Dataset for Drone Problem Identification and Severity Estimation

This dataset contains a collection of drone flight log messages that was acquired from publicly accessible sources on Mendeley Data [1] and AirData [2]. 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 [1], and the later task used the merged collection of log messages from both sources. Each subtask has train and test split with 80:20 ratio generated with stratified sampling. This dataset covers a diverse drone models across various industrial sectors. Since the log messages are human-readable, this dataset can be used to develop NLP-based solutions to find problem-indicating log records and assist in forensic investigation.