Change search
Link to record
Permanent link

Direct link
BETA
Alternative names
Publications (10 of 83) Show all publications
Garcia, J. & Brunström, A. (2018). Clustering-based separation of media transfers in DPI-classified cellular video and VoIP traffic. In: 2018 IEEE Wireless Communications and Networking Conference (WCNC): . Paper presented at 2018 IEEE Wireless Communications and Networking Conference (WCNC), 15-18 April 2018, Barcelona, Spain.. IEEE
Open this publication in new window or tab >>Clustering-based separation of media transfers in DPI-classified cellular video and VoIP traffic
2018 (English)In: 2018 IEEE Wireless Communications and Networking Conference (WCNC), IEEE, 2018Conference paper, Published paper (Refereed)
Abstract [en]

Identifying VoIP and video traffic is often useful in the context of managing a cellular network, and to perform such traffic classification deep packet inspection (DPI) approaches are often used. Commercial DPI classifiers do not necessarily differentiate between, for example, YouTube traffic that arises from browsing inside the YouTube app, and traffic arising from the actual viewing of a YouTube video. Here we apply unsupervised clustering methods on such cellular DPI-labeled VoIP and video traffic to identify the characteristic behavior of the two sub-groups of media-transfer and non media-transfer flows. The analysis is based on a measurement campaign performed inside the core network of a commercial cellular operator, collecting data for more than two billion packets in 40+ million flows. A specially instrumented commercial DPI appliance allows the simultaneous collection of per packet information in addition to the DPI classification output. We show that the majority of flows falls into clusters that are easily identifiable as belonging to one of the traffic sub-groups, and that a surprising majority of DPIlabeled VoIP and video traffic is non-media related.

Place, publisher, year, edition, pages
IEEE, 2018
Series
IEEE Wireless Communications and Networking Conference. Proceedings, ISSN 1525-3511, E-ISSN 1558-2612
Keywords
Media, YouTube, Clustering algorithms, Cryptography, Downlink, Engines, Uplink
National Category
Computer Sciences
Research subject
Computer Science
Identifiers
urn:nbn:se:kau:diva-67798 (URN)10.1109/WCNC.2018.8377027 (DOI)000435542400081 ()978-1-5386-1734-2 (ISBN)978-1-5386-1735-9 (ISBN)
Conference
2018 IEEE Wireless Communications and Networking Conference (WCNC), 15-18 April 2018, Barcelona, Spain.
Projects
HITS
Available from: 2018-06-19 Created: 2018-06-19 Last updated: 2019-04-05Bibliographically approved
Garcia, J. & Korhonen, T. (2018). Efficient Distribution-Derived Features for High-Speed Encrypted Flow Classification. In: NetAI'18 Proceedings of the 2018 Workshop on Network Meets AI & ML: . Paper presented at 2018 Workshop on Network Meets AI & ML. August 24 - 24, 2018. Budapest, Hungary. (pp. 21-27). New York: ACM Digital Library
Open this publication in new window or tab >>Efficient Distribution-Derived Features for High-Speed Encrypted Flow Classification
2018 (English)In: NetAI'18 Proceedings of the 2018 Workshop on Network Meets AI & ML, New York: ACM Digital Library, 2018, p. 21-27Conference paper, Published paper (Refereed)
Abstract [en]

Flow classification is an important tool to enable efficient network resource usage, support traffic engineering, and aid QoS mechanisms. As traffic is increasingly becoming encrypted by default, flow classification is turning towards the use of machine learning methods employing features that are also available for encrypted traffic. In this work we evaluate flow features that capture the distributional properties of in-flow per-packet metrics such as packet size and inter-arrival time. The characteristics of such distributions are often captured with general statistical measures such as standard deviation, variance, etc. We instead propose a Kolmogorov-Smirnov discretization (KSD) algorithm to perform histogram bin construction based on the distributional properties observed in the data. This allows for a richer, histogram based, representation which also requires less resources for feature computation than higher order statistical moments. A comprehensive evaluation using synthetic data from Gaussian and Beta mixtures show that the KSD approach provides Jensen-Shannon distance results surpassing those of uniform binning and probabilistic binning. An empirical evaluation using live traffic traces from a cellular network further shows that when coupled with a random forest classifier the KSD-constructed features improve classification performance compared to general statistical features based on higher order moments, or alternative bin placement approaches.

