EPiCS News

PheroMusic iOS App released

2014-08-28T22:00:00Z

The EPiCS team at the University of Oslo has just released the iPhone app PheroMusic on the iTunes app store. The pheromone algorithm developed as part of Work Package 2 and used in the smart camera application has been adapted for use in active music. The app exploits the temporal properties of a pheromone graph which builds up and evaporates over time to realise an artificial agent with musical memory. As such, the self-aware music system is able to remember transitions between musical sections as selected by the user, and thus follow the preferences of the user in future iterations of the musical piece.

Screenshot of the PheroMusic iOS app.

Feature article on EPiCS in University of Paderborn Research Magazine 'Forschung inSight'

2014-08-28T22:00:00Z

University of Paderborn's research magazine 'Forschung inSight' (research insight) aims at making current research results accessible to a broad audience. Recently, an article titled 'Die Psychologie der Rechner' (The psychology of computers) has appeared that describes the goals and results of the EPiCS research project. The article discusses, how the we have translated the psychological concept of self-awareness to the domain of computer science and engineering and what applications can be enabled by this effort.

A copy of the full article in German language can be downloaded here.

Article on Hypermusic in Norwegian Newspapger 'Dagens næringsliv'

2014-06-19T22:00:00Z

Jim Tørresen and Kristian Nymoen of the EPiCS team at University of Oslo have contributed an article to the Norwegian newspaper Dagens næringsliv (comparable to the Financial Times) on their work on Hypermusic. Here is a summary of the article in English:

People with ear buds plugged into the smart phone is a common sight in today's cityscape. The same phone has various sensors built in to register movement: both how fast we are moving, how the phone is oriented and where we are. These can be combined with music listening. By enabling computerised generation of music on the fly, the sensors in the phone may control the pace and type of music. We are talking about moving in a musical landscape through user-controlled active music. Either by direct user selection, just like clicking around in a web browser or more indirectly by using sensor readings from the smart phone. When given a flexible framework for music, music producers may create flexible music that allows the listener to make choices while listening.

It is artificial intelligence that enables this music revolution. The main idea of artificial intelligence is to develop intelligent systems that can adapt to the users rather than forcing users to adapt to the technology. We do this in the form of self-learning methods, often inspired by biology. An example of a biological inspired method is found in ants, when searching for food. The ants find a food source, and leave pheromones on the way home so that other ants know where to go. When the food source runs out or a better one is found, the pheromones evaporate and the trail disappears. In the EU project Engineering Proprioception in Computing Systems (EPICS), we have seen that this method is useful in wide variety of application areas, such as active music and coordination between surveillance cameras.

A copy of the full article in Norwegian language can be downloaded here.

Best performing student award for Jennifer Simonjan

2014-06-11T22:00:00Z

We are happy to announce that Jennifer Simonjan – a student researcher of the EPiCS team at Alpen-Adria-Universität (AAU) Klagenfurt – received the Best Performing Student Award of the Faculty of Technical Sciences at AAU. This award is handed over to the faculty’s top performing students of the year. Jennifer also completed her master study with distinction three weeks ago.

Let’s congratulate Jennifer for this great success!

Jennifer Simonjan receiving the Best Performing Student Award of the Faculty of Technical Sciences at Alpen-Adria-University (AAU) Klagenfurt.

Best paper award for Georg Nebehay and Roman Pflugfelder at WACV'14

2014-04-15T22:00:00Z

We are happy to announce that Georg Nebehay and Roman Pflugfelder, who work on EPiCS at AIT, have receive the best paper award of the WACV'14 conference for their paper Consensus-based Matching and Tracking of Keypoints for Object Tracking.

Keypoints (white) vote for the object center (green) while taking into account the mutal keypoint constellation (red). The object is localized by establishing consensus in the voting behaviour.

Consensus-based Matching and Tracking of Keypoints (CMT) is an object tracking algorithm that is able to visually track a wide variety of object classes in a multitude of scenes without the need of adapting the algorithm to specific scenarios in any way. The novelty of our approach is a keypoint-based object representation, where each keypoint votes independently for the location of the object of interest. Experiments have shown that CMT is able to achieve excellent results on a dataset that is as large as 60 sequences. The Python implementation for this work is freely available under the BSD license here.

We congratulate Georg and Roman on this great success and recognition of their work!

EPiCS in Norwegian Media

2014-03-28T23:00:00Z

The largest newspaper in Norway, Aftenposten, published on 29 March, 2014 on their web page a popular science article prepared by the EPiCS partner University of Oslo, featuring their work in active music systems in the project. This application is used as an example of novel work in the field of artificial intelligence. The article (in Norwegian) can be found here.

EPiCS Video Student Contest Awards

2013-10-16T22:00:00Z

We are happy to announce the winners of the EPiCS Video Student contest:

The following two videos have been awarded a price:

Adaptive Online Tracker created by Alankar Aryal Atreya (Alpen-Adria Universität Klagenfurt)
Self-Awareness in Technical Systems created by Nadjia Pejic and Jan Krekeler (University of Paderborn).

We congratulate the authors of these excellent and entertaining videos for their prizes. Both videos can be watched on the EPiCS video channel.

Introduction to the Ella Middleware

2013-09-24T22:00:00Z

We have just published an introductory article for the Ella middleware on the Codeproject developer portal. The article covers the basics of publish/subscribe and how to write publishers and subscribers using Ella.

The article can be found at here.

