overheads, and user QoE; and we present a novel defense design that boasts both broader applicability and greater efficacy than existing proposals.

Inference Analysis of Video Quality of Experience in Relation with Face Emotion, Video Advertisement, and ITU-T P.1203

This study introduces an FER-based machine learning framework for real-time QoE assessment in video streaming. This study’s aim is to address the challenges posed by end-to-end encryption and video advertisement while enhancing user QoE. Our proposed framework significantly outperforms the base reference, ITU-T P.1203, by up to 37.1% in terms of accuracy and 21.74% after attribute selection. Our study contributes to the field in two ways. First, we offer a promising solution to enhance user satisfaction in video streaming services via real-time user emotion and user feedback integration, providing a more holistic understanding of user experience. Second, high-quality data collection and insights are offered by collecting real data from diverse regions to minimize any potential biases and provide advertisement placement suggestions.

A Dynamic Task Scheduling Algorithm for Airborne Device Clouds

The rapid development of mobile Internet has promoted the rapid rise of cloud computing technology. Mobile terminal devices have greatly expanded the service capacity of mobile terminals by migrating complex computing tasks to run in the cloud. However, in the process of data exchange between mobile terminals and cloud computing centers, on the one hand, it consumes the limited power of mobile terminals, and on the other hand, it results in longer communication time, which negatively affects user QoE. Mobile cloud can effectively improve user QoE by shortening the data transmission distance, reducing the power consumption, and shortening the communication time at the same time. In this paper, we utilize the property that genetic algorithm can perform global search seeking the global optimal solution and construct a dynamic task scheduling model by combining the device-cloud link. The task scheduling model based on genetic algorithm and random scheduling algorithm is compared through comparison experiments, which show that the assignment time of the task scheduling model based on genetic algorithm is shortened by 11.82% to 48.51% and the energy consumption is reduced by 22.28% to 47.52% under different load conditions.

Enabling Metaheuristics with Deep Learning based Resource Allocation in Unmanned Aerial Vehicles Wireless Networks

Unmanned aerial vehicle (UAV) network offers a variety of applications in public safety, disaster management, advertising and broadcasting, overload situation, etc. Due to the dynamic characteristics of MU, it is challenging to provide robust transmission services to mobile users (MU). Resource allocation (RA), including sub-channel, serving user, and transmit power, is a crucial problem; also, it is critical to enhance the coverage and energy efficiency of UAV-enabled communication protocol. Furthermore, system resources are limited (for example, spectrum, and transmission power) and UAV transmission coverage and on-board energy are limited. In order to meet the QoE of any user with limited UAV energy and limited resource system, we jointly enhance UAV trajectory, user communication scheduling, and bandwidth allocation and transmit power to satisfy user QoE requirements and increase energy efficiency. Thus, the study proposes a new mud ring optimization with deep belief network-based resource allocation scheme (MRODBN-RAS) technique for UAV-enabled wireless networks. The proposed MRODBN-RAS approach focuses on the effectual accomplishment of the computational and energy-effective decision. Besides, the MRODBN-RAS technique assumed the UAV as a learning agent by forming RA decisions as actions. In addition, the MRODBN-RAS technique designed a reward function to reduce the weighted resource utilization. The MRODBN-RAS technique uses DBN model with hyperparameter tuning using MRO algorithm to allocate the resources. The design of the MRO algorithm helps in the optimal selection of the hyperparameter related to the DBN model. The simulation results of the MRODBN-RAS method are examined under various measures. The extensive comparison study highlighted the better performance of the MRODBN-RAS approach over existing techniques.

Profit Maximization for Cache-Enabled Vehicular Mobile Edge Computing Networks

In this paper, we investigate a multiuser cache-enabled vehicular mobile edge computing (MEC) network, where one edge server (ES) has some caching and computing capabilities to assist the task computing from the vehicular users. The introduce of caching into the MEC network significantly affects the system performance such as the latency, energy consumption and profit at the ES, which imposes a critical challenge on the system design and optimization. To solve this challenge, we firstly design the vehicular MEC network in a non-competitive environment by maximizing the profit of the ES with a predetermined threshold of user QoE, and jointly exploit the caching and computing resources in the network. We then model the optimization problem into a binary integer programming problem, and adopt the cross entropy (CE) method to obtain the effective offloading and caching decision with a low complexity. Simulation results are finally presented to verify that the proposed scheme can achieve the near optimal performance of the conventional branch and bound (BnB) scheme, while sharply reduce the computational complexity compared to the BnB.

