• International journal of advanced smart convergence
• /
• v.8 no.4
• /
• pp.75-81
• /
• 2019

Though recent advancement of deep learning methods have provided satisfactory results from large data domain, somehow yield poor performance on few-shot classification tasks. In order to train a model with strong performance, i.e. deep convolutional neural network, it depends heavily on huge dataset and the labeled classes of the dataset can be extremely humongous. The cost of human annotation and scarcity of the data among the classes have drastically limited the capability of current image classification model. On the contrary, humans are excellent in terms of learning or recognizing new unseen classes with merely small set of labeled examples. Few-shot learning aims to train a classification model with limited labeled samples to recognize new classes that have neverseen during training process. In this paper, we increase the backbone depth of the embedding network in orderto learn the variation between the intra-class. By increasing the network depth of the embedding module, we are able to achieve competitive performance due to the minimized intra-class variation.

• Journal of Korean Society for Quality Management
• /
• v.49 no.4
• /
• pp.569-579
• /
• 2021

Purpose: The purpose of this study is the time series analysis for predicting the yield of crops applicable to each farm using environmental variables measured by smart farms cultivating tomato. In addition, it is intended to confirm the influence of environmental variables using a deep learning model that can be explained to some extent. Methods: A time series analysis was performed to predict production using environmental variables measured at 75 smart farms cultivating tomato in two periods. An LSTM-based encoder-decoder model was used for cases of several farms with similar length. In particular, Dual Attention Mechanism was applied to use environmental variables as exogenous variables and to confirm their influence. Results: As a result of the analysis, Dual Attention LSTM with a window size of 12 weeks showed the best predictive power. It was verified that the environmental variables has a similar effect on prediction through wieghtss extracted from the prediction model, and it was also verified that the previous time point has a greater effect than the time point close to the prediction point. Conclusion: It is expected that it will be possible to attempt various crops as a model that can be explained by supplementing the shortcomings of general deep learning model.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.40 no.5
• /
• pp.449-456
• /
• 2022

This study proposes a deep learning algorithm to predict crop yield using GIS (Geographic Information System) to extract soil properties from Soilgrids and soil suitability class maps. The proposed model modified the structure of a published CNN-RNN (Convolutional Neural Network-Recurrent Neural Network) based crop yield prediction model suitable for the domestic crop environment. The existing model has two characteristics. The first is that it replaces the original yield with the average yield of the year, and the second is that it trains the data of the predicted year. The new model uses the original field value to ensure accuracy, and the network structure has been improved so that it can train only with data prior to the year to be predicted. The proposed model predicted the yield per unit area of autumn cabbage for kimchi by region based on weather, soil, soil suitability classes, and yield data from 1980 to 2020. As a result of computing and predicting data for each of the four years from 2018 to 2021, the error amount for the test data set was about 10%, enabling accurate yield prediction, especially in regions with a large proportion of total yield. In addition, both the proposed model and the existing model show that the error gradually decreases as the number of years of training data increases, resulting in improved general-purpose performance as the number of training data increases.

• Korean Journal of Remote Sensing
• /
• v.33 no.5_2
• /
• pp.631-640
• /
• 2017

The estimation of rice yield affects the income of farmers as well as the fields related to agriculture. Moreover, it has an important effect on the government's policy making including the control of supply demand and the price estimation. Thus, it is necessary to build the crop yield estimation model and from the past, many studies utilizing empirical statistical models or artificial neural network algorithms have been conducted through climatic and satellite data. Presently, scientists have achieved successful results with deep learning algorithms in the field of pattern recognition, computer vision, speech recognition, etc. Among deep learning algorithms, the SSAE (Stacked Sparse AutoEncoder) algorithm has been confirmed to be applicable in the field of forecasting through time series data and in this study, SSAE was utilized to estimate the rice yield in South Korea. The climatic and satellite data were used as the input variables and different types of input data were constructed according to the period of rice growth in South Korea. As a result, the combination of the satellite data from May to September and the climatic data using the 16 day average value showed the best performance with showing average annual %RMSE (percent Root Mean Square Error) and region %RMSE of 7.43% and 7.16% that the applicability of the SSAE algorithm could be proved in the field of rice yield estimation.

• The KIPS Transactions:PartB
• /
• v.10B no.6
• /
• pp.593-598
• /
• 2003

Machine learning organizes knowledge for efficient and accurate reuse. This paper is concerned with methods of concept learning from examples, which glean knowledge from a training set of preclassified ‘objects’. Ideally, training facilitates classification of novel, previously unseen objects. However, every learning system relies on processing and representation assumptions that may be detrimental under certain circumstances. We explore the biases of a well-known learning system, ID3, review improvements, and introduce some improvements of our own, each designed to yield accurate and pedagogically sound classification.