FPGA Heater Cores released

2013-08-31T22:00:00Z

In the publication "M. Happe, H. Hangmann, A. Agne, and C. Plessl. Eight ways to put your FPGA on fire – a systematic study of heat generators. In Proc. Int. Conf. on ReConFigurable Computing and FPGAs (ReConFig), pages 1–8. IEEE Computer Society, Dec. 2012.", which won the best paper award at the ReConFig'2012 conference, University of Paderborn has presented a study on the systematic design and evaluation of circuits that are optimised for generating a maximum amount of heat on FPGAs. Such heater cores can be used for automatically generating and calibrating thermal models of FPGA devices. Also the heater cores can be used to expose distinct areas of the devices to high temperatures with the objective to induce soft-errors, due to an increase in switching time.

To make the heater cores available for other researchers for experimentation, we have released them as pcore modules, that can be integrated as components in Xilinx FPGA designs. The amount of heat that is generated can be adjusted in 32 levels.

More information and the MIT-licensed open source code of the FPGA heater cores can be found at http://epics.uni-paderborn.de/fpga-heater.

Deadline for EPiCS Video Student Contest extended

2013-08-19T22:00:00Z

We have extended the deadline for submissions to the EPiCS Video Student Contest to August 31.

In this challenge we invite students to produce a short video that explains the role of self-awareness in technical systems. The best video will be awarded with cash prices up to 500€.

More information can be found here.

EPiCS Video Channel

2013-08-11T22:00:00Z

We are happy to announce that the EPiCS consortium has setup an EPiCS video channel at Vimeo, where we share videos for demonstrating and disseminating our research results to a broad audience. The first couple of videos have been already published and several new videos are currently in production. Stay tuned!

Research Exchange of Peter Lewis with Politecnico di Milano

2013-08-08T22:00:00Z

Dr. Peter Lewis, who is based at the University of Birmingham and works on the EPiCS project, visited Professor Marco Santambrogio at the NECST Lab at the Politecnico di Milano on a Research Exchange visit. The visit took place between the 19th and 21st March 2013, and enabled these two active researchers in the field of self-aware computing to explore several collaborations and areas for future research.

Dr. Lewis's work in the EPiCS project has been primarily concerned with developing concepts and foundations for computational self-awareness. On the conceptual side, his recent work includes the development of a psychology-inspired conceptual framework for describing and comparing computational self-awareness capabilities. On the foundational side, his work has involved developing and applying novel nature-inspired learning and adaptation algorithms to realise the vision of computational self-awareness, e.g. in distributed smart camera networks. This work forms a core aspect of the EPiCS project.

Dr. Lewis gave an invited talk, describing the developed conceptual framework for computational self-awareness and how the capabilities it describes it could be implemented. The talk generated a lively discussion amongst researchers and students from disparate backgrounds including electronic and computer engineering, context aware systems, bioengineering and control theory. Several collaboration scoping sessions were conducted, with researchers from a range of fields. In particular, focus areas included how to apply meta-self-aware algorithm selection to a self-adaptive fault tolerance problem, and the relationship between computational self-awareness, context awareness and control theory.

Peter Lewis is giving an invited talk describing the developed conceptual framework for computational self-awareness and how the capabilities it describes it could be implemented.

Ella distributed publish/subscribe middleware released

2013-08-06T22:00:00Z

Ella, the Middleware developed in the EPiCS Project, has just been released as open source.

Ella is a fully distributed publish/subscribe middleware enabling rapid development of data-driven distributed applications. Ella features a simple and fluent facade making it easy to use. A special focus in the design of the middleware has been put easy integration of Ella into existing code. It does not require any inheritance but instead uses code annotations to make classes suitable for use in the system.

Ella can be downloaded from http://ella.codeplex.com

CamSim simulator for distributed camera networks released

2013-08-05T22:00:00Z

CamSim, the simulator for distributed smart camera networks, has just been released in its first version. In the last few months, the pre-release of CamSim went through various major refactoring processes.

The key changes as well as benefits of CamSim are:

Ease of generating test scenarios, with cameras and objects limited only by computer memory.
Camera behaviour, using an economic and pheromone inspired approach is implemented, as well as several communication policies. These approaches and communication policies are described in Socio-Economic Vision Graph Generation and Handover in Distributed Smart Camera Networks by Lukas Esterle, Peter R. Lewis, Xin Yao and Bernhard Rinner.
Several bandit solvers are implemented to provide meta-management at the camera level, selecting between communication policies and auction strategies dynamically at runtime. This behaviour is described in Learning to be Different: Heterogeneity and Efficiency in Distributed Smart Camera Networks by Peter R. Lewis, Lukas Esterle, Arjun Chandra, Bernhard Rinner and Xin Yao.
The motion behaviour of objects can be replaced using reflection mechanism. Besides prior known movements 'straight' and 'waypoints', where 'straight' defines movement in a straight line and random bouncing off the simulation boundary and 'waypoints' defines a movement along a predefined path, another movement behaviour based on Brownian motion has been added to the collection.
All aspects of camera behaviour, including bandit solvers, communication strategies and pheromone learning can be replaced using reflection mechanisms.

To provide prospective developers with a low entrance level, abstract classes are available for extension. Furthermore, introductory tutorials are available online at the GitHub Repository.

The first release can be downloaded from https://github.com/EPiCS/CamSim/releases/tag/v1.0.

EPiCS Video Student Contest, win 500€ in cash!

2013-07-31T22:00:00Z

We are pleased to announce that EPiCS Video Student Contest. In this challenge we invite students to produce a short video that explains the role of self-awareness in technical systems. The best video will be awarded with cash prices up to 500€.

More information can be found here.