A general framework for parallel distributed processing
Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
Neural Computation
Data fusion in robotics and machine intelligence
Data fusion in robotics and machine intelligence
Principles and techniques for sensor data fusion
Signal Processing - Intelligent systems for signal and image understanding
Multisensor image fusion using the wavelet transform
Graphical Models and Image Processing
Sensor and Data Fusion Concepts and Applications
Sensor and Data Fusion Concepts and Applications
Multisensor for Computer Vision
Multisensor for Computer Vision
An analysis of the behavior of a class of genetic adaptive systems.
An analysis of the behavior of a class of genetic adaptive systems.
| Hi-index | 0.00 |
In this paper a new Back-Propagation (BP) algorithm cost function is appropriately studied for the modeling of air pollution time series. The underlying idea is that of modifying the error definition in order to improve the capabilities of this kind of models to forecast episodes of poor air quality. The proposed error definition can be regarded as a generalization of the traditional squared error cost function thanks to the presence of a parameter 驴 which allows to obtain the ordinary BP as a special case when 驴驴=驴1. A criterion for choosing this parameter is stated based on setting a-priori a maximum level of allowable false alarms. The goodness of the proposed approach is assessed by means of case studies both on synthetic and measured air quality data.