• Journal of Bio-Environment Control
• /
• v.31 no.3
• /
• pp.255-260
• /
• 2022

This study aimed to develop a service model that uses a deep learning algorithm for detecting diseases and pests in strawberries through image data. In addition, the pest detection performance of deep learning models was further improved by proposing segmented image data sets specialized in disease and pest symptoms. The CNN-based YOLO deep learning model was selected to enhance the existing R-CNN-based model's slow learning speed and inference speed. A general image data set and a proposed segmented image dataset was prepared to train the pest and disease detection model. When the deep learning model was trained with the general training data set, the pest detection rate was 81.35%, and the pest detection reliability was 73.35%. On the other hand, when the deep learning model was trained with the segmented image dataset, the pest detection rate increased to 91.93%, and detection reliability was increased to 83.41%. This study concludes with the possibility of improving the performance of the deep learning model by using a segmented image dataset instead of a general image dataset.

• Journal of Aerospace System Engineering
• /
• v.14 no.2
• /
• pp.50-56
• /
• 2020

In this study, we investigated whether long short-term memory (LSTM) can be used in the future to predict F10.7 index data; the F10.7 index is a space environment factor affecting atomic oxygen erosion. Based on this, we compared the prediction performances of LSTM, the Autoregressive integrated moving average (ARIMA) model (which is a traditional statistical prediction model), and the similar pattern searching method used for long-term prediction. The LSTM model yielded superior results compared to the other techniques in the prediction period starting from the max/min points, but presented inferior results in the prediction period including the inflection points. It was found that efficient learning was not achieved, owing to the lack of currently available learning data in the prediction period including the maximum points. To overcome this, we proposed a method to increase the size of the learning samples using the sunspot data and to upgrade the LSTM model.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.24 no.3
• /
• pp.1-9
• /
• 2021

In this study, we evaluated the accuracy of deep learning-based tree species classification model trained by using high-resolution images. We selected five species classed, i.e., pine, birch, larch, korean pine, mongolian oak for classification. We created 5,000 datasets using high-resolution orthophoto and forest type map. CNN deep learning model is used to tree species classification. We divided training data, verification data, and test data by a 5:3:2 ratio of the datasets and used it for the learning and evaluation of the model. The overall accuracy of the model was 89%. The accuracy of each species were pine 95%, birch 89%, larch 80%, korean pine 86% and mongolian oak 98%.

• Journal of Internet Computing and Services
• /
• v.19 no.4
• /
• pp.35-44
• /
• 2018

Monitoring through Synthesis Aperture Radar (SAR) is responsible for marine safety from floating icebergs. However, there are limits to distinguishing between icebergs and ships in SAR images. Convolutional Neural Network (CNN) is used to distinguish the iceberg from the ship. The goal of this paper is to increase the accuracy of identifying icebergs from SAR images. The metrics for performance evaluation uses the log loss. The two-layer CNN model proposed in research of C.Bentes et al.[1] is used as a benchmark model and compared with the four-layer CNN model using data augmentation. Finally, the performance of the final CNN model using the VGG-16 pre-trained model is compared with the previous model. This paper shows how to improve the benchmark model and propose the final CNN model.

• The Journal of Information Systems
• /
• v.21 no.1
• /
• pp.117-152
• /
• 2012

The purpose of this study was to identify the negative factors affecting personnel u-Learning acceptance and to analyze the interrelation among the factors in this research model. The two independent variables avoidable convenience and reliant convenience, based on pilot test results, and learning performance and perceived interactivity, based on the relevant literature, are used to examine the research model. The research problem was tested with data collected from 577 respondents in 23 universities. This study developed and empirically analyzed a model representing the relationship by using the Structural Equation Model. The major findings of this study are, firstly, that the higher reliant convenience is negatively affecting the degree of system use and learner’s satisfaction, whereas avoidable convenience is only affecting the learner’s satisfaction. Secondly, the higher learning performance and stronger perceived interactivity affects the degree of system use as well as learner’s satisfaction. Finally, the degree of system use affects the learner’s satisfaction.

