Event Detection with Convolutional Neural Networks for Forensic Investigation

Abstract : Traditional approaches rely on domain expertise to acquire complicated features. Meanwhile, existing Natural Language Processing (NLP) tools and techniques are not competent to extract information from digital artifacts collected for investigation. In this paper, we propose an improved framework based on a Convolutional neural network (CNN) to capture significant clues for event identification. The experiments show that our solution achieves excellent results.
Document type :
Conference papers
Complete list of metadatas

Cited literature [18 references]  Display  Hide  Download

https://hal.inria.fr/hal-01614980
Contributor : Hal Ifip <>
Submitted on : Wednesday, October 11, 2017 - 4:57:20 PM
Last modification on : Wednesday, March 28, 2018 - 1:26:01 PM
Long-term archiving on: Friday, January 12, 2018 - 3:20:58 PM

File

433802_1_En_11_Chapter.pdf
Files produced by the author(s)

Licence


Distributed under a Creative Commons Attribution 4.0 International License

Identifiers

Citation

Bo Yang, Ning Li, Zhigang Lu, Jianguo Jiang. Event Detection with Convolutional Neural Networks for Forensic Investigation. 9th International Conference on Intelligent Information Processing (IIP), Nov 2016, Melbourne, VIC, Australia. pp.97-107, ⟨10.1007/978-3-319-48390-0_11⟩. ⟨hal-01614980⟩

Share

Metrics

Record views

121

Files downloads

127