• KIPS Transactions on Software and Data Engineering
• /
• v.7 no.12
• /
• pp.485-496
• /
• 2018

So far, the deep learning, a field of artificial intelligence, has achieved remarkable results in solving problems from unstructured data. However, it is difficult to comprehensively judge situations like humans, and did not reach the level of intelligence that deduced their relations and predicted the next situation. Recently, deep neural networks show that artificial intelligence can possess powerful relational reasoning that is core intellectual ability of human being. In this paper, to analyze and observe the performance of Relation Networks (RN) among the neural networks for relational reasoning, two types of RN-based deep neural network models were constructed and compared with the baseline model. One is a visual question answering RN model using Sort-of-CLEVR and the other is a text-based question answering RN model using bAbI task. In order to maximize the performance of the RN-based model, various performance improvement experiments such as hyper parameters tuning have been proposed and performed. The effectiveness of the proposed performance improvement methods has been verified by applying to the visual QA RN model and the text-based QA RN model, and the new domain model using the dialogue-based LL dataset. As a result of the various experiments, it is found that the initial learning rate is a key factor in determining the performance of the model in both types of RN models. We have observed that the optimal initial learning rate setting found by the proposed random search method can improve the performance of the model up to 99.8%.

• The Korean Journal of Applied Statistics
• /
• v.35 no.4
• /
• pp.543-552
• /
• 2022

When frost occurs, crops are directly damaged. When crops come into contact with low temperatures, tissues freeze, which hardens and destroys the cell membranes or chloroplasts, or dry cells to death. In July 2020, a sudden sub-zero weather and frost hit the Minas Gerais state of Brazil, the world's largest coffee producer, damaging about 30% of local coffee trees. As a result, coffee prices have risen significantly due to the damage, and farmers with severe damage can produce coffee only after three years for crops to recover, which is expected to cause long-term damage. In this paper, we tried to predict frost using frost generation data and weather observation data provided by the Korea Meteorological Administration to prevent severe frost. A model was constructed by reflecting weather factors such as wind speed, temperature, humidity, precipitation, and cloudiness. Using XGB(eXtreme Gradient Boosting), SVM(Support Vector Machine), Random Forest, and MLP(Multi Layer perceptron) models, various hyper parameters were applied as training data to select the best model for each model. Finally, the results were evaluated as accuracy(acc) and CSI(Critical Success Index) in test data. XGB was the best model compared to other models with 90.4% ac and 64.4% CSI, followed by SVM with 89.7% ac and 61.2% CSI. Random Forest and MLP showed similar performance with about 89% ac and about 60% CSI.

• Tunnel and Underground Space
• /
• v.32 no.6
• /
• pp.502-517
• /
• 2022

As the use of TBM increases, research has recently increased to to analyze TBM data with machine learning techniques to predict the exchange cycle of disc cutters, and predict the advance rate of TBM. In this study, a regression prediction of disc cutte wear of slurry shield TBM site was made by combining machine learning based on the machine data and the geotechnical data obtained during the excavation. The data were divided into 7:3 for training and testing the prediction of disc cutter wear, and the hyper-parameters are optimized by cross-validated grid-search over a parameter grid. As a result, gradient boosting based on the ensemble model showed good performance with a determination coefficient of 0.852 and a root-mean-square-error of 3.111 and especially excellent results in fit times along with learning performance. Based on the results, it is judged that the suitability of the prediction model using data including mechanical data and geotechnical information is high. In addition, research is needed to increase the diversity of ground conditions and the amount of disc cutter data.

• Journal of Navigation and Port Research
• /
• v.46 no.4
• /
• pp.367-374
• /
• 2022

The purpose of this study was to propose a deep learning algorithm that applies to the fault diagnosis of fuel pumps and purifiers of autonomous ships. A deep learning algorithm reflecting the time dependence of the measured signal was configured, and the failure pattern was trained using the vibration signal, measured in the equipment's regular operation and failure state. Considering the sequential time-dependence of deterioration implied in the vibration signal, this study adopts Conv1D with sliding window computation for fault detection. The time dependence was also reflected, by transferring the measured signal from two-dimensional to three-dimensional. Additionally, the optimal values of the hyper-parameters of the Conv1D model were determined, using the grid search technique. Finally, the results show that the proposed data preprocessing method as well as the Conv1D model, can reflect the sequential dependency between the fault and its effect on the measured signal, and appropriately perform anomaly as well as failure detection, of the equipment chosen for application.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.22 no.5
• /
• pp.1-18
• /
• 2023

With the recent developments in big data and deep learning, a variety of traffic information is collected widely and used for traffic operations. In particular, long short-term memory (LSTM) is used in the field of traffic information prediction with time series characteristics. Since trends, seasons, and cycles differ due to the nature of time series data input for an LSTM, a trial-and-error method based on characteristics of the data is essential for prediction models based on time series data in order to find hyperparameters. If a methodology is established to find suitable hyperparameters, it is possible to reduce the time spent in constructing high-accuracy models. Therefore, in this study, a traffic information prediction model is developed based on highway vehicle detection system (VDS) data and LSTM, and an impact assessment is conducted through changes in the LSTM evaluation indicators for each hyperparameter. In addition, a methodology for finding hyperparameters suitable for predicting highway traffic information in the transportation field is presented.