Ebublio: Edge-Assisted Multiuser 360° Video Streaming

As one of the most important manifestations of virtual reality (VR), 3600 panoramic videos in recent years have experienced booming development due to the desire for immersive and interactive experiences. Compared to traditional videos, 3600 videos are featured with uncertain user field of view (FoV), more sensitive delay tolerance, and much higher bandwidth requirement, bringing unprecedented challenges to 3600 video streaming. Meanwhile, the development of 5G and mobile edge computing starts to pave the way for high-bandwidth low-latency video streaming. Some preliminary works focus on either individual FoV prediction or multi-user QoE oriented cache strategy design, while how to design a holistic solution toward optimizing the overall user QoE with considerations over fairness and long-term system cost remains a non-trivial problem. In this paper, we propose Ebublio, a novel intelligent edge caching framework to address the aforementioned challenges in 3600 video streaming. Ebublio consists of a collaborative FoV prediction (CFP) module and a long-term tile caching optimization (LTO) module to jointly optimize the long-term user QoE and system cost. The former module integrates the features of video content, user trajectory, and other users records for combined prediction. The latter one employs the Lyapunov framework and a subgradient optimization approach towards the optimal caching replacement policy. Our trace-driven evaluation demonstrates the superiority of our framework, with about 42% improvement in FoV prediction, and 36% improvement in QoE at similar traffic consumption.

Ad Hoc Wireless Networks With QoS Guarntees For LTE Femtocell-Macrocell Networks

LTE analysis is this thesis' goal. Femtocell Network Implementation Indoor data traffic is predicted to dominate future data traffic. Using macrocellular coverage in high-traffic areas is difficult and expensive. Femtocells, low-power cellular base stations, can improve coverage and data throughput. A connected femtocell-macrocell network improves coverage, QoS, cost, and energy efficiency. In an integrated network, the number of Femtocell Access Points (FAPs) and macrocell-femtocell interference must be considered to ensure service quality. Control transfer, interference management, and resource allocation affect service quality. A seamless transition between macrocell and femtocell networks ensures service quality. Due to their small size, femtocells may handover often. Thus, effective decision methods are needed for smooth macrocell-femtocell transitions. One handover selection technique for macrocells to femtocells and another for femtocells to macrocells is provided. These algorithms consider numerous parameters, including UE velocity and RSS strength. Boosting throughput and spectrum efficiency while lowering packet loss ratio, handover latency, and packet delay can improve quality of service. Several quality of service measures were used to evaluate the handover strategy. LTE-compatible MANETs are another option. MANET topology management and routing techniques were studied in this work. GPSR routing and Boos flock topology management were used to build the network. Simulations are done using MatLab's "MONSTeR" model. The model is built with MatLab LTE system tools. Anyone can use the model on GitHub. This power-saving approach also affects user QoE in throughput and retransmissions. By training, testing, and validating our models using the KDD Cup 2015 dataset, we may improve femtocell networks employing mobile ad hoc network communication. The data show that switching from "always-on" to "on-when-needed" may sustain QoE

Online Optimal Service Selection, Resource Allocation and Task Offloading for Multi-Access Edge Computing: A Utility-Based Approach

Multi-access edge computing promises satisfactory user experience by offloading tasks to the MEC server deployed at the network edge. However, since the MEC server is often resource-limited as compared to the cloud infrastructure, how to efficiently utilize its resources for system performance optimization becomes a challenge. In this paper, we study this problem with the aim at maximizing user's QoE through jointly optimizing service selection, computation resource allocation and task offloading decision, which is less studied in existing literature. We formulate a mixed-integer nonlinear programming problem (MINLP) for the task and propose a utility-based approach together with a low-complexity resource-efficiency based heuristic to address the problem. We consider realistic settings, where centralized solutions may not apply and an optimal mechanism needs to adapt as system operates. A distributed algorithm based on the Lagrangian-dual based decomposition theory is proposed, and we prove all sub-problems derived can be efficiently solved. In line with the current VM technology, we develop a cost-aware online algorithm that explicitly incorporates the cost of service switches into service selection and resource allocation. We evaluate our mechanism through both synthetic and trace-driven simulations, and results indicate they are effective as compared to representative baseline algorithms.

