Intelligent Multi-Sensor Detection System for Monitoring Indoor Building Fires

Baek, Jae-Seung; Alhindi, Taha J.; Jeong, Young-Seon; Jeong, Myong K.; Seo, Seongho; Kang, Jahyo; Heo, Yoseob

doi:10.1109/jsen.2021.3124266

Cited by 23 publications

(10 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For discrete data, it can be regarded as a simple state classification task, and the corresponding classification situation of each state can be designed in advance. For the input data of the video stream, the video stream can be divided into image frames, and the input node data can be classified into discrete states using an image classification algorithm [23]. These discretization algorithms can be embedded in the IoT devices and implemented by edge computing, or the monitoring data can be transmitted to the cloud for cloud computing.…”

Section: Fire Risk Monitoring Systemmentioning

confidence: 99%

See 1 more Smart Citation

A Trustworthy Classification Model for Intelligent Building Fire Risk

Wang

Chen

2022

IEEE Access

View full text Add to dashboard Cite

The occurrence of intelligent building fires causes huge economic losses to the country and society, and even people's safety. It is necessary to accurately assess the degree of intelligent building fire risk so that the fire emergency management department can make scientific decisions. In this paper, a trustworthy classification model for intelligent building fire risk is proposed, which provides a scientific and reasonable model supporting the classification assessment of intelligent building fire risk. The model integrates Bayesian Network (BN) and software trustworthy computing approach. BN is used to calculate the risk value of attributes that describe the fire risk situation of the intelligent building from 7 profiles. Based on the fire risk attribute values, trustworthy computing is adopted to classify the fire risk into 5 ranks which indicates the severity degree of building fire risk: the higher the rank is, the greater the harm is. Taking the Shanghai Jing'an 11.15 fire as an example, the result confirms that the method proposed in this paper has good theoretical significance and practical value. In addition, we compare our method with 3 fire risk assessment methods in the reference. The comparisons illustrate that the trustworthy classification model proposed in this paper is more comprehensive, rational, and scientific.

show abstract

Section: Fire Risk Monitoring Systemmentioning

confidence: 99%

“…Combining risk indicators and environment context to make empirical judgments on important fire information. 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.…”

Section: Introductionmentioning

confidence: 99%

A Trustworthy Classification Model for Intelligent Building Fire Risk

Wang

Chen

2022

IEEE Access

View full text Add to dashboard Cite

show abstract

“…These rule-based approaches are developed by designing appropriate logic rules based on experimental engineering knowledge. However, they only consider current observations and ignore historical information in the decision-making process, resulting in increased false alarms due to environmental noise or sensor faults [8]. Moreover, directly finding desired rules over high-dimensional data, such as multivariate time series, is extremely difficult due to their complex temporal and intersensor dependency.…”

Section: Introductionmentioning

confidence: 99%

“…In recent years, more advanced data-driven information fusion methods have been proposed [8][9][10][11][12][13]. Among these data-driven approaches, deep learning (DL) has received significant attention due to its effective pattern extraction and recognition capabilities by training from raw data itself.…”

Section: Introductionmentioning

confidence: 99%

Uncertainty Assessment-Based Active Learning for Reliable Fire Detection Systems

Kim

2022

IEEE Access

View full text Add to dashboard Cite

Deep learning technologies, due to their advanced pattern extraction and recognition of highdimensional data, have been widely adopted into multisensor-based fire detection systems. Since deep learning approaches can generate erroneous predictions due to incomplete training datasets, a retraining process over unseen observations is needed. However, storing a large amount of data from continuous multisensor streams and labeling them to create a retraining dataset are costly and time-consuming. In this paper, we propose an active learning framework based on an informative experience memory that is populated with meaningful retraining data by assessing the uncertainty of the data. In the proposed framework, the deep learning model predicts fire occurrence and estimates model uncertainty by taking advantage of a Bayesian neural network using Monte Carlo dropout. By storing only higher uncertain data points into the fixed-size informative experience memory and querying them to the system managers, the storage and labeling costs are minimized while improving performance. To evaluate our active learning framework with different neural network structures, we develop three Bayesian neural networks based on conventional classification networks, including the feedforward neural network, fully convolutional network, and long short-term memory. We further investigate various uncertainty assessment scoring methods for classification tasks such as entropy, BALD, variation ratios, and mean STD. Experiments on a real dataset show that the Bayesian FCN using the BALD assessment method has the highest performance gain with an F1 score of 0.95, with an improvement of 24% using only 700 data points.

show abstract

“…While such efforts have been successful in improving the level of detection compared to single sensor detectors [6]), they typically rely on a range of chemical (e.g. species) detection methods, heat and particle detection [8].…”

Section: Introductionmentioning

confidence: 99%

A Novel Method for Smart Fire Detection Using Acoustic Measurements and Machine Learning: Proof of Concept

et al. 2022

View full text Add to dashboard Cite

Fires are a major hazard resulting in high monetary costs, personal suffering, and irreplaceable losses. The consequences of a fire can be mitigated by early detection systems which increase the potential for successful intervention. The number of false alarms in current systems can for some applications be very high, but could be reduced by increasing the reliability of the detection system by using complementary signals from multiple sensors. The current study investigates the novel use of machine learning for fire event detection based on acoustic sensor measurements. Many materials exposed to heat give rise to acoustic emissions during heating, pyrolysis and burning phases. Further, sound is generated by the heat flow associated with the flame itself. The acoustic data collected in this study is used to define an acoustic sound event detection task, and the proposed machine learning method is trained to detect the presence of a fire event based on the emitted acoustic signal. The method is able to detect the presence of fire events from the examined material types with an overall F-score of 98.4%. The method has been developed using laboratory scale tests as a proof of concept and needs further development using realistic scenarios in the future.

show abstract

Intelligent Multi-Sensor Detection System for Monitoring Indoor Building Fires

Cited by 23 publications

References 34 publications

A Trustworthy Classification Model for Intelligent Building Fire Risk

A Trustworthy Classification Model for Intelligent Building Fire Risk

Uncertainty Assessment-Based Active Learning for Reliable Fire Detection Systems

A Novel Method for Smart Fire Detection Using Acoustic Measurements and Machine Learning: Proof of Concept

Contact Info

Product

Resources

About