A program to find frequent molecular substructures and discriminative fragments in a database of molecule descriptions. The algorithm is based on the Eclat algorithm for frequent item set mining.
A program to demonstrate the optimization process of particle swarm optimization. A two-dimensional objective function is visualized by level of grey: the lighter the color, the higher the function value. The particles are shown as red circles, their trajectory as red lines.
A program to demonstrate the optimization process of ant colony optimization for the traveling saleman problem (TSP). The cities are shown as red circles, the pheromone on the connections between them (fully connected graph) by gray lines. The darker the grey, the more pheromone is currently on the edge. During the optimization, the currently best found tour is drawn in red. To run the optimization, first create a random TSP, then create an ant colony, and finally run the optimization.
A program to find frequent itemsets (also closed and maximal) with the eclat algorithm ,which carries out a depth first search on the subset lattice and determines the support of itemsets by intersecting transaction lists.
Programs to induce a naive possibilistic classifier (a possibilistic analog of the naive Bayes classifier) and to classify new data with an induced naive possibilistic classifier.
This OpenNL, a library to easily construct and solve sparse linear systems.
* OpenNL is supplied with a set of built-in iterative solvers (Conjugate gradient,BICGSTAB, GMRes) and preconditioners (Jacobi, SSOR).
* OpenNL can also use other solvers (SuperLU 3.0 is supported as an OpenNL extension,MUMPS will be supported in a future version)
Computes the hafnian of a nonnegative integer matrix. Notes: Copy hafnian.c to main.c, in the same directory as Rothberg s code (see above). You can download the .tar directory with the code weighted-match.tar here. Then "make" the codes (this codes are in C, not C++). The program is then run by the command "wmatch".
