Change search
Link to record
Permanent link

Direct link
BETA
Alternative names
Publications (10 of 23) Show all publications
Mehri, V. A. A., Ilie, D. & Tutschku, K. (2019). Designing a Secure IoT System Architecture from a Virtual Premise for a Collaborative AI Lab. In: : . Paper presented at Workshop on Decentralized IoT Systems and Security (DISS) 24 February 2019, San Diego, CA,.
Open this publication in new window or tab >>Designing a Secure IoT System Architecture from a Virtual Premise for a Collaborative AI Lab
2019 (English)Conference paper, Published paper (Refereed)
Abstract [en]

IoT systems are increasingly composed out of flexible, programmable, virtualised, and arbitrarily chained IoT elements and services using portable code. Moreover, they might be sliced, i.e. allowing multiple logical IoT systems (network + application) to run on top of a shared physical network and compute infrastructure. However, implementing and designing particularly security mechanisms for such IoT systems is challenging since a) promising technologies are still maturing, and b) the relationships among the many requirements, technologies and components are difficult to model a-priori.

The aim of the paper is to define design cues for the security architecture and mechanisms of future, virtualised, arbitrarily chained, and eventually sliced IoT systems. Hereby, our focus is laid on the authorisation and authentication of user, host, and code integrity in these virtualised systems. The design cues are derived from the design and implementation of a secure virtual environment for distributed and collaborative AI system engineering using so called AI pipelines. The pipelines apply chained virtual elements and services and facilitate the slicing of the system. The virtual environment is denoted for short as the virtual premise (VP). The use-case of the VP for AI design provides insight into the complex interactions in the architecture, leading us to believe that the VP concept can be generalised to the IoT systems mentioned above. In addition, the use-case permits to derive, implement, and test solutions. This paper describes the flexible architecture of the VP and the design and implementation of access and execution control in virtual and containerised environments. 

Keywords
IoT, AI, Security, Authentication, Collaboration
National Category
Telecommunications
Identifiers
urn:nbn:se:bth-17550 (URN)10.14722/diss.2019.23xxx (DOI)1-891562-56-8 (ISBN)
Conference
Workshop on Decentralized IoT Systems and Security (DISS) 24 February 2019, San Diego, CA,
Funder
EU, Horizon 2020, 732204
Available from: 2019-01-30 Created: 2019-01-30 Last updated: 2019-01-30Bibliographically approved
Maksimov, Y. V., Fricker, S. & Tutschku, K. (2018). Artifact Compatibility for Enabling Collaboration in the Artificial Intelligence Ecosystem. In: Lecture Notes in Business Information Processing: . Paper presented at 9th International Conference on Software Business, ICSOB 2018; Tallinn; Estonia; 11 June 2018 through 12 June 2018 (pp. 56-71). Springer, 336
Open this publication in new window or tab >>Artifact Compatibility for Enabling Collaboration in the Artificial Intelligence Ecosystem
2018 (English)In: Lecture Notes in Business Information Processing, Springer, 2018, Vol. 336, p. 56-71Conference paper, Published paper (Refereed)
Abstract [en]

Different types of software components and data have to be combined to solve an artificial intelligence challenge. An emerging marketplace for these components will allow for their exchange and distribution. To facilitate and boost the collaboration on the marketplace a solution for finding compatible artifacts is needed. We propose a concept to define compatibility on such a marketplace and suggest appropriate scenarios on how users can interact with it to support the different types of required compatibility. We also propose an initial architecture that derives from and implements the compatibility principles and makes the scenarios feasible. We matured our concept in focus group workshops and interviews with potential marketplace users from industry and academia. The results demonstrate the applicability of the concept in a real-world scenario.

