What is known and what remains unexplored: A review of the firefighter information technologies literature

Weidinger, Julian

doi:10.1016/j.ijdrr.2022.103115

Cited by 6 publications

(3 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Table 2 shows the 25 attributes available in the CNVVF dataset with the rate of missing values, which are imputed as presented in the supplementary material. 1 In order to automatically identify relevant interventions we implement an algorithm that links messages of the SMS dataset to the interventions in the CNVVF dataset, which is discussed with more detail in the supplementary material as its presentation is not central with respect to the scope of this work. In summary, we first pre-filter each message in the SMS dataset by looking for candidate records in the CNVVF dataset that match according to different criteria.…”

Section: Materials and Data Preprocessingmentioning

confidence: 99%

“…To tackle this limitation, here we present an artificial intelligence (AI)-based decision support system (DSS) that automatically identifies the relevant interventions, an issue that has never been tackled in the literature to the best of our knowledge. Nevertheless, some researchers and practitioners have recently started investigating the use of AI to develop services able to support firefighters' activities in the different phases of the emergency, such as the preparation, the response, the recovery and the mitigation [1]. In our case, the identification of relevant events would help the control room to develop services for better management of the resources and to reduce the time required to identify an appropriate response, so that we fall within both the preparation and the response phases.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Cascade of Learners for Firemen’ Emergency Events Classification

Caruso,

Soda,

Giammichele

et al. 2023

IEEE Access

View full text Add to dashboard Cite

The main objective of firefighters is to optimise readiness in response to hazardous events and to minimise their collateral effects. In this context, few but growing research is investigating machine learning algorithms to support firefighters' work. Hence, this paper presents a decision support system to promptly identify relevant interventions, which are those events for which the national control room needs to alert the competent authorities because they could be dangerous for the community. The aim is to provide firefighters useful information for the management of such interventions and of the available resources. We define a set of new hand-crafted features specifically designed for the task, which catch both static and dynamic characteristics of the events. Furthermore, we design a learning approach based on a cascade of binary classifiers, which exploits the ability of most of the available classification algorithms to learn binary functions and it takes advantage of some characteristic of the dataset. The experiments were performed in leave-one-out on a real-world data set provided by the Italian National Fire Corps, analysing how the system works to distinguish among relevant and not-relevant interventions, both at the time of the call and during the events updates. The results show that machine learning-based decision support system significantly outperform the human operator. INDEX TERMS Firefighting operations, supervised learning approaches.Open Access funding provided by 'Università "Campus Bio-Medico" di Roma' within the CRUI CARE Agreement

show abstract

Section: Materials and Data Preprocessingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A Cascade of Learners for Firemen’ Emergency Events Classification

Caruso,

Soda,

Giammichele

et al. 2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…On the other hand, technological development has led to the Manhattanizing and enlargement of buildings [7][8][9]. The number of building users is increasing and interior building structures are complicated, which has caused difficulties in rescue and evacuation [10][11][12]. As a result, some research indicates the necessity of an advanced management system to tackle difficult fire-response scenarios [13][14][15].…”

Section: Introductionmentioning

confidence: 99%

The Prediction of Fire Disaster Using BIM-Based Visualization for Expediting the Management Process

2023

View full text Add to dashboard Cite

As buildings become larger and more complex, fire disaster management is of great concern. A building’s fire response and/or rescue system plays a pivotal role in minimizing fire victims and loss. To improve the current fire disaster management, it is important to link building (static) information, i.e., structural elements, fire escapes, and openings, with the fire (dynamic) information. When a building fire occurs, real-time fire information is required to be effectively linked with the on-site building information because the fire rescue teams, in most cases, are unfamiliar with the buildings. This study has proposed a Building Information Model (BIM)-based fire disaster management process which can digitally track the building data and the dynamic fire data simultaneously. To expedite this algorithm, an application program, i.e., Smart Fire Rescue Management (SFRM) has been developed using Revit™ software. A real-case project has been applied to evaluate the feasibility of the system. An expert survey has also been conducted to analyze the practical applicability. As a result, the system has been evaluated as exceptional, but it is necessary to upgrade the application from the practitioner’s viewpoint. The SFRM contributes to expediting the conventional disaster management process by enhancing the efficiency of the building fire response and/or rescue system.

show abstract