Eric Fock

A node pruning algorithm based on a Fourier amplitude sensitivity test method

In this paper, we propose a new pruning algorithm to obtain the optimal number of hidden units of a single layer of a fully connected neural network (NN). The technique relies on a global sensitivity analysis of model output. The relevance of the hidden nodes is determined by analysing the Fourier decomposition of the variance of the model output. Each hidden unit is assigned a ratio (the fraction of variance which the unit accounts for) that gives their ranking. This quantitative information therefore leads to a suggestion of the most favorable units to eliminate. Experimental results suggest that the method can be seen as an effective tool available to the user in controlling the complexity in NNs.

Bayesian and Sensitivity Analysis Approaches to Modeling the Direct Solar Irradiance

In this paper, emphasis is put on the design of a neural network (NN) to model the direct solar irradiance. Since, unfortunately, a neural network is not a statistician -in-a-box, building a NN for a particular problem is a nontrivial task. As a consequence, we argue that in order to properly model the direct solar irradiance, a systematic methodology must be employed. For this purpose, we propose a two-step approach to building the NN model. The first step deals with a probabilistic interpretation of the NN learning by using Bayesian techniques. The Bayesian approach to modeling offers significant advantages over the classical NN learning process. Among others, one can cite (i) automatic complexity control of the NN using all the available data and (ii) selection of the most important input variables. The second step consists of using a new sensitivity analysis-based pruning method in order to infer the optimal NN structure. We show that the combination of the two approaches makes the practical implementation of the Bayesian techniques more reliable.

Global Sensitivity Analysis Approach for Input Selection and System Identification Purposes—A New Framework for Feedforward Neural Networks

A new algorithm for the selection of input variables of neural network is proposed. This new method, applied after the training stage, ranks the inputs according to their importance in the variance of the model output. The use of a global sensitivity analysis technique, extended Fourier amplitude sensitivity test, gives the total sensitivity index for each variable, which allows for the ranking and the removal of the less relevant inputs. Applied to some benchmarking problems in the field of features selection, the proposed approach shows good agreement in keeping the relevant variables. This new method is a useful tool for removing superfluous inputs and for system identification.

Development of a New Model of Single-Speed Air Conditioners at Part-Load Conditions for Hourly Simulations

This paper deals with a new model of HVAC systems for hourly simulations. The former is derived from a short time step model that is priory described. The hourly model is appraised by comparing its predictions to those of the short time step simulations. Finally, a sensitivity analysis is carried out to understand the cause of the discrepancies between the two models when it occurs. The analysis also allows to identify the factors that mainly affect the system performance.

Experimental Study of the Thermal Performances of a Composite Roof Including a Reflective Insulation Material Under Tropical Humid Climatic Conditions

Publisher Summary This chapter deals with the evaluation of the outdoor performances of a composite roof that is composed of a corrugated iron rooftop, a radiant barrier, and a ceiling made of wood, each component being separated by an air space. This assembly is mounted on a small-scale test cell, named isotest. An isotest is designed for research purposes. It is installed on an experimental platform, dedicated to the complete study of the outdoor performances of radiant barrier systems. The chapter essentially describes the entire experimental disposal in detail. The results are then presented and followed by an analysis. It is noted that the results so obtained tends to confirm the great potential of radiant barrier systems in tropical humid climatic conditions. It also determines that the performances of such an assembly are closely linked to the ventilation conditions in the air space facing the reflective side of the radiant barrier.

A new saliency measure for inputs selection and node pruning in neural network

This paper deals with a new saliency measure for ranking and removing the less important inputs and hidden nodes. This new metric is the result of a global sensitivity analysis, EFAST, performed on the neural network. EFAST is model independent, does not interact with the training stage and does not rely on any assumption regards to local minima for instance, contrary to a wide range of local sensitivity-based saliency measure. EFAST apportions the output variance among all the units, and hence, allows their quantitative ranking. New input selection and node pruning algorithms have been derived and are presented here. Some experimental results are provided and show with a good agreement the efficiency of the approach for inputs selection, system identification and node pruning applications.