Disaster identification scheme based on federated learning and Cognitive Internet of Vehicles

Muhammad Junaid Anjum; Muhammad Shoaib Farooq; Tariq Umer; Momina Shaheen

doi:10.1016/j.comcom.2025.108216

Disaster identification scheme based on federated learning and Cognitive Internet of Vehicles

Muhammad Junaid Anjum, Muhammad Shoaib Farooq, Tariq Umer, Momina Shaheen

Research output: Contribution to journal › Article › peer-review

Abstract

The rate of disaster occurrences has been increasing over the last decade due to the alarming effects of global warming. A major challenge with such disasters is identifying their nature before substantial loss of lives and property occurs. Existing systems often fail to determine the type of disaster until significant damage has been done. This research proposes a novel scheme to identify disasters as they occur, leveraging Federated Learning (FL) and Cognitive Internet of Vehicles (CIoV) since vehicles are a common presence in disaster scenarios. The proposed scheme utilizes various machine learning (ML) and deep learning algorithms to predict disaster types in real-time. Additionally, it introduces a custom federated averaging algorithm to maintain result privacy. The research evaluated the scheme’s performance using a data set of recorded disasters from various countries, training different algorithms to determine optimal results. The results indicate that the proposed scheme can achieve a 90% accuracy in disaster-type identification using deep learning and random forest algorithms.

Original language	English
Pages (from-to)	108216
Journal	Computer Communications
Early online date	17 May 2025
DOIs	https://doi.org/10.1016/j.comcom.2025.108216
Publication status	E-pub ahead of print - 17 May 2025

Access to Document

10.1016/j.comcom.2025.108216

Cite this

@article{6d0fac36e04b46578385e4e3679342b4,

title = "Disaster identification scheme based on federated learning and Cognitive Internet of Vehicles",

abstract = "The rate of disaster occurrences has been increasing over the last decade due to the alarming effects of global warming. A major challenge with such disasters is identifying their nature before substantial loss of lives and property occurs. Existing systems often fail to determine the type of disaster until significant damage has been done. This research proposes a novel scheme to identify disasters as they occur, leveraging Federated Learning (FL) and Cognitive Internet of Vehicles (CIoV) since vehicles are a common presence in disaster scenarios. The proposed scheme utilizes various machine learning (ML) and deep learning algorithms to predict disaster types in real-time. Additionally, it introduces a custom federated averaging algorithm to maintain result privacy. The research evaluated the scheme{\textquoteright}s performance using a data set of recorded disasters from various countries, training different algorithms to determine optimal results. The results indicate that the proposed scheme can achieve a 90% accuracy in disaster-type identification using deep learning and random forest algorithms.",

author = "Anjum, {Muhammad Junaid} and Farooq, {Muhammad Shoaib} and Tariq Umer and Momina Shaheen",

year = "2025",

month = may,

day = "17",

doi = "10.1016/j.comcom.2025.108216",

language = "English",

pages = "108216",

journal = "Computer Communications",

issn = "0140-3664",

publisher = "Elsevier B.V.",

}

TY - JOUR

T1 - Disaster identification scheme based on federated learning and Cognitive Internet of Vehicles

AU - Anjum, Muhammad Junaid

AU - Farooq, Muhammad Shoaib

AU - Umer, Tariq

AU - Shaheen, Momina

PY - 2025/5/17

Y1 - 2025/5/17

N2 - The rate of disaster occurrences has been increasing over the last decade due to the alarming effects of global warming. A major challenge with such disasters is identifying their nature before substantial loss of lives and property occurs. Existing systems often fail to determine the type of disaster until significant damage has been done. This research proposes a novel scheme to identify disasters as they occur, leveraging Federated Learning (FL) and Cognitive Internet of Vehicles (CIoV) since vehicles are a common presence in disaster scenarios. The proposed scheme utilizes various machine learning (ML) and deep learning algorithms to predict disaster types in real-time. Additionally, it introduces a custom federated averaging algorithm to maintain result privacy. The research evaluated the scheme’s performance using a data set of recorded disasters from various countries, training different algorithms to determine optimal results. The results indicate that the proposed scheme can achieve a 90% accuracy in disaster-type identification using deep learning and random forest algorithms.

AB - The rate of disaster occurrences has been increasing over the last decade due to the alarming effects of global warming. A major challenge with such disasters is identifying their nature before substantial loss of lives and property occurs. Existing systems often fail to determine the type of disaster until significant damage has been done. This research proposes a novel scheme to identify disasters as they occur, leveraging Federated Learning (FL) and Cognitive Internet of Vehicles (CIoV) since vehicles are a common presence in disaster scenarios. The proposed scheme utilizes various machine learning (ML) and deep learning algorithms to predict disaster types in real-time. Additionally, it introduces a custom federated averaging algorithm to maintain result privacy. The research evaluated the scheme’s performance using a data set of recorded disasters from various countries, training different algorithms to determine optimal results. The results indicate that the proposed scheme can achieve a 90% accuracy in disaster-type identification using deep learning and random forest algorithms.

U2 - 10.1016/j.comcom.2025.108216

DO - 10.1016/j.comcom.2025.108216

M3 - Article

SN - 0140-3664

SP - 108216

JO - Computer Communications

JF - Computer Communications

ER -