• Proceedings of the Korean Society for Agricultural Machinery Conference
• /
• 2017.04a
• /
• pp.135-135
• /
• 2017

Greenhouse have been developed to provide the plants with good environmental conditions for cultivation crop, two major factors of which are the inside air temperature and humidity. The inside temperature are influenced by the heating systems, ventilators and for systems among others, which in turn are geverned by some type of controller. Likewise, humidity environment is the result of complex mass exchanges between the inside air and the several elements of the greenhouse and the outside boundaries. Most of the existing models are based on the energy balance method and heat balance equation for modelling the heat and mass fluxes and generating dynamic elements. However, greenhouse are classified as complex system, and need to make a sophisticated modeling. Furthermore, there is a difficulty in using classical control methods for complex process system due to the process are non linear and multi-output(MIMO) systems. In order to predict the time evolution of conditions in certain greenhouse as a function, we present here to use of recurrent neural networks(RNN) which has been used to implement the direct dynamics of the inside temperature and inside humidity of greenhouse. For the training, we used algorithm of a backpropagation Through Time (BPTT). Because the environmental parameters are shared by all time steps in the network, the gradient at each output depends not only on the calculations of the current time step, but also the previous time steps. The training data was emulated to 13 input variables during March 1 to 7, and the model was tested with database file of March 8. The RMSE of results of the temperature modeling was $0.976^{\circ}C$, and the RMSE of humidity simulation was 4.11%, which will be given to prove the performance of RNN in prediction of the greenhouse environment.

• Journal of Animal Science and Technology
• /
• v.52 no.1
• /
• pp.51-56
• /
• 2010

This study was conducted to clarify the characteristics of Holstein dairy cow's vocalization in postpartum related with calf isolation. Vocalizations of 16 individuals of cows were recorded 6 hours per day (1:00am~4:00am and 1:00pm~4:00pm) using digital recorder and microphone during October 2008 and May 2009. Vocalizations were divided into 4 types. Characteristics of frequency, intensity and duration were analyzed by GLM (general linear model) and Duncan's multi-test. There were significant differences in frequency and intensity based on analyses of spectrogram and spectrum among 4 types of vocalizations. Frequencies of vocalizations were dramatically decreased on 2nd and 3rd day. Vocalization would be important factor affecting the motheryoung bond in Holstein dairy cattle.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.36 no.8
• /
• pp.797-806
• /
• 2008

In a double-passage cascade apparatus, only two blades are installed in order to increase the accuracy of experimental result by applying bigger blade than the size of multi-blades on the same apparatus. However, this causes difficulties to make correct periodic condition. In this study, sidewalls are designed to meet periodic condition without removing the operating fluid or adjusting tail boards. Surface Mach number on the blade surface is applied to a responsible variable, and 12 design variables which are related with sidewall profile control are selected. A gradient-based optimization is adopted for wall design and CFX-11 is used for the internal flow computation. The computed result shows that it could obtain the same flow structure by modifying only the sidewalls of the double-passage cascade apparatus.

• Journal of the Society of Naval Architects of Korea
• /
• v.51 no.4
• /
• pp.274-282
• /
• 2014

Time series of the dynamic response of a slender marine structure was predicted using quadratic Volterra series. The wave-structure interaction system was identified using the NARX(Nonlinear Autoregressive with Exogenous Input) technique, and the network parameters were determined through the supervised training with the prepared datasets. The dataset used for the network training was obtained by carrying out the nonlinear finite element analysis on the freely standing riser under random ocean waves of white noise. The nonlinearities involved in the analysis were both large deformation of the structure under consideration and the quadratic term of relative velocity between the water particle and structure in Morison formula. The linear and quadratic frequency response functions of the given system were extracted using the multi-tone harmonic probing method and the time series of response of the structure was predicted using the quadratic Volterra series. In order to check the applicability of the method, the response of structure under the realistic ocean wave environment with given significant wave height and modal period was predicted and compared with the nonlinear time domain simulation results. It turned out that the predicted time series of the response of structure with quadratic Volterra series successfully captures the slowly varying response with reasonably good accuracy. It is expected that the method can be used in predicting the response of the slender offshore structure exposed to the Morison type load without relying on the computationally expensive time domain analysis, especially for the screening purpose.

