• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.6
• /
• pp.1331-1336
• /
• 2023

In text-based fish disease classification using machine learning, there is a problem that the input parameters of the machine learning model are too many, but due to performance problems, the input parameters cannot be arbitrarily reduced. This paper proposes a method of optimizing input parameters specialized for Paralichthys olivaceus disease classification using SHAP analysis techniques to solve this problem,. The proposed method includes data preprocessing of disease information extracted from the halibut disease questionnaire by applying the SHAP analysis technique and evaluating a machine learning model using AutoML. Through this, the performance of the input parameters of AutoML is evaluated and the optimal input parameter combination is derived. In this study, the proposed method is expected to be able to maintain the existing performance while reducing the number of input parameters required, which will contribute to enhancing the efficiency and practicality of text-based Paralichthys olivaceus disease classification.

• Journal of the Korean Society for Industrial and Applied Mathematics
• /
• v.13 no.1
• /
• pp.1-11
• /
• 2009

Current therapies against ulcers caused by H. pylori infection consist of antibiotics, an acid reducer, and some clinical trials underway to develop a H. pylori vaccine. We develop a structured model with age-dependent mortality of peptic ulcers and H. pylori infection. Our main goal is to analyze our structured model mathematically and to compare it to our previously unstructured model to examine the disease transmission dynamics in terms of annual prevalence and annual incidence of the disease.

• Korean Journal of Pharmacognosy
• /
• v.42 no.4
• /
• pp.341-347
• /
• 2011

The neuroprotective effects of herbal ethanol extracts from Gynostemma pentaphyllum (GP-EX) in 6-hydroxydopamine (6-OHDA)-lesioned rat model of Parkinson's disease treated with L-DOPA were investigated. Rats were prepared for the Parkinson's disease model by 6-OHDA-lesioning for 14 days. The rats were then treated with L-DOPA (10 and 20 mg/kg) with or without the oral administration of GP-EX (30 mg/kg, daily) for 28 days. L-DOPA (20 mg/kg) treatment for 28 days enhanced dopaminergic neuronal cell death in 6-OHDA-lesioned rat groups, but L-DOPA (10 mg/kg) did not. However, the oral administration of GP-EX (30 mg/kg) for 28 days ameliorated the enhanced neurotoxic effects induced by chronic L-DOPA treatment in 6-OHDA-lesioned rat groups by increasing tyrosine hydroxylase (TH)-immunohistochemical staining and the number of TH-immunopositive cells surviving in the substantia nigra. In addition, GP-EX administration (30 mg/kg) for 28 days recovered the levels of dopamine and norepinephrine of the striatum in 6-OHDA-lesioned rat groups, which were markedly reduced by L-DOPA treatment (20 mg/kg). GP-EX (30 mg/kg) did not produce any signs of toxicity, such as weight loss, diarrhea, or vomiting in rats during the 28-day treatment period. These results suggest that GP-EX has protective functions against chronic L-DOPA-induced neurotoxic reactions in dopaminergic neurons in the 6-OHDA-lesioned rat model of Parkinson's disease. Therefore, GP-EX may be beneficial in the prevention of adverse symptoms in parkisonian patients.

• Nutritional Sciences
• /
• v.9 no.2
• /
• pp.61-67
• /
• 2006

Green tea has attracted attention with respect to its potential for preventing and treating neurodegenerative disease. The neurotoxin, 6-hydroxydopamine (6-OHDA), was used to produce experimental Parkinson's disease (PD) model. The purpose of this study was to investigate the effects of green tea diet on behavioral changes, striatal dopamine content, and hepatic antioxidant parameters of PD model rats. In this study, we used male Sprague-Dawley rats weighing $200\sim220g$ and injected 6-OHDA into the right substantia nigra and medial forebrain bundle of the brain. The supply of green tea diet was started at 2 weeks before 6-OHDA lesion and continually supplied during 0, 2, and 4 weeks after 6-OHDA lesion (GT-0, GT-2, GT-4). Behavioral disturbance was measured by the stepping and d-amphetamine drug-induced rotation tests. Then, we assayed the striatal dopamine content and the hepatic malondialdehyde (MDA), hydrogen peroxide $(H_2O_2)$, and superoxide dismutase (SOD) activity. The percentage of lesioned forepaw to non-lesioned forepaw step scores was the highest in GT-4 group among all groups at both 3 and 4 weeks after 6-OHDA lesion. At 4 weeks after 6-OHDA lesion, the rotation score was the lowest in GT-2 group (p<0.05). However, increasing rate of the rotation score from 2 to 4 weeks after 6-OHDA lesion was the lowest in GT-4 group. The striatal dopamine content was not significantly different among four groups by green tea diet. The hepatic MDA level was the lowest in GT-4 group among four groups. The hepatic SOD activity was increased with the prolongation of green tea diet period These results suggest that green tea diet affects behavioral changes in rats of PD model. It seems that continuous green tea supplementation has an influence on the reduction of behavioral disturbance and the hepatic MDA level. Accordingly, continuous green tea supplementation was recommended for the prevention and treatment of PD. However, further studies are needed to investigate the mechanisms and efficacy of green tea in PD.

