Video quality and traffic QoS in learning-based subsampled and receiver-interpolated video sequences

Cramer, Christopher; Gelenbe, Erol

doi:10.1109/49.824788

Cited by 77 publications

(37 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, as in the previously tested CPN routing scheme [20], we have to widen our probing at random over other paths, so that we do not miss out on paths whose latency has substantially improved over recent history, and we use Reinforcement Learning [27] to adjust the parameters of a Random Neural Network (RNN), acting as an adaptive critic, as first suggested in [28]. The RNN has been used in many other applications, such as image processing [29], [30] and virtual reality [31].…”

Section: Learning With the Random Neural Networkmentioning

confidence: 99%

Big Data for Autonomic Intercontinental Overlays

Brun

Wang

Gelenbe

2016

IEEE J. Select. Areas Commun.

View full text Add to dashboard Cite

Abstract-This paper uses Big Data and Machine Learning for the real-time management of Internet scale Qualityof-Service Route Optimisation with an overlay network. Based on the collection of data sampled each 2 minutes over a large number of source-destinations pairs, we show that intercontinental Internet Protocol (IP) paths are far from optimal with respect to Quality of Service (QoS) metrics such as end-to-end round-trip delay. We therefore develop a machine learning based scheme that exploits large scale data collected from communicating node pairs in a multi-hop overlay network that uses IP between the overlay nodes, and selects paths that provide substantially better QoS than IP. Inspired from Cognitive Packet Network protocol, it uses Random Neural Networks with Reinforcement Learning based on the massive data that is collected, to select intermediate overlay hops. The routing scheme is illustrated on a 20-node intercontinental overlay network that collects some 2 × 10 6 measurements per week, and makes scalable distributed routing decisions. Experimental results show that this approach improves QoS significantly and efficiently.

show abstract

Section: Learning With the Random Neural Networkmentioning

confidence: 99%

Big Data for Autonomic Intercontinental Overlays

Brun

Wang

Gelenbe

2016

IEEE J. Select. Areas Commun.

View full text Add to dashboard Cite

show abstract

“…Their approach was to interpolate video sequences and compensate for frames that may have been lost or deliberately dropped [22].…”

Section: Data Communicationsmentioning

confidence: 99%

Industrial applications of soft computing: a review

Dote

Ovaska²

2001

Proc. IEEE

137

View full text Add to dashboard Cite

show abstract

“…The communication schemes may be opportunistic [25] and attacks may use similar opportunistic means to access IoT devices, viruses and worms will continue being important threats [16] and they can diffuse opportunistically through a network [17], video input is one of the uses of the IoT and video encoding [7] can also be specifically targeted by attacks. Furthermore, many network services are organised to flow over overlay networks [4] that cooperate with the Cloud [43,44] to offer easy deployable and flexible services for the mobile network control plane.…”

Section: Introductionmentioning

confidence: 99%

Signalling Attacks in Mobile Telephony

Pavloski

2018

Communications in Computer and Information Science

View full text Add to dashboard Cite

Abstract. Many emerging Internet of Things devices, gateways and networks, rely either on mobile networks or on Internet Protocols to support their connectivity. However it is known that both types of networks are susceptible to different types of attacks that can significantly disrupt their operations. In particular 3rd and 4th generation mobile networks experience signalling related attacks, such as signalling storms, that have been a common problem in the last decade. This paper presents a generic model of a mobile network that includes different end user behaviours, including possible attacks to the signalling system. We then suggest two attack detection mechanisms, and evaluate them by analysis and simulation based on the generic mobile network model. Our findings suggest that mobile networks can be modified to be able to automatically detect attacks. Our results also suggest that attack mitigation can be carriedout both via the signalling system and on a "per mobile terminal" basis.

show abstract

Video quality and traffic QoS in learning-based subsampled and receiver-interpolated video sequences

Cited by 77 publications

References 42 publications

Big Data for Autonomic Intercontinental Overlays

Big Data for Autonomic Intercontinental Overlays

Industrial applications of soft computing: a review

Signalling Attacks in Mobile Telephony

Contact Info

Product

Resources

About