• Journal of the Korean Institute of Intelligent Systems
• /
• v.15 no.7
• /
• pp.893-898
• /
• 2005

Due to the merits that only a small amount of computation is needed for solutions and stochastic policies can be handled explicitly, the actor-critic algorithm, which is a class of reinforcement learning methods, has recently attracted a lot of interests in the area of artificial intelligence. The actor-critic network composes of tile actor network for selecting control inputs and the critic network for estimating value functions, and in its training stage, the actor and critic networks take the strategy, of changing their parameters adaptively in order to select excellent control inputs and yield accurate approximation for value functions as fast as possible. In this paper, we consider a new actor-critic algorithm employing an RLS(Recursive Least Square) method for critic learning, and policy gradients for actor learning. The applicability of the considered algorithm is illustrated with experiments on the two linked robot arm.

• Journal of Information Processing Systems
• /
• v.13 no.4
• /
• pp.778-804
• /
• 2017

Software today has become an inseparable part of our life. In order to achieve the ever demanding needs of customers, it has to rapidly evolve and include a number of changes. In this paper, our aim is to study the relationship of object oriented metrics with change proneness attribute of a class. Prediction models based on this study can help us in identifying change prone classes of a software. We can then focus our efforts on these change prone classes during testing to yield a better quality software. Previously, researchers have used statistical methods for predicting change prone classes. But machine learning methods are rarely used for identification of change prone classes. In our study, we evaluate and compare the performances of ten machine learning methods with the statistical method. This evaluation is based on two open source software systems developed in Java language. We also validated the developed prediction models using other software data set in the same domain (3D modelling). The performance of the predicted models was evaluated using receiver operating characteristic analysis. The results indicate that the machine learning methods are at par with the statistical method for prediction of change prone classes. Another analysis showed that the models constructed for a software can also be used to predict change prone nature of classes of another software in the same domain. This study would help developers in performing effective regression testing at low cost and effort. It will also help the developers to design an effective model that results in less change prone classes, hence better maintenance.

• Journal of The Korean Society of Grassland and Forage Science
• /
• v.43 no.3
• /
• pp.190-198
• /
• 2023

This study was conducted to calculate the damage of Italian ryegrass (IRG) by abnormal climate using machine learning and present the damage through the map. The IRG data collected 1,384. The climate data was collected from the Korea Meteorological Administration Meteorological data open portal.The machine learning model called xDeepFM was used to detect IRG damage. The damage was calculated using climate data from the Automated Synoptic Observing System (95 sites) by machine learning. The calculation of damage was the difference between the Dry matter yield (DMY)_normal and DMY_abnormal. The normal climate was set as the 40-year of climate data according to the year of IRG data (1986~2020). The level of abnormal climate was set as a multiple of the standard deviation applying the World Meteorological Organization (WMO) standard. The DMY_normal was ranged from 5,678 to 15,188 kg/ha. The damage of IRG differed according to region and level of abnormal climate with abnormal temperature, precipitation, and wind speed from -1,380 to 1,176, -3 to 2,465, and -830 to 962 kg/ha, respectively. The maximum damage was 1,176 kg/ha when the abnormal temperature was -2 level (+1.04℃), 2,465 kg/ha when the abnormal precipitation was all level and 962 kg/ha when the abnormal wind speed was -2 level (+1.60 ㎧). The damage calculated through the WMO method was presented as an map using QGIS. There was some blank area because there was no climate data. In order to calculate the damage of blank area, it would be possible to use the automatic weather system (AWS), which provides data from more sites than the automated synoptic observing system (ASOS).

• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.6
• /
• pp.1269-1276
• /
• 2023

Crop estimation is essential for the multinational meal and powerful demand due to its numerous aspects like soil, rain, climate, atmosphere, and their relations. The consequence of climate shift impacts the farming yield products. We operate the dataset with temperature, rainfall, humidity, etc. The current research focuses on feature selection with multifarious classifiers to assist farmers and agriculturalists. The crop yield estimation utilizing the feature selection approach is 96% accuracy. Feature selection affects a machine learning model's performance. Additionally, the performance of the current graph classifier accepts 81.5%. Eventually, the random forest regressor without feature selections owns 78% accuracy and the decision tree regressor without feature selections retains 67% accuracy. Our research merit is to reveal the experimental results of with and without feature selection significance for the proposed ten algorithms. These findings support learners and students in choosing the appropriate models for crop classification studies.