Place, publisher, year, edition, pages
Springer, 2018
Series
Lecture Notes in Business Information Processing, ISSN 18651348
Keywords
compatibility, licensing, marketplace, artificial intelligence, machine learning, deep learning
National Category
Software Engineering
Identifiers
urn:nbn:se:bth-16465 (URN)10.1007/978-3-030-04840-2_5 (DOI)9783030048396 (ISBN)
Conference
9th International Conference on Software Business, ICSOB 2018; Tallinn; Estonia; 11 June 2018 through 12 June 2018
Available from: 2018-06-13 Created: 2018-06-13 Last updated: 2019-01-09Bibliographically approved
Llewellyn, T., Milagro Fernández Carrobles, M. d., Deniz, O., Fricker, S., Storkey, A., Pazos, N., . . . Tutschku, K. (2017). BONSEYES: Platform for Open Development of Systems of Artificial Intelligence. In: : . Paper presented at ACM International Conference on Computing Frontiers 2017. ACM Digital Library
Open this publication in new window or tab >>BONSEYES: Platform for Open Development of Systems of Artificial Intelligence
Show others...
2017 (English)Conference paper, Published paper (Other academic)
Abstract [en]

The Bonseyes EU H2020 collaborative project aims to develop a platform consisting of a Data Marketplace, a Deep Learning Toolbox, and Developer Reference Platforms for organizations wanting to adopt Artificial Intelligence. The project will be focused on using artificial intelligence in low power Internet of Things (IoT) devices ("edge computing"), embedded computing systems, and data center servers ("cloud computing"). It will bring about orders of magnitude improvements in efficiency, performance, reliability, security, and productivity in the design and programming of systems of artificial intelligence that incorporate Smart Cyber-Physical Systems (CPS). In addition, it will solve a causality problem for organizations who lack access to Data and Models. Its open software architecture will facilitate adoption of the whole concept on a wider scale. To evaluate the effectiveness, technical feasibility, and to quantify the real-world improvements in efficiency, security, performance, effort and cost of adding AI to products and services using the Bonseyes platform, four complementary demonstrators will be built. Bonseyes platform capabilities are aimed at being aligned with the European FI-PPP activities and take advantage of its flagship project FIWARE. This paper provides a description of the project motivation, goals and preliminary work.

Place, publisher, year, edition, pages
ACM Digital Library, 2017
Keywords
Artificial Intelligence, Data Marketplace, Cloud computing
National Category
Computer Systems
Identifiers
urn:nbn:se:bth-15781 (URN)10.1145/3075564.3076259 (DOI)978-1-4503-4487-6 (ISBN)
Conference
ACM International Conference on Computing Frontiers 2017
Projects
www.bonseyes.com
Funder
EU, Horizon 2020, 732204
Note

Invited paper

Available from: 2018-01-17 Created: 2018-01-17 Last updated: 2018-01-19Bibliographically approved
Mehri, V. A. A. & Tutschku, K. (2017). Flexible Privacy and High Trust in the Next Generation Internet: The Use Case of a Cloud-based Marketplace for AI. In: : . Paper presented at SNCNW - Swedish National Computer Networking Workshop, Halmstad. Halmstad university
Open this publication in new window or tab >>Flexible Privacy and High Trust in the Next Generation Internet: The Use Case of a Cloud-based Marketplace for AI
2017 (English)Conference paper, Published paper (Refereed)
Abstract [en]

Cloudified architectures facilitate resource ac-cess and sharing which is independent from physical lo-cations. They permit high availability of resources at lowoperational costs. These advantages, however, do not comefor free. End users might fear that they lose control overthe location of their data and, thus, of their autonomy indeciding to whom the data is communicate to. Thus, strongprivacy and trust concerns arise for end users.In this work we will review and investigate privacy andtrust requirements for Cloud systems in general and for acloud-based marketplace (CMP) for AI in particular. We willinvestigate whether and how the current privacy and trustdimensions can be applied to Clouds and for the design ofa CMP. We also propose the concept of a "virtual premise"for enabling "Privacy-by-Design" [1] in Clouds. The ideaof a "virtual premise" might probably not be a universalsolution for any privacy requirement. However, we expectthat it provides flexibility in designing privacy in Cloudsand thus leading to higher trust.

