Giovanni Raimondo

MULP: a multi-layer perceptron application to long-term, out-of-sample time series prediction

A forecasting approach based on Multi-Layer Perceptron (MLP) Artificial Neural Networks (named by the authors MULP) is proposed for the NN5 111 time series long-term, out of sample forecasting competition This approach follows a direct prediction strategy and is completely automatic It has been chosen after having been compared with other regression methods (as for example Support Vector Machines (SVMs)) and with a recursive approach to prediction Good results have also been obtained using the ANNs forecaster together with a dimensional reduction of the input features space performed through a Principal Component Analysis (PCA) and a proper information theory based backward selection algorithm Using this methodology we took the 10th place among the best 50% scorers in the final results table of the NN5 competition.

An information theoretic approach for improving data driven prediction of protein model quality

We present the results of an information theory-based approach to select an optimal subset of features for the prediction of protein model quality. The optimal subset of features was calculated by means of a backward selection procedure. The performances of a probabilistic classifier modeled by means of a Kernel Probability Density Estimation method (KPDE) were compared with those of a feed-forward Artificial Neural Network (ANN) and a Support Vector Machine (SVM).

Data-driven models to forecast PM 10 concentration

The research activity described in this paper concerns the study of the phenomena responsible for the urban and suburban air pollution. The analysis carries on the work already developed by the NeMeFo (neural meteo forecasting) research project for meteorological data short-term forecasting. The study analyzed the air pollution principal causes and identified the best subset of features (meteorological data and air pollutants concentrations) for each air pollutant in order to predict its medium-term concentration (in particular for the particulate matter with an aerodynamic diameter of up to 10 mum called PM10). The selection of the best subset of features was implemented by means of a backward selection algorithm which is based on the information theory notion of relative entropy. The final aim of the research is the implementation of a prognostic tool able to reduce the risk for the air pollutants concentrations to be above the alarm thresholds fixed by the law. The implementation of this tool will be carried out using data-driven models based on some of the most wide-spread statistical data-learning techniques (artificial neural networks and support vector machines).

An application of machine learning methods to PM 10 Level medium-term prediction

The study described in this paper, analyzed the urban and suburban air pollution principal causes and identified the best subset of features (meteorological data and air pollutants concentrations) for each air pollutant in order to predict its medium-term concentration (in particular for the PM10). An information theoretic approach to feature selection has been applied in order to determine the best subset of features by means of a proper backward selection algorithm. The final aim of the research is the implementation of a prognostic tool able to reduce the risk for the air pollutants concentrations to be above the alarm thresholds fixed by the law. The implementation of this tool will be carried out using machine learning methods based on some of the most widespread statistical data driven techniques (Artificial Neural Networks, ANN, and Support Vector Machines, SVM).

Feature Selection for Data Driven Prediction of Protein Model Quality

Features selection to assess the accuracy of a protein three-dimensional model, when only the protein sequence is known, is a challenging task because it is not clear which features are most important and how they should best be combined. We present the results of an information theory-based approach to select an optimal subset of features for the prediction of protein model quality. The optimal subset of features was calculated by means of a backward selection procedure, starting from a set of structural features belonging to the following three categories: atomic interactions, solvent accessibility, and secondary structure. Three statistical-learning approaches were evaluated to predict the quality of a protein model starting from an optimum subset of features. The performances of a probabilistic classifier modeled by means of a kernel probability density estimation method (KPDE) were compared with those of a feed-forward artificial neural network (ANN) and a support vector machine (SVM).