Place, publisher, year, edition, pages
New York: ACM Digital Library, 2018
Keywords
Traffic classification, Discretization, Machine learning
National Category
Computer Sciences
Research subject
Computer Science
Identifiers
urn:nbn:se:kau:diva-68707 (URN)10.1145/3229543.3229548 (DOI)978-1-4503-5911-5 (ISBN)
Conference
2018 Workshop on Network Meets AI & ML. August 24 - 24, 2018. Budapest, Hungary.
Projects
HITS
Available from: 2018-08-14 Created: 2018-08-14 Last updated: 2019-01-14Bibliographically approved
Garcia, J. & Korhonen, T. (2018). On Runtime and Classification Performance of the Discretize-Optimize (DISCO) Classification Approach. Performance Evaulaton Review, 46(3), 167-170
Open this publication in new window or tab >>On Runtime and Classification Performance of the Discretize-Optimize (DISCO) Classification Approach
2018 (English)In: Performance Evaulaton Review, Vol. 46, no 3, p. 167-170Article in journal (Refereed) Published
Abstract [en]

Using machine learning in high-speed networks for tasks such as flow classification typically requires either very resource efficient classification approaches, large amounts of computational resources, or specialized hardware. Here we provide a sketch of the discretize-optimize (DISCO) approach which can construct an extremely efficient classifier for low dimensional problems by combining feature selection, efficient discretization, novel bin placement, and lookup. As feature selection and discretization parameters are crucial, appropriate combinatorial optimization is an important aspect of the approach. A performance evaluation is performed for a YouTube classification task using a cellular traffic data set. The initial evaluation results show that the DISCO approach can move the Pareto boundary in the classification performance versus runtime trade-off by up to an order of magnitude compared to runtime optimized random forest and decision tree classifiers.

Place, publisher, year, edition, pages
New york, USA: , 2018
National Category
Computer Sciences
Research subject
Computer Science
Identifiers
urn:nbn:se:kau:diva-71213 (URN)10.1145/3308897.3308965 (DOI)
Projects
HITS, 4707
Funder
Knowledge Foundation
Available from: 2019-02-20 Created: 2019-02-20 Last updated: 2019-03-14Bibliographically approved
Afzal, Z., Garcia, J., Lindskog, S. & Brunström, A. (2018). Slice Distance: An Insert-Only Levenshtein Distance with a Focus on Security Applications. In: Proceedings of NTMS 2018 Conference and Workshop: . Paper presented at 9th IFIP International Conference on New Technologies, Mobility and Security, 26-28 February 2018, Paris, France (pp. 1-5). New York: IEEE
Open this publication in new window or tab >>Slice Distance: An Insert-Only Levenshtein Distance with a Focus on Security Applications
2018 (English)In: Proceedings of NTMS 2018 Conference and Workshop, New York: IEEE, 2018, p. 1-5Conference paper, Published paper (Refereed)
Abstract [en]

Levenshtein distance is well known for its use in comparing two strings for similarity. However, the set of considered edit operations used when comparing can be reduced in a number of situations. In such cases, the application of the generic Levenshtein distance can result in degraded detection and computational performance. Other metrics in the literature enable limiting the considered edit operations to a smaller subset. However, the possibility where a difference can only result from deleted bytes is not yet explored. To this end, we propose an insert-only variation of the Levenshtein distance to enable comparison of two strings for the case in which differences occur only because of missing bytes. The proposed distance metric is named slice distance and is formally presented and its computational complexity is discussed. We also provide a discussion of the potential security applications of the slice distance.

Place, publisher, year, edition, pages
New York: IEEE, 2018
Keywords
Measurement, Pattern matching, Time complexity, Transforms, Security, DNA
National Category
Computer Sciences
Research subject
Computer Science
Identifiers
urn:nbn:se:kau:diva-67012 (URN)10.1109/NTMS.2018.8328718 (DOI)000448864200049 ()978-1-5386-3662-6 (ISBN)978-1-5386-3663-3 (ISBN)
Conference
9th IFIP International Conference on New Technologies, Mobility and Security, 26-28 February 2018, Paris, France
Funder
Knowledge Foundation, 4707
Available from: 2018-04-17 Created: 2018-04-17 Last updated: 2018-11-23Bibliographically approved
Garcia, J., Korhonen, T., Andersson, R. & Västlund, F. (2018). Towards Video Flow Classification at a Million Encrypted Flows Per Second. In: Leonard Barolli, Makoto Takizawa, Tomoya Enokido, Marek R. Ogiela, Lidia Ogiela & Nadeem Javaid (Ed.), Proceedings of 32nd International Conference on Advanced Information Networking and Applications (AINA): . Paper presented at 32nd International Conference on Advanced Information Networking and Applications (AINA). Krakow, Poland, 16-18 May 2018.. Krakow: IEEE
Open this publication in new window or tab >>Towards Video Flow Classification at a Million Encrypted Flows Per Second
2018 (English)In: Proceedings of 32nd International Conference on Advanced Information Networking and Applications (AINA) / [ed] Leonard Barolli, Makoto Takizawa, Tomoya Enokido, Marek R. Ogiela, Lidia Ogiela & Nadeem Javaid, Krakow: IEEE, 2018Conference paper, Published paper (Refereed)
Abstract [en]