Place, publisher, year, edition, pages
Halmstad university, 2017
Keywords
marketplace, privacy, trust, cloud computing
National Category
Telecommunications
Identifiers
urn:nbn:se:bth-14963 (URN)
Conference
SNCNW - Swedish National Computer Networking Workshop, Halmstad
Projects
Horizon 2020 Bonseyes
Funder
EU, Horizon 2020, 732204
Available from: 2017-07-25 Created: 2017-07-25 Last updated: 2017-08-23Bibliographically approved
Mehri, V. A. A. & Tutschku, K. (2017). Privacy and trust in cloud-based marketplaces for AI and data resources. In: IFIP Advances in Information and Communication Technology: . Paper presented at 11th IFIP WG 11.11 International Conference on Trust Management, IFIPTM,Gothenburg (pp. 223-225). Springer New York LLC, 505
Open this publication in new window or tab >>Privacy and trust in cloud-based marketplaces for AI and data resources
2017 (English)In: IFIP Advances in Information and Communication Technology, Springer New York LLC , 2017, Vol. 505, p. 223-225Conference paper, Published paper (Refereed)
Abstract [en]

The processing of the huge amounts of information from the Internet of Things (IoT) has become challenging. Artificial Intelligence (AI) techniques have been developed to handle this task efficiently. However, they require annotated data sets for training, while manual preprocessing of the data sets is costly. The H2020 project “Bonseyes” has suggested a “Market Place for AI”, where the stakeholders can engage trustfully in business around AI resources and data sets. The MP permits trading of resources that have high privacy requirements (e.g. data sets containing patient medical information) as well as ones with low requirements (e.g. fuel consumption of cars) for the sake of its generality. In this abstract we review trust and privacy definitions and provide a first requirement analysis for them with regards to Cloud-based Market Places (CMPs). The comparison of definitions and requirements allows for the identification of the research gap that will be addressed by the main authors PhD project. © IFIP International Federation for Information Processing 2017.

Place, publisher, year, edition, pages
Springer New York LLC, 2017
Series
IFIP Advances in Information and Communication Technology, ISSN 1868-4238, E-ISSN 1868-422X ; 505
Keywords
AI, Cloud, IoT, Marketplace, Privacy, Trust, Artificial intelligence, Clouds, Commerce, Internet of things, Trusted computing, Data resources, Internet of thing (IOT), Medical information, Privacy and trusts, Privacy requirements, Requirement analysis, Data privacy
National Category
Other Computer and Information Science
Identifiers
urn:nbn:se:bth-14841 (URN)10.1007/978-3-319-59171-1 (DOI)000432194900017 ()2-s2.0-85020537534 (Scopus ID)9783319591704 (ISBN)
Conference
11th IFIP WG 11.11 International Conference on Trust Management, IFIPTM,Gothenburg
Available from: 2017-07-03 Created: 2017-07-03 Last updated: 2018-05-31Bibliographically approved
Tutschku, K., Ahmadi Mehri, V., Carlsson, A., Chivukula, K. V. & Johan, C. (2016). On Resource Description Capabilities of On-Board Tools for Resource Management in Cloud Networking and NFV Infrastructures. In: 2016 IEEE INTERNATIONAL CONFERENCE ON COMMUNICATIONS WORKSHOPS (ICC): . Paper presented at IEEE International Conference on Communications (ICC), Kuala Lumpur (pp. 442-447).
Open this publication in new window or tab >>On Resource Description Capabilities of On-Board Tools for Resource Management in Cloud Networking and NFV Infrastructures
Show others...
2016 (English)In: 2016 IEEE INTERNATIONAL CONFERENCE ON COMMUNICATIONS WORKSHOPS (ICC), 2016, p. 442-447Conference paper, Published paper (Refereed)
Abstract [en]

The rapid adoption of networks that are based on "cloudification" and Network Function Virtualisation (NFV) comes from the anticipated high cost savings of up to 70% in their build and operation. The high savings are founded in the use of general standard servers, instead of single-purpose hardware, and by efficiency resource sharing through virtualisation concepts. In this paper, we discuss the capabilities of resource description of "on-board" tools, i.e. using standard Linux commands, to enable OPEX savings. We put a focus on monitoring resources on small time-scales and on the variation observed on such scales. We introduce a QoE-based comparative concept that relates guest and host views on "utilisation" and "load" for the analysis of the variations. We describe the order of variations in "utilisation" and "load" by measurement and by graphical analysis of the measurements. We do these evaluations for different host operating systems and monitoring tools.

