CHAIR OF

COMPUTATIONAL

INTELLIGENCE

The CI group is very happy to receive two awards for the best research from the faculty of Computer science: 

Heiner received the “FIN-Forschungspreis für Nachwuchswissenschaftler” for his contribution to the field of Large-Scale Multi-Objective Optimization by publishing the paper: 

• Heiner Zille, Hisao Ishibuchi, Sanaz Mostaghim and Yusuke Nojima
• A Framework for Large-scale Multi-objective Optimization based on Problem Transformation (Download) (Supplement Material) (Sourcecode) 
  
• IEEE Transactions on Evolutionary Computation, Vol. 22, Issue 2, pp. 260-275, April 2018. --> Link 

Lukas Hoyer received the “ FIN-Forschungspreis für Studierende” for his contribution to the field of Robot Localization by publishing the paper: 

• Lukas Hoyer, Christoph Steup and Sanaz Mostaghim
• A Robot Localization Framework Using CNNs for Object Detection and Pose Estimation
• In the Proceedings of the IEEE Symposium Series on Computational Intelligence (SSCI), IEEE SSCI 2018, Pages 1388-1395, India, November 2018 --> Link

Congratulations to both of them! 

The Computational Intelligence group celebrated the Christmas 2019: 

Sanaz celebrated the Christmas 2019 with the students from the Stiftung der Deutschen Wirtschaft (sdw): 

Heiner successfully defended his PhD Thesis on: 

The RoboCup Team which got the second place at the WorldCup 2019 in Sydney, was invited by the mayor of the city Magdeburg and was honored to sign in the golden book of the city:

On Monday 18.11.2019, we organized the second MOSAIK project meeting at the SwarmLab. Our project partners from the University of Erlangen, German research center for AI (German: DFKI), NETSYNO and BOSCH GmBH visited us. We had a very fruitful meeting and a great team-building event in the evening:

Xenija's paper which got published at IEEE Transactions on Games is featured at IEEE Computational Magazine:

• Xenija Neufeld, Sanaz Mostaghim, Dario L. Sancho-Pradel and Sandy Brand
• Building a Planner: A Survey of Planning Systems Used in Commercial Video Games 
• IEEE Transactions on Games, Volume, 11 , Issue: 2 , June 2019 (Download) --> Link

https://engage.ieee.org/CI-Magazine-PDF-Download.html <https://engage.ieee.org/CI-Magazine-PDF-Download.html

Alexander Dockhorn and Rudolf Kruse attended the 11th Conference of the European Society for Fuzzy Logic and Technology conference in Prague.

There, Alexander received the distinguished student paper award for his paper:

• Alexander Dockhorn, Tony Schwensfeier, and Rudolf Kruse
• Fuzzy Multiset Clustering for Metagame Analysis
• In the Proceedings of the 11th Conference of the European Society for Fuzzy Logic and Technology, Prague, September 2019 --> PDF, Github

Mahrokh and Sanaz attended the Eurogen conference 2019 in Guimaraes Portugal and presented two papers: 

• Mahrokh Javadi, Cristian Ramirez-Atencia and Sanaz Mostaghim
• Combining Manhattan and Crowding distances in Decision Space for Multimodal and Multi-objective Optimization Problems
• In EUROGEN conference, September 2019
  

• Mahrokh Javadi, Heiner Zille and Sanaz Mostaghim
• The effects of Crowding Distance and Mutation in Multimodal and Multi-objective Optimization Problems
• In EUROGEN conference, September 2019

Xenija received the best poster award at IEEE Conference on Games in London for the paper:

• Xenija Neufeld, Sanaz Mostaghim and Diego Perez-Liebana
• Evolving Game State Evaluation Functions for a Hybrid Planning Approach
• IEEE Conference on Games, London, August 2019

The picture from Award Ceremony will be uploaded soon... 

Palina and Sebastian presented three papers at EPIA 2019:

• Palina Bartashevich and Sanaz Mostaghim
• Ising Model as a Switch Voting Mechanism in Collective Perception (Download)
• EPIA Conference on Artificial Intelligence 2019. Lecture Notes in Computer Science, vol 11805. Springer, pp. 617-629, September 2019 --> Link

• Palina Bartashevich and Sanaz Mostaghim
• Benchmarking Collective Perception: New Task Difficulty Metrics for Collective Decision-Making (Download)
• EPIA Conference on Artificial Intelligence 2019. Lecture Notes in Computer Science, vol 11804. Springer, pp. 699-711, September 2019 --> Link

• Sebastian Mai, Heiner Zille, Christoph Steup and Sanaz Mostaghim
• Online Optimization of Movement Cost for Robotic Applications of PSO
• EPIA Conference on Artificial Intelligence 2019, Lecture Notes in Computer Science, vol 11804. Springer, pp. 699-711, September 2019 --> Link

Xenija, Alex and Sanaz were part of the IEEE Conference on Games which took place last week (20-23 August 2019) in London. We have been very successful!! Sanaz has been one of the general chairs, Alex was part of the video competition committee and Xenija received the Best Poster Award!

Jens, Palina, Mahrokh, Sebastian, Heiner and Sanaz visited GECCO 2019 in Prague and presented 5 papers. The highlight of the conference was the keynote talk of Professor Ingo Rechenberg (photo with him):

The students of the course Computational Intelligence in Games 2019 attended an internal competetion before getting ready for the international competition, which will take place at the IEEE International Conference on Games in August 2019 in London.

Special thanks to our sponsors RegioCom and AxeTrading.

Here some pictures of the event:

Professor Ray and Dr. Singh from UNSW visited SwarmLab. We had very good discussions about common research and future works: 

Our Team RobOtto got the 2nd place at WorldCup RoboCup@Work League which took place from 2 to 8 July in Sydney. Here some pictures:

Jens, Thomas and Sanaz attended the Kick Off Meeting of our newly accepted BMBF project in Nürnberg.

Dr. Annabel Latham from Manchester Metropolitan University, UK, is visiting us:

She will give a talk about: 

Automated Profiling of Individual Traits: Modelling Learning Styles with Oscar Conversational Intelligent Tutoring System

Use of computational intelligence methods for automated user profiling have been widely publicised recently following the Cambridge Analytica / FaceBook scandal, with implications for the ethics and governance of tracking data held on social media and other platforms. Debate over the validity of psychological models of personality and learning styles is not new, however adaptive and targeted online advertisements that rely on such models are big business. This talk explores the application of intelligent systems to user profiling in the online learning domain. It will describe research to develop methods for profiling individual traits in a learning context, introducing a Conversational Intelligent Tutoring System called Oscar and the experiments to automatically predict each individual learner’s preferred style in order to provide an adaptive learning experience. Using the Felder-Silverman model of learning styles, a set of typical behaviours is mapped to a set of variables to capture each learner’s behaviour during an adaptive conversational tutorial. The complexities of capturing data implicitly during a real-time tutoring conversation in a live teaching/learning environment will be discussed. A number of methods and algorithms (e.g. rule-based, MLP neural networks, decision trees, fuzzy decision trees) were applied to the behaviour dataset to determine the best predictions for each of the 4 dimensions of learning style, and for attribute selection to reduce time/complexity for application in real-time tutoring conversations.

SwarmLab opened the doors to the visitors on Saturday 25th May. We welcomed many visitors: 

https://wissenschaft.magdeburg.de/programm/ovgu/2149-wenn-sich-roboter-beim-fliegen-absprechen