• Journal of Korean Society on Water Environment
• /
• v.37 no.5
• /
• pp.335-343
• /
• 2021

Water quality prediction is essential for the proper management of water supply systems. Increased suspended sediment concentration (SSC) has various effects on water supply systems such as increased treatment cost and consequently, there have been various efforts to develop a model for predicting SSC. However, SSC is affected by both the natural and anthropogenic environment, making it challenging to predict SSC. Recently, advanced machine learning models have increasingly been used for water quality prediction. This study developed an ensemble machine learning model to predict SSC using the XGBoost (XGB) algorithm. The observed discharge (Q) and SSC in two fields monitoring stations were used to develop the model. The input variables were clustered in two groups with low and high ranges of Q using the k-means clustering algorithm. Then each group of data was separately used to optimize XGB (Model 1). The model performance was compared with that of the XGB model using the entire data (Model 2). The models were evaluated by mean squared error-ob servation standard deviation ratio (RSR) and root mean squared error. The RSR were 0.51 and 0.57 in the two monitoring stations for Model 2, respectively, while the model performance improved to RSR 0.46 and 0.55, respectively, for Model 1.

• Journal of Information Processing Systems
• /
• v.16 no.3
• /
• pp.572-587
• /
• 2020

Experience API provides a learner-centered model for learning data collection and learning process recording. In particular, it can record learning data from multiple data sources. Therefore, Experience API provides very good support for ubiquitous learning. In this paper, we put forward the architecture of ubiquitous learning system and the method of reading the learning record from the ubiquitous learning system. We analyze students' learning behavior from two aspects: horizontal and vertical, and give the analysis results. The system can provide personalized suggestions for learners according to the results of learning analysis. According to the feedback from learners, we can see that this u-learning system can greatly improve learning interest and quality of learners.

• Journal of information and communication convergence engineering
• /
• v.16 no.3
• /
• pp.173-178
• /
• 2018

Accurate classification of cloud images is a challenging task. Almost all the existing methods rely on hand-crafted feature extraction. Their limitation is low discriminative power. In the recent years, deep learning with convolution neural networks (CNNs), which can auto extract features, has achieved promising results in many computer vision and image understanding fields. However, deep learning approaches usually need large datasets. This paper proposes a deep learning approach for classification of cloud image patches on small datasets. First, we design a suitable deep learning model for small datasets using a CNN, and then we apply data augmentation and dropout regularization techniques to increase the generalization of the model. The experiments for the proposed approach were performed on SWIMCAT small dataset with k-fold cross-validation. The experimental results demonstrated perfect classification accuracy for most classes on every fold, and confirmed both the high accuracy and the robustness of the proposed model.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.8 no.2
• /
• pp.1-10
• /
• 2012

In this study, software products developed in the course of testing, software managers in the process of testing software test and test tools for effective learning effects perspective has been studied using the NHPP software. The finite failure nonhomogeneous Poisson process models presented and the life distribution applied exponential and log shaped type hazard function. Software error detection techniques known in advance, but influencing factors for considering the errors found automatically and learning factors, by prior experience, to find precisely the error factor setting up the testing manager are presented comparing the problem. As a result, the learning factor is greater than autonomous errors-detected factor that is generally efficient model could be confirmed. This paper, a failure data analysis of applying using time between failures and parameter estimation using maximum likelihood estimation method, after the efficiency of the data through trend analysis model selection were efficient using the mean square error and coefficient of determination.

• Journal of the Semiconductor & Display Technology
• /
• v.22 no.4
• /
• pp.136-141
• /
• 2023

The continuous shrinking of transistors in integrated circuits leads to difficulties in improving performance, resulting in the emerging transistors such as nanosheet field-effect transistors. In this paper, we propose a TCAD-machine learning framework of nanosheet FETs to model the current-voltage characteristics. Sentaurus TCAD simulations of nanosheet FETs are performed to obtain a large amount of device data. A machine learning model of I-V characteristics is trained using the multi-layer perceptron from these TCAD data. The weights and biases obtained from multi-layer perceptron are implemented in a PSPICE netlist to verify the accuracy of I-V and the DC transfer characteristics of a CMOS inverter. It is found that the proposed machine learning model is applicable to the prediction of nanosheet field-effect transistors device and circuit performance.