论文信息 - Using Coupled Hidden Markov Models to Model Suspect Interactions in Digital Forensic Analysis

Using Coupled Hidden Markov Models to Model Suspect Interactions in Digital Forensic Analysis

This paper expands the use of hidden Markov models in digital forensics by using coupled hidden Markov models to investigate interactions between multiple suspects in forensic cases. This paper compares the output of a coupled hidden Markov model to a similarly trained single-chain hidden Markov models and to expert knowledge in a simulated digital forensic case with two suspects. In the situation modelled, there was a notable improvement in the accuracy of the coupled model compared to single chain models. This demonstrates that there is some form of interaction between suspects in this digital forensic case, and that this interaction can be effectively modelled by a coupled hidden Markov model

[1] Jaimyoung Kwon. Modeling Freeway Traffic with Coupled HMMs , 2000 .

[2] Sholom M. Weiss,et al. Automated learning of decision rules for text categorization , 1994, TOIS.

[3] R. Jones,et al. Digital Evidence and Computer Crime: Forensic Science, Computers and the Internet , 2003, Int. J. Law Inf. Technol..

[4] Stuart J. Russell,et al. Dynamic bayesian networks: representation, inference and learning , 2002 .

[5] Michael I. Jordan,et al. Factorial Hidden Markov Models , 1995, Machine Learning.

[6] Nianjun Liu,et al. An Embedded Bayesian Network Hidden Markov Model for Digital Forensics , 2006, ISI.

[7] Zoubin Ghahramani,et al. Learning Dynamic Bayesian Networks , 1997, Summer School on Neural Networks.

[8] Lawrence R. Rabiner,et al. A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.

[9] S. Roberts,et al. Learning interaction dynamics with coupled hidden Markov models , 2000 .

[10] Thomas S. Huang,et al. An experimental study of coupled hidden Markov models , 2002, 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing.