hh.sePublications
Change search
Link to record
Permanent link

Direct link
BETA
Bilstrup, Urban
Publications (10 of 46) Show all publications
Parsapoor, M., Bilstrup, U. & Svensson, B. (2018). Forecasting Solar Activity with Computational Intelligence Models. IEEE Access, 6, 70902-70909
Open this publication in new window or tab >>Forecasting Solar Activity with Computational Intelligence Models
2018 (English)In: IEEE Access, E-ISSN 2169-3536, Vol. 6, p. 70902-70909Article in journal (Refereed) Published
Abstract [en]

It is vital to accurately predict solar activity, in order to decrease the plausible damage of electronic equipment in the event of a large high-intensity solar eruption. Recently, we have proposed brain emotional learning-based fuzzy inference system (BELFIS) as a tool for the forecasting of chaotic systems. The structure of BELFIS is designed based on the neural structure of fear conditioning. The function of BELFIS is implemented by assigning adaptive networks to the components of the BELFIS structure. This paper especially focuses on the performance evaluation of BELFIS as a predictor by forecasting solar cycles 16-24. The performance of BELFIS is compared with other computational models used for this purpose, in particular with the adaptive neuro-fuzzy inference system. © 2018 IEEE.

Place, publisher, year, edition, pages
Piscataway, N.J.: Institute of Electrical and Electronics Engineers Inc., 2018
Keywords
Adaptive systems, Brain, Brain models, Chaotic systems, Forecasting, Fuzzy logic, Fuzzy neural networks, Fuzzy systems, Intelligent control, Neural networks, Oscillators (electronic), Solar energy, Solar radiation, Time series analysis, Adaptive neuro-fuzzy inference system, Brain emotional learning, Predictive models, Solar activity, Solar cycle, Fuzzy inference
National Category
Computer Systems Computer Sciences Bioinformatics (Computational Biology)
Identifiers
urn:nbn:se:hh:diva-38724 (URN)10.1109/ACCESS.2018.2867516 (DOI)000453302000001 ()2-s2.0-85056589499 (Scopus ID)
Available from: 2019-01-08 Created: 2019-01-08 Last updated: 2019-01-08Bibliographically approved
Bilstrup, U. & Stranne, F. (2016). Peace in Cyberspace Will Not Take Place. In: : . Paper presented at International Studies Association, ISA's 57th Annual Convention, Atlanta, Georgia, USA, March 16th-19th, 2016.
Open this publication in new window or tab >>Peace in Cyberspace Will Not Take Place
2016 (English)Conference paper, Oral presentation only (Refereed)
Abstract [en]

The ongoing debate whether cyberwar exists or not is odd and to large extent based on an Industrial age view of the definition of war. The ongoing digital revolution ends the industrial age and it was in the context of the industrial age that the Clausewitzian theories of war were defined. The industrial age was built upon machines and physical objects, and the theories of war in this era were also based on these elements. However, when the importance of physical values is vanishing and replaced by other values, as information and knowledge, the fundamental elements of war in the industrial age becomes week. An extension of the theories of war in the information age is that destruction of digital assets is representing the same element of violence, if it potentially cripples an enemy to defeat. When a society’s valuable assets are in the digital form and not necessarily even present within the geographical area of a sovereign state one maybe have to reconsider the understanding of war. This paper explores the discourse framing war in the information age, and conducts a discussion on how to define peace and war in cyberspace, especially in the context of digital violence.

National Category
Other Social Sciences not elsewhere specified
Identifiers
urn:nbn:se:hh:diva-30783 (URN)
Conference
International Studies Association, ISA's 57th Annual Convention, Atlanta, Georgia, USA, March 16th-19th, 2016
Available from: 2016-04-21 Created: 2016-04-21 Last updated: 2018-03-22Bibliographically approved
Stranne, F., Bilstrup, U. & Ewertsson, L. (2015). Behind the Mask – Attribution of antagonists in cyberspace and its implications on international conflicts and security issues. In: : . Paper presented at International Studies Association (ISA)’s 56th Annual, Convention – Global IR and Regional Worlds. A New Agenda for International Studies, New Orleans, Louisiana, United States, February 18-21, 2015.
Open this publication in new window or tab >>Behind the Mask – Attribution of antagonists in cyberspace and its implications on international conflicts and security issues
2015 (English)Conference paper, Published paper (Refereed)
Abstract [en]

