• The Korean Journal of Applied Statistics
• /
• v.29 no.1
• /
• pp.145-155
• /
• 2016

In this paper, we compare forecasting models for disease occurrences in elderly patients due to the weather. For the analysis, the medical data of aged patients released from Health Insurance Review and the weather data of the Korea Meteorological Administration are weekly and regionally merged. The ARMAX model, the VARMAX model and the TSCS regression model are considered to analyze the number of weekly occurrences of some diseases attributable to climate conditions. These models are compared with MSE, MAPE, and MAE criteria.

• Research in Plant Disease
• /
• v.21 no.2
• /
• pp.67-73
• /
• 2015

Bacterial blossom blight of kiwifruit (Actinidia deliciosa) caused by Pseudomonas syringae pv. syringae is known to be largely affected by weather conditions during the blooming period. While there have been many studies that investigated scientific relations between weather conditions and the epidemics of bacterial blossom blight of kiwifruit, no forecasting models have been developed thus far. In this study, we collected all the relevant information on the epidemiology of the blossom blight in relation to weather variables, and developed the Pss-KBB Risk Model that is based on the Maryblyt model for the fire blight of apple and pear. Subsequent model validation was conducted using 10 years of ground truth data from kiwifruit orchards in Haenam, Korea. As a result, it was shown that the Pss-KBB Risk Model resulted in better performance in estimating the disease severity compared with other two simple models using either temperature or precipitation information only. Overall, we concluded that by utilizing the Pss-KBB Risk Model and weather forecast information, potential infection risk of the bacterial blossom blight of kiwifruit can be accurately predicted, which will eventually lead kiwifruit growers to utilize the best practices related to spraying chemicals at the most effective time.

• International Journal of Contents
• /
• v.17 no.3
• /
• pp.1-14
• /
• 2021

Since the outbreak of the coronavirus disease 2019 (COVID-19) pandemic, a lot of efforts have been made in the field of data science to help combat against this disease. Among them, forecasting the number of cases of infection is a crucial problem to predict the development of the pandemic. Many deep learning-based models can be applied to solve this type of time series problem. In this research, we would like to take a step forward to incorporate spatial data (geography) with time series data to forecast the cases of region-level infection simultaneously. Specifically, we model a single spatio-temporal graph, in which nodes represent the geographic regions, spatial edges represent the distance between each pair of regions, and temporal edges indicate the node features through time. We evaluate this approach in COVID-19 in a Korean dataset, and we show a decrease of approximately 10% in both RMSE and MAE, and a significant boost to the training speed compared to the baseline models. Moreover, the training efficiency allows this approach to be extended for a large-scale spatio-temporal dataset.

• Research in Plant Disease
• /
• v.7 no.1
• /
• pp.20-24
• /
• 2001

As stand-missing rate (SMR) of ginseng plants in fields are directly related to the ginseng root rot, the forecasting model for the root rot progress in ginseng fields was developed, using the estimated SMRs by disease incidence (DI) of ginseng seedling in the soil-indexing bioassay and the estimate of DI derived from soil environmental factors or rhizoplane microflora. For fitness analysis of the forecasting model, simple correlation and linear regression between SMRs at different planting ages in fields and their estimates by 3 factors of the model were evaluated.The SMR estimated from the factor of DI in the bioassay had much higher fitness to the SMR observed in fields than that from the factors of soil environments and rhizoplane microflora. The estimated SMRs in young and aged ginseng fields by DI in the bioassay were significantly correlated with the observed SMRs in 3- and 5-year-old ginseng fields, respectively (p=0.01). this implicates that indexing preplanting field soils with the forecasting model using DI in the bioassay can provide an information to determine the suitability of the fields for ginseng cultivation, and that indexing cultivating field soils can be helpful to determine the time of harvesting to reduce further yield loss by root rot in continuous cultivation in the next year.

• Smart Media Journal
• /
• v.8 no.3
• /
• pp.88-94
• /
• 2019

Livestock disease is a very important issue in the livestock industry because if livestock disease is not responded quickly enough, its damage can be devastating. To solve the issues involving the occurrence of livestock disease, it is necessary to diagnose in advance the status of livestock disease and develop systematic and scientific livestock feeding technologies. However, there is a lack of domestic studies on such technologies in Korea. This paper, therefore, proposes Livestock Disease Forecasting and Livestock Farm Integrated Control System using Cloud Computing to quickly manage livestock disease. The proposed system collects a variety of livestock data from wireless sensor networks and application. Moreover, it saves and manages the data with the use of the column-oriented database Hadoop HBase, a column-oriented database management system. This provides livestock disease forecasting and livestock farm integrated controlling service through MapReduce Model-based parallel data processing. Lastly, it also provides REST-based web service so that users can receive the service on various platforms, such as PCs or mobile devices.

