A database for publications published by researchers and students at SimulaMet.
Research area
Proceedings, refereed
A comparison of deep learning with global features for gastrointestinal disease detection
In MediaEval Benchmark 2017. Dublin, Ireland: CEUR-WS.org, 2017.Status: Published
A comparison of deep learning with global features for gastrointestinal disease detection
| Afilliation | Communication Systems |
| Project(s) | Efficient EONS: Execution of Large Workloads on Elastic Heterogeneous Resources |
| Publication Type | Proceedings, refereed |
| Year of Publication | 2017 |
| Conference Name | MediaEval Benchmark 2017 |
| Date Published | 09/2017 |
| Publisher | CEUR-WS.org |
| Place Published | Dublin, Ireland |
A Framework for Less than Best Effort Congestion Control with Soft Deadlines
In 2017 IFIP Networking Conference (IFIP Networking) and Workshops. IEEE, 2017.Status: Published
A Framework for Less than Best Effort Congestion Control with Soft Deadlines
Applications like inter data-centre synchronisation or client-to-cloud backups require a reliable end-to-end data transfer, however, they typically do not have strong capacity or latency constraints, just a loose delivery deadline. Besides, their potential to disrupt more quality-constrained flows should be kept to a minimum. These applications could be well served by a transport protocol providing a less-than-best-effort (LBE) or scavenger service rather than TCP but, neither TCP nor standard LBE methods like LEDBAT consider any notion of deadline or completion time. TCP simply tries to maximise the use of available capacity, while LEDBAT tries to enforce an LBE behaviour regardless of any timeliness requirements.
This paper introduces a framework for adding both LBE behaviour and awareness of “soft” delivery deadlines to any congestion control (CC) algorithm, whether loss-based, delay-based or explicit signaling-based. This effectively allows it to turn an arbitrary CC protocol into a scavenger protocol that dynamically adapts its sending rate to network conditions and remaining time before the deadline, to balance timeliness and transmission aggressiveness. Network utility maximization (NUM) theory provides a solid foundation for the proposal. The effectiveness of the approach is validated by numerical and simulation experiments, with TCP Cubic and Vegas used as examples.
| Afilliation | Communication Systems |
| Project(s) | NEAT: A New, Evolutive API and Transport-Layer Architecture for the Internet |
| Publication Type | Proceedings, refereed |
| Year of Publication | 2017 |
| Conference Name | 2017 IFIP Networking Conference (IFIP Networking) and Workshops |
| Publisher | IEEE |
| ISBN Number | 978-3-901882-94-4 |
| URL | http://dl.ifip.org/db/conf/networking/networking2017/1570334752.pdf |
| DOI | 10.23919/IFIPNetworking.2017.8264853 |
A Holistic Multimedia System for Gastrointestinal Tract Disease Detection
In 8th annual ACM conference on Multimedia Systems (MMSys). ACM, 2017.Status: Published
A Holistic Multimedia System for Gastrointestinal Tract Disease Detection
Analysis of medical videos for detection of abnormalities and diseases requires both high precision and recall, but also real-time processing for live feedback and scalability for massive screening of entire populations. Existing work on this field does not provide the necessary combination of retrieval accuracy and performance.
In this paper, a multimedia system is presented where the aim is to tackle automatic analysis of videos from the human gastrointestinal (GI) tract. The system includes the whole pipeline from data collection, processing and analysis, to visualization. The system combines filters using machine learning, image recognition and extraction of global and local image features. Furthermore, it is built in a modular way so that it can easily be extended. At the same time, it is developed for efficient processing in order to provide real-time feedback to the doctors. Our experimental evaluation proves that our system has detection and localisation accuracy at least as good as existing systems for polyp detection, it is capable of detecting a wider range of diseases, it can analyze video in real-time, and it has a low resource consumption for scalability.
