• The Korean Journal of Applied Statistics
• /
• v.26 no.5
• /
• pp.821-834
• /
• 2013

Law et al. (2004) proposed a normal distribution based salient mixture model for variable selection in clustering. However, this model has substantial problems such as the unidentifiability of components an the inaccurate selection of informative variables in the case of a small cluster size. We propose an alternative method to overcome problems and demonstrate a good performance through experiments on simulated data and real data.

• Journal of the Korean Statistical Society
• /
• v.23 no.2
• /
• pp.325-340
• /
• 1994

Effects of temporal aggregation on estimation for ARMA models are studied by investigating the Hannan & Rissanen (1982)'s procedure. The temporal aggregation of autoregressive process has a representation of an autoregressive moving average. The characteristic polynomials associated with autoregressive part and moving average part tend to have roots close to zero or almost identical. This caused a numerical problem in the Hannan & Rissanen procedure for identifying and estimating the temporally aggregated autoregressive model. A Monte-Carlo simulation is conducted to show the effects of temporal aggregation in predicting one period ahead realization.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.34 no.2
• /
• pp.193-206
• /
• 2024

In tandem with the advancements in the digital era, the significance of digital data has escalated, necessitating an increased focus on digital forensics investigations. However, the process of collecting and analyzing digital evidence faces significant challenges, such as the unidentifiability of damaged files due to issues like media corruption and anti-forensic techniques. Moreover, the technological limitations of existing tools hinder the recovery of damaged files, posing difficulties in the evidence collection process. This paper aims to propose solutions for the recovery of corrupted MS Office files commonly used in digital data creation. To achieve this, we analyze the structure of MS Office files in the OOXML format and present a novel approach to overcome the limitations of current recovery tools. Through these efforts, we aim to contribute to enhancing the quality of evidence collection in the field of digital forensics by efficiently recovering and identifying damaged data.