Recurrent Trend Predictive Neural Network for Multi-Sensor Fire Detection

Abstract

We propose a Recurrent Trend Predictive Neural Network (rTPNN) for multi-sensor fire detection based on the trend as well as level prediction and fusion of sensor readings. The rTPNN model significantly differs from the existing methods due to recurrent sensor data processing employed in its architecture. rTPNN performs trend prediction and level prediction for the time series of each sensor reading and captures trends on multivariate time series data produced by multi-sensor detector. We compare the performance of the rTPNN model with that of each of the Linear Regression (LR), Nonlinear Perceptron (NP), Multi-Layer Perceptron (MLP), Kendall-τ combined with MLP, Probabilistic Bayesian Neural Network (PBNN), Long-Short Term Memory (LSTM), and Support Vector Machine (SVM) on a publicly available fire data set. Our results show that rTPNN model significantly outperforms all of the other models (with 96% accuracy) while it is the only model that achieves high True Positive and True Negative rates (both above 92%) at the same time. rTPNN also triggers an alarm in only 11 s from the start of the fire, where this duration is 22 s for the second-best model. Moreover, we present that the execution time of rTPNN is acceptable for real-time applications.

A Trustworthy Classification Model for Intelligent Building Fire Risk

“…Attribute decomposition is based on daily fire-fighting practice and related work [6][7][8][9]18,25,27], as well as the Chinese fire alarm and emergency rescue classification standard [3]. The process of attribute decomposition is demonstrated in figure 3.…”

“…An intelligent multi-sensor detection system [22,23] is established for monitoring building fires. Deep learning [24] and neural network [25] methods are adopted to process diverse sensor signals in real-time. The firebird model [26] proposes a data-driven method to extract information about fire risk and introduces time-related dynamic risks, which can be updated by fire inspection checks every time.…”

Fuzzy Neural Networks to Multi-source Information

“…For target recognition systems with information fusion, it is better suited to handle the fusion of feature layers. As feature spaces consisting of multiple source features are usually very large, artificial neural networks have great potential to solve these problems [19][20].…”

Overheating fault alarming for compact insulated busways in buildings by gas sensing

“…Various elements such as image (including the inferred image), temperature, smoke, heat, and gases (CO, CO 2 , etc.) are detected by multiple sensors and used for decision in fire alarm (Chen and Fu, 2012;Lin and Wang, 2017;Sarwar et al, 2018;Luo et al, 2019;Nakip et al, 2021;Wu et al, 2021;Dai et al, 2022;Kewon et al, 2022;Li et al, 2022). With the development of modern sensor technology, especially the application of high-sensitivity gas sensors in fire alarm systems, we can reduce the false alarms caused by other signal interference and get better accuracy than before.…”