As end-to-end encryption on the Internet is becoming more prevalent, techniques such as deep packet inspection (DPI) can no longer be expected to be able to classify traffic. In many cellular networks a large fraction of all traffic is video traffic, and being able to divide flows in the network into video and non-video can provide considerable traffic engineering benefits. In this study we examine machine learning based flow classification using features that are available also for encrypted flows. Using a data set of several several billion packets from a live cellular network we examine the obtainable classification performance for two different ensemble-based classifiers. Further, we contrast the classification performance of a statistical-based feature set with a less computationally demanding alternate feature set. To also examine the runtime aspects of the problem, we export the trained models and use a tailor-made C implementation to evaluate the runtime performance. The results quantify the trade-off between classification and runtime performance, and show that up to 1 million classifications per second can be achieved for a single core. Considering that only the subset of flows reaching some minimum flow length will need to be classified, the results are promising with regards to deployment also in scenarios with very high flow arrival rates.

Place, publisher, year, edition, pages
Krakow: IEEE, 2018
Series
Advanced Information Networking and Applications, ISSN 1550-445X, E-ISSN 2332-5658
Keywords
Cryptography, Runtime, Cellular networks, Machine learning, Forestry, Data models, Support vector machines
National Category
Computer Sciences
Research subject
Computer Science
Identifiers
urn:nbn:se:kau:diva-68705 (URN)10.1109/AINA.2018.00061 (DOI)000454817500048 ()978-1-5386-2196-7 (ISBN)978-1-5386-2195-0 (ISBN)
Conference
32nd International Conference on Advanced Information Networking and Applications (AINA). Krakow, Poland, 16-18 May 2018.
Projects
HITS
Available from: 2018-08-14 Created: 2018-08-14 Last updated: 2019-02-14Bibliographically approved
Jalili, L., Parichehreh, A., Alfredsson, S., Garcia, J. & Brunström, A. (2017). Efficient traffic offloading for seamless connectivity in 5G networks onboard high speed trains. In: IEEE International Symposium on Personal, Indoor and Mobile Radio Communications, PIMRC: . Paper presented at 28th Annual IEEE International Symposium on Personal, Indoor and Mobile Radio Communications, PIMRC 2017, 8-13 October 2017, Montreal, Canada (pp. 1-6). IEEE
Open this publication in new window or tab >>Efficient traffic offloading for seamless connectivity in 5G networks onboard high speed trains
Show others...
2017 (English)In: IEEE International Symposium on Personal, Indoor and Mobile Radio Communications, PIMRC, IEEE, 2017, p. 1-6Conference paper, Published paper (Refereed)
Abstract [en]

Seamless wireless connectivity in high mobility scenarios (≥ 300 km/h), is one of the fundamental key requirements for the future 5G networks. High speed train (HST) is one of the preferred mid-range transportation systems, and highlights the challenges of providing wireless connectivity in high mobility scenarios for the 5G networks. Advanced version of Long Term Evolution (LTE-A) from the Third Generation Partnership Project (3GPP) with peak data rate up to 100 Mbps in high mobility scenarios paved the road toward high quality and cost effective onboard Internet in HSTs. However, frequent handovers (HO) of large number of onboard users increase the service interruptions that in turn inevitably decrease the experienced quality of service (QoS). In this paper, according to the two-tier architecture of the HST wireless connectivity, we propose a novel and practically viable onboard traffic offloading mechanism among the HST carriages that effectively mitigates the service interruptions caused by frequent HOs of massive number of onboard users. The proposed architecture does not imply any change on the LTE network standardization. Conclusions are supported by numerical results for realistic LTE parameters and current HST settings.

