en 2-Electronic Components Technology Electronic Components Technology Research Paper Research Paper <span style="font-size:10.0pt"><span style="font-family:&quot;Times New Roman&quot;,serif">Fires in indoor spaces such as residential and office buildings pose significant threats to human lives and property, causing substantial damage each year. Early and accurate fire detection plays a critical role in mitigating these risks and ensuring timely responses. However, conventional methods such as smoke sensors, temperature indicators, and standalone computer vision models suffer from limitations like false alarms, delayed detection, and high hardware demands. To address these challenges, we propose a novel three-layer verification framework for indoor fire detection to reduce false alarms, integrating smoke sensors, computer vision, and temperature monitoring into a multi-modal validation framework. The process begins with smoke sensors detecting potential fire incidents. The custom-trained YOLOv11n computer vision model verifies the detection using predefined thresholds, allowing immediate response without waiting for temperature escalation. If the computer vision model does not confirm the fire, the system initiates a temperature check as a final validation layer. Experimental evaluation of our model demonstrates a significantly high precision of 0.979 and a recall of 0.971. This layered approach ensures comprehensive detection, balancing reliability and resource efficiency. Our proposed hybrid AI-physical systematic framework demonstrates significant potential in reducing false alarms, improving detection accuracy, and prioritizing methodological scalability over industrial hardware. It lays the foundation for more reliable and energy-efficient fire safety solutions in smart buildings and industrial safety applications.</span></span> False Alarm, Internet of Things (IoT), Computer Vision, Indoor Fire. 3733 3733 http://ijeee.iust.ac.ir/browse.php?a_code=A-10-5049-7&slc_lang=en&sid=1 Kausar Ahmed kausar.ahmed.cse@ulab.edu.bd 1800319475328460017652 1800319475328460017652 No Department of Computer Science and Engineering (CSE), University of Liberal Arts Bangladesh (ULAB), Dhaka, Bangladesh Bibhor Regan Gomes regan.gomes.cse@ulab.edu.bd 1800319475328460017653 1800319475328460017653 No Department of Computer Science and Engineering (CSE), University of Liberal Arts Bangladesh (ULAB), Dhaka, Bangladesh S.M. Jobair Hossain jobair.hossain.cse@ulab.edu.bd 1800319475328460017654 1800319475328460017654 No Department of Computer Science and Engineering (CSE), University of Liberal Arts Bangladesh (ULAB), Dhaka, Bangladesh Emran Khan Musa emran.khan.cse@ulab.edu.bd 1800319475328460017655 1800319475328460017655 No Department of Computer Science and Engineering (CSE), University of Liberal Arts Bangladesh (ULAB), Dhaka, Bangladesh Fuyad Hasan Bhoyan fuyad.hasan.cse@ulab.edu.bd 1800319475328460017656 1800319475328460017656 No Department of Computer Science and Engineering (CSE), University of Liberal Arts Bangladesh (ULAB), Dhaka, Bangladesh Md Humaion Kabir Mehedi humaion.kabir.mehedi@g.bracu.ac.bd 1800319475328460017657 1800319475328460017657 No Department of Department of Computer Science and Engineering (CSE), BRAC University, Dhaka, Bangladesh. Jia Uddin jia.uddin@wsu.ac.kr 1800319475328460017658 1800319475328460017658 Yes AI and Big Data Department, Endicott College, Woosong University, Daejeon, 34606, Republic of Korea.