May Salama

A new hybrid algorithm for fire vision recognition

This paper proposes a novel method to detect fire and/or smoke in real-time by processing the video data generated by an ordinary camera monitoring a scene. The objective of this work is recognizing and modeling fire shape evolution in stochastic visual phenomenon. It focuses on detection of fire in image sequences by applying a new hybrid algorithm that depends on optimizing the back-propagation algorithm, after canny edge detection, for determining the smoke and fire boundaries. Another clue is used in the fire detection algorithm that detects smoke and fire flicker by analyzing the video in the wavelet domain. Color variations in flame regions are detected by computing the spatial wavelet transform of moving fire-colored regions. Experimental results show that the proposed algorithm is very successful in detecting fire and/or smoke.

An Improved DV-hop Localization Algorithm Based on Modified Hop-Size

DV-Hop algorithm is a range free algorithm that uses hop distance in its calculations. An improved DV-Hop algorithm is proposed by changing the average hop-size. The evaluation of the performance was carried out on wireless sensor network localization. Sensors were placed according to two functions, pseudo random and sobol quasi random. The latter was chosen because it guarantees space coverage when space dimensions increase. Localization errors are compared to those of the basic DV-Hop algorithm. The proposed algorithm proved effectiveness in remarkably decreasing the localization error of the sensors. An important application is in a nuclear power plant process control test facility (NPCTF) where a wireless sensor network is an effective tool to collect data for fault diagnostics. The location of the fault is crucial. Hence, minimum localization error is of utmost importance.

C38. Appraisal of different particle filter resampling schemes effect in robot localization

This paper considers the effect of the Resampling schemes in the behavior of Particle Filter (PF) based robot localizer. The investigated schemes are Multinomial Resampling, Residual Resampling, Residual Systematic Resampling, Stratified Resampling and Systematic Resampling. An algorithm is built in Matlab environment to host these schemes. The performances are evaluated in terms of computational complexity and error from ground truth and the results are reported. The results showed that the localization plan which adopts the Systematic or Stratified Resampling scheme achieves higher accuracy localization while decreasing consumed computational time. However, the difference is not significant. Moreover, a particle excitation strategy is proposed. This strategy achieved significant improvement in the behavior of PF based robot localization.

E-Health in Egypt: A Brief Review

E-health is defined as the use of information and communications technologies (ICT) in supporting health and health-related fields. The goal of this review is to survey efforts and accomplishments performed on e-health systems in Egypt, assess their potential impact, and guide future implementations and evaluations. The review shows that Egypt has still a long way to go in realizing a fully integrated efficient e-health system, but there is an undeniable hope that it has started on the long tedious journey towards e-health system.

C24. An Enhanced Particle / Kalman Filter for Robot Localization

This paper investigates the effect of using different filters namely: Kalman filter (KF), Particle Filter (PF) and a proposed enhanced particle / Kalman (EPKF) filter based robot localizer. An algorithm is built in Matlab environment to host these filters. The performances of these filters are evaluated in terms of computational time and error from ground truth and the results are reported. The results showed that the proposed localization plan which adopts the particle filter as initialization step to Kalman filter achieves higher accuracy localization while, the computational cost is not significant.

Effect of Mechanical Ventilation on Controlling Fire in Closed Room

The work models and simulates fire growth in a closed room. It examines the effect of various airflow rates of mechanical ventilation on wall and ceiling temperatures, Heat Release Rate, oxygen and carbon dioxide rates when smoke/fire is detected. The objective of the simulation is to find a way to control the temperature, fire growth and gas rates in the room until fire fighters have control of the situation. The model assumes that the ventilators are continuously operating. The results of the simulation show that there is a certain airflow rate for the mechanical ventilators that achieves the goal, thus avoiding fire breakout. The modeling and simulation is carried by CFAST which is a zone model tool for fire modeling and simulation.