Place, publisher, year, edition, pages
IEEE, 2017
Keywords
5G networks, High speed trains, QoS provisioning, Traffic offloading, Cost effectiveness, Long Term Evolution (LTE), Mobile telecommunication systems, Network architecture, Quality of service, Queueing networks, Radio communication, Railroad cars, Railroad transportation, Railroads, Wireless telecommunication systems, High speed train (HST), Proposed architectures, Seamless connectivity, Third generation partnership project (3GPP), Two-tier architecture, Wireless connectivities, 5G mobile communication systems
National Category
Telecommunications Computer Sciences Software Engineering
Identifiers
urn:nbn:se:kau:diva-67276 (URN)10.1109/PIMRC.2017.8292462 (DOI)2-s2.0-85045264762 (Scopus ID)9781538635315 (ISBN)
Conference
28th Annual IEEE International Symposium on Personal, Indoor and Mobile Radio Communications, PIMRC 2017, 8-13 October 2017, Montreal, Canada
Available from: 2018-05-04 Created: 2018-05-04 Last updated: 2018-09-14Bibliographically approved
Beckman, C., Garcia, J., Alfredsson, S. & Brunström, A. (2017). On the Impact of Velocity on the Train-to-Earth MIMO Propagation Channel: Statistical Observations and Qualitative Analysis. In: 2017 IEEE International Symposium on Antennas and Propagation & USNC/URSI National Radio Science Meeting: . Paper presented at 2017 IEEE AP-S Symposium on Antennas and Propagation and USNC-URSI Radio Science Meeting, July 9–14, 2017. San Diego, California, USA (pp. 1865-1866). IEEE
Open this publication in new window or tab >>On the Impact of Velocity on the Train-to-Earth MIMO Propagation Channel: Statistical Observations and Qualitative Analysis
2017 (English)In: 2017 IEEE International Symposium on Antennas and Propagation & USNC/URSI National Radio Science Meeting, IEEE, 2017, p. 1865-1866Conference paper, Published paper (Refereed)
Abstract [en]

We provide measured data collected from 97 trains completing over 7000 journeys in Sweden showing that the throughput over LTE is impacted by train velocity. In order to explain these observations we assume that the underlying causes can be found in the implementation of the MIMO system into LTE Rel. 8 and the diffuse scattering of signals from ground reflections.

Place, publisher, year, edition, pages
IEEE, 2017
Series
EEE Antennas and Propagation Society International Symposium
Keywords
Train-to-Earth propagation channel, statistical data, velocity, MIMO, scattering.
National Category
Computer Sciences Telecommunications
Research subject
Computer Science
Identifiers
urn:nbn:se:kau:diva-65250 (URN)10.1109/APUSNCURSINRSM.2017.8072975 (DOI)000424765301472 ()978-1-5386-3284-0 (ISBN)
Conference
2017 IEEE AP-S Symposium on Antennas and Propagation and USNC-URSI Radio Science Meeting, July 9–14, 2017. San Diego, California, USA
Projects
HITS
Available from: 2017-11-22 Created: 2017-11-22 Last updated: 2018-08-14Bibliographically approved
Garcia, J., Alfredsson, S., Brunström, A. & Beckman, C. (2017). Train Velocity and Data Throughput: A Large Scale LTE Cellular Measurements Study. In: Proceedings of the 2017 IEEE 86th Vehicular Technology Conference (VTC Fall): . Paper presented at 86th IEEE Vehicular Technology Conference (VTC-Fall), Toronto, Canada, 24–27 September 2017 (pp. 1-6). New York: IEEE
Open this publication in new window or tab >>Train Velocity and Data Throughput: A Large Scale LTE Cellular Measurements Study
2017 (English)In: Proceedings of the 2017 IEEE 86th Vehicular Technology Conference (VTC Fall), New York: IEEE, 2017, p. 1-6Conference paper, Published paper (Refereed)
Abstract [en]

Train-mounted aggregation routers that provide WiFi access to train passengers and bundle external communication over multiple cellular modems/links is an efficient way of providing communication services on trains. However, the characteristics of such systems have received limited attention in the literature. In this paper we address this gap by examining the communication characteristics of such systems based on a large data set gathered over six months from an operational Swedish railway system. We focus our examination on the relationship between per link throughput and train velocity. Using Levenberg- Marquardt non-linear regression a noticeable critical point is observed for an RS-SINR of around 12 dB. At this point the impact of increased train velocity on per link throughput changes from being negative to becoming positive. Using a machine learning approach we also explore the relative importance of several observed metrics in relation to per link throughput.

