Publications by authors named "Geunsoo Jang"
Understanding the impacts of climate change on oceanic carbon cycling is important from a carbon sequestration perspective. A sediment trap study focused on the biological carbon pump system in the Ulleung Basin (UB) in the southwestern part of the East Sea (Japan Sea) was conducted from 2011 to 2017. Particulate organic carbon (POC) flux significantly increased by 37, 56, and 43% from 2014 to 2016 during the El Niño phase.
View Article and Find Full Text PDFIntroduction: The COVID-19 pandemic has profoundly impacted global health systems, requiring the monitoring of infection waves and strategies to control transmission. Estimating the time-varying reproduction number is crucial for understanding the epidemic and guiding interventions.
Methods: Probability distributions of serial interval are estimated for Pre-Delta and Delta periods.
This study analyzes the impact of COVID-19 variants on cost-effectiveness across age groups, considering vaccination efforts and nonpharmaceutical interventions in Republic of Korea. We aim to assess the costs needed to reduce COVID-19 cases and deaths using age-structured model. The proposed age-structured model analyzes COVID-19 transmission dynamics, evaluates vaccination effectiveness, and assesses the impact of the Delta and Omicron variants.
View Article and Find Full Text PDFAlthough deep learning architecture has been used to process sequential data, only a few studies have explored the usefulness of deep learning algorithms to detect glaucoma progression. Here, we proposed a bidirectional gated recurrent unit (Bi-GRU) algorithm to predict visual field loss. In total, 5413 eyes from 3321 patients were included in the training set, whereas 1272 eyes from 1272 patients were included in the test set.
View Article and Find Full Text PDFArticle Synopsis
- The study aimed to evaluate the impact of data preprocessing and augmentation on the performance of recurrent neural networks (RNN) in predicting visual field (VF) outcomes using a large multi-central dataset.
- It utilized data from five glaucoma clinics, resulting in a total of 5,430 and 13,747 visual fields by standardizing test intervals to 365 days and 180 days, respectively, for patients with multiple VF tests.
- The findings revealed that a periodic RNN model significantly outperformed an aperiodic model in prediction accuracy, indicating that a higher frequency of perimetric tests and an increased number of input VFs led to improved predictions, particularly with the 6-long short-term memory (LSTM) setup.
Background: The norovirus is a major cause of acute gastroenteritis at all ages but particularly has a high chance of affecting children under the age of five. Given that the outbreak of norovirus in Korea is seasonal, it is important to try and predict the start and end of norovirus outbreaks.
Methods: We predicted weekly norovirus warnings using six machine learning algorithms using test data from 2017 to 2018 and training data from 2009 to 2016.