Content Collaborative Caching Strategy in the Edge Maintenance of Communication Network: A Joint Download Delay and Energy Consumption Method

With the development of Big Data technology and Internet, the surge of data in the network will cause network congestion and untimely task processing. Additionally, caching content in the core network may cause redundant access of content and backhaul bottlenecks. Due to the increasing requirements of users for task processing efficiency, the centralized maintenance system based on traditional cloud computing cannot meet the current computing requirements. In view of these problems, we propose a content collaborative caching mechanism based on joint decision of download delay and energy consumption. By integrating network coding and content caching technology, the work content maintained in the communication network is deployed near the edge of the network in the form of coding to reduce the redundant transmission of content and acquisition time of content. This article establishes a user QoE satisfaction model, which consists of two indexes that measure time delay and energy consumption. This article proposes a <inline-formula><tex-math notation="LaTeX">$\varepsilon$</tex-math></inline-formula> -hybrid Q-learning algorithm to optimize the placement of cache files, and made the cache action selection based on the combination of improved heuristic greedy algorithm and simulated annealing algorithm. The experimental results show that the proposed cache strategy can reduce the delay of users downloading content and the energy consumption of content cache, so as to improve the quality of field maintenance work in communication network.

A Path Load-Aware Based Caching Strategy for Information-Centric Networking

Ubiquitous in-network caching plays an important role in improving the efficiency of content access and distribution in Information-Centric Networks (ICN). Content placement strategies, which determine the location distribution of content replicas in the network, have a decisive impact on the performance of the cache system. Existing strategies primarily focus on pushing popular content to the network edge, aiming to improve the overall cache hit ratio while neglecting to effectively balance the traffic load between network links; this leads to insufficient utilization of network bandwidth resources and further excessive content delivery time and user QoE degradation. In this paper, a Path Load-Aware Based Caching strategy (PLABC) is proposed, in which content-related information and dynamic network-related information are comprehensively considered to make cache decisions. Specifically, the utility of caching the content at each on-path node is calculated according to the bandwidth consumption savings and the load level of the transmission path, and the node with the greatest utility value is selected as the caching node. Extensive simulations are conducted to compare the performance of PLABC with other state-of-the-art schemes by quantitative analysis. Simulation results validate the PLABC strategy’s effectiveness, especially in balancing link load and reducing content delivery time.

Muster: Multi-source Streaming for Tile-based 360° Videos within Cloud Native 5G Networks

360&#x00B0; videos generally require a large amount of bandwidth between video servers and users, which puts much burden on the current CDN-based single-source video streaming solutions. The emerging cloud native 5G networks can bridge the distance between video servers and users by leveraging in-network single-source video streaming to enhance 360&#x00B0; video quality. Unfortunately, the restricted bandwidth of in-network servers becomes the main bottleneck. Although tile-based video streaming is promising to reduce video transmission size while keeping user QoE, it highly depends on the accuracy of user FoV prediction, which existing prediction methods cannot guarantee. Recently, some researchers advocate the idea of &#x201C;super FoV&#x201D; (i.e., an extended range of predicted FoV) to cope with the inaccurate FoV prediction, which however could lower the effect of tile-based video streaming. Alternatively, we present Muster, a multi-source streaming for tile-based 360&#x00B0; videos within cloud native 5G networks. We detail the system components, provide a comprehensive model, formulate joint server selection and tile requesting problems, and correspondingly propose efficient online algorithms with a performance guarantee. Small-scale testbed and large-scale simulation based evaluation confirm the superiority of the proposed algorithms.

When Scents Help Me Remember My Password

Current authentication processes overwhelmingly rely on audiovisual data, comprising images, text or audio. However, the use of olfactory data (scents) has remained unexploited in the authentication process, notwithstanding their verified potential to act as cues for information recall. Accordingly, in this paper, a new authentication process is proposed in which olfactory media are used as cues in the login phase. To this end, PassSmell , a proof of concept authentication application, is developed in which words and olfactory media act as passwords and olfactory passwords, respectively. In order to evaluate the potential of PassSmell, two different versions were developed, namely one which was olfactory-enhanced and another which did not employ olfactory media. Forty-two participants were invited to take part in the experiment, evenly split into a control and experimental group. For assessment purposes, we recorded the time taken to logon as well as the number of failed/successful login attempts; we also asked users to complete a Quality of Experience (QoE) questionnaire. In terms of time taken, a significant difference was found between the experimental and the control groups, as determined by an independent sample t-test. Similar results were found with respect to average scores and the number of successful attempts. Regarding user QoE, having olfactory media with words influenced the users positively, emphasizing the potential of using this kind of authentication application in the future.

