Dataset for drone problem identification and severity estimation

Swardiantara Silalahi; Tohari Ahmad; Hudan Studiawan

doi:10.1016/j.dib.2026.112494

Dataset for drone problem identification and severity estimation

Swardiantara Silalahi
, Tohari Ahmad^*
, Hudan Studiawan

^*Corresponding author for this work

Institut Teknologi Sepuluh Nopember

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

Abstract

The paper proposes DroSev, a dataset for drone problem identification and severity estimation. The collection of drone flight log messages was acquired from publicly accessible sources on Mendeley Data and AirData. This dataset consists of two subtasks: binary problem identification and multiclass problem severity classification. The former task used only the collection of log messages from Mendeley Data, and the latter task used the merged collection of log messages from both sources. Each subtask has a train and test split with an 80:20 ratio generated with stratified sampling. Further syntactical characteristics are reported and summarized.

Original language	English
Article number	112494
Journal	Data in Brief
Volume	65
DOIs	https://doi.org/10.1016/j.dib.2026.112494
Publication status	Published - Apr 2026

Keywords

Drone dataset
Drone forensics
Infrastructure
Log analysis
Problem identification
Problem severity

Access to Document

10.1016/j.dib.2026.112494

Cite this

@article{45e7a8f858164078bd05c1a9e96f6370,

title = "Dataset for drone problem identification and severity estimation",

abstract = "The paper proposes DroSev, a dataset for drone problem identification and severity estimation. The collection of drone flight log messages was acquired from publicly accessible sources on Mendeley Data and AirData. This dataset consists of two subtasks: binary problem identification and multiclass problem severity classification. The former task used only the collection of log messages from Mendeley Data, and the latter task used the merged collection of log messages from both sources. Each subtask has a train and test split with an 80:20 ratio generated with stratified sampling. Further syntactical characteristics are reported and summarized.",

keywords = "Drone dataset, Drone forensics, Infrastructure, Log analysis, Problem identification, Problem severity",

author = "Swardiantara Silalahi and Tohari Ahmad and Hudan Studiawan",

note = "Publisher Copyright: {\textcopyright} 2026 The Author(s).",

year = "2026",

month = apr,

doi = "10.1016/j.dib.2026.112494",

language = "English",

volume = "65",

journal = "Data in Brief",

issn = "2352-3409",

publisher = "Elsevier Inc.",

}

TY - JOUR

T1 - Dataset for drone problem identification and severity estimation

AU - Silalahi, Swardiantara

AU - Ahmad, Tohari

AU - Studiawan, Hudan

PY - 2026/4

Y1 - 2026/4

N2 - The paper proposes DroSev, a dataset for drone problem identification and severity estimation. The collection of drone flight log messages was acquired from publicly accessible sources on Mendeley Data and AirData. This dataset consists of two subtasks: binary problem identification and multiclass problem severity classification. The former task used only the collection of log messages from Mendeley Data, and the latter task used the merged collection of log messages from both sources. Each subtask has a train and test split with an 80:20 ratio generated with stratified sampling. Further syntactical characteristics are reported and summarized.

AB - The paper proposes DroSev, a dataset for drone problem identification and severity estimation. The collection of drone flight log messages was acquired from publicly accessible sources on Mendeley Data and AirData. This dataset consists of two subtasks: binary problem identification and multiclass problem severity classification. The former task used only the collection of log messages from Mendeley Data, and the latter task used the merged collection of log messages from both sources. Each subtask has a train and test split with an 80:20 ratio generated with stratified sampling. Further syntactical characteristics are reported and summarized.

KW - Drone dataset

KW - Drone forensics

KW - Infrastructure

KW - Log analysis

KW - Problem identification

KW - Problem severity

UR - https://www.scopus.com/pages/publications/105029057556

U2 - 10.1016/j.dib.2026.112494

DO - 10.1016/j.dib.2026.112494

M3 - Article

AN - SCOPUS:105029057556

SN - 2352-3409

VL - 65

JO - Data in Brief

JF - Data in Brief

M1 - 112494

ER -

Dataset for drone problem identification and severity estimation

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Reports Outline Science and Technology Study Findings from Institut Teknologi Sepuluh Nopember (Dataset for drone problem identification and severity estimationMendeley Data)

Cite this

Dataset for drone problem identification and severity estimation

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Press/Media

Reports Outline Science and Technology Study Findings from Institut Teknologi Sepuluh Nopember (Dataset for drone problem identification and severity estimationMendeley Data)

Cite this