Fire Detection and Fire Signal Processing

Dear Colleagues,

Fire, a complex combustion process involving oxidative reactions that release heat, light, smoke, and gaseous byproducts, poses inherent risks to human societies and ecosystems. The scientific foundation of this Special Issue, titled ‘Fire Detection and Fire Signal Processing’, lies in understanding the physical and chemical signatures of fire evolution, from incipient smoldering (low-temperature, smoke-dominated) to fully developed flames (high-temperature, radiation-intensive). Traditional detection systems rely on basic sensing principles, such as ionization detectors, photoelectric detectors and thermal, face fundamental limitations rooted in signal ambiguity: non-fire sources (e.g., kitchen steam, industrial dust) often produce signals indistinguishable from early fire, leading to false alarms, while slow signal response or limited sensing range delays detection of fast-spreading fires (e.g., wildfires, electrical blazes).

Advancements in signal processing, sensor technology, and data science have transformed the field. Modern fire detection leverages interdisciplinary knowledge: materials science for high-sensitivity sensors, signal processing for noise reduction, artificial intelligence for feature extraction, and IoT for real-time data transmission. For instance, multi-sensor fusion integrates data from smoke, temperature, and gas sensors to exploit complementary fire signatures, addressing the limitations of single-sensor systems, while flame flicker—characterized by a frequency range of 1–20 Hz—can be distinguished from artificial light via spectral and temporal signal analysis.

This Special Issue of Fire aims to develop rapid, accurate, and adaptable fire detection systems that identify incipient fire events while minimizing false triggers. This objective encompasses three key pillars: (1) Enhancing signal sensitivity to detect faint, early-stage fire signatures (e.g., trace gas emissions, subtle temperature changes) before fires escalate; (2) improving signal specificity to distinguish fire signals from non-fire interferents (e.g., dust, humidity, artificial flames) using advanced data analytics; (3) ensuring system adaptability to diverse environments, from confined indoor spaces to large outdoor areas, while optimizing energy efficiency and real-time performance. Ultimately, the research seeks to bridge the gap between sensing hardware and data processing, creating solutions that safeguard lives, property, and the environment through proactive, reliable fire detection.

Original research articles, reviews, and case studies showing the results of experiments, theoretical modeling, and numerical simulations are welcome. Research areas may include (but are not limited to) the following:

Energy-Efficient and Sustainable Systems: Designing low-power sensors and self-powered detection devices (e.g., solar-powered wildfire monitors) to extend operational life in remote areas and reduce environmental impact.

Multi-Sensor Fusion for Heterogeneous Data: Exploring techniques to integrate data from diverse sensors (e.g., optical, thermal, gas, acoustic) and non-traditional sources (e.g., satellite imagery for wildfires) to enhance detection accuracy and coverage.

Specialized Detection for Emerging Hazards: Addressing unique fire risks, such as lithium-ion battery thermal runaway, large space, refrigeration house, wildfires and so on.

AI-Driven Signal Classification: Developing robust machine learning and deep learning models to analyze complex fire signatures, especially in noisy environments (e.g., industrial dust, extreme weather), reducing false alarms and improving detection speed.

Edge Computing for Real-Time Processing: Optimizing signal processing algorithms for edge devices (e.g., smart detectors) to reduce latency, enable real-time alerts, and minimize reliance on cloud connectivity—critical for remote or low-bandwidth environments.

Human–Machine Interface Optimization: Enhancing alarm clarity and emergency response coordination, such as location-specific alerts or integration with smart home/industrial control systems to automate safety protocols (e.g., sprinkler activation, door locking).

We look forward to receiving your contributions.

Dr. Tian Deng
Dr. Shu Wang
Dr. Wenbo Xu
Dr. Andreas Nienkötter
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 250 words) can be sent to the Editorial Office for assessment.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Fire is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• early fire detection
• anti-false technology
• smart fire sensor
• specialized fire detection
• intelligent fire warning
• reliable fire detection network
• week signal processing
• emergency rescue platform