Search

Background With the occurrence of a number of major disasters around the world, there is growing interest in chemical disaster medicine. In South Korea, there is a training program for mass casualty incidents (MCI) and backup by legal regulations by the Framework Act on the Management of Disasters and Safety. However, there is no program focusing on chemical disasters. Thus, the authors newly created a program, the Chemical-Mass Casualty Incident Response Education Module (C-MCIREM) in September 2019. This was a pilot study to verify the educational effect of the program. Method A pre/post study was conducted of a chemical MCI training program based on simulation. A total of 25 representative and qualified participants were recruited from fire departments, administrative staff of public health centers, and healthcare workers of hospitals in the Gyeonggi-do province of South Korea. They participated in a one-day training program. A knowledge test and confidence survey were provided to participants just before training, and again immediately following the training online. The authors compared improvements of pre/post-test results. In the tabletop drill exercise, quantified qualitative analyses were used to measure the educational effect on the participants. Results In the knowledge test, the mean (standard deviation) scores for all 25 participants at baseline and after training were 41.72 (15.186) and 77.96 (11.227), respectively (p

Imbalanced dataset classification is a challenging problem, since many classifiers are sensitive to class distribution so that the classifiers’ prediction has bias towards majority class. Hellinger Distance has been proven that it is skew-insensitive and the decision trees that employ Hellinger Distance as a splitting criterion have shown better performance than other decision trees based on Information Gain. We propose a new decision tree induction classifier (HeDEx) based on Hellinger Distance that is randomized ensemble trees selecting both attribute and split-point at random. We also propose hyperplane as a decision surface for HeDEx to improve the performance. A new pattern-based oversampling method is also proposed in this paper to reduce the bias towards majority class. The patterns are detected from HeDEx and the new instances generated are applied after verification process using Hellinger Distance Decision Trees. Our experiments show that the proposed methods show performance improvements on imbalanced datasets over the state-of-the-art Hellinger Distance Decision Trees.