Cyber systems and critical infrastructure are changing the dynamics of international conflicts, security issues, and challenge traditional ways of understanding warfare. Early warning and attribution of who is accountable for a cyber-attack and what is the intention with the attack is crucial information. To be able to efficiently response to a cyber-antagonist the measure of response must be decided at network speed, which is far beyond what is possible with traditional attribution methods. The ongoing “cyber arm raze” push towards the development and use of autonomous cyber response systems. An autonomous cyber response would most probably use the complexity of attack vector as a tool for attribution, not considering the identity of the antagonist for deciding the measure of response. This will challenge traditional ways of understanding conflict, war, and how nation states handle different kinds of aggressions. This leads to a new kind of deterrence increasing the need to theorize cyber conflicts, as well as empirically study how different actors are acting and reacting in relation to this new threat. This paper initiates the discourse on the implications of the use of autonomous cyber response systems for the international system/relations.

National Category
Social Sciences
Identifiers
urn:nbn:se:hh:diva-28047 (URN)
Conference
International Studies Association (ISA)’s 56th Annual, Convention – Global IR and Regional Worlds. A New Agenda for International Studies, New Orleans, Louisiana, United States, February 18-21, 2015
Available from: 2015-04-02 Created: 2015-04-02 Last updated: 2018-03-22Bibliographically approved
Ramazanali, H., Jonsson, M., Vinel, A. & Bilstrup, U. (2015). Multichannel admission control for military training network. In: Lisa O’Conner (Ed.), 2015 IEEE 18th International Symposium on Real-Time Distributed Computing (ISORC) : . Paper presented at 2015 IEEE 18th International Symposium on Real-Time Distributed Computing (IEEE ISORC), Auckland, New Zealand, Apr. 13-17, 2015 (pp. 150-157). Los Alamitos, CA: IEEE Computer Society
Open this publication in new window or tab >>Multichannel admission control for military training network
2015 (English)In: 2015 IEEE 18th International Symposium on Real-Time Distributed Computing (ISORC) / [ed] Lisa O’Conner, Los Alamitos, CA: IEEE Computer Society, 2015, p. 150-157Conference paper, Published paper (Refereed)
Abstract [en]

A military training radio network requires support for a large number of mobile nodes with heterogeneous traffic and real-time requirements. We propose a deterministic protocol and an admission control using real-time analysis for a centralized radio network with a multichannel base station. The admission control implements an algorithm for frequency allocation to mobile nodes, and guarantees timely treatment of real-time traffic. The proposed online heuristic frequency allocation algorithm is compared to other known heuristic algorithms: round robin over channels and fill one channel first. The goal with the heuristic algorithms is to maximize the number of supported mobile nodes. Our results show that when the high utilization part of the traffic have shorter deadlines it is advantageous to differentiate different types of nodes onto separate frequencies, whilst if the deadline is increased it is advantageous to mix different types of nodes on each frequency. © Copyright 2015 IEEE

Place, publisher, year, edition, pages
Los Alamitos, CA: IEEE Computer Society, 2015
Keywords
Military training radio networks, real-time guarantees, admission control, EDF scheduling, MAC, multichannel
National Category
Engineering and Technology
Identifiers
urn:nbn:se:hh:diva-29203 (URN)10.1109/ISORC.2015.28 (DOI)000380606500019 ()2-s2.0-84962891450 (Scopus ID)978-1-4799-8781-8 (ISBN)
Conference
2015 IEEE 18th International Symposium on Real-Time Distributed Computing (IEEE ISORC), Auckland, New Zealand, Apr. 13-17, 2015
Available from: 2015-08-15 Created: 2015-08-15 Last updated: 2018-03-22Bibliographically approved
Parsapoor, M., Bilstrup, U. & Svensson, B. (2015). Prediction of Solar Cycle 24: Using a Connectionist Model of the Emotional System. In: 2015 International Joint Conference on Neural Networks (IJCNN): . Paper presented at 2015 International Joint Conference on Neural Networks (IJCNN 2015), Killarney, Ireland, July 12–17, 2015. Piscataway, NJ: IEEE Press, Article ID 7280839.
Open this publication in new window or tab >>Prediction of Solar Cycle 24: Using a Connectionist Model of the Emotional System
2015 (English)In: 2015 International Joint Conference on Neural Networks (IJCNN), Piscataway, NJ: IEEE Press, 2015, article id 7280839Conference paper, Published paper (Other (popular science, discussion, etc.))
Abstract [en]

