A friendly guide to wavelets
Artificial intelligence: a modern approach
Artificial intelligence: a modern approach
On power-law relationships of the Internet topology
Proceedings of the conference on Applications, technologies, architectures, and protocols for computer communication
Data mining: concepts and techniques
Data mining: concepts and techniques
Shape Analysis and Classification: Theory and Practice
Shape Analysis and Classification: Theory and Practice
Pattern Classification (2nd Edition)
Pattern Classification (2nd Edition)
Graphs and Digraphs, Fourth Edition
Graphs and Digraphs, Fourth Edition
Pattern Recognition and Machine Learning (Information Science and Statistics)
Pattern Recognition and Machine Learning (Information Science and Statistics)
Computational Methods of Feature Selection (Chapman & Hall/Crc Data Mining and Knowledge Discovery Series)
Digital Signal Processing (4th Edition)
Digital Signal Processing (4th Edition)
Diffusion of time-varying signals in cortical networks
DSP'09 Proceedings of the 16th international conference on Digital Signal Processing
Hi-index | 0.00 |
Comprehensive understanding of biology can only be achieved by integrating several type of data and models across wide time and space scales, ranging from molecules to ecology. While substantial advances have been obtained through the reductionist approach, where specific sybsystems are investigated separately, usually at microscopic scale, the integration of structural and dynamical concepts along several scales holds the key for major breakthroughs. Such endeavours are part of the so-called Systems Biology area. This article discusses and illustrates how complex networks, image analysis, signal processing and artificial intelligence can be integrated into systems biology research, providing an unprecedented opportunity for scientific and technologic advances. The generality of complex networks for system representation allows this type of structures to be effectively used to model both the architecture and function of virtually any biological entity. At the same time, image analysis paves the way not only for the characterization of phenotipic traits, but also for mapping several geometric biological structures (e.g. neuronal systems, bone canals, cell organelles, etc.) as complex networks. Several concepts and methods from signal processing can then be applied in order to characterize, classify and model the structure and dynamics in such network representations. Artificial intelligence approaches, especially pattern recognition, are also necessary in order to automate, integrate and interprete all such myriad of data and models. In addition to discussing, in a brief though accessiblefashion, each of these areas as well as their integration into systems biology, the current work also illustrates the respective potential of this approach with respect to some of the author's recent works.