Optimizing Video QoE for Mobile eMBMS Users in Cellular Networks

Evolved Multimedia Broadcast Multicast Service (eMBMS) is used in cellular networks to improve the utilization of scarce wireless resources in high user density service areas. However, eMBMS configuration involves interwoven decisions including which base stations (eNB) to synchronize to form Single Frequency Networks (SFN), which video qualities to be serviced, and how to distribute resources among different videos. These decisions should accommodate disparate channel conditions for eMBMS users, and the impact of eNB's unicast-load in the service area. In this paper, we formulate eMBMS configuration as an optimization problem that maximizes the video QoE for users. Additionally, we present NIMBLE as an eMBMS configuration heuristic, guided by our optimization framework, to solve the problem in realtime. Furthermore, NIMBLE's design integrates elements to accommodate the dynamic nature of cellular networks resulting from changes in both user, and network state over time. We developed a simulation testbed, and performed extensive experiments to show that, in comparison to state-of-the-art schemes, NIMBLE can increase the average user throughput by 150%, and reduce the bitrate switches by 75%.

Edge Caching Strategy Based on User Preference and Game Theory

Caching video content to the mobile edge server is an effective solution to avoid multiple repeated requests from mobile terminal devices, reduce latency costs, and improve user QoE. In addition, mobile users in nearby areas tend to request the same video resource task, so reasonable deployment of video content to edge servers can effectively reduce the response time of user requests. This fact prompted us to design a caching strategy based on user preferences. The system model considered in this article contains multiple mobile users, multiple servers, and remote central servers. Based on the recommendation system predicting the user’s preference for specific video resources, the recommended value ranking of the video resources in the future time period is obtained, and then based on the game theory method, in each edge cache server, each video resource is calculated for the local area and neighboring areas. The cache value of the area, based on the cache value of the video resource to be cached, minimizes the delay for users to obtain the video resource, and obtains the optimal video resource cache distribution strategy. The simulation experiment results show that compared with other caching strategies, the proposed caching strategy is better than other caching strategies in terms of response time and cache task hit rate.

Trace-Driven Optimization on Bitrate Adaptation for Mobile Video Streaming

Mobile video streaming occupies three-quarters of today's cellular network traffic. The quality of mobile videos becomes increasingly important for video providers to attract more users. For example, they invest in network bandwidth resources and conduct adaptive bitrate techniques to improve video quality. Prior adaptive bitrate (ABR) algorithms perform well under given throughput traces on broadband and WiFi networks. They may perform poorly for mobile video streaming due to the high network dynamics of cellular networks. To study the properties of throughput traces under cellular networks, we collect 4G network throughput traces for over four months in two large cities, Beijing and Suzhou in China. We derive the environment-specific Markov property of throughputs in the dataset. Accordingly, we propose NEIVA, an environment identification based technique to adaptively predict future throughput for different types of environments. We also implement NEIVA and integrate it with the state-of-the-art ABR algorithm, model predictive control (MPC) approach in our testbed for experiments. By emulating mobile video streaming under throughput traces in our dataset, NEIVA achieves 20 - 25 percent improvement on throughput prediction accuracy comparing to baseline predictors. Meanwhile, NEIVA achieves 11 - 20 percent user QoE improvement over MPC with baseline predictors.

Intelligent and Application-Aware Network Traffic Prediction in Smart Access Gateways

Network measurement and management are critical to the future smart network QoS and enhancing user QoE. Accurate prediction of network status can support network measurement and provide extra time for network management. However, it is challenging to achieve high accuracy in real-time due to the complexity of user behavior as well as the diversity of network applications. The future SDN will enable data-driven techniques to provide accurate network traffic prediction from access gateways. To demonstrate the concept, a DL-based encrypted packet classifier is first developed in this work to identify network applications. With the achievement of application awareness, a DL-based network traffic prediction scheme is further proposed and developed to provide accurate network traffic prediction. Datasets of network packets from an open-source as well as traffic flow collected in real life are applied to conduct evaluations and case studies. The evaluation results demonstrate that the proposed network traffic classification and prediction framework can successfully predict network traffic in access networks. The proposed framework will contribute significantly to the transition toward intelligent communication and networking to enhance user QoE.