Accurate prediction of solar activity as one aspect of space weather phenomena is essential to decrease the damage from these activities on the ground based communication, power grids, etc. Recently, the connectionist models of the brain such as neural networks and neuro-fuzzy methods have been proposed to forecast space weather phenomena; however, they have not been able to predict solar activity accurately. That has been a motivation for the development of the connectionist model of the brain; this paper aims to apply a connectionist model of the brain to accurately forecasting solar activity, in particular, solar cycle 24. The neuro-fuzzy method has been referred to as the brain emotional learning-based recurrent fuzzy system (BELRFS). BELRFS is tested for prediction of solar cycle 24, and the obtained results are compared with well-known neuro-fuzzy methods and neural networks as well as with physical-based methods. @2015 IEEE

Place, publisher, year, edition, pages
Piscataway, NJ: IEEE Press, 2015
Keywords
brain emotional learning-based recurrent fuzzy system, emotional system, solar activity forecasting
National Category
Electrical Engineering, Electronic Engineering, Information Engineering Computer Systems
Identifiers
urn:nbn:se:hh:diva-29236 (URN)10.1109/IJCNN.2015.7280839 (DOI)000370730603137 ()2-s2.0-84951103535 (Scopus ID)978-1-4799-1959-8 (ISBN)978-1-4799-1959-15 (ISBN)
Conference
2015 International Joint Conference on Neural Networks (IJCNN 2015), Killarney, Ireland, July 12–17, 2015
Available from: 2015-08-19 Created: 2015-08-19 Last updated: 2018-03-22Bibliographically approved
Parsapoor, M., Bilstrup, U. & Svensson, B. (2014). A Brain Emotional Learning-based Prediction Model for the Prediction of Geomagnetic Storms. In: Proceedings of the 2014 Federated Conference on Computer Science and Information Systems: . Paper presented at 9th International Symposium Advances in Artificial Intelligence and Applications (AAIA'14), Warsaw, Poland, 7-10 September, 2014 (pp. 35-42). Los Alamitos, CA: IEEE Press
Open this publication in new window or tab >>A Brain Emotional Learning-based Prediction Model for the Prediction of Geomagnetic Storms
2014 (English)In: Proceedings of the 2014 Federated Conference on Computer Science and Information Systems, Los Alamitos, CA: IEEE Press, 2014, p. 35-42Conference paper, Published paper (Refereed)
Abstract [en]

This paper introduces a new type of brain emotional learning inspired models (BELIMs). The suggested model is  utilized as a suitable model for predicting geomagnetic storms. The model is known as BELPM which is an acronym for Brain Emotional Learning-based Prediction Model. The structure of the suggested model consists of four main parts and mimics the corresponding regions of the neural structure underlying fear conditioning. The functions of these parts are implemented by assigning adaptive networks to the different parts. The learning algorithm of BELPM is based on the steepest descent (SD) and the least square estimator (LSE). In this paper, BELPM is employed to predict geomagnetic storms using the Disturbance Storm Time (Dst) index. To evaluate the performance of BELPM, the obtained results have been compared with the results of the adaptive neuro-fuzzy inference system (ANFIS). © 2014 Polish Information Processing Society.

Place, publisher, year, edition, pages
Los Alamitos, CA: IEEE Press, 2014
Series
Annals of Computer Science and Information Systems, ISSN 2300-5963 ; 2
Keywords
Brain Emotional Learning Inspired Models, Disturbance Storm Time (Dst)
National Category
Probability Theory and Statistics
Identifiers
urn:nbn:se:hh:diva-26711 (URN)10.15439/2014F231 (DOI)000358008500005 ()2-s2.0-84912092029 (Scopus ID)978-83-60810-58-3 (ISBN)978-83-60810-57-6 (ISBN)978-83-60810-61-3 (ISBN)
Conference
9th International Symposium Advances in Artificial Intelligence and Applications (AAIA'14), Warsaw, Poland, 7-10 September, 2014
Available from: 2014-10-12 Created: 2014-10-12 Last updated: 2018-03-22Bibliographically approved
Parsapoor, M. & Bilstrup, U. (2014). An Imperialist Competitive Algorithm For Interference-Aware Cluster-heads Selection in Ad hoc Networks. In: Proceedings: 2014 IEEE 28th International Conference on Advanced Information Networking and Applications: IEEE AINA 2014: 13-16 May 2014: University of Victoria, Victoria, Canada. Paper presented at 28th IEEE International Conference on Advanced Information Networking and Applications, IEEE AINA 2014, Victoria, BC, Canada, 13-16 May, 2014 (pp. 41-48). Los Alamitos, CA: IEEE Computer Society
Open this publication in new window or tab >>An Imperialist Competitive Algorithm For Interference-Aware Cluster-heads Selection in Ad hoc Networks
2014 (English)In: Proceedings: 2014 IEEE 28th International Conference on Advanced Information Networking and Applications: IEEE AINA 2014: 13-16 May 2014: University of Victoria, Victoria, Canada, Los Alamitos, CA: IEEE Computer Society, 2014, p. 41-48Conference paper, Published paper (Other academic) [Artistic work]
Abstract [en]