• The Journal of the Korea Contents Association
• /
• v.17 no.5
• /
• pp.565-573
• /
• 2017

The ex-post evaluation of governmental crisis management is an important issues since it is necessary to prepare for the future disasters and becomes the cornerstone of our success as well. In this paper, we propose a data cube model with data mining techniques for the analysis of governmental crisis management strategies and ripple effects of foot-and-mouth(FMD) disease using the online news articles. Based on the construction of the data cube model, a multidimensional FMD analysis is performed using on line analytical processing operations (OLAP) to assess the temporal perspectives of the spread of the disease with varying levels of abstraction. Furthermore, the proposed analysis model provides useful information that generates the causal relationship between crisis response actions and its social ripple effects of FMD outbreaks by applying association rule mining. We confirmed the feasibility and applicability of the proposed FMD analysis model by implementing and applying an analysis system to FMD outbreaks from July 2010 to December 2011 in South Korea.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.12
• /
• pp.213-220
• /
• 2021

As the coronavirus disease(COVID-19) pandemic is declared and the number of confirmed cases and deaths increases in countries around the world, the world is gripped with fear. Therefore, in this study, psychological factors of infection prevention behaviors of firefighters and maritime police officers were analyzed based on the Health Belief Model. Although there was no significant difference in the COVID-19 prevention behaviors between the two groups, there was a significant positive correlation between the perceived disease infection possibility, perceived severity, and perceived benefits in the general characteristics and the COVID-19 prevention behaviors. There was no significant difference with perceived obstacles. This study is of great significance in that it is the first analysis of firefighters and maritime police officers as a health belief model, and can be used as basic data for the implementation of new infectious disease prevention actions.

• BMB Reports
• /
• v.55 no.5
• /
• pp.205-212
• /
• 2022

Interstitial cystitis/bladder pain syndrome (IC/BPS) is a debilitating chronic disorder characterized by suprapubic pain and urinary symptoms such as urgency, nocturia, and frequency. The prevalence of IC/BPS is increasing as diagnostic criteria become more comprehensive. Conventional pharmacotherapy against IC/BPS has shown suboptimal effects, and consequently, patients with end-stage IC/BPS are subjected to surgery. The novel treatment strategies should have two main functions, anti-inflammatory action and the regeneration of glycosaminoglycan and urothelium layers. Stem cell therapy has been shown to have dual functions. Mesenchymal stem cells (MSCs) are a promising therapeutic option for IC/BPS, but they come with several shortcomings, such as immune activation and tumorigenicity. MSC-derived extracellular vesicles (MSC-EVs) hold numerous therapeutic cargos and are thus a viable cell-free therapeutic option. In this review, we provide a brief overview of IC/BPS pathophysiology and limitations of the MSC-based therapies. Then we provide a detailed explanation and discussion of therapeutic applications of EVs in IC/BPS as well as the possible mechanisms. We believe our review will give an insight into the strengths and drawbacks of EV-mediated IC/BPS therapy and will provide a basis for further development.

• Smart Media Journal
• /
• v.13 no.7
• /
• pp.36-44
• /
• 2024

Identifying plant species and diseases is crucial for maintaining biodiversity and achieving optimal crop yields, making it a topic of significant practical importance. Recent studies have extended plant disease recognition from traditional closed-set scenarios to open-set environments, where the goal is to reject samples that do not belong to known categories. However, in open-world tasks, it is essential not only to define unknown samples as "unknown" but also to classify them further. This task assumes that images and labels of known categories are available and that samples of unknown categories can be accessed. The model classifies unknown samples by learning the prior knowledge of known categories. To the best of our knowledge, there is no existing research on this topic in plant-related recognition tasks. To address this gap, this paper utilizes knowledge distillation to model the category space relationships between known and unknown categories. Specifically, we identify similarities between different species or diseases. By leveraging a fine-tuned model on known categories, we generate pseudo-labels for unknown categories. Additionally, we enhance the baseline method's performance by using a larger pre-trained model, dino-v2. We evaluate the effectiveness of our method on the large plant specimen dataset Herbarium 19 and the disease dataset Plant Village. Notably, our method outperforms the baseline by 1% to 20% in terms of accuracy for novel category classification. We believe this study will contribute to the community.

• Journal of Korean Institute of Industrial Engineers
• /
• v.40 no.2
• /
• pp.163-171
• /
• 2014

Epidemic models are used to analyze the spreading of epidemic diseases, estimate public health needs, and assess the effectiveness of mitigation strategies. Modeling scope of an epidemic model ranges from the regional scale to national and global scale. Most of the epidemic models developed in Korea are at the national scale using the equation-based model. While these models are useful for designing and evaluating national public health policies, they do not provide sufficient details. As an alternative, individual-based models at the regional scale are often used to describe disease spreading, so that various mitigation strategies can be designed and tested. This paper presents an individual-based epidemic spreading model at regional scale. This model incorporates 2005 census data to build the synthetic population in the model representing Daejeon in 2005. The model's capability is demonstrated by an example where we assess the effectiveness of several mitigation strategies using the model.

• Korean Journal of Exercise Nutrition
• /
• v.25 no.4
• /
• pp.17-23
• /
• 2021

[Purpose] This study aimed to investigate the effect of education based on the health belief model on the physical activity of the staff of the University of Medical Sciences. [Methods] This semi-experimental study was conducted on 130 university staff aged 25-50 years from the Hamadan University of Medical Sciences. Inclusion criteria were having at least 1 year of work experience, lack of acute and chronic physical and mental illnesses, and not using drugs that affect physical activity. The samples were randomly divided into two groups. The experimental group received three training sessions based on the health belief model. Before and 2 months after training, the control and experimental groups were evaluated via the following questionnaires: (1) demographic information questionnaire, (2) Health Belief Model Questionnaire, and (3) International Physical Activity Questionnaire. Finally, data were analyzed statistically. [Results] The training process resulted in a significant increase in the mean scores of the health belief model constructs in the experimental group, but changes in the control group were not significant. Self-efficacy was the strongest predictor of physical activity. [Conclusion] The health belief model is a useful model for improving individuals' understanding of the benefits of physical activity.