Representation Learning in Wireless Multimedia Communications

With the advent of 5G wireless communication systems, multimedia data is predicted to grow rapidly in the near future. As a result, the large amount of multimedia data puts huge pressure on wireless communication, which poses a huge challenge to network capacity. Multimedia data (image/ video) intelligent compression is an effective way to increase the network capacity and improve the user's QoE. The success of image/video compression generally depends on data representations. Although specific domain knowledge can be used to help design representations, learning with generic priors can also be used, and the quest for AI is motivating the design of more powerful representation learning algorithms implementing such priors. This article proposes an intelligent computing communication framework to reduce the amount of transferred data. Simultaneously, it reviews the area of representation learning, covering advances in dictionary learning, RoI, and deep learning image/video compression methods. Furthermore, we compare various compression methods as well as point out promising future works.

On Leveraging Machine and Deep Learning for Throughput Prediction in Cellular Networks: Design, Performance, and Challenges

The highly dynamic wireless communication environment poses a challenge for many applications (e.g., adaptive multimedia streaming services). Providing accurate TP can significantly improve performance of these applications. The scheduling algorithms in cellular networks consider various PHY metrics, (e.g., CQI) and throughput history when assigning resources for each user. This article explains how AI can be leveraged for accurate TP in cellular networks using PHY and application layer metrics. We present key architectural components and implementation options, illustrating their advantages and limitations. We also highlight key design choices and investigate their impact on prediction accuracy using real data. We believe this is the first study that examines the impact of integrating network-level data and applying a deep learning technique (on PHY and application data) for TP in cellular systems. Using video streaming as a use case, we illustrate how accurate TP improves the end user's QoE. Furthermore, we identify open questions and research challenges in the area of AI-driven TP. Finally, we report on lessons learned and provide conclusions that we believe will be useful to network practitioners seeking to apply AI.

QoE of cross-modally mapped Mulsemedia: an assessment using eye gaze and heart rate

A great deal of research effort has been put in exploring crossmodal correspondences in the field of cognitive science which refer to the systematic associations frequently made between different sensory modalities (e.g. high pitch is matched with angular shapes). However, the possibilities cross-modality opens in the digital world have been relatively unexplored. Therefore, we consider that studying the plasticity and the effects of crossmodal correspondences in a mulsemedia setup can bring novel insights about improving the human-computer dialogue and experience. Mulsemedia refers to the combination of three or more senses to create immersive experiences. In our experiments, users were shown six video clips associated with certain visual features based on color, brightness, and shape. We examined if the pairing with crossmodal matching sound and the corresponding auto-generated haptic effect, and smell would lead to an enhanced user QoE. For this, we used an eye-tracking device as well as a heart rate monitor wristband to capture users’ eye gaze and heart rate whilst they were experiencing mulsemedia. After each video clip, we asked the users to complete an on-screen questionnaire with a set of questions related to smell, sound and haptic effects targeting their enjoyment and perception of the experiment. Accordingly, the eye gaze and heart rate results showed significant influence of the cross-modally mapped multisensorial effects on the users’ QoE. Our results highlight that when the olfactory content is crossmodally congruent with the visual content, the visual attention of the users seems shifted towards the correspondent visual feature. Crosmodally matched media is also shown to result in an enhanced QoE compared to a video only condition.

A Bandwidth-Aware Video Segments Request Strategy to Optimize User’s QoE in Connected Vehicle Networks

In ITS environment, the driver-assistant services usually demand delivering video content to vehicular users, which is very useful in the intervention of emergency services, and reminds the drivers the traffic jam in ahead road. Nowadays for online video delivery in connected vehicle networks, HTTP adaptive streaming (HAS) is one of the most promising technologies, where a video is encoded into multiple bitrates and then split into small segments. It is crux for ITS service providers how to improve users' QoE through an adaptive video segments request strategy. From the perspective of adaptive matching among segment bitrate, network bandwidth, and buffer occupancy, we propose a bandwidth-aware video segment request strategy to optimize user's QoE (for short Bw-QoE), which consists of two parts, i.e., available bandwidth estimation, and segment's bitrate selection. First, based on the severity of bandwidth fluctuation, Bw-QoE estimates the available bandwidth with different historical weighted average methods. Then constrained by the estimated available bandwidth and buffer occupancy, the adaptive bitrate selection is formulated as an optimization model to maximize user's QoE of a video streaming session. It is fairly attractive for Bw-QoE to prevent buffer overflow, underflow and unuseful download, and to reduce bitrate switching. Compared with the classic strategy (e.g., LIU's strategy), the simulation results show that the proposed strategy Bw-QoE has higher average video bitrate (about 8%-10%), less interruption (about 100%), less segment bitrate switching (about 15%-17%) and higher buffer occupancy (about 13%-51%), which demonstrate that our strategy effectively improves QoE.