A Content-based File Identification Dataset (machine learning-based dataset)
Uložené v:
| Názov: | A Content-based File Identification Dataset (machine learning-based dataset) |
|---|---|
| Autori: | Khudhur, Saja, Jeiad, Hassan |
| Informácie o vydavateľovi: | Open Science Framework, 2022. |
| Rok vydania: | 2022 |
| Predmety: | file type identification, FTI, digital forensic, file fragments classification |
| Popis: | content-based dataset that composes of 12 features for eight common types of files (JPG, PNG, HTML, TXT, MP4, M4A, MOV, and MP3) to be suitable for file type identification (FTI). These features were extracted from pool of file fragment of size 512 byte each from all the prementioned eight types. This dataset is developed in such a way that can be used for supervised and unsupervised ML model. It provides the ability to classifying and clustering the above-mentioned type into two levels. As a fine grain level (by their file type exactly, JPG, PNG, HTML, TXT, MP4, M4A, MOV, and MP3) and as a coarse-grain level (by their broad type, image, text, audio, video). |
| Druh dokumentu: | Other literature type |
| DOI: | 10.17605/osf.io/8bk3r |
| Prístupové číslo: | edsair.doi...........89891ff5bf07389e133502f72027a86e |
| Databáza: | OpenAIRE |
Nájsť tento článok vo Web of Science | Abstrakt: | content-based dataset that composes of 12 features for eight common types of files (JPG, PNG, HTML, TXT, MP4, M4A, MOV, and MP3) to be suitable for file type identification (FTI). These features were extracted from pool of file fragment of size 512 byte each from all the prementioned eight types. This dataset is developed in such a way that can be used for supervised and unsupervised ML model. It provides the ability to classifying and clustering the above-mentioned type into two levels. As a fine grain level (by their file type exactly, JPG, PNG, HTML, TXT, MP4, M4A, MOV, and MP3) and as a coarse-grain level (by their broad type, image, text, audio, video). |
|---|---|
| DOI: | 10.17605/osf.io/8bk3r |