This paper presents the results of applying a new clustering algorithm in ad hoc networks. This algorithm is a centralized method and is designed on the basis of an imperialist competitive algorithm (ICA). This algorithm aims to find a minimum number of cluster-heads while satisfying two constraints, the connectivity and interference. This work is a part of an ongoing research to develop a distributed interference aware cluster-based channel allocation method. As a matter of fact, the results of the centralized method are required to provide an upper level for the performance of the distributed version. The suggested method is evaluated for several scenarios and compares the obtained results with the reported results of ant colony optimization-based methods. © 2014 IEEE.

Place, publisher, year, edition, pages
Los Alamitos, CA: IEEE Computer Society, 2014
Series
Proceedings: International Conference on Advanced Information Networking and Applications, ISSN 1550-445X
Keywords
Ad Hoc Network, Cluster Formation, Imperialist Competitive Algorithm
National Category
Telecommunications
Identifiers
urn:nbn:se:hh:diva-25529 (URN)10.1109/AINA.2014.12 (DOI)000358605300006 ()2-s2.0-84903839955 (Scopus ID)978-1-4799-3629-8 (ISBN)
Conference
28th IEEE International Conference on Advanced Information Networking and Applications, IEEE AINA 2014, Victoria, BC, Canada, 13-16 May, 2014
Note

Article number: 6838646

Available from: 2014-06-07 Created: 2014-06-07 Last updated: 2018-03-22Bibliographically approved
Parsapoor, M. & Bilstrup, U. (2014). Emotional Learning Inspired Engine: for Cognitive Radio Networks. In: : . Paper presented at 10th Swedish National Computer Networking Workshop, SNCNW 2014, Mälardalen University, Västerås, Sweden, June 2-3, 2014.
Open this publication in new window or tab >>Emotional Learning Inspired Engine: for Cognitive Radio Networks
2014 (English)Conference paper (Other academic)
Abstract [en]

This paper suggests a new engine to be used to develop cognitive nodes in cognitive radio networks. Instead of the traditional cognitive cycle, the suggested engine could be designed based on an emotional cycle that is inspired by the emotional system that reacts to the received stimulus and learns from the reaction. The engine is called ELIE that stands for Emotional Learning Inspired Engine. This paper presents the structure of ELIE and explains how it can be implemented on the basis of generic policy architecture. This paper also discusses the possible applications of the suggested engine.

Keywords
cognitive radio networks, Emotional learning, Emotional Learning Inspired Engine
National Category
Computer Sciences
Identifiers
urn:nbn:se:hh:diva-25441 (URN)
Conference
10th Swedish National Computer Networking Workshop, SNCNW 2014, Mälardalen University, Västerås, Sweden, June 2-3, 2014
Available from: 2014-05-28 Created: 2014-05-28 Last updated: 2018-03-22Bibliographically approved
Ramazanali, H., Jonsson, M., Kunert, K. & Bilstrup, U. (2014). Military Training Network with Admission Control using Real-Time Analysis. In: 2014 IEEE 19th International Workshop on Computer Aided Modeling and Design of Communication Links and Networks (CAMAD): . Paper presented at 2014 IEEE 19th International Workshop on Computer Aided Modeling and Design of Communication Links and Networks (CAMAD), Athens, Greece, December 1-3, 2014 (pp. 249-254). Piscataway, NJ: IEEE Press, Article ID 7033244.
Open this publication in new window or tab >>Military Training Network with Admission Control using Real-Time Analysis
2014 (English)In: 2014 IEEE 19th International Workshop on Computer Aided Modeling and Design of Communication Links and Networks (CAMAD), Piscataway, NJ: IEEE Press, 2014, p. 249-254, article id 7033244Conference paper, Published paper (Refereed)
Abstract [en]

