Biologically Inspired Computing Research Group
The Biologically Inspired Computing (BIC) research group at K-State is involved in theoretical and applied research in evolutionary algorithms, ant colony optimization, particle swarm optimization, artificial immune systems, memetic algorithms and neural networks for multi-objective and constrained optimization, prediction, structure discovery, learning and other tasks. Our funded research is in in the areas of plant gene regulatory network modeling and power distribution systems. We are also interested in other applications (communications & networks, engineering, computer science, biology & finance).
Projects
- Multi-objective hybrid evolutionary algorithm with Nelder-Mead based local search
- Parameter estimation of differential equation models of gene regulatory networks
- Reduced complexity particle swarm hybrid algorithm with local search for multi-objective/constrained optimization
- Structure discovery of gene regulatory networks using genetic programming and ant colony algorithms
- Overhead distribution system failure rate prediction using radial basis function networks and wavelet decomposition
- Overhead distribution system anomaly detection using the negative selection algorithm
- Distribution system reconfiguration using multi-objective ant colony optimization and evolutionary strategies
- Multi-objective DS-CDMA code design using the clonal selection principle
Software
Fuzzy Simplex Genetic Algorithm (FSGA)
FSGA is a general purpose hybrid algorithm for fast multi-objective optimization that was developed by Praveen Koduru, Sanjoy Das and Stephen M. Welch that has outperformed all major multi-objective evolutionary algorithms
- Matlab implementation
- C implementation
- Related documents