57 resultados para Proceedings
Resumo:
Recently major processor manufacturers have announced a dramatic shift in their paradigm to increase computing power over the coming years. Instead of focusing on faster clock speeds and more powerful single core CPUs, the trend clearly goes towards multi core systems. This will also result in a paradigm shift for the development of algorithms for computationally expensive tasks, such as data mining applications. Obviously, work on parallel algorithms is not new per se but concentrated efforts in the many application domains are still missing. Multi-core systems, but also clusters of workstations and even large-scale distributed computing infrastructures provide new opportunities and pose new challenges for the design of parallel and distributed algorithms. Since data mining and machine learning systems rely on high performance computing systems, research on the corresponding algorithms must be on the forefront of parallel algorithm research in order to keep pushing data mining and machine learning applications to be more powerful and, especially for the former, interactive. To bring together researchers and practitioners working in this exciting field, a workshop on parallel data mining was organized as part of PKDD/ECML 2006 (Berlin, Germany). The six contributions selected for the program describe various aspects of data mining and machine learning approaches featuring low to high degrees of parallelism: The first contribution focuses the classic problem of distributed association rule mining and focuses on communication efficiency to improve the state of the art. After this a parallelization technique for speeding up decision tree construction by means of thread-level parallelism for shared memory systems is presented. The next paper discusses the design of a parallel approach for dis- tributed memory systems of the frequent subgraphs mining problem. This approach is based on a hierarchical communication topology to solve issues related to multi-domain computational envi- ronments. The forth paper describes the combined use and the customization of software packages to facilitate a top down parallelism in the tuning of Support Vector Machines (SVM) and the next contribution presents an interesting idea concerning parallel training of Conditional Random Fields (CRFs) and motivates their use in labeling sequential data. The last contribution finally focuses on very efficient feature selection. It describes a parallel algorithm for feature selection from random subsets. Selecting the papers included in this volume would not have been possible without the help of an international Program Committee that has provided detailed reviews for each paper. We would like to also thank Matthew Otey who helped with publicity for the workshop.
Resumo:
The proceedings of the conference
Resumo:
The proceedings of the conference
Resumo:
The proceedings of the conference
Resumo:
The proceedings of the conference
Resumo:
The proceedings of the conference
Resumo:
This conference was an unusual and interesting event. Celebrating 25 years of Construction Management and Economics provides us with an opportunity to reflect on the research that has been reported over the years, to consider where we are now, and to think about the future of academic research in this area. Hence the sub-title of this conference: “past, present and future”. Looking through these papers, some things are clear. First, the range of topics considered interesting has expanded hugely since the journal was first published. Second, the research methods are also more diverse. Third, the involvement of wider groups of stakeholder is evident. There is a danger that this might lead to dilution of the field. But my instinct has always been to argue against the notion that Construction Management and Economics represents a discipline, as such. Granted, there are plenty of university departments around the world that would justify the idea of a discipline. But the vast majority of academic departments who contribute to the life of this journal carry different names to this. Indeed, the range and breadth of methodological approaches to the research reported in Construction Management and Economics indicates that there are several different academic disciplines being brought to bear on the construction sector. Some papers are based on economics, some on psychology and others on operational research, sociology, law, statistics, information technology, and so on. This is why I maintain that construction management is not an academic discipline, but a field of study to which a range of academic disciplines are applied. This may be why it is so interesting to be involved in this journal. The problems to which the papers are applied develop and grow. But the broad topics of the earliest papers in the journal are still relevant today. What has changed a lot is our interpretation of the problems that confront the construction sector all over the world, and the methodological approaches to resolving them. There is a constant difficulty in dealing with topics as inherently practical as these. While the demands of the academic world are driven by the need for the rigorous application of sound methods, the demands of the practical world are quite different. It can be difficult to meet the needs of both sets of stakeholders at the same time. However, increasing numbers of postgraduate courses in our area result in larger numbers of practitioners with a deeper appreciation of what research is all about, and how to interpret and apply the lessons from research. It also seems that there are contributions coming not just from construction-related university departments, but also from departments with identifiable methodological traditions of their own. I like to think that our authors can publish in journals beyond the construction-related areas, to disseminate their theoretical insights into other disciplines, and to contribute to the strength of this journal by citing our articles in more mono-disciplinary journals. This would contribute to the future of the journal in a very strong and developmental way. The greatest danger we face is in excessive self-citation, i.e. referring only to sources within the CM&E literature or, worse, referring only to other articles in the same journal. The only way to ensure a strong and influential position for journals and university departments like ours is to be sure that our work is informing other academic disciplines. This is what I would see as the future, our logical next step. If, as a community of researchers, we are not producing papers that challenge and inform the fundamentals of research methods and analytical processes, then no matter how practically relevant our output is to the industry, it will remain derivative and secondary, based on the methodological insights of others. The balancing act between methodological rigour and practical relevance is a difficult one, but not, of course, a balance that has to be struck in every single paper.
Resumo:
The proceedings of the conference