• Korean Journal of Psychosomatic Medicine
• /
• v.19 no.2
• /
• pp.74-82
• /
• 2011

Objective:The aim of this study was to evaluate the relationship between sustained attention deficits in Attention-Deficit/Hyperactivity Disorder(ADHD) children and short-term Heart Rate Variability(HRV) parameters. In addition, we evaluate the relationship between The ADHD rating scale(ARS), the computerized ADHD diagnostic system(ADS) and Parenting stress index- short form(PSI-SF). Methods:This study was performed in the department of children and Adolescent psychiatry, Korea university Guro hospital from august 2008 to January 2009. We evaluated HRV parameters by short-term recordings of 5 minutes. K-ARS and ADS are used for screening and identifying ADHD children. Intelligence was measured using Korean educational Developmental Institute-wechsler Intelligence Scale for Children. The caregivers Complete Parenting Stress Index scale for evaluation parent stress. Results:The low frequency(LF) was significantly correlated with response variability of ADS. However, the other variables of ARS and ADS were not significantly correlated with LF. Hyperactivity subscale of ARS was significantly correlated with parental distress subscale and difficult child subscale of PSI-SF and inattention subscale of ARS was also significantly correlated with dysfunctional interaction and difficult child subscale of PSI-SF. Conclusion:The LF, 0.10-Hz component of HRV is known to measure effort allocation. This study shows that the LF component of HRV is significantly correlated with the response variability of ADS. This means that more severe symptoms of ADHD were correlated with the increase in the LF that means decreased effort allocation. These results also support the clinical usability of HRV in the assessment of ADHD. Furthermore, PSI-SF is correlated with hyperactivity and inattention variables of ARS.

• Journal of Environmental Impact Assessment
• /
• v.26 no.6
• /
• pp.404-417
• /
• 2017

In this study, we analyzed response patterns of rotifer community to eutrophic state, and estimated the applicability of rotifer community as an environmental indicator for highly eutrophicated reservoirs. In order to evaluate the relationships among spatial and temporal distributions and the water quality of rotifer community, we selected the Jundae Reservoir and Chodae Reservoir in Chungcheongnam-do, Korea, which are geographically adjacent but have different water quality, particularly in their eutrophic states. For the analyses on their correlations, monthly survey of water quality and rotifer community, was conducted from April to November 2013 in both reservoirs. The rotifer community was divided into different compositions of functional groups as well as species. Functional groups were classified according to the structure and shape of trophi which can represent feeding behavior of rotifer genus. To reflect ecological characteristics of species, body size and habitat preferences were also considered. Species-based composition did not show a consistent tendency with water quality parameters related with eutrophication. On the contrary, functional group composition showed relatively clear group-specific patterns, increasing or decreasing according to the parameters. The results suggest the possible application of rotifer functional group composition as an indicatorforthe lentic systems, especially hyper-eutrophicated reservoirs. The present study can suggest the applicability based on the field observations from the limited time scale and sites, and further studies on feeding behavior of the rotifer functional group and its interactions with environmental variables are necessary for the further application.

• Journal of Nutrition and Health
• /
• v.41 no.8
• /
• pp.742-753
• /
• 2008

The purpose of this study is to investigate risk factors of pre-hypertension and hypertension in rural residents. Nine hundred and ninety four subjects aged 40-70 yrs in Chungnam-do participated in this study. The subjects (n = 824) were classified into three groups of hypertensive, pre-hypertensive, and normotensive according to the Joint National Committee (JNC)-7 criteria. The weight, body mass index (BMI), waist-hip ratio (WHR), and serum total protein, albumin, BUN, and triglyceride (TG) were positively correlated with SBP and DBP. After adjusted by age, sex and BMI, the total protein, albumin and TG were significantly correlated with SBP and DBP (p < 0.01). There was no significant difference in eating habits according to the level of blood pressure. The serum albumin, creatinine, Glu-FBS, Glu-PP l20, and triglyceride were higher in both prehypertensive and hypertensive group than in the normotensive group. However, mean serum cholesterol was not different among three blood pressure groups. In this study, the common risk factors of pre-hypertension and hyper-tension were male, age of fifties, lower education level, ex-smoking, higher drinking frequency, higher BMI, body fat %, waist circumference, WHR, serum albumin and diabetes, even though the degree of risks in these variables were higher in the hypertensive group. The higher BUN was a risk factor of prehypertension, while the family history, prediabetes, serum total protein, Glu-PP l20 and higher alcohol drinking amount were the risk factors of hypertension. This result suggests that maintaining good health habit and normal range of blood parameters as well as controlling body weight have to be paid attention in order to prevent hypertention, and further reseasch on the relationship of blood pressure and BUN are needed.