| Afilliation | Communication Systems |
| Project(s) | Efficient EONS: Execution of Large Workloads on Elastic Heterogeneous Resources, Unified PCIe IO: Unified PCI Express for Distributed Component Virtualization |
| Publication Type | Proceedings, refereed |
| Year of Publication | 2017 |
| Conference Name | 8th annual ACM conference on Multimedia Systems (MMSys) |
| Pagination | 112-123 |
| Date Published | 06/2017 |
| Publisher | ACM |
| ISBN Number | 978-1-4503-5002-0 |
| URL | http://dl.acm.org/citation.cfm?id=3083189 |
| DOI | 10.1145/3083187.3083189 |
A NEAT Way to Browse the Web
In Proceedings of the Applied Networking Research Workshop (ANRW). Praha/Czech Republic: IEEE, 2017.Status: Published
A NEAT Way to Browse the Web
There is a growing concern that the Internet transport layer has become ossified in the face of emerging novel applications, and that further evolution has become very difficult. The NEAT system is a novel and evolvable transport system that decouples applications from the underlying transport layer and network services. In so doing, it facilitates dynamic transport selection. This demo shows how the NEAT system is able to dynamically select the most appropriate transport solution for the Mozilla Firefox web browser.
| Afilliation | Communication Systems |
| Project(s) | NEAT: A New, Evolutive API and Transport-Layer Architecture for the Internet, NorNet |
| Publication Type | Proceedings, refereed |
| Year of Publication | 2017 |
| Conference Name | Proceedings of the Applied Networking Research Workshop (ANRW) |
| Date Published | 07/15/2017 |
| Publisher | IEEE |
| Place Published | Praha/Czech Republic |
| Keywords | NEAT, ossification, SCTP, tcp, Transport Selection, Transport Service |
| Notes | Demo Presentation |
| URL | https://irtf.org/anrw/2017/anrw17-final13.pdf |
Adding the Next Nine: An Investigation of Mobile Broadband Networks Availability
In Proceedings of the 23rd Annual International Conference on Mobile Computing and Networking. New York, NY, USA: ACM, 2017.Status: Published
Adding the Next Nine: An Investigation of Mobile Broadband Networks Availability
| Afilliation | Communication Systems |
| Project(s) | DOMINOS: Dissecting and Modeling Interdependencies in Communication Networks |
| Publication Type | Proceedings, refereed |
| Year of Publication | 2017 |
| Conference Name | Proceedings of the 23rd Annual International Conference on Mobile Computing and Networking |
| Pagination | 88–100 |
| Publisher | ACM |
| Place Published | New York, NY, USA |
| ISBN Number | 978-1-4503-4916-1 |
| Keywords | correlation networks, interdependent networks, ultra-reliable communication |
| URL | http://doi.acm.org/10.1145/3117811.3117842 |
| DOI | 10.1145/3117811.3117842 |
Alternative Backoff: Achieving Low Latency and High Throughput with ECN and AQM
In IFIP Networking. IFIP, 2017.Status: Published
Alternative Backoff: Achieving Low Latency and High Throughput with ECN and AQM
A number of recently proposed Active Queue Management (AQM) mechanisms instantiate shallow buffers with burst tolerance to minimise the time that packets spend enqueued at a bottleneck. However, shallow buffering causes noticeable TCP performance degradation as a path’s underlying round trip time (RTT) heads above typical intra-country levels. Using less-aggressive multiplicative backoffs in TCP can compensate for shallow bottleneck buffering. AQM mechanisms may either drop packets or mark them using Explicit Congestion Notification (ECN), depending on whether the sender marked packets as ECN-capable. While a drop may therefore stem from any type of queue, an ECN-mark indicates that an AQM mechanism has done its job, and therefore the queue is likely to be shallow. We propose ABE: “Alternative Backoff with ECN”, which consists of enabling ECN and letting individual TCP senders back off less aggressively in reaction to ECN-marks from AQM-enabled bottlenecks. Using controlled testbed experiments with standard NewReno and CUBIC flows, we show significant performance gains in lightly-multiplexed scenarios, without losing the delay-reduction benefits of deploying AQM. ABE is a sender-side-only modification that can be deployed across networks incrementally (requiring no flag-day) and offers a compelling reason to deploy and enable ECN across the Internet.
