Real-time fire detection based on CNN and inception V3 algorithms

Abstract

Fire is an abnormal event that can cause significant damage to lives and property within a very short time. The main cause of fire disaster includes a human error or system failure which results in severe loss of human life and other damages. Traditional fire alarms are based on sensors that require proximity for activation. They need human involvement to confirm a fire. To overcome these limitations, vision-based real-time fire detection has been enabled in surveillance devices. Once fire appears in any camera, the approach can detect it and send a signal to respective officers of the fire region. This work focused on an intelligent approach using the Deep Learning model for preventing fire hazards from going out of control in high-fire-risk areas. Deep Learning models are effective for fire detection. Convolutional Neural Networks outperform other algorithms in terms of accuracy. In this work Convolution, Neural Network model Inception V3 is used to detect fire indoors and outdoors and protect the surroundings and living beings.

Diseño e implementación de dos dispositivos biomédicos para pacientes con Síndrome de Apnea Obstructiva del Sueño (SAOS) basados en la detección de apneas e hipopneas y rehabilitación por medio de estimulación eléctrica

“…Este sensor genera a su salida una magnitud de voltaje, el cual puede ser captado por un conversor análogo digital (CAD) para su posterior almacenamiento o procesamiento. Esta tarjeta ha sido utilizada en algunos proyectos relacionados para la caracterización de músculos [118][119], desarrollo de sistemas biónicos [120][121][122], entre otros. a b Figura 28. a. Distribución de pines sensor Mioware y b. Sensor de electromiografía Myoware Fuente: [117] Dentro de las principales características del sensor están:…”