• Asian-Australasian Journal of Animal Sciences
• /
• v.31 no.8
• /
• pp.1098-1102
• /
• 2018

Objective: Temperament can be defined as a type of behavioral tendency that appears in a relatively stable manner in responses to various external stimuli over time. The aim of this study was to estimate genetic parameters for the records of temperament testing that are used to improve the temperament of Jeju crossbred (Jeju${\times}$Thoroughbred) horses. Methods: This study was conducted using 205 horses (101 females and 104 males) produced between 2010 and 2015. The experimental animals were imprinted and tamed according to the Manual for Horse Taming and Evaluation for Therapeutic Riding Horses and evaluated according to the categories for temperament testing (gentleness, patience, aggressiveness, sensitivity, and friendliness) between 15 months and 18 months of age. Each category was scored on a five-point linear scale. Genetic parameters for the test categories were analyzed using a multi-trait mixed model with repeated records. The ASReml program was used to analyze the data. Results: The heritability of gentleness, patience, aggressiveness, sensitivity and friendliness ranged from 0.08 to 0.53. The standard errors of estimated heritability ranged from 0.13 to 0.17. The test categories showed high genetic correlations with each other, ranging from 0.96 to 0.99 and high repeatability, ranging from 0.70 to 0.73. Conclusion: The results of this study showed that the test categories had moderate heritability and high genetic correlations, but additional studies may be necessary to use the results for the improvement programs of the temperament of Jeju crossbred horses.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.15 no.3
• /
• pp.289-293
• /
• 2005

Pattern classification extracts various types of pattern information expressing objects in the real world and decides their class. The top priority of pattern classification technologies is to improve the performance of classification and, for this, many researches have tried various approaches for the last 40 years. Classification methods used in pattern classification include base classifier based on the probabilistic inference of patterns, decision tree, method based on distance function, neural network and clustering but they are not efficient in analyzing a large amount of multi-dimensional data. Thus, there are active researches on multiple classifier systems, which improve the performance of classification by combining problems using a number of mutually compensatory classifiers. The present study identifies problems in previous researches on multiple SVM classifiers, and proposes BORSE, a model that, based on 1:M policy in order to expand SVM to a multiple class classifier, regards each SVM output as a signal with non-linear pattern, trains the neural network for the pattern and combine the final results of classification performance.

• Magazine of the Korean Society of Agricultural Engineers
• /
• v.44 no.7
• /
• pp.64-73
• /
• 2002

This study was performed to evaluate effects of physical characteristics of both watershed and reservoir on nutrient-chlorophyll relationship in Korean reservoirs. Simple linear models were developed with published data in Korea including 415 reservoirs and 11 multi-purpose dams, and physico-chemical parameters of reservoirs and characteristics relationship of models were analyzed. Theoretical residence time in Korean reservoirs was strongly correlated with the ratio of TA/ST (drainage area + surface area / storage volume) in the logarithmic function. As a result of monthly nutrients-chlorophyll-a regression analysis, significant Chl-a-TP relationship appeared during May～July. The high Chl-a yields per total phosphorus appeared during this time (R$\^$2/=0.51, p<0.001, N= 1088). Chlorophyll-a demonstrated much stronger relationship with TP. than TN. Seasonal algal-nutrient coupling were closely related with N:P ratio in the reservoir water, and it was, in turn, dependent on the monsoon climatic condition (precipitation). Based on the results of regression analysis and high N:P ratio, a major limiting factor of algal growth appeared to be phosphorus during this time. Unlikely TA/ST ratio, DA/SA ratio (drainage area f surface area) was likely to influence directly on the nutrient-Chl-a relationship, indicating that if storage volume and inflowing water volume were the same, algal biomass could be developed more in reservoirs with large surface area. Thus, DA/SA ratio seemed to be an important factor to affect the development of algal biomass in Korean reservoirs. With low determination coefficient of TP-Chl-a relationship, our findings indicated not only nutrient (phosphorus) but also other physical factors, such as DA/SA ratio, may affect algal biomass development in Korean reservoirs, where actual residence time appears to be more closely related to reservoir surface area rather than storage volume.

