ARCHIVE

Xavier Llorà, a member of NCSA's Data Intensive Technologies and Applications division, recently received several significant honors for his research. Llorà received two Bronze Humies at GECCO 2007 (the Genetic and Evolutionary Computation Conference) in London in July. The Humies are awarded annually to recognize human-competitive results produced by genetic and evolutionary computation. Each bronze award carries a $1,000 prize. Llorà and NCSA faculty fellow Rohit Bhargava, a member of the University of Illinois Bioengineering Department and researcher at the Beckman Institute, received a Bronze Humie for "Towards Better than Human Capability in Diagnosing Prostate Cancer Using Infrared Spectroscopic Imaging." The team used a novel genetics-based machine learning technique to diagnose prostate cancer. Their innovative data handling and analysis strategies demonstrate fast learning and accurate classification that scales well with parallelization. For the first time, an automated discovery method has performed as accurately in predicting prostate cancer as human experts. Along with co-authors Jaume Bacardit, Michael Stout, Jonathan D. Hirst, Natalio Krasnogor (all University of Nottingham), and Kumara Sastry (University of Illinois), Llorà was also awarded a Bronze Humie for "Automated Alphabet Reduction Method with Evolutionary Algorithms for Protein Structure Prediction." The paper demonstrates that certain automated procedures can be used to reduce the size of the amino acid alphabet used for protein structure prediction from 20 to just three letters with no significant loss of accuracy. This discovery has the potential for enabling a faster and easier learning process, as well as for generating more compact and human-readable classifiers. Llorà and co-authors Sastry and David E. Goldberg (University of Illinois) also earned a best paper award at GECCO 2007 for "Toward Billion Bit Optimization via Parallel Estimation of Distribution Algorithm." The collaborators took on a major problem in the field of genetic algorithms, which is devoted to search procedures based on the mechanics of natural selection and genetics. Until now, genetic algorithms have been criticized as being slow, suitable for optimizing problems with only a few variables. However, Llorà and his co-authors show that genetic algorithms—by using a number of memory and computational efficiencies—can be scaled to present principled solutions to solve boundedly difficult, large-scale problems with millions to billions of binary variables. Moreover, they showed that their fully parallelized, highly-efficient compact genetic algorithm was able to do so against a class of additively separable problems even with additive noise, when local search methods failed to do so in the presence of just a modest amount. Llorà and co-authors Goldberg, Noriko Imafuji Yasu (University of Illinois), and marketing researchers Yuichi Washida and Hiroshi Tamura also netted a best paper award at the International Conference on Enterprise Information Systems in June for "Delineating Topic and Discussant Transitions in Online Collaborative Environments." The paper details a new algorithmic method for analyzing discussion dynamics and social networking in online collaborative environments (in this case, focus group discussions for product conceptualization). The team developed an algorithm named KEE (Key Elements Extraction) and determined that it provided a better understanding and depiction of participants' ideas than the traditional method. The KEE algorithm research is associated with the Illinois Genetic Algorithms Laboratory's DISCUS project, which targets innovation support through network-based communication. Next, the team plans to use the KEE algorithm for knowledge discovery in Web logs or Web forums.