• Steel and Composite Structures
• /
• v.45 no.2
• /
• pp.159-173
• /
• 2022

This paper proposes a hybrid machine-learning model, which is called DANN-IP, that combines a deep artificial neural network (DANN) and an interior-point (IP) algorithm in order to improve the prediction capacity on the patch loading resistance of steel plate girders. For this purpose, 394 steel plate girders that were subjected to patch loading were tested in order to construct the DANN-IP model. Firstly, several DANN models were developed in order to establish the relationship between the patch loading resistance and the web panel length, the web height, the web thickness, the flange width, the flange thickness, the applied load length, the web yield strength, and the flange yield strength of steel plate girders. Accordingly, the best DANN model was chosen based on three performance indices, which included the R^2, RMSE, and a20-index. The IP algorithm was then adopted to optimize the weights and biases of the DANN model in order to establish the hybrid DANN-IP model. The results obtained from the proposed DANN-IP model were compared with of the results from the DANN model and the existing empirical formulas. The comparison showed that the proposed DANN-IP model achieved the best accuracy with an R^2 of 0.996, an RMSE of 23.260 kN, and an a20-index of 0.891. Finally, a Graphical User Interface (GUI) tool was developed in order to effectively use the proposed DANN-IP model for practical applications.

• Proceedings of the Korean Society of Crop Science Conference
• /
• 2022.10a
• /
• pp.81-81
• /
• 2022

Recently, many studies on big data based smart farming have been conducted. Research to quantify morphological characteristics using image data from various crops in smart farming is underway. Rice is one of the most important food crops in the world. Much research has been done to predict and model rice crop yield production. The number of productive tillers per plant is one of the important agronomic traits associated with the grain yield of rice crop. However, modeling the basic growth characteristics of rice requires accurate data measurements. The existing method of measurement by humans is not only labor intensive but also prone to human error. Therefore, conversion to digital data is necessary to obtain accurate and phenotyping quickly. In this study, we present an image-based method to predict leaf number and evaluate tiller number of individual rice crop using YOLOv5 deep learning network. We performed using various network of the YOLOv5 model and compared them to determine higher prediction accuracy. We ako performed data augmentation, a method we use to complement small datasets. Based on the number of leaves and tiller actually measured in rice crop, the number of leaves predicted by the model from the image data and the existing regression equation were used to evaluate the number of tillers using the image data.

• Korean Journal of Remote Sensing
• /
• v.37 no.2
• /
• pp.337-357
• /
• 2021

Because the growth of paddy rice is affected by meteorological factors, the selection of appropriate meteorological variables is essential to build a rice yield prediction model. This paper examines the suitability of multiple meteorological datasets for the rice yield modeling in South Korea, 1996-2019, and a hindcast experiment for rice yield using a machine learning method by considering the nonlinear relationships between meteorological variables and the rice yield. In addition to the ASOS in-situ observations, we used CRU-JRA ver. 2.1 and ERA5 reanalysis. From the multiple meteorological datasets, we extracted the four common variables (air temperature, relative humidity, solar radiation, and precipitation) and analyzed the characteristics of each data and the associations with rice yields. CRU-JRA ver. 2.1 showed an overall agreement with the other datasets. While relative humidity had a rare relationship with rice yields, solar radiation showed a somewhat high correlation with rice yields. Using the air temperature, solar radiation, and precipitation of July, August, and September, we built a random forest model for the hindcast experiments of rice yields. The model with CRU-JRA ver. 2.1 showed the best performance with a correlation coefficient of 0.772. The solar radiation in the prediction model had the most significant importance among the variables, which is in accordance with the generic agricultural knowledge. This paper has an implication for selecting from multiple meteorological datasets for rice yield modeling.

