Development of neural network committee machines for automatic forest fire detection using lidar

Lidar has considerable potential as an early forest "re detection technique, presenting considerable advantages when compared to the passive detection methods based on infrared cameras currently in common use, due to its higher sensitivity, ability to accurately locate the "re and the fact that it does not need line of sight to the 3ames. The method has recently been demonstrated by the authors, but its automation requires the availability of a rapid signal analysis technique, for prompt alarm emission whenever required. In the present paper a novel method of classifying lidar signals using committee machines composed of neural networks is proposed. A new method based on ROC curves and the Neyman-Pearson criterion is used to choose the optimal number of training epochs for each neural networkin order to avoid over"tting. The best committee machine, obtained on the basis of these principles and selected to lead to the lowest percentage of false alarms for a true detection percentage of 90% for a test set created by adding random noise to patterns obtained experimentally, was composed of three single-layer perceptrons and presented a true detection e:ciency of 94.4% and 0.553% of false alarms in the validation set.

[1]  C. E. Harris,et al.  Laser Radar Systems , 1991 .

[2]  Gérard Dreyfus,et al.  Single-layer learning revisited: a stepwise procedure for building and training a neural network , 1989, NATO Neurocomputing.

[3]  S. Chakrabarti,et al.  Robust radar target classifier using artificial neural networks , 1995, IEEE Trans. Neural Networks.

[4]  Christopher M. Bishop,et al.  Current address: Microsoft Research, , 2022 .

[5]  PrecheltLutz.  Automatic early stopping using cross validation , 1998 .

[6]  Andrei B. Utkin,et al.  Detection of small forest fires by lidar , 2002 .

[7]  Rui Vilar,et al.  Estimation of required parameters for detection of small smoke plumes by lidar at 1.54 μm , 2000 .

[8]  Gérard Dreyfus,et al.  Handwritten digit recognition by neural networks with single-layer training , 1992, IEEE Trans. Neural Networks.

[9]  D. Signorini,et al.  Neural networks , 1995, The Lancet.

[10]  Andrei B. Utkin,et al.  Forest-fire detection by means of lidar. , 2002 .

[11]  Lutz Prechelt,et al.  Automatic early stopping using cross validation: quantifying the criteria , 1998, Neural Networks.

[12]  Paul C. Simon,et al.  Instrument Development for Atmospheric Research and Monitoring , 1997 .

[13]  John W. Fisher,et al.  Target discrimination in synthetic aperture radar using artificial neural networks , 1998, IEEE Trans. Image Process..

[14]  U. Panne.  Laser remote sensing , 1998 .

[15]  Christian Lebiere,et al.  The Cascade-Correlation Learning Architecture , 1989, NIPS.

[16]  J. Nazuno.  Haykin, Simon. Neural networks: A comprehensive foundation, Prentice Hall, Inc. Segunda Edición, 1999 , 2000 .

[17]  W Kinzel,et al.  Receiver operating characteristics of perceptrons: influence of sample size and prevalence. , 1999, Physical review. E, Statistical physics, plasmas, fluids, and related interdisciplinary topics.

[18]  Armando FERNANDES,et al.  Recognition of Smoke Signatures in Lidar Signal with a Perceptron , 2002 .

[19]  Petri Koistinen,et al.  Using additive noise in back-propagation training , 1992, IEEE Trans. Neural Networks.

[20]  Mahesan Niranjan,et al.  Parcel: Feature Subset Selection in Variable Cost Domains , 1998 .

[21]  Alexander P. Lavrov,et al.  Application of lidar at 1.54 μm for forest fire detection , 1999, Remote Sensing.