A Hybrid Framework for Expediting Emergency Vehicle Movement on Indian Roads

Raman, Abhishek; Kaushik, S. Sivaram; Rao, K. V. S. Rajeswara; Moharir, Minal

doi:10.1109/icimia48430.2020.9074933

Cited by 18 publications

(2 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[37][38][39][40] Visualbased models mainly used deep learning with variable performance (AUC = 0.78-1.00) [40][41][42] while hybrid models incorporated both audio and image inputs and typically relied on deep learning yield strong results (0.86-0.98). 40,43 The performance of these models indicates the viability of employing ML to detect ambulances and expedite their passage through intersections and traffic congestion.…”

Section: Discussionmentioning

confidence: 99%

Applications and Performance of Machine Learning Algorithms in Emergency Medical Services: A Scoping Review

Alrawashdeh,

Alqahtani,

Alkhatib

et al. 2024

Prehosp. Disaster med.

View full text Add to dashboard Cite

Objective: The aim of this study was to summarize the literature on the applications of machine learning (ML) and their performance in Emergency Medical Services (EMS). Methods: Four relevant electronic databases were searched (from inception through January 2024) for all original studies that employed EMS-guided ML algorithms to enhance the clinical and operational performance of EMS. Two reviewers screened the retrieved studies and extracted relevant data from the included studies. The characteristics of included studies, employed ML algorithms, and their performance were quantitively described across primary domains and subdomains. Results: This review included a total of 164 studies published from 2005 through 2024. Of those, 125 were clinical domain focused and 39 were operational. The characteristics of ML algorithms such as sample size, number and type of input features, and performance varied between and within domains and subdomains of applications. Clinical applications of ML algorithms involved triage or diagnosis classification (n = 62), treatment prediction (n = 12), or clinical outcome prediction (n = 50), mainly for out-of-hospital cardiac arrest/OHCA (n = 62), cardiovascular diseases/CVDs (n = 19), and trauma (n = 24). The performance of these ML algorithms varied, with a median area under the receiver operating characteristic curve (AUC) of 85.6%, accuracy of 88.1%, sensitivity of 86.05%, and specificity of 86.5%. Within the operational studies, the operational task of most ML algorithms was ambulance allocation (n = 21), followed by ambulance detection (n = 5), ambulance deployment (n = 5), route optimization (n = 5), and quality assurance (n = 3). The performance of all operational ML algorithms varied and had a median AUC of 96.1%, accuracy of 90.0%, sensitivity of 94.4%, and specificity of 87.7%. Generally, neural network and ensemble algorithms, to some degree, out-performed other ML algorithms. Conclusion: Triaging and managing different prehospital medical conditions and augmenting ambulance performance can be improved by ML algorithms. Future reports should focus on a specific clinical condition or operational task to improve the precision of the performance metrics of ML models.

show abstract

Section: Discussionmentioning

confidence: 99%

Applications and Performance of Machine Learning Algorithms in Emergency Medical Services: A Scoping Review

Alrawashdeh,

Alqahtani,

Alkhatib

et al. 2024

Prehosp. Disaster med.

View full text Add to dashboard Cite

show abstract

“…Another research study was trying to achieve similar results by solving crossing problems using a complex RFID-based system [14]. The system is designed to be able to detect both image and sound from the IRS vehicles and thus be able to change the order of phases at light-controlled intersections.…”

Section: The Current Approachmentioning

confidence: 99%

Comprehensive Analysis of Housing Estate Infrastructure in Relation to the Passability of Firefighting Equipment

et al. 2021

View full text Add to dashboard Cite

The article focuses on the assessment and evaluation of the passability in densely populated parts of cities with multi-storey housing estates, in terms of the operation of the integrated rescue system (IRS) in the Czech Republic. The aim of the research is to minimize the arrival times to conduct the intervention as efficiently as possible. The presented problem is caused by unsystematic development of housing estates and the emergence of secondary problems in the form of inability to reach the place of intervention by the larger IRS vehicles. The vision presented in this document presents a systematic approach to improve the serviceability of individual blocks of flats. The main aim is to ensure passability, even for the largest equipment, such as fire engine ladders. Detailed mapping of the selected sites by drones, construction of their digital model, and subsequent virtual verification of the passability by specific vehicle models on identified access roads was performed. The results obtained by this procedure can then be implemented in the navigation of the fire safety forces and facilitate their arrival at the site of intervention. At the end, specific ways are presented in which the whole system can be modified to be able to intuitively change and choose individual access routes in real time, based on the current situation in the area.

show abstract