dtian09 Goto Github PK

collaborative_github_exercise

git-lesson

optimization-of-neural-network-architectures

Matlab programs to find optimal architectures of neural networks (multilayer perceptrons) for detecting loss of coolant accidents (LOCA) of a nuclear power plant (NPP) by training a number of network architectures on a transient dataset of LOCA. The transient dataset is not available to the public due to security issues. The neural networks take 37 inputs (representing 37 signals e.g. pressure, temperature and flow rates etc. of the primary heat transport of a NPP) and output the size of a break on the inlet header of the primary heat transport of the NPP. The size of a break is defined to be the double cross-sectional area of the inlet header and in the range 0% and 200% where 0% is no break and 200% is the complete rupture of the inlet header. The networks output a value between 0 (i.e. 0%) and 200 (i.e. 200%).

python-tools-to-analyse-genetic-data

Python programs (and R programs) to retrieve, transform, analyse the mouse genes (text and numeric) stored in the online bioinformatics databases MGI, Ensembl, Uniprot and Unigene and to validate the ids of the genes. Each program is a data analysis tool. After processing data using the tools, the processed data can be used to train machine learning classifiers such as random forest and SVM for predicting the essentialities of the genes.

rough-set-feature-selection-tools

Rough set feature selection (RSFS) algorithms implemented in java. RSFS can be used to remove the irrelevant and redundant features from a training set before training machine learning classifiers such as neural networks and Bayesian network to improve the classification performance of the classifiers. The following RSFS algorithms are implemented: genetic algorithm (GA_Reducts.java), QuickReduct (QuickReduct.java), random forward search (Random_RSFS.java), random backward search (Random_RSFS.java), random forward-backward search (Random_RSFS.java), a multi-object genetic local search (Hybrid_NSGAII.java), computation of degree of dependency (Gamma_and_Relative_Dependency.java) and computation of relative dependency (Gamma_and_Relative_Dependency.java).