Series
IEEE International Conference on Communications Workshops, ISSN 2164-7038
National Category
Communication Systems
Identifiers
urn:nbn:se:bth-11902 (URN)000386326800074 ()978-1-5090-0448-5 (ISBN)
Conference
IEEE International Conference on Communications (ICC), Kuala Lumpur
Note

Held in conjunction with the IEEE International Conference on Communications (ICC 2016)

Available from: 2016-05-21 Created: 2016-05-21 Last updated: 2017-06-16Bibliographically approved
Tutschku, K. T., Ahmadi Mehri, V. & Carlsson, A. (2016). Towards Multi-layer Resource Management in Cloud Networking and NFV Infrastructures. In: : . Paper presented at 12th Swedish National Computer Networking Workshop (SNCNW), Sundsvall, Sweden.
Open this publication in new window or tab >>Towards Multi-layer Resource Management in Cloud Networking and NFV Infrastructures
2016 (English)Conference paper, Published paper (Refereed)
Abstract [en]

Cloud Networking (CN) and related conceptsoffer appealing novelties to Cloud Computing (CC) customers.They can do a one-stop-shopping for network-enhanced cloudservices. In addition, the costs of such services might below due to multiple customers sharing the infrastructures.Moreover, telecommunication network operators are adopt-ing the CN in theirNetwork Functions Virtualisation (NFV)framework for reducing costs and increasing the flexibility oftheir networks. The technical appeal of CN comes from thetight integration of CC and smart networks. The economicalattractiveness results from avoiding dedicated hardware, shar-ing of resources, and simplified resource management (RM) asseen by the users respectively by the applications. The visionof cheap and integrated CN services is obviously attractive,but it is also evident that it will require more complex RMprocedures for efficiently balancing the usage of all resources.In this contribution, we suggest an initial architecture forintegrated and practical RM in CN and NFV systems. TheRM concept aims at locating and analysing performancebottlenecks, efficiency problems, and eventually discover un-used resources. The suggested architecture is based on alayered view on the system. Moreover, we detail difficultiesin practical resources usage monitoring which, in turn, definerequirements for a RM architecture. The requirement analysisis based on measurements in a CN infrastructure.

National Category
Communication Systems
Identifiers
urn:nbn:se:bth-11903 (URN)
Conference
12th Swedish National Computer Networking Workshop (SNCNW), Sundsvall, Sweden
Available from: 2016-05-21 Created: 2016-05-21 Last updated: 2016-05-25Bibliographically approved
Biernacki, A. & Tutschku, K. (2014). Comparative Performance Study of LTE Downlink Schedulers. Wireless personal communications, 7(2), 585-599
Open this publication in new window or tab >>Comparative Performance Study of LTE Downlink Schedulers
2014 (English)In: Wireless personal communications, ISSN 0929-6212, E-ISSN 1572-834X, Vol. 7, no 2, p. 585-599Article in journal (Refereed) Published
Abstract [en]

Long time evolution (LTE) represents an emerging and promising technology for providing broadband, mobile Internet access. Because of the limitation of available spectrum resource, high spectrum efficiency technologies such as channel-aware scheduling need to be explored. In this work, we evaluate the performance of three scheduling algorithms proposed for LTE downlink transmission. The evaluation takes place in mixed traffic scenarios and aims at exploring strengths and weaknesses of the proposed algorithms. Simulation results illustrate the importance of real-time traffic awareness by schedulers when a specified level of quality of service is required. The research shows that lack of prioritisation of multimedia traffic will lead to severe degradation of video and VoIP services even with a relatively low network load.