• ETRI Journal
• /
• v.38 no.5
• /
• pp.1019-1029
• /
• 2016

The probability hypothesis density (PHD) filter is an effective means to track multiple targets in that it avoids explicit data associations between the measurements and targets. However, the target birth intensity as a prior is assumed to be known before tracking in a traditional target-tracking algorithm; otherwise, the performance of a conventional PHD filter will decline sharply. Aiming at this problem, a novel target birth intensity scheme and an improved measurement-driven scheme are incorporated into the PHD filter. The target birth intensity estimation scheme, composed of both PHD pre-filter technology and a target velocity extent method, is introduced to recursively estimate the target birth intensity by using the latest measurements at each time step. Second, based on the improved measurement-driven scheme, the measurement set at each time step is divided into the survival target measurement set, birth target measurement set, and clutter set, and meanwhile, the survival and birth target measurement sets are used to update the survival and birth targets, respectively. Lastly, a Gaussian mixture implementation of the PHD filter is presented under a linear Gaussian model assumption. The results of numerical experiments demonstrate that the proposed approach can achieve a better performance in tracking systems with an unknown newborn target intensity.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.53 no.3
• /
• pp.135-144
• /
• 2004

In this paper, we propose competitive fuzzy polynomial neurons-based advanced Self-Organizing Neural Networks(SONN) architecture for optimal model identification and discuss a comprehensive design methodology supporting its development. The proposed SONN dwells on the ideas of fuzzy rule-based computing and neural networks. And it consists of layers with activation nodes based on fuzzy inference rules and regression polynomial. Each activation node is presented as Fuzzy Polynomial Neuron(FPN) which includes either the simplified or regression polynomial fuzzy inference rules. As the form of the conclusion part of the rules, especially the regression polynomial uses several types of high-order polynomials such as linear, quadratic, and modified quadratic. As the premise part of the rules, both triangular and Gaussian-like membership (unction are studied and the number of the premise input variables used in the rules depends on that of the inputs of its node in each layer. We introduce two kinds of SONN architectures, that is, the basic and modified one with both the generic and the advanced type. Here the basic and modified architecture depend on the number of input variables and the order of polynomial in each layer. The number of the layers and the nodes in each layer of the SONN are not predetermined, unlike in the case of the popular multi-layer perceptron structure, but these are generated in a dynamic way. The superiority and effectiveness of the Proposed SONN architecture is demonstrated through two representative numerical examples.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2005.11a
• /
• pp.518-521
• /
• 2005

The Structures or buildings nowadays draw more complexity in design due to space limitation and other factor that affect the height and dimensions, that results to instability. So the various methods have been carried out to improve the safety factor from an earthquake or a boom until recently. But, it is very hard to get model precisely because these structures are the non-linear and multi-variable systems. For this reason, we developed the active control system that is applied the adaptive control method on the U type Tuned Liquid Damper(TLD) passive control system. It is proven that the proposed active control strategy of the plate carrying U type TLD system is the more effective control method to suppress the vibration of the structure. The entire hybrid control system is composed of the actuator acted in the opposite direction of the TLD system's motion direction and the active control device with an air pressure adjuster. This paper proposed the adaptive control methods to improve the problem of U type TLD system which is used widely for the passive control of the building. And it is proved by the simulation. In advanced, it is developed the pressure control method that is improved the hybrid controller's performance by using air chamber pressure controller. These methods take the advantage of the decrease of the maximum displacement by using the controller as soon as the impact is loaded. This is a very important element for the safety design and economic design of structures.