• The Plant Pathology Journal
• /
• v.38 no.4
• /
• pp.395-402
• /
• 2022

To predict rice blast, many machine learning methods have been proposed. As the quality and quantity of input data are essential for machine learning techniques, this study develops three artificial neural network (ANN)-based rice blast prediction models by combining two ANN models, the feed-forward neural network (FFNN) and long short-term memory, with diverse input datasets, and compares their performance. The Blast_Weathe long short-term memory r_FFNN model had the highest recall score (66.3%) for rice blast prediction. This model requires two types of input data: blast occurrence data for the last 3 years and weather data (daily maximum temperature, relative humidity, and precipitation) between January and July of the prediction year. This study showed that the performance of an ANN-based disease prediction model was improved by applying suitable machine learning techniques together with the optimization of hyperparameter tuning involving input data. Moreover, we highlight the importance of the systematic collection of long-term disease data.

• Korean Management Science Review
• /
• v.32 no.2
• /
• pp.69-78
• /
• 2015

This paper considers a Bayesian Poisson model for multivariate count data using multiplicative rates. More specifically we compose the parameter for overall arrival rates by the product of two parameters, a common effect and an individual effect. The common effect is composed of autoregressive evolution of the parameter, which allows for analysis on seasonal effects on all multivariate time series. In addition, analysis on individual effects allows the researcher to differentiate the time series by whatevercharacterization of their choice. This type of model allows the researcher to specifically analyze two different forms of effects separately and produce a more robust result. We illustrate a simple MCMC generation combined with a Gibbs sampler step in estimating the posterior joint distribution of all parameters in the model. On the whole, the model presented in this study is an intuitive model which may handle complicated problems, and we highlight the properties and possible applications of the model with an example, analyzing real time series data involving customer arrivals to a large retail store.

• Journal of Power Electronics
• /
• v.11 no.4
• /
• pp.439-448
• /
• 2011

In this work the Multi-Domain model of an electric vehicle is developed. The electric domain model consists on the traction drive and allows including faults associated with stator winding. The thermal model is based on a spatial discretization. It receives the power dissipated in the electric domain, it interacts with the environment and provides the temperature distribution in the induction motor. The mechanical model is a half vehicle model. Given that all models are obtained using the same approach (Bond Graph) their integration becomes straightforward. This complete model allows simulating the whole system dynamics and the analysis of electrical/mechanical/thermal interaction. First, experimental results are aimed to validate the proposed model. Then, simulation results illustrate the interaction between the different domains and highlight the capability of including faults.

• The Journal of the Acoustical Society of Korea
• /
• v.33 no.3
• /
• pp.174-183
• /
• 2014

When a active sonar signal is transmitted and returned back from a target, it has been distorted by various properties of acoustic channel such as multipath arrivals. And signals have been appeared to be different form by target position and attitude. Therefore, we simulated the target echo signal using 3 dimensional target model include reflects target features. In this paper, we develop components form of a simulated target model is made up equally spaced highlight points, and each part of the target consists of shape function. We can simulate a target echo signal and Target strength (TS) according to wave incident angle. To verify, we made small scale target in kit form and we had got underwater target signal for comparing simulation result in water tank.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.22 no.3
• /
• pp.418-424
• /
• 2018

Detection and classification of underwater targets is an important issue for both military and non-military purposes. Recently, many performance improvements are being reported in the field of pattern recognition with the development of deep learning technology. Among the results, DBN showed good performance when used for pre-training of DNN. In this paper, DBN was used for the classification of underwater targets using active sonar, and the results are compared with that of the conventional BPNN. We synthesized active sonar target signals using 3-dimensional highlight model. Then, features were extracted based on FrFT. In the single aspect based experiment, the classification result using DBN was improved about 3.83% compared with the BPNN. In the case of multi-aspect based experiment, a performance of 95% or more is obtained when the number of observation sequence exceeds three.

• Nuclear Engineering and Technology
• /
• v.39 no.2
• /
• pp.133-142
• /
• 2007

The Electric Power Research Institute (EPRI) demonstrated a method for monitoring the performance of instrument channels in Topical Report (TR) 104965, 'On-Line Monitoring of Instrument Channel Performance.' This paper presents the results of several models originally developed by EPRI to monitor three nuclear plant sensor sets: Pressurizer Level, Reactor Protection System (RPS) Loop A, and Reactor Coolant System (RCS) Loop A Steam Generator (SG) Level. The sensor sets investigated include one redundant sensor model and two non-redundant sensor models. Each model employs an Auto-Associative Kernel Regression (AAKR) model architecture to predict correct sensor behavior. Performance of each of the developed models is evaluated using four metrics: accuracy, auto-sensitivity, cross-sensitivity, and newly developed Error Uncertainty Limit Monitoring (EULM) detectability. The uncertainty estimate for each model is also calculated through two methods: analytic formulas and Monte Carlo estimation. The uncertainty estimates are verified by calculating confidence interval coverages to assure that 95% of the measured data fall within the confidence intervals. The model performance evaluation identified the Pressurizer Level model as acceptable for on-line monitoring (OLM) implementation. The other two models, RPS Loop A and RCS Loop A SG Level, highlight two common problems that occur in model development and evaluation, namely faulty data and poor signal selection