• Korean Journal of Food Science and Technology
• /
• v.40 no.1
• /
• pp.82-87
• /
• 2008

Atopic dermatitis (AD) is characterized by chronic relapsing inflammation and is associated with hyper-production of immunoglobulin E (IgE). Recent studies have suggested that one of the treatments to alleviate symptoms of AD could be a supplementation of probiotics, Lactobacillus, Rhamnosus, Bifidus, etc. The purpose of this study was to evaluate the effects of probiotics on immune parameters in NC/Nga mice treated with 1-chloro-2,4-dinitro-benzene (DNCB). To induce atopic dermatitis, DNCB was treated to the back of mice for 2 weeks. Then, NC/Nga mice were divided into the four experimental groups randomly. Probiotics fragment, probiotics with other complex (Lactobacillus rhamnosus GG, Bifidobacterium lactis Bb-12LbL, L. plantarum K8, L. plantarum K8 fragment, ${\gamma}$-linolenic acid), antihistamine, and distilled water were administrated orally to the NC/Nga mouse for 4 weeks of experimental period. The groups were probiotics fragment group (DPF), probiotics with other complex group (DPOC), antihistamine group (DAH) and distilled water group (DDW) as a control group. The levels of serum IgE, interlukin-4 (IL-4), interlukin-5 (IL-5), interferon-gamma (IFN-${\gamma}$) and spleenocyte IgE were measured. The levels of serum IgE were significantly different among the four experimental groups. Before the treatment, there was no differences among the groups. However, from the first through the third week of the treatments, the levels of serum IgE in the probiotics (DPF, DPOC) and antihistamine (DAH) groups were lower than those of control group (p < 0.05). The levels of serum IL-4 of DPOC group was significantly lower than that of control group (p < 0.05) and serum IL-5 levels of DPF, DPOC, and DAH groups were significantly lower than that of control group. The levels of serum IFN-${\gamma}$ were not different among the four experimental groups. The levels of serum IgE in supernatant of spleen lymphocytes were not significantly different among the groups. These results suggest that probiotics supplementation showed partial effectiveness in the DNCB treated NC/Nga mice via modulation of IgE level and IL-4, IL-5 production. Based on these findings, probiotics exhibited the inhibitory effect via IL-4 production thereby inhibited the production of IgE in atopic animal model NC/Nga mice.

• Journal of Intelligence and Information Systems
• /
• v.24 no.4
• /
• pp.137-154
• /
• 2018

Animal infectious diseases, such as avian influenza and foot and mouth disease, occur almost every year and cause huge economic and social damage to the country. In order to prevent this, the anti-quarantine authorities have tried various human and material endeavors, but the infectious diseases have continued to occur. Avian influenza is known to be developed in 1878 and it rose as a national issue due to its high lethality. Food and mouth disease is considered as most critical animal infectious disease internationally. In a nation where this disease has not been spread, food and mouth disease is recognized as economic disease or political disease because it restricts international trade by making it complex to import processed and non-processed live stock, and also quarantine is costly. In a society where whole nation is connected by zone of life, there is no way to prevent the spread of infectious disease fully. Hence, there is a need to be aware of occurrence of the disease and to take action before it is distributed. Epidemiological investigation on definite diagnosis target is implemented and measures are taken to prevent the spread of disease according to the investigation results, simultaneously with the confirmation of both human infectious disease and animal infectious disease. The foundation of epidemiological investigation is figuring out to where one has been, and whom he or she has met. In a data perspective, this can be defined as an action taken to predict the cause of disease outbreak, outbreak location, and future infection, by collecting and analyzing geographic data and relation data. Recently, an attempt has been made to develop a prediction model of infectious disease by using Big Data and deep learning technology, but there is no active research on model building studies and case reports. KT and the Ministry of Science and ICT have been carrying out big data projects since 2014 as part of national R &D projects to analyze and predict the route of livestock related vehicles. To prevent animal infectious diseases, the researchers first developed a prediction model based on a regression analysis using vehicle movement data. After that, more accurate prediction model was constructed using machine learning algorithms such as Logistic Regression, Lasso, Support Vector Machine and Random Forest. In particular, the prediction model for 2017 added the risk of diffusion to the facilities, and the performance of the model was improved by considering the hyper-parameters of the modeling in various ways. Confusion Matrix and ROC Curve show that the model constructed in 2017 is superior to the machine learning model. The difference between the2016 model and the 2017 model is that visiting information on facilities such as feed factory and slaughter house, and information on bird livestock, which was limited to chicken and duck but now expanded to goose and quail, has been used for analysis in the later model. In addition, an explanation of the results was added to help the authorities in making decisions and to establish a basis for persuading stakeholders in 2017. This study reports an animal infectious disease prevention system which is constructed on the basis of hazardous vehicle movement, farm and environment Big Data. The significance of this study is that it describes the evolution process of the prediction model using Big Data which is used in the field and the model is expected to be more complete if the form of viruses is put into consideration. This will contribute to data utilization and analysis model development in related field. In addition, we expect that the system constructed in this study will provide more preventive and effective prevention.