Comparative Study of Different Data Mining Techniques in Predicting Forest Fire in Lebanon and Mediterranean

Hamadeh, Nizar; Karouni, Ali; Daya, Bassam; Chauvet, Pierre

doi:10.1007/978-3-319-56994-9_51

Cited by 1 publication

(1 citation statement)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These techniques were applied on 34575 samples of road accidents in Hong Kong for the year 2008 that are categorized into three categories respectively accident, vehicle and casualty. This perspective showed that Random Forest Tree outperforms the other models of classification based on the higher accuracy rate of correct classification.Hamdeh et.al [5] was made a comparative study of performance of several data mining applications suchbas Neural network ( MLP) in one hidden layer , Decision tree J48, Fuzzy Logic, Linear Descriminant Analysis (LDA), and Support Vector Machine (SVM). This study demonstrated that decision tree outperformed all others with a high accuracy (97.8%) in forest fire prediction as aim to decrease the fire occurrence in Lebanon by using four main meteorological parameters (Yemperature, Humidity, Precipittion, and Wind speed).…”

Section: Introduction and Related Workmentioning

confidence: 99%

Comparative Study Between Decision Trees and Neural Networks to Predictfatal Road Accidents in Lebanon

Farhat¹,

Karouni²,

Daya³

et al. 2019

5th International Conference on Computer Science, Information Technology (CSITEC 2019)

Self Cite

View full text Add to dashboard Cite

Nowadays, road traffic accidents are one of the leading causes of deaths in this world. It is a complex phenomenon leaving a significant negative impact on human's life and properties. Classification techniques of data mining are found efficient to deal with such phenomena. After collecting data from Lebanese Internal Security Forces, data are split into training and testing sets using 10-fold cross validation. This paper aims to apply two different algorithms of Decision Trees C4.5 and CART, and various Artificial Neural Networks (MLP) in order to predict the fatality of road accidents in Lebanon. Afterwards, a comparative study is made to find the best performing algorithm. The results have shown that MLP with 2 hidden layers and 42 neurons in each layer is the best algorithm with accuracy rate of prediction (94.6%) and area under curve (AUC 95.71%).

show abstract

Section: Introduction and Related Workmentioning

confidence: 99%