Place, publisher, year, edition, pages
New York: IEEE, 2017
Series
IEEE Vehicular Technology Conference VTC
Keywords
Cellular networks, LTE, 4G, Trains
National Category
Computer Sciences Telecommunications
Research subject
Computer Science
Identifiers
urn:nbn:se:kau:diva-65251 (URN)10.1109/VTCFall.2017.8288294 (DOI)000428141602054 ()978-1-5090-5935-5 (ISBN)
Conference
86th IEEE Vehicular Technology Conference (VTC-Fall), Toronto, Canada, 24–27 September 2017
Projects
HITS
Available from: 2017-11-22 Created: 2017-11-22 Last updated: 2018-08-16Bibliographically approved
Garcia, J. & Hurtig, P. (2016). Deterministic network emulation using KauNetEm. In: : . Paper presented at Netdev 1.1 Technical Conference on Linux Networking, February 10-12, Seville, Spain.
Open this publication in new window or tab >>Deterministic network emulation using KauNetEm
2016 (English)Conference paper, Published paper (Other academic)
Abstract [en]

This paper presents KauNetEm, an extension to the Linux-based NetEm emulator that provides deterministic network emulation. KauNetEm enables precise and repeatable placement of NetEm emulation effects, a functionality that canconsiderably simplify several aspects of protocol evaluation. KauNetEm can be instructed to drop specific packets, apply a configurable delay or other emulation effects at predefinedpoints in time. The motivation for deterministic emulation, the overall design of KauNetEm, and usage examples are provided

National Category
Communication Systems
Research subject
Computer Science
Identifiers
urn:nbn:se:kau:diva-47771 (URN)
Conference
Netdev 1.1 Technical Conference on Linux Networking, February 10-12, Seville, Spain
Projects
HITS
Available from: 2017-01-27 Created: 2017-01-27 Last updated: 2018-08-14Bibliographically approved
Garcia, J., Alfredsson, S. & Brunstrom, A. (2015). Delay metrics and delay characteristics: A study of four Swedish HSDPA+ and LTE networks. In: 2015 European Conference on Networks and Communications (EuCNC): . Paper presented at 2015 European Conference on Networks and Communications (EuCNC), June 29 2015-July 2 2015, Paris, France (pp. 234-238). IEEE conference proceedings
Open this publication in new window or tab >>Delay metrics and delay characteristics: A study of four Swedish HSDPA+ and LTE networks
2015 (English)In: 2015 European Conference on Networks and Communications (EuCNC), IEEE conference proceedings, 2015, p. 234-238Conference paper, Published paper (Refereed)
Abstract [en]

Network delays and user perceived latencies are of major importance in many applications in cellular networks. Delays can be measured with multiple approaches and at different protocol layers. This work involves a detailed examination of several delay metrics from a network, transport, and application perspective. The study explores base delay as well as latency under load, capturing also the effect of buffering. The examination is based on a comprehensive active measurement campaign performed in the networks of four Swedish operators. The results show that the delay captured by different metrics can vary significantly, with delay captured from the TCP three-way-handshake and adaptive ping measurements giving the most consistent results for base network delay in our measurements. As expected, when background traffic is introduced measured delay increases by an order of magnitude due to buffering in the network, highlighting the importance of also capturing latency under load when describing network performance. Finally, using an analytic model of flow completion time, we show that well-selected network measurements can provide a good prediction of higher layer delay performance.

Place, publisher, year, edition, pages
IEEE conference proceedings, 2015
Keywords
Cellular networks, Delay metrics, HSDPA, LTE, 4G, Performance measurements, Completion time
National Category
Communication Systems Telecommunications Computer Sciences
Research subject
Computer Science
Identifiers
urn:nbn:se:kau:diva-37756 (URN)10.1109/EuCNC.2015.7194075 (DOI)000380399400047 ()978-1-4673-7359-3 (ISBN)
Conference
2015 European Conference on Networks and Communications (EuCNC), June 29 2015-July 2 2015, Paris, France
Projects
HITS
Funder
Knowledge Foundation, 20140037.SE (The Internet Infrastructure Foundation), IFv2014-0135
Available from: 2015-08-26 Created: 2015-08-24 Last updated: 2018-08-14Bibliographically approved
Organisations
Identifiers
ORCID iD: ORCID iD iconorcid.org/0000-0003-3461-7079

Search in DiVA

Show all publications