Neural network and GA approaches for dwelling fire occurrence prediction

Abstract This paper describes three approaches for the prediction of dwelling fire occurrences in Derbyshire, a region in the United Kingdom. The system has been designed to calculate the number of fire occurrences for each of the 189 wards in the Derbyshire. In terms of the results from statistical analysis, eight factors are initially selected as the inputs of the neural network. Principal Component Analysis (PCA) is employed for pre-processing the input data set to reduce the number of the inputs. The first three principal components of the available data set are chosen as the inputs, the number of the fires as the output. The first approach is a logistic regression model, which has been widely used in the forest fire prediction. The prediction results of the logistic regression model are not acceptable. The second approach uses a feed-forward neural network to model the relationship between the number of fires and the factors that influence fire occurrence. The model of the neural network gives a prediction with an acceptable accuracy for the fires in dwelling areas. Genetic algorithms (GAs) are the third approach discussed in this study. The first three principle components of the available data set are classified into the different groups according to their number of fires. An iterative GA is proposed and applied to extract features for each data group. Once the features for all the groups have been identified the test data set can be easily clustered into one of the groups based on the group features. The number of fires for the group, which the test data belongs to, is the prediction of the fire occurrence for the test data. The three approaches have been compared. Our results indicate that the neural network based and the GA based approaches perform satisfactorily, with MSEs of 2.375 and 2.875, respectively, but the GA approach is much better understood and more transparent.

[1]  Chris Chatfield,et al.  Time series forecasting with neural networks: a comparative study using the air line data , 2008 .

[2]  David L. Martell,et al.  A logistic model for predicting daily people-caused forest fire occurrence in Ontario , 1987 .

[3]  S. Qin,et al.  Selection of the Number of Principal Components: The Variance of the Reconstruction Error Criterion with a Comparison to Other Methods† , 1999 .

[4]  E. L. García Diez,et al.  Prediction of the Daily Number of Forest Fires , 1999 .

[5]  Richard A. Minnich,et al.  Mapping probability of fire occurrence in San Jacinto Mountains, California, USA , 1993 .

[6]  N. F. F. Ebecken,et al.  Data mining III , 2002 .

[7]  James C. Bezdek,et al.  Clustering with a genetically optimized approach , 1999, IEEE Trans. Evol. Comput..

[8]  J. Faraway,et al.  Time series forecasting with neural networks: a comparative study using the air line data , 2008 .

[9]  Amparo Alonso-Betanzos,et al.  A Neural Network Approach for Forestal Fire Risk Estimation , 2002, ECAI.

[10]  Q. Henry Wu,et al.  A Faster Genetic Clustering Algorithm , 2000, EvoWorkshops.

[11]  Pieter Adriaans,et al.  Data mining , 1996 .

[12]  José Angel Olivas.  Applications of Fuzzy Prototypes: Forest Fire Prediction and Medical Diagnosis , 1999, IC-AI.

[13]  Deng Chao,et al.  Neural network approach for RHR calculation and prediction in fire science , 1996, Proceedings of Third International Conference on Signal Processing (ICSP'96).

[14]  Dougal Drysdale,et al.  Using cone calorimeter data for the prediction of fire hazard , 2002 .

[15]  A. C. Fernandez-Pello,et al.  The Challenge of Fire Prediction , 1994 .

[16]  Lili Yang,et al.  Prediction Of Dwelling Fire Occurrences Using Data Mining Technologies , 2002 .

[17]  Wiktor L. Adamowicz,et al.  A Logit Model for Predicting the Daily Occurrence of Human Caused Forest-Fires , 1995 .