Military training radio networks typically consist of large numbers of mobile nodes and have to provide real-time (RT) communication between these nodes. This paper introduces a method on how to manage radio resources and provide Quality of Service (QoS) guarantees for heterogeneous traffic by using admission control, deterministic queuing, and scheduling methods. The proposed solution is based on the use of a RT feasibility test in the admission control and earliest deadline first (EDF) scheduling and queuing. This deterministic solution handles heterogeneous traffic through a novel combination of RT downlink and two types of RT uplink dynamic scheduling mechanisms. The uplink scheduling consists of a control packet based mechanism for sporadic RT traffic and a periodic short-latency mechanism for periodic RT traffic. The method presented in this paper is investigated by computer simulation, evaluating its performance and determining the maximum number of nodes supported, given a worst-case user scenario. To the best of our knowledge this is the first centralized protocol designed for a military training network providing application-specific RT support for heterogeneous traffic. ©2014 IEEE.

Place, publisher, year, edition, pages
Piscataway, NJ: IEEE Press, 2014
Keywords
Military training radio networks, real-time guarantees, admission control, EDF scheduling, MAC
National Category
Telecommunications
Identifiers
urn:nbn:se:hh:diva-27413 (URN)10.1109/CAMAD.2014.7033244 (DOI)000380484700051 ()2-s2.0-84949928539 (Scopus ID)978-1-4799-5725-5 (ISBN)
Conference
2014 IEEE 19th International Workshop on Computer Aided Modeling and Design of Communication Links and Networks (CAMAD), Athens, Greece, December 1-3, 2014
Available from: 2015-01-06 Created: 2015-01-06 Last updated: 2018-03-22Bibliographically approved
Parsapoor, M., Bilstrup, U. & Svensson, B. (2014). Neuro-fuzzy Models for Geomagnetic Storms Prediction: Using the Auroral Electrojet Index. In: 2014 10th International Conference on Natural Computation (ICNC): . Paper presented at 11th International Conference on Fuzzy Systems and Knowledge Discovery (FSKD 2014), Xiamen, China, 19–21 August, 2014 (pp. 12-17). Piscataway, NJ: IEEE Press, Article ID 6975802.
Open this publication in new window or tab >>Neuro-fuzzy Models for Geomagnetic Storms Prediction: Using the Auroral Electrojet Index
2014 (English)In: 2014 10th International Conference on Natural Computation (ICNC), Piscataway, NJ: IEEE Press, 2014, p. 12-17, article id 6975802Conference paper, Published paper (Refereed)
Abstract [en]

This study presents comparative results obtained from employing four different neuro-fuzzy models to predict geomagnetic storms. Two of these neuro-fuzzy models can be classified as Brain Emotional Learning Inspired Models (BELIMs). These two models are BELFIS (Brain Emotional Learning Based Fuzzy Inference System) and BELRFS (Brain Emotional Learning Recurrent Fuzzy System). The two other models are Adaptive Neuro-Fuzzy Inference System (ANFIS) and Locally Linear Model Tree (LoLiMoT) learning algorithm, two powerful neuro-fuzzy models to accurately predict a nonlinear system. These models are compared for their ability to predict geomagnetic storms using the AE index.

Place, publisher, year, edition, pages
Piscataway, NJ: IEEE Press, 2014
Keywords
Adaptive Neuro-fuzzy Inference System, Auroral Electrojet, Brain Emotional Learning-inspired Model, Locally linear model tree learning algorithm
National Category
Engineering and Technology
Identifiers
urn:nbn:se:hh:diva-26904 (URN)10.1109/ICNC.2014.6975802 (DOI)000393406200003 ()2-s2.0-84926663387 (Scopus ID)978-1-4799-5151-2 (ISBN)
Conference
11th International Conference on Fuzzy Systems and Knowledge Discovery (FSKD 2014), Xiamen, China, 19–21 August, 2014
Available from: 2014-11-02 Created: 2014-11-02 Last updated: 2018-03-22Bibliographically approved
Organisations

Search in DiVA

Show all publications