On the Identification and Prediction of Stalling Events to Improve QoE in Video Streaming

Monitoring the Quality of user Experience is a challenge for video streaming services. Models for Quality of User Experience (QoE) evaluation such as the ITU-T Rec. P.1203 are very promising. Among the input data that they require are the occurrence and duration of stalling events. A stalling even5 is an interruption in the playback of multimedia content, and its negative impact on QoE is immense. Given the idiosyncrasy of this type of event, to count it and its duration is a complex task to be automated, i.e., without the participation of the user who visualizes the events or without direct access to the final device. In this work, we propose two methods to overcome these limitations in video streaming using the DASH framework. The first method is intended to detect stalling events. For simplicity, it is based on the behavior of the transport layer data and is able to classify an IP packet as belonging (or not) to a stalling event. The second method aims to predict if the next IP packet of a multimedia stream will belong to a stalling event (or not), using a recurrent neural network with a variant of the Long Short–Term Memory (LSTM). Our results show that the detection model is able to spot the occurrence of a stalling event before being experienced by the user, and the prediction model is able to forecast if the next packet will belong to a stalling event with an error rate of 10.83%, achieving an F1 score of 0.923.

DAF: An adaptive computing framework for multimedia data streams analysis

We consider the problem of efficiently online computing/filtering or analysis multimedia streams. In this scenario, we register a large scale of continuous analysis queries to filter pornographic stream items. Each query is a conjunction of filters. For instance, the query “does this image contain a people basking in the beach?” can be resolved by applying the conjunction of water, people, sand, sea filters successively on the stream item. However, the online evaluation of multimedia filters is indeed very expensive, fortunately there usually exist multiple filters shared among a lot of queries. In other words, each filter may occur in multiple queries. An open problem in such a filtering scenario is how to order the filters in an optimal sequence to achieve significant performance. Existing methods are based on a greedy strategy which orders the filters according to three factors (selectivity, popularity, cost). Although all these methods achieve good results, there are still some problems that haven’t addressed yet. First, the selectivity factor is set empirically, which can not adaptively adjust with multimedia stream. Second, the proportion relationships among the three factors (selectivity, cost, popularity) were not considerably explored. Under these observations,in this paper, we propose a Dynamic-Analytic hierarchy process Framework (DAF) which use a time-based compositional forecasting method, which is based on the idea of exponential smoothing, to deal with the factors’ proportion relationships dynamics. Experiments on both synthetic and real lift multimedia streams demonstrate that our proposed framework (DAF) provides much great adaptability in modeling the factors proportion relationships changing over multimedia stream environment.

Assessing Jitter when Processing Traffic in the G/G/1 System

Analysis of the parameters of the functioning of IP-networks in the processing of multimedia streams is a very important task. There are many approaches to assessing the quality of service parameters in the G/G/1 system. Changing the delay of packets on the network is a very important parameter that deter-mines the quality of traffic processing. The change in delay is usually defined either as packet jitter or as a variation in packet delay. At the same time, the required accuracy in determining the parameters can be obtained quite accurately, since all decisions are mainly based on certain assumptions. The paper presents an approach to determining the change in packet delay in the G/G/1 system as packet jitter. The basis of the presented approach is the approximation of arbitrary distributions by hyperexponential distributions, i.e. modeling of the G/G/1 system by the H2/H2/1 system. The solution to the jitter estima-tion problem is to determine the distribution parameters. To evaluate the parameters of hyperexponen-tial distributions, the EM algorithm is used. As the traffic studied, a multimedia stream registered on a real network was used. An analytical estimate of jitter in the G/G/1 system is obtained. The results ob-tained are applicable for independent flows and for random variables uncorrelated in the structure of each sequence.

A Novel Stream Cipher for Multimedia Security

In the last decades the tremendous usage of multimedia data like audio, video and images through communication channels create a need on the security over networks. Since multimedia content utilize large amount of storage for storing images, audio and video, classical cryptographic algorithms such as DES, AES are not efficient in encrypting multimedia data. In future these data are represented as media stream, like real time audio and video. Therefore it is urgent need to protect the multimedia data from attackers in between communication channels. In this paper we propose a new algorithm that encrypt and decrypt compressed multimedia stream of image or audio or video. The compression results in less time in encrypting data because more compression results in less data volume. Our work ensures that multimedia data streams can be secured according to the requirements of the current scenario.

Novel Queueing Model for Multimedia Over Downlink in 3.5G Wireless Network

In this paper, a model for multimedia transmission over downlink shared channel in 3.5G wireless network is presented. The multimedia stream consists of multiplesubstreams that are aggregated into one real-time and onenonreal-time flows. Correlation with each flow and between flows is assumed. Additionally, we propose a combined time-space priority buffer management scheme to optimise quality of service requirements for each flow. The problem is formulated in terms of a queue with two priority classes, one of which has time priority while the another has space priority. The input is described by the Batch Marked Markovian Arrival Process (BMMAP). Service time distributions are of PH (phase) type dependent on the class of a customer. The buffer is finite, but the customers of a class having higher priority for taking into the service from a buffer (time priority) can occupy only a part of this buffer. Queueing system's behavior is described in terms ofmulti-dimensional continuous time skip-free to the left Markov chain. It allows to exploit an effective algorithm for calculation of the stationary distribution of the queueing system. Loss probability for customers of both classes is calculated. Waiting time distribution for priority customers is calculated.

Multimedia Big Data Frame Combination Storage Strategy Based on Virtual Space Distortion

<p>Aiming at the transmission reliability and storage management of multimedia data, the multimedia big data frame combination storage strategy is proposed based on the virtual space distortion analysis model. On the one hand, the virtual space distortion analysis model is established. This model can be used to find the high similarity of video frames and flow structures in different multimedia streams. The model can be used to uniform the multimedia stream state and effectively improve the efficiency of data mining. The model can effectively analyze the difference between the multimedia stream of virtual space and the storage of the server group. On the other hand, based on the distorted efforts of the virtual space and heterogeneous of the multimedia data stream, combined with big data multimedia service requirements, the big data frame combination of storage space and virtual space integration would be integrated as a whole through the multimedia data frame combination and distorted perception. Finally, the combination of multimedia data frames is proposed. The delay, channel, storage and big data processing level of the virtual space storage scheme and were analyzed and evaluated by the simulation experiment, compared with the physical storage scheme of the multimedia big data. The experimental results show that the proposed scheme has significant advantages in the above aspects.</p>

MoveSteg: A Method of Network Steganography Detection

This article presents a new method for detecting a source point of time based network steganography - MoveSteg. A steganography carrier could be an example of multimedia stream made with packets. These packets are then delayed intentionally to send hidden information using time based steganography methods. The presented analysis describes a method that allows finding the source of steganography stream in network that is under our management.