Abstract [sv]

Open access article

Place, publisher, year, edition, pages
Springer US, 2014
Keywords
4G Mobile communication, Scheduling algorithm, Multimedia communication
National Category
Computer Sciences
Identifiers
urn:nbn:se:bth-6547 (URN)10.1007/s11277-013-1308-4 (DOI)oai:bth.se:forskinfo2E365D9E88315B26C1257BC900187DCC (Local ID)oai:bth.se:forskinfo2E365D9E88315B26C1257BC900187DCC (Archive number)oai:bth.se:forskinfo2E365D9E88315B26C1257BC900187DCC (OAI)
Available from: 2014-11-20 Created: 2013-08-16 Last updated: 2018-01-11Bibliographically approved
Metzger, F., Rafetseder, A., Romirer-Maierhofer, P. & Tutschku, K. (2014). Exploratory Analysis of a GGSN’s PDP Context Signaling Load. Journal of Computer Networks and Communications, 2014
Open this publication in new window or tab >>Exploratory Analysis of a GGSN’s PDP Context Signaling Load
2014 (English)In: Journal of Computer Networks and Communications, ISSN 2090-7141, E-ISSN 2090-715X, Vol. 2014Article in journal (Refereed) Published
Abstract [en]

This paper takes an exploratory look on control plane signaling in a mobile cellular core network. In contrast to most contributions in this field, our focus does not lie on the wireless or user-oriented parts of the network, but on signaling in the core network. In an investigation of core network data we take a look at statistics related to GTP tunnels and their signaling. Based on the results thereof we propose a definition of load at the GGSN and create an initial load queuingmodel.We find signs of user devices putting burden on the core network through their behavior

Place, publisher, year, edition, pages
Hindawi Publishing Corporation, 2014
Keywords
Performance Model, GGSN, Signaling Load
National Category
Computer Sciences
Identifiers
urn:nbn:se:bth-6418 (URN)10.1155/9613 (DOI)oai:bth.se:forskinfo03108A4A2BD71972C1257D94003CE3AD (Local ID)oai:bth.se:forskinfo03108A4A2BD71972C1257D94003CE3AD (Archive number)oai:bth.se:forskinfo03108A4A2BD71972C1257D94003CE3AD (OAI)
Note

Open Access journal

Available from: 2015-02-17 Created: 2014-11-18 Last updated: 2018-01-11Bibliographically approved
Biernacki, A. & Tutschku, K. (2014). Performance of HTTP Video Streaming Under Different Network Conditions. Multimedia tools and applications, 72(2), 1143-1166
Open this publication in new window or tab >>Performance of HTTP Video Streaming Under Different Network Conditions
2014 (English)In: Multimedia tools and applications, ISSN 1380-7501, E-ISSN 1573-7721, Vol. 72, no 2, p. 1143-1166Article in journal (Refereed) Published
Abstract [en]

The Internet video sharing services have been gaining importance and increasing their share in the multimedia market. In order to compete effectively and provide broadcast television with a comparable level of quality, the Internet video should fulfil stringent quality of service (QoS) constraints. However, as the Internet video is based on packet transmission, it is influenced by delays, transmission errors, data losses and bandwidth limitations which can have a devastating influence on the perceived quality of the multimedia content. There are many works which describe the impact of network impairments on the Internet video. Nevertheless, little is known about how network conditions influence the video streamed by the currently popular services such as YouTube, where video is transmitted over reliable TCP/HTTP protocols. Therefore using a network simulator, we conducted an experimental evaluation of theHTTP based video transmission analysing how the network impairments mentioned above influence the streamed video. The experiments were validated against a network emulator supplied with real network traces. As a result of this work, we can state that the buffering strategies implemented by a video player are in many cases able to mitigate unfavourable network conditions what allow to play the streamed video smoothly. The results may serve Internet Service Providers so that they could tune their network characteristics in order to match the demand from HTTP video.

Place, publisher, year, edition, pages
Springer US, 2014
Keywords
Multimedia communication, Network measurements, Quality of service, Video streaming
National Category
Computer Sciences
Identifiers
urn:nbn:se:bth-6591 (URN)10.1007/s11042-013-1424-x (DOI)000339891300007 ()oai:bth.se:forskinfoF49A043F266AEC84C1257BC9001990FC (Local ID)oai:bth.se:forskinfoF49A043F266AEC84C1257BC9001990FC (Archive number)oai:bth.se:forskinfoF49A043F266AEC84C1257BC9001990FC (OAI)
Available from: 2014-10-10 Created: 2013-08-16 Last updated: 2018-01-11Bibliographically approved
Organisations
Identifiers
ORCID iD: ORCID iD iconorcid.org/0000-0003-4814-4428

Search in DiVA

Show all publications