Time-sensitive-aware scheduling traffic system is capable to eliminate the queuing delay in the network that resulting hard real-time guarantees. Hence, this article aims to develop a time-sensitive-aware scheduling t...
详细信息
Software defined networking (SDN) with OpenFlow-enabled switches operate alongside traditional switches has become a matter of fact in ISP network paradigms which are known as a hybrid SDN (H-SDN) network. When the ce...
详细信息
Increasingly growing various multimedia services (e.g., interactive live video and so on) have brought tremendous pressure on existing static defense techniques. To cope with inherent drawback of static defense techni...
详细信息
ISBN:
(数字)9781728131290
ISBN:
(纸本)9781728131306
Increasingly growing various multimedia services (e.g., interactive live video and so on) have brought tremendous pressure on existing static defense techniques. To cope with inherent drawback of static defense techniques, Network Moving Target Defense (NMTD) such as route mutation (RM) was proposed. What's more, applying reinforcement learning (RL) into RM has been proved feasible in our previous work. But two main problems still need to be considered in this combination of RL with RM: 1) It lacks the consideration of multiple flows situation. 2) With the state-action space grow larger, current solution can't handle efficiently. In this paper, we propose a deep Q-learning method for RM (DQ-RM) to solve above two problems. Firstly, benefited from the satisfiability module theory, we formalize RM space considering single flow and multiple flows concurrently. Then we further propose a deep reinforcement learning-based RM scheme based on our previous work, which is suitable for large-scale state-action space. Finally, extensive experimental results highlight the improvement of DQ-RM in defense performance and convergence speed compared to the representative solution.
The following topics are dealt with: learning (artificial intelligence); video signal processing; image classification; convolutional neural nets; image segmentation; feature extraction; neural nets; video retrieval; ...
The following topics are dealt with: learning (artificial intelligence); video signal processing; image classification; convolutional neural nets; image segmentation; feature extraction; neural nets; video retrieval; multimediacomputing; social networking (online).
In recent years, virtual reality technologies have been improving in terms of resolution, convenience and portability, fostering their adoption in real life applications. The Vive Controllers and Leap Motion are two o...
详细信息
This article presents a design of the system for acoustic event detection. The proposed pilot application is focused on child's emotion/behaviour related sounds such as cry and laugh detection. Monitoring behaviou...
详细信息
ISBN:
(纸本)9781728118642
This article presents a design of the system for acoustic event detection. The proposed pilot application is focused on child's emotion/behaviour related sounds such as cry and laugh detection. Monitoring behaviour and safety of small children is particularly crucial in in-car environment and in households. The proposed application is based on Gaussian Mixture Model - Universal Background Model approach. The system is optimized by balancing false acceptance and false rejection rate. The classification accuracy of 71.6% was achieved although the system was trained only on small amount of data. The proposed approach has low computing and memory requirements thus is also suitable for implementation in embedded systems.
From the future social trends, economic trends and technological trends, it can be clearly found that the advent of the Internet of Things and the development of communication technologies have jointly subverted the d...
详细信息
The rapid growth of technology has lead to an exponential increase in the number of high-end smart phone users. This accounts for an explosion in mobile data traffic, especially, video traffic. To deal with this, devi...
详细信息
ISBN:
(纸本)9781538636527
The rapid growth of technology has lead to an exponential increase in the number of high-end smart phone users. This accounts for an explosion in mobile data traffic, especially, video traffic. To deal with this, device to device (D2D) communication is an effective approach to ensure an improved quality of service (QoS). In this context, this paper proposes a framework for adaptive multimedia streaming between heterogeneous users using D2D (Wi-Fi Direct) and dynamic Wi-Fi configuration. Experimental study has been conducted to analyze the QoS performance of adaptive multimedia streaming between heterogeneous users over Wi-Fi Direct and dynamic Wi-Fi configuration. Dynamic network configuration and quality selection algorithms have been proposed based on experimental data. Experimental study shows the impact of different quality levels onto end-to-end delay and packet re-transmission rate. The results validate the efficacy of the proposed scheme in terms of a considerable decrease in end-to-end transmission delay and packet re-transmission rate.
Evolution of multicast routing protocols for MANET are becoming the center of attraction for scholars of these days. This is due to varying applications areas, which in turn requires appropriate routing schemes for th...
详细信息
The integration of Cloud computing and Internet of Things (IoT) is foreseen as an enabler to suit a plethora of novel latency critical applications (e.g, e-health, intelligent transportation, safety, energy, smart cit...
详细信息
ISBN:
(纸本)9781538636527
The integration of Cloud computing and Internet of Things (IoT) is foreseen as an enabler to suit a plethora of novel latency critical applications (e.g, e-health, intelligent transportation, safety, energy, smart cities, and many others). These applications require multimedia (mainly video) flows to be handled by the underlying network in an efficient and scalable way, as they expect to consume a massive data produced by billions of things. In view of this, we propose a dynamic multiuser session control plane which leverages 5G's support of Software-Defined networking (SDN) substrate to advance beyond todays limited, per-flow IP-based communication systems. We handle such limitations by proposing CLASSICO, a Cross-LAyer Sdn SessIon COntrol architecture that exploits SDN to offload the flow streaming computation operations from the IoT cloud platform to the network edge, affording high timeliness and scalability for the IoT-cloudified system. CLASSICO dynamically builds Application Layer multiuser data sessions and maps them into enhanced group-enabled data paths featuring SDN replication at branching nodes. We applied our solution to multimedia-alike use case, and results show that CLASSICO outperforms typical SDN-enabled IoT systems in terms to Quality of Service (QoS) and Quality of Experience (QoE) video metrics.
暂无评论