• Korean Journal of Applied Biomechanics
• /
• v.17 no.1
• /
• pp.81-90
• /
• 2007

The effort identifying positioning information of the moving object in real time has been a issue not only in sport biomechanics but also other academic areas. In order to solve this issue, this study tried to track the movement of a pitched ball that might provide an easier prediction because of a clear focus and simple movement of the object. Machine learning has been leading the research of extracting information from continuous images such as object tracking. Though the rule-based methods in artificial intelligence prevailed for decades, it has evolved into the methods of statistical approach that finds the maximum a posterior location in the image. The development of machine learning, accompanied by the development of recording technology and computational power of computer, made it possible to extract the trajectory of pitched baseball from recorded images. We present a method of baseball tracking, based on object tracking methods in machine learning. We introduce three state-of-the-art researches regarding the object tracking and show how we can combine these researches to yield a novel engine that finds trajectory from continuous pitching images. The first research is about mean shift method which finds the mode of a supposed continuous distribution from a set of data. The second research is about the research that explains how we can find the mode and object region effectively when we are given the previous image's location of object and the region. The third is about the research of representing data into features that we can deal with. From those features, we can establish a distribution to generate a set of data for mean shift. In this paper, we combine three works to track baseball's location in the continuous image frames. From the information of locations from two sets of images, we can reconstruct the real 3-D trajectory of pitched ball. We show how this works in real pitching images.

• Geomechanics and Engineering
• /
• v.37 no.1
• /
• pp.49-64
• /
• 2024

Rocks undergoing repeated loading and unloading over an extended period, such as due to earthquakes, human excavation, and blasting, may result in the gradual accumulation of stress and deformation within the rock mass, eventually reaching an unstable state. In this study, a CNN-CCM is proposed to address the mechanical behavior. The structure and hyperparameters of CNN-CCM include Conv2D layers × 5; Max pooling2D layers × 4; Dense layers × 4; learning rate=0.001; Epoch=50; Batch size=64; Dropout=0.5. Training and validation data for deep learning include 71 rock samples and 122,152 data points. The AI Rock Constitutive Model learned by CNN-CCM can predict strain values(ε₁) using Mass (M), Axial stress (σ₁), Density (ρ), Cyclic number (N), Confining pressure (σ₃), and Young's modulus (E). Five evaluation indicators R², MAPE, RMSE, MSE, and MAE yield respective values of 0.929, 16.44%, 0.954, 0.913, and 0.542, illustrating good predictive performance and generalization ability of model. Finally, interpreting the AI Rock Constitutive Model using the SHAP explaining method reveals that feature importance follows the order N > M > σ₁ > E > ρ > σ₃.Positive SHAP values indicate positive effects on predicting strain ε₁ for N, M, σ₁, and σ₃, while negative SHAP values have negative effects. For E, a positive value has a negative effect on predicting strain ε₁, consistent with the influence patterns of conventional physical rock constitutive equations. The present study offers a novel approach to the investigation of the mechanical constitutive model of rocks under cyclic loading and unloading conditions.

• Journal of Auto-vehicle Safety Association
• /
• v.14 no.3
• /
• pp.65-70
• /
• 2022

Lane change in urban environments is a challenge for both human-driving and automated driving due to their complexity and non-linearity. With the recent development of deep-learning, the use of the RNN network, which uses time series data, has become the mainstream in this field. Many researches using RNN show high accuracy in highway environments, but still do not for urban environments where the surrounding situation is complex and rapidly changing. Therefore, this paper proposes a lane change possibility decision network by adopting Attention layer, which is an SOTA in the field of seq2seq. By weighting each time step within a given time horizon, the context of the road situation is more human-like. A total 7D vectors of x, y distances and longitudinal relative speed of side front and rear vehicles, and longitudinal speed of ego vehicle were used as input. A total 5,614 expert data of 4,098 yield cases and 1,516 non-yield cases were used for training, and the performance of this network was tested through 1,817 data. Our network achieves 99.641% of test accuracy, which is about 4% higher than a network using only LSTM in an urban environment. Furthermore, it shows robust behavior to false-positive or true-negative objects.