| Afilliation | Communication Systems |
| Project(s) | RITE: Reducing Internet Transport Latency |
| Publication Type | Proceedings, refereed |
| Year of Publication | 2017 |
| Conference Name | IFIP Networking |
| Publisher | IFIP |
| Keywords | AQM, congestion control, ECN, low latency, tcp |
| Notes | Best Paper Award |
| URL | http://dl.ifip.org/db/conf/networking/networking2017/1570335770.pdf |
Talks, invited
A Practical Introduction to NEAT at Hainan University
In Haikou, Hainan, People's Republic of China. Haikou, Hainan, People's Republic of China, 2017.Status: Published
A Practical Introduction to NEAT at Hainan University
The goal of NEAT (A New, Evolutive API and Transport-Layer Architecture for the Internet) is to allow network "services" offered to applications – such as reliability, low-delay communication or security – to be dynamically tailored based on application demands, current network conditions, hardware capabilities or local policies, and also to support the integration of new network functionality in an evolutionary fashion, without applications having to be rewritten. This talk gives a practical introduction to NEAT from a developer's perspective: after an introduction to NEAT, the APIs and in particular the NEAT Sockets API are explained. This is followed by pseudo-code examples and finally running-code examples. These running-code examples particularly also show how to use NEAT in NorNet Core
| Afilliation | Communication Systems |
| Project(s) | NEAT: A New, Evolutive API and Transport-Layer Architecture for the Internet, NorNet |
| Publication Type | Talks, invited |
| Year of Publication | 2017 |
| Location of Talk | Haikou, Hainan, People's Republic of China |
| Place Published | Haikou, Hainan, People's Republic of China |
| Type of Talk | Invited Talk |
| Keywords | Client, Examples, NEAT, NEAT Sockets API, NorNet Core, programming, Server |
Public outreach
An interview with David Ayman Shamma
ACM, 2017.Status: Published
An interview with David Ayman Shamma
| Afilliation | Communication Systems |
| Project(s) | Efficient EONS: Execution of Large Workloads on Elastic Heterogeneous Resources |
| Publication Type | Public outreach |
| Year of Publication | 2017 |
| Date Published | 07/2017 |
| Publisher | ACM |
Technical reports
AQM Characterization Guidelines
IETF, 2016.Status: Published
AQM Characterization Guidelines
Unmanaged large buffers in today's networks have given rise to a slew of performance issues. These performance issues can be addressed by some form of Active Queue Management (AQM) mechanism, optionally in combination with a packet scheduling scheme such as fair queuing. The IETF Active Queue Management and Packet Scheduling working group was formed to standardize AQM schemes that are robust, easily implementable, and successfully deployable in today's networks. This document describes various criteria for performing precautionary characterizations of AQM proposals. This document also helps in ascertaining whether any given AQM proposal should be taken up for standardization by the AQM WG.
| Afilliation | Media, The Center for Resilient Networks and Applications, Communication Systems |
| Project(s) | RITE: Reducing Internet Transport Latency, The Center for Resilient Networks and Applications |
| Publication Type | Technical reports |
| Year of Publication | 2016 |
| Date Published | 07/2016 |
| Publisher | IETF |
| ISSN Number | 2070-1721 |
| Keywords | Active Queue Management |
| URL | https://tools.ietf.org/html/rfc7928 |
Talks, keynote
Automatic Detection of Angiectasia: Evaluation of Deep Learning and Handcrafted Approaches
In IEEE Conference on Biomedical and Health Informatics (BHI) 2018, 2018.Status: Published
Automatic Detection of Angiectasia: Evaluation of Deep Learning and Handcrafted Approaches
Angiectasia, formerly called angiodysplasia, is one of the most frequent vascular lesions and often the cause of gastrointestinal bleedings. Medical specialists assessing videos of examinations reach a detection performance of 16% for the detection of bleeding to 69% for the detection of angiectasia. In this paper, we present several machine-learning-based approaches for angiectasia detection in wireless video capsule endoscopy images. The most promising results for pixel-wise localization and frame-wise detection are obtained by the proposed deep learning approach using generative adversarial networks (GANs) with a sensitivity of 88% and specificity of 99.9% for pixel-wise localization and a sensitivity of 98% and a specificity of 100% for frame-wise detection, which fits the requirements for automatic angiectasia detection in real clinical settings.
| Afilliation | Communication Systems |
| Project(s) | Efficient EONS: Execution of Large Workloads on Elastic Heterogeneous Resources, Department of Holistic Systems |
| Publication Type | Talk, keynote |
| Year of Publication | 2018 |
| Location of Talk | IEEE Conference on Biomedical and Health Informatics (BHI) 2018 |