Current Issue : January - March Volume : 2018 Issue Number : 1 Articles : 5 Articles
It is well known that cloud computing has many potential advantages over traditional\ndistributed systems. Many enterprises can build their own private cloud with open source\ninfrastructure as a service (IaaS) frameworks. Since enterprise applications and data are migrating to\nprivate cloud, the performance of cloud computing environments is of utmost importance for both\ncloud providers and users. To improve the performance, previous studies on cloud consolidation\nhave been focused on live migration of virtual machines based on resource utilization. However,\nthe approaches are not suitable for multimedia big data applications. In this paper, we reveal the\nperformance bottleneck of multimedia big data applications in cloud computing environments\nand propose a cloud consolidation algorithm that considers application types. We show that our\nconsolidation algorithm outperforms previous approaches....
Due to the variations of viewpoint, pose, and illumination, a given individual may appear considerably different across different\ncamera views. Tracking individuals across camera networks with no overlapping fields is still a challenging problem. Previousworks\nmainly focus on feature representation and metric learning individually which tend to have a suboptimal solution. To address this\nissue, in this work, we propose a novel framework to do the feature representation learning and metric learning jointly. Different\nfrom previous works, we represent the pairs of pedestrian images as new resized input and use linear Support Vector Machine\nto replace softmax activation function for similarity learning. Particularly, dropout and data augmentation techniques are also\nemployed in this model to prevent the network from overfitting. Extensive experiments on two publically available datasets VIPeR\nand CUHK01 demonstrate the effectiveness of our proposed approach....
Mobility, redundancy, and bandwidth requirements are transforming the communication models used for IoT, mainly in case\nof Critical Communications and multimedia streaming (ââ?¬Å?IoMT, Internet of Multimedia Thingsââ?¬Â), as wireless video traffic is\nexpected to be 60ââ?¬â??75% of the global mobile traffic by 2020. One of the characteristics of 5G networks will be the proliferation\nof different/heterogeneous radio networks (virtualized radio access networks, RAN, new energy-efficient radios, femtocells, and\noffloading capabilities) and the possibility for IoT objects to connect and load-balance between dual andmultiple RANs.This paper\nfocuses on the possibility of using LISP (Locator Identifier Separation Protocol) formultihoming and load-balancing purposes and\npresents an illustrative scenario for the case of mobile IoT (e.g., the ââ?¬Å?thingsââ?¬Â part of vehicular or public transportation systems, PTS)\nthat are also intensive bandwidth consumers, like the case of connected multimedia ââ?¬Å?things.ââ?¬Â We have implemented and tested a\ndemonstrator of a mobile LISP IoT gateway that is also integrated with Cloud-based video analytics....
In this paper, aiming to improve the quality of multimedia transmission while\nsatisfying the quality of service (QoS) requirements, we propose an optimal\nsubcarrier allocation by jointly considering the video coding rate and the\navailable power resource. We jointly analyses the effects on the performance\nof multimedia transmission from video coding rate at the application layer as\nwell as the power control at the physical layer. This proposed joint power and\nsubcarrier allocation algorithm in MIMO OFDM systems enables us both to\novercome the challenge of full CSI (channel state information) with RD (the\nrate-distortion) to make minimum of the distortion of each users under delay\nand power constraints. Simulation results show that the proposed optimal\nsubcarrier allocation algorithm improves the multimedia transmission quality\nconsiderably through the comparison with the resource allocation algorithms\nonly use a single layer of information....
Recently, various adaptationmethods have been proposed to copewith throughput fluctuations inHTTP adaptive streaming (HAS).\nHowever, thesemethods have mostly focused on constant bitrate (CBR) videos.Moreover,most of themare qualitative in the sense\nthat performance metrics could only be obtained after a streaming session. In this paper, we propose a new adaptation method for\nstreaming variable bitrate (VBR) videos using stochastic dynamic programming (SDP).With this approach, the system should have\na probabilistic characterization along with the definition of a cost function that is minimized by a control strategy. Our solution\nis based on a new statistical model where the future streaming performance is directly related to the past bandwidth statistics.We\ndevelop mathematical models to predict and develop simulation models to measure the average performance of the adaptation\npolicy. The experimental results show that the prediction models can provide accurate performance prediction which is useful in\nplanning adaptation policy and that our proposed adaptation method outperforms the existing ones in terms of average quality\nand average quality switch....
Loading....