• Environmental Engineering Research
• /
• v.16 no.4
• /
• pp.243-252
• /
• 2011

Several mathematical relationships have been developed to describe bacterial responses to UV irradiation. Pseudomonas aeruginosa was taken as a bacterial model. The results obtained showed that the kinetics of disinfection is far to be as uniform. In fact, application of the model of Chick-Watson in its original form or modification, taking into account the speed change during the disinfection process, has not significantly improved results. The application of both models of Collins-Selleck and Hom constitute a major opportunity to simulate goodly the kinetics of UV disinfection. The results obtained showed that despite the major advantage held by applying the Hom model in this process of disinfection and for all strains studied, the model of Collins-Selleck gave the best results for the description of the UV inactivation process. The design of reactors, operating in continuous disinfection system, requires taking into account the hydrodynamic behaviour of water in the reactor. Knowing that a reduction of 4-log is necessary in the case of wastewater reuse for irrigation, a model integrating the expression of disinfection kinetics and the hydrodynamics through the UV irradiation room was proposed. The results highlight the interest to develop reactors in series working as four perfectly mixed reactors.

• Journal of the Korean Society for Precision Engineering
• /
• v.34 no.4
• /
• pp.273-279
• /
• 2017

In sheet metal forming numerical analysis, the strain hardening equation has a significant effect on calculation results, especially in the field of spring-back. This study introduces the Kim-Tuan strain hardening model. This model represents sheet material behavior over the entire strain hardening range. The proposed model is compared to other well known strain hardening models using a series of uniaxial tensile tests. These tests are performed to determine the stress-strain relationship for Al6016-T4, DP980, and CP Ti sheets. In addition, the Kim-Tuan model is used to integrate the CP Ti sheet strain hardening equation in ABAQUS analysis to predict spring-back amount in a bending test. These tests highlight the improved accuracy of the proposed equation in the numerical field. Bending tests to evaluate prediction accuracy are also performed and compared with numerical analysis results.

• The Journal of Asian Finance, Economics and Business
• /
• v.7 no.8
• /
• pp.485-494
• /
• 2020

The paper proposes a conceptual model which provides direction for researchers to empirically establish the connections between dynamic capabilities, innovation capabilities, entrepreneurial capabilities and financial and strategic performance. The author uses systematic literature review process to select the articles used in this study. First, the present paper review and discuss some major contributions to the theories of dynamic capabilities, innovation capabilities, entrepreneurial capabilities and their consequences. The author seeks to highlight different understandings of the concepts to clarify the distinctions between them. Second, the conceptual model and propositions for future studies were developed. The proposed model highlights the different measures of dynamic capabilities, innovation capabilities, entrepreneurial capabilities and their consequences. The model with its associated propositions was developed base on limitations and gaps observed from past studies. It is focused on empirically testing the direct impact of dynamic capabilities, innovation capabilities, and entrepreneurial capabilities on the performance of SMEs in Vietnam. Nevertheless, the proposed model can be applied to similar situations in different contexts and countries. Further empirical testing of proposed model would contribute to enriching existing knowledge of dynamic capabilities, innovation capabilities and entrepreneurial capabilities within SMEs and how these capabilities foster superior performance.

• Reproductive and Developmental Biology
• /
• v.37 no.1
• /
• pp.41-49
• /
• 2013

Ovarian cancer is the most lethal world-wide gynecological disease among women due to the lack of molecular biomarkers to diagnose the disease at an early stage. In addition, there are few well established relevant animal models for research on human ovarian cancer. For instance, rodent models have been established through highly specialized genetic manipulations, but they are not an excellent model for human ovarian cancer because histological features are not comparable to those of women, mice have a low incidence of tumorigenesis, and they experience a protracted period of tumor development. However, the laying hen is a unique and highly relevant animal model for research on human ovarian cancer because they spontaneously develop epithelial cell-derived ovarian cancer (EOC) as occurs in women. Our research group has identified common histological and physiological aspects of ovarian tumors from women and laying hens, and we have provided evidence for several potential biomarkers to detect, monitor and target for treatment of human ovarian cancers based on the use of both genetic and epigenetic factors. Therefore, this review focuses on ovarian cancer of laying hens and relevant regulatory mechanisms, based on genetic and epigenetic aspects of the disease in order to provide new information and to highlight the advantages of the laying hen model for research in ovarian carcinogenesis.