New Matlab toolbox available for the calculation of high level data fusion (consensus) approaches (majority voting and Bayes consensus with discrete probability distributions): https://michem.unimib.it/download/data/bayes-and-majority-voting-consensus-for-matlab/
Category Archives: Data and software
Classification toolbox for MATLAB: new release
In this new release (5.4), class modelling methods (SIMCA, Potential Functions – Kernel Density Estimators, UNEQ) can now be calculated on a specific target class. The toolbox can be downloaded here.
Kohonen and CPANN toolbox for MATLAB: new release
In this new release, batch training has been optimised and now it is faster than previous versions (computational time has been decreased on about 60%). RMSE (squared residuals between sampels and weights of winning neurons) and the average changing of the topological distance between previous and updated winning neurons can be plotted as a function of epochs during training.
The toolbox can be downloaded here.
QSAR models to predict Acute Oral Toxicity
Our latest publication on QSAR models to predict Acute Oral Toxicity: D. Ballabio, F. Grisoni, V. Consonni, R. Todeschini (2019), Integrated QSAR models to predict acute oral systemic toxicity, Molecular Informatics, 38, 1800124 [link]. Data and code to reproduce models availbale here!
New release of our MATLAB toolboxes
we would like to announce that new versions of our toolboxes for MATLAB have been released. A graphical user interface (GUI), which allows an easy model calculation and analysis of results, is provided with all the toolboxes.
The Classification toolbox for MATLAB is a collection of MATLAB modules for calculating classification (supervised pattern recognition) multivariate models.
In this new release, Backpropagation Neural Networks (BPNN) was added as classification method and the maximum number of classes that can be loaded (and modelled) has been extended to 20.
The toolbox can be downloaded here.
The Kohonen and CPANN toolbox for MATLAB is a collection of MATLAB modules for training Kohonen Maps (Self Organising Maps, SOMs) and supervised SOMs.
In this new release, the maximum number of classes that can be loaded (and modelled) has been extended to 20. Numerical results related to the position of samples in the top map and net weights have been added to the results menu.
The toolbox can be downloaded here.
The PCA toolbox for MATLAB is a collection of MATLAB modules for calculating unsupervised multivariate models (PCA, MDS and Cluster Analysis).
In this new release, the maximum number of classes that can be loaded has been extended to 20.
The toolbox can be downloaded here.
Finally, have a look to our data repository where you can freely download available data.
Kohonen and CPANN toolbox: new release
A new version of the Kohonen and CPANN toolbox (for MATLAB) is now available for download. This is a collection of MATLAB modules for training Kohonen Maps (Self Organising Maps, SOMs), Counterpropagation Artificial Neural networs (CPANNs), Supervised Kohonen networks (SKN), XY-fused networks (XY-F). In this new release, the graphical interface has been improved. Now forms with plots can be resized, classes can be loaded both as numerical or string arrays. Assignation method based on class threshold and ROC curves has been introduced. Validation based on Montecarlo random sampling has been added. Have fun!
PCA toolbox: new release
A new version of the PCA toolbox (for MATLAB) is now available for download. This is a collection of MATLAB modules for calculating unsupervised multivariate models for data structure analysis: Principal Component Analysis (PCA), Multidimensional Scaling (MDS) and Cluster Analysis. In this new release, the graphical interface has been improved. Now forms with plots can be resized, classes can be loaded both as numerical or string arrays, visualisation of class potential in the score plots was added. Have fun!
Classification toolbox: new release
A new version of the Classification toolbox (for MATLAB) is now available for download. The Classification toolbox for MATLAB is a collection of MATLAB modules for calculating classification (supervised pattern recognition) multivariate models: Discriminant Analysis, Partial Least Square Discriminant Analysis (PLSDA), Classification trees (CART), K-Nearest Neighbors (kNN), class modeling Potential Functions (Kernel Density Estimators), Support Vector Machines (SVM), Unequal class models (UNEQ) and Soft Independent Modeling of Class Analogy (SIMCA). In this new release, the graphical interface has been improved. Now forms with plots can be resized and classes can be loaded both as numerical or string arrays. Have fun!