George E. Sakr

Efficient forest fire occurrence prediction for developing countries using two weather parameters

Forest fire occurrence prediction plays a major role in resource allocation, mitigation and recovery efforts. This paper compares two artificial intelligence based methods, artificial neural networks (ANN) and support vector machines (SVM), utilizing a reduced set of weather parameters. Using a reduced set of parameters results in an efficient and reduced cost prediction system especially for developing countries. In this paper the aim is to predict forest fire occurrence by reducing the number of monitored features, and eliminating the need for weather prediction mechanisms. The reason is to reduce errors due to inaccuracies in weather prediction. The challenge is to choose a limited number of easily measurable features in the aim of reducing the cost of the system and its maintenance. At the same time, the chosen features must have a high correlation with the risk of fire occurrence. A literature review of forest fire prediction methods divided into systems/indices, and artificial intelligence is provided. The two fire danger prediction algorithms utilize relative humidity and cumulative precipitation to output a risk estimate. The assessment of these algorithms, using data from Lebanon, demonstrated their ability to accurately predict the risk of fire occurrence on a scale of four levels.

Artificial intelligence for forest fire prediction

Forest fire prediction constitutes a significant component of forest fire management. It plays a major role in resource allocation, mitigation and recovery efforts. This paper presents a description and analysis of forest fire prediction methods based on artificial intelligence. A novel forest fire risk prediction algorithm, based on support vector machines, is presented. The algorithm depends on previous weather conditions in order to predict the fire hazard level of a day. The implementation of the algorithm using data from Lebanon demonstrated its ability to accurately predict the hazard of fire occurrence.

Multi level SVM for subject independent agitation detection

The need to automate the detection of agitation for dementia patients is a major requirement for caregivers. This research aims at detecting the agitation status of the subjects using soft computing techniques that does not require supervision beyond the training phase. An autonomous multi-sensory device has been developed to achieve automatic assessment of agitation and to control stimulation that will reduce the agitation level automatically. The focus of this paper is the agitation detection algorithm. Three vital signs are monitored for agitation detection: the Heart Rate (HR) the Galvanic Skin Response (GSR) and Skin Temperature (ST). These measures are fed into a new SVM architecture: “The Multi level SVM learning machine”. Results show very high detection accuracy of agitation, quick adaptation to the subject and a strong correlation between the physiological signals monitored and the emotional states of the subjects. The result is a learning algorithm that is “Subject-Independent”.

Subject independent agitation detection

The need to automate the detection of agitation for dementia patients is a major requirement for caregivers. This research aims at sensing and recognizing negative emotions specifically ldquostressrdquo for patients with dementia. An autonomous multi-sensory device has been developed to achieve automatic assessment of agitation and to control stimulation that will reduce the agitation level automatically. The focus of this paper is the agitation detection algorithm. Three vital signs are monitored for agitation detection: the Heart Rate (HR) the Galvanic Skin Response (GSR) and Skin Temperature (ST). These measures are fed into an SVM based learning machine. Results show accurate detection of agitation, quick adaptation to the subject and a strong correlation between the physiological signals monitored and the emotional states of the subjects. The result is a learning algorithm that is ldquoSubject-Independentrdquo.

VC-based confidence and credibility for support vector machines

Assigning a confidence and a credibility measures is a challenging stochastic inference problem. Some algorithms only yield the predicted value without evaluating the measure of confidence or credibility over the decision. Support vector machines (SVM) is one algorithm that showed state-of-the-art decision accuracy but lacks a measure of confidence and credibility over the decisions. In this paper we propose a new confidence measure based on the Vapnik and Chervonenkis (VC) dimension of a learning algorithm and the notion of complexity as defined by Kolmogorov. We also propose a new credibility measure based on the VC dimension. The resulting confidence and credibility measures are then tested on the well-known US postal handwritten digit recognition, on the Wisconsin breast cancer dataset and are also tested for agitation detection. The results show high and improved correlation between the decision and the confidence/credibility measures compared to Vovk’s and Platt’s methods.

Digit recognition with confidence

Assigning a confidence measure is a challenging stochastic inference problem. Some algorithms only yield the predicted value without evaluating the measure of confidence over the decision. Support vector machines is one algorithm that showed state of the art decision accuracy but lacks a measure of confidence over the decisions. In this paper we propose a confidence measure based on the VC (Vapnik and Chervonenkis) dimension of a learning algorithm. The resulting confidence measure is then tested on the well known US postal handwritten digit recognition. The results show high and improved correlation between the decision and the confidence measure.