• Korean Journal of Agricultural Science
• /
• v.41 no.1
• /
• pp.23-27
• /
• 2014

Potato late blight occurrence is caused by various environmental factors, and the progress can be regularly predicted so that several predictive models have been developed. The models predict the timing of the disease occurrence, but they do not include the methods of the disease control. Effective fungicide control, economic threshold, prediction models were investigated in the study to reflect on customized control modules for the model forecasting the occurrence of potato late blight.

• Korean Journal of Agricultural Science
• /
• v.41 no.1
• /
• pp.29-34
• /
• 2014

Phytophthora blight occurrence is caused by various environmental factors, and the progress can be regularly predicted so that several predictive models have been developed. The models predict the timing of the disease occurrence, but they do not include the methods of the disease control. Effective fungicide control, control threshold, prediction models were investigated in the study to reflect on customized control modules for the model forecasting the occurrence of Phytophthora blight on hot pepper.

• International Journal of Computer Science & Network Security
• /
• v.22 no.1
• /
• pp.225-233
• /
• 2022

The recent outbreak of corona virus (COVID-19) infectious disease had made its forecasting critical cornerstones in most scientific studies. This study adopts a machine learning based time series model - Auto Regressive Integrated Moving Average (ARIMA) model to forecast COVID-19 confirmed cases in Botswana over 60 days period. Findings of the study show that COVID-19 confirmed cases in Botswana are steadily rising in a steep upward trend with random fluctuations. This trend can also be described effectively using an additive model when scrutinized in Seasonal Trend Decomposition method by Loess. In selecting the best fit ARIMA model, a Grid Search Algorithm was developed with python language and was used to optimize an Akaike Information Criterion (AIC) metric. The best fit ARIMA model was determined at ARIMA (5, 1, 1), which depicted the least AIC score of 3885.091. Results of the study proved that ARIMA model can be useful in generating reliable and volatile forecasts that can used to guide on understanding of the future spread of infectious diseases or pandemics. Most significantly, findings of the study are expected to raise social awareness to disease monitoring institutions and government regulatory bodies where it can be used to support strategic health decisions and initiate policy improvement for better management of the COVID-19 pandemic.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.3 no.1
• /
• pp.16-21
• /
• 2001

Regression models were obtained on the base of the correlation between Phytophthora blight incidence in red pepper and the microclimate data obtained from automated weather station (AWS) during 1997 and 1998. A computer program (PEPBLIGHT) was constructed based on the model that the R2 value is highest among regression models. This computer program uses the microclimate data from more than one AWS through the common dialogue box easy and it is able provide disease forecasting information. In addition, it could be applied far other diseases and converts the microclimate data of AWS to the input data for Statical Analysis System (SAS). PEPBLIGHT was first developed for the forecasting computer system of red pepper blight in Korea. PEPBLIGHT is operated on the MS Windows, so that it is easy to use.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 1996.04a
• /
• pp.505-510
• /
• 1996

Many diseases cause other diseases with strength of influences and time intervals. Prognostic and therapeutic assessments are the important part of clinical medicine as well as diagnostic assessments. In cases where a patient already has manufestations of multiple disorders (complications), progress forecasting and therapy decision by physicians without support tools are very dificult: physicians often say that "Once complications set in, the patient may die". Treating complications are difficult tasks for physicians, because they have to consider all of the complexities, possibilities and interactions between the diseases. The prediction of multiple disorders has many bundles that arise from such time-dependent interrelationships between diseases and nonlinear progress. This paper proposes a model based on time-dependent influences, which appropriately describes the progress of mulitple disorders, and gives some modificaitons for applying this model to medical domains: time-dependent influence matrix manifestation vector, therapy efficacy matrix, S-shaped curve approximation, definitions of which are provided. This research proposes an algorithm for forecasting the state of each disease on the time horizon and for evaluation of therapy alternatives with not toy example, but real patient history of multiple disorders.disorders.