Identifying Community Fire Hazards from Citizen Communication by Applying Transfer Learning and Machine Learning Techniq
- PDF / 2,159,009 Bytes
- 30 Pages / 439.37 x 666.142 pts Page_size
- 52 Downloads / 198 Views
Identifying Community Fire Hazards from Citizen Communication by Applying Transfer Learning and Machine Learning Techniques Zhao-Ge Liu * and Xiang-Yang Li, School of Management, Harbin Institute of Technology, Harbin 150001, China Grunde Jomaas, School of Engineering, University of Edinburgh, Edinburgh EH9 3FG, UK Received: 22 February 2020/Accepted: 20 August 2020
Abstract. A cross-region transfer learning method is proposed to identify community (e.g. car parks, public spaces and shopping centers) fire hazards based on text input provided by community members. The key component of the method, which also accounts for data imbalance, is an improved transfer component analysis that is embedded with a local discriminant analysis to transfer non-local rich knowledge to the fire hazard identification of local communities with an insufficient number of samples. In addition, a fire hazard knowledge map is established and applied to supplement the missing key features for fire hazard identification, and ontology modeling is applied to standardize the text features and reduce the effect of semantic ambiguity brought by cross-region knowledge transfer. The proposed method is verified based on the text data of nine fire hazard classes from Lanzhou and Beidaihe in China. Machine learning experiments show that fire hazard identification performance of all nine classes were improved with the overall accuracy, precision, recall, F1 score and AUC increased by 12%, 15%, 16%, 15% and 15%, respectively. Under data imbalance scenarios, the proposed method outperforms the state of the art methods, such as sampling-based methods, FastText and ULMFiT. The results also show that the proposed method can achieve desired performance with only half of the training samples. These findings illustrate that the proposed method can assist regions by improving fire identification results significantly through knowledge transfer. The proposed approach can be followed to build smart systems for community fire risk management with reasonable performance and high efficiency. Keywords: Community fire hazards, Hazard identification, Citizen communication, Text classification, Machine learning, Transfer learning
*Correspondence should be addressed to: Zhao-Ge Liu, E-mail: [email protected]
1
Fire Technology 2020
1. Introduction In recent years, the fire statistics in normal buildings have gradually improved [1], but in communities (i.e. public places such as car parks and shopping centers), fire statistics showed the opposite trend. As presented in Table 1, both the frequencies and consequences of community fire incidents have been increasing [2–4] (see table caption for what is regarded as a ‘community’ in this paper). Examples of significant fires are the car park fires in Liverpool, UK and Stavanger, Norway, as well as the shopping center fire in Kazan, Russia in 2015, which caused 17 deaths and 55 injuries. These incidents and trends suggest the importance of improving fire risk management within communities. As with other fires, community fire incidents are usually caused
Data Loading...
