Fire Detection using Artificial Intelligence for Fire-Fighting Robots

Ramasubramanian, Sreesruthi; Muthukumaraswamy, Senthil Arumugam; Sasikala, A.

doi:10.1109/iciccs48265.2020.9121017

Cited by 24 publications

(4 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…When numerous fires were to be detected, the results produced using the Haar Cascade Classifier were not particularly accurate. To boost accuracy, transfer learning from a pre-trained YOLOv3 model was employed to train the model for fire detection (Ramasubramanian et al, 2020).…”

Section: Fire Sensing and Extinguishing Technologiesmentioning

confidence: 99%

Design and implementation of an autonomous fire-extinguishing robot with SMS alert functionality

Kolajo,

Ogbuju,

Adebayo

et al. 2024

KJSET

View full text Add to dashboard Cite

Fire outbreak represents a formidable threat, capable of causing loss of life, property destruction, and permanent injuries. Firefighters bravely confront these hazards, placing themselves at serious risk to protect communities. Despite the inherent dangers, their selfless service remains vital. Among recent technological advancements, firefighting robots have emerged as significant tools for mitigating such risks. These robots utilize machine learning and cutting-edge sensor technologies to enhance fire detection accuracy, minimizing false alarms. To improve the performance of the fire robot, this study designed and implemented an Arduino UNO microcontroller based on the ATmega32 and developed using C++ language. In addition to equipping it with SMS capability that allows it to notify the concerned entity about an outbreak, the developed robot operates autonomously thereby minimizing human error in its operation. With the aid of the ultrasonic sensors, the robot navigates and avoids obstacles collision with high precision. Integrated with flame and smoke sensors controlled by the microcontroller ensures swift fire detection. By autonomously sprinkling water from a mounted container, it effectively suppresses fires. Through this innovative design, the study aims to bolster fire response capabilities, reducing reliance on human intervention and enhancing safety for both firefighters and civilians. From the performance evaluation carried out on the developed robot, it was observed that the robot has exhibited an effective performance in detecting and extinguishing fires using the various sensors.

show abstract

Section: Fire Sensing and Extinguishing Technologiesmentioning

confidence: 99%

Design and implementation of an autonomous fire-extinguishing robot with SMS alert functionality

Kolajo,

Ogbuju,

Adebayo

et al. 2024

KJSET

View full text Add to dashboard Cite

show abstract

“…Penelitian ini mengembangkan sistem deteksi kebakaran yang menggunakan Artificial Neural Network (ANN) dan Tensor Neural Network (TNN) untuk memproses data sensor yang terkait dengan kebakaran. Sistem tersebut kemudian digunakan untuk mengendalikan robot pemadam kebakaran secara otomatis dan mampu mengenali kebakaran dengan tingkat keberhasilan sebesar 98% [11]. Penelitian yang dilakukan Hongyu, Huang, dkk.…”

Section: Tinjauan Pustakaunclassified

Sistem Pendeteksi Api Dini Berbasis Raspberry Pi Termonitoring Aplikasi Telegram

Prakoso,

Pahlevi,

Shtevanie

2023

logic

View full text Add to dashboard Cite

Kebakaran merupakan peristiwa yang meninbulkan terjadinya api, dimana bencana kebakaran dapat menimbulkan kerugian yang sangat besar dan dapat mengancam keselamatan jiwa. Peristiwa kebaran lebih sering disebabkan oleh kelalaian manusia. Banyak penelitian mengenai permasalahan ini, namun mereka hanya berfokus pada akurasi pendeteksian tanpa mempertimbangkan mobilitas dan kemudahan yang pada kenyataanya ini sangat dibutuhkan dalam merancang sistem pendeteksian api. Penelitian ini dirancang untuk membuat sistem pendeteksi api berbasis kamera didalam ruangan, dengan memanfaatkan aplikasi Bot Telegram sebagai layanan notifikasi saat terjadinya kebaran. Pada sistem ini menggunakan TensorFlow Lite sebagai kerangka kerja untuk pembelajaran mesin dan model Yolov5 sebagai model pretraining pendeteksi api lalu Mini PC (Raspberry Pi 4 Model B) sebagai pengolah data dan alat pengontrol sistem ini. Setelah dilakukan pengujian sistem pendeteksi api ini mendapatkan akurasi sebesar 85%, dan membuktikan bahwa sistem ini dibangun dengan mobilitas yang baik tanpa mengurangi akurasi pendeteksian api

show abstract

“…However, the weaknesses of using flame sensors were solved using deep learning to detect fire in real-time, with detailed outcomes relative to machine learning [24].…”

Section: Literature Reviewmentioning

confidence: 99%

A Soft Actor-Critic Approach to Complex Dynamic Flight Control for a Flying Firefighter Robot with Water-Jet Propulsion

Syafiqah Lagiman,

Abu Ubaidah Shamsudin,

Zubair Adil Soomro

et al. 2023

ARASET

View full text Add to dashboard Cite

Most of the robots nowadays become more intelligent in line AI technology are being applied in industry. Deep Reinforcement Learning (DRL) is involves gaining knowledge by making errors and fixing them. Hence, the robot will learn from mistakes and keep improving by process. Deep Reinforcement Learning is a kind of machine learning method that focuses on teaching models to act in ways that maximize rewards in an environment. Since the algorithm receives feedback in the form of rewards or consequences for its actions, this is often accomplished through trial and error. Soft Actor Critic (SAC) is the most recent Deep Reinforcement Learning technique. In this research, to design a simulation robot that can be trained by using Soft-Actor Critic. This purpose is to train and evaluate the performance of robot in MATLAB and VMware platform. According to this study, robots might learn and adapt to their surroundings more quickly and effectively with the aid of a system that utilises a suitable reward together with a guidance technique. Decisively, the simulation shows that the Soft Actor Critic algorithm successfully simulates the control of flying fire fighter robot in terms of stability.

show abstract

Fire Detection using Artificial Intelligence for Fire-Fighting Robots

Cited by 24 publications

References 7 publications

Design and implementation of an autonomous fire-extinguishing robot with SMS alert functionality

Design and implementation of an autonomous fire-extinguishing robot with SMS alert functionality

Sistem Pendeteksi Api Dini Berbasis Raspberry Pi Termonitoring Aplikasi Telegram

A Soft Actor-Critic Approach to Complex Dynamic Flight Control for a Flying Firefighter Robot with Water-Jet Propulsion

Contact Info

Product

Resources

About