• Journal of the Korean Statistical Society
• /
• v.36 no.3
• /
• pp.367-372
• /
• 2007

Classification as a tool to extract information from data plays an important role in science and engineering. Among various classification methodologies, support vector machine has recently seen significant developments. The central problem this paper addresses is the accuracy of support vector machine. In particular, we are interested in the situations where fast rates of convergence to the Bayes risk can be achieved by support vector machine. Through learning examples, we illustrate that support vector machine may yield fast rates if the space spanned by an adopted kernel is sufficiently large.

• ETRI Journal
• /
• v.43 no.3
• /
• pp.549-560
• /
• 2021

Cyberattacks are often difficult to identify with traditional signature-based detection, because attackers continually find ways to bypass the detection methods. Therefore, researchers have introduced artificial intelligence (AI) technology for cybersecurity analysis to detect malicious PowerShell scripts. In this paper, we propose a feature optimization technique for AI-based approaches to enhance the accuracy of malicious PowerShell script detection. We statically analyze the PowerShell script and preprocess it with a method based on the tokens and abstract syntax tree (AST) for feature selection. Here, tokens and AST represent the vocabulary and structure of the PowerShell script, respectively. Performance evaluations with optimized features yield detection rates of 98% in both machine learning (ML) and deep learning (DL) experiments. Among them, the ML model with the 3-gram of selected five tokens and the DL model with experiments based on the AST 3-gram deliver the best performance.

• English Language & Literature Teaching
• /
• v.16 no.3
• /
• pp.59-80
• /
• 2010

The present study investigated what kind of form-focused instruction would yield better results for incidental learning of English verb patterns in two experiments. Experiment 1 compared the effectiveness of focus on form (reading + translation) and focus on forms (verb pattern list + translation) tasks in learning new English verb patterns incidentally in Korean EFL college classrooms. The results of Experiment 1 showed significantly higher results for the focus on forms group. Since it was revealed by Experiment 1 that the learners did not notice unknown target verb patterns, Experiment 2 was undertaken to examine whether the difference between the focus on form and focus on forms conditions found in Experiment 1 would be retained even after the isolated form-focused instruction or focus on forms aiming at teaching students how to recognize verb patterns was provided for the learners before the focus on form and focus on forms tasks were carried out. The results showed that the focus on form group yielded significantly higher incidental learning scores than the focus on forms group. The effectiveness rates of the focus on form in Experiment 2 were statistically higher than those of the focus on forms in Experiment 1. The results of the two experiments indicated that the combination of the isolated form-focused instruction and focus on form was significantly more effective in learning English verb patterns incidentally. In conclusion, form-focused instruction including both isolated form-focused instruction and focus on form is an effective way to incidental learning of English verb patterns.

• Journal of the Earthquake Engineering Society of Korea
• /
• v.28 no.2
• /
• pp.113-119
• /
• 2024

Existing reinforced concrete buildings with seismically deficient column details affect the overall behavior depending on the failure type of column. This study aims to develop and validate a machine learning-based prediction model for the column failure modes (shear, flexure-shear, and flexure failure modes). For this purpose, artificial neural network (ANN), K-nearest neighbor (KNN), decision tree (DT), and random forest (RF) models were used, considering previously collected experimental data. Using four machine learning methodologies, we developed a classification learning model that can predict the column failure modes in terms of the input variables using concrete compressive strength, steel yield strength, axial load ratio, height-to-dept aspect ratio, longitudinal reinforcement ratio, and transverse reinforcement ratio. The performance of each machine learning model was compared and verified by calculating accuracy, precision, recall, F1-Score, and ROC. Based on the performance measurements of the classification model, the RF model represents the highest average value of the classification model performance measurements among the considered learning methods, and it can conservatively predict the shear failure mode. Thus, the RF model can rapidly predict the column failure modes with simple column details.

• Journal of the Korean Society for Precision Engineering
• /
• v.16 no.11
• /
• pp.98-105
• /
• 1999

As the IC(Integrated Circuit) has been densified and complicated, it is required to thorough process control to improve yield. Experts, for this purpose, focused on the process analysis automation, which is came from the strict data management in semiconductor manufacturing. In this paper, we presents the process analysis system that can analyze causes, for a output after processes. Also, the plasma etching process that highly affects yield among semiconductor process is modeled to predict a output before the process. To approach this problem, we use adaptively trained neural networks that exhibit superior accuracy over statistical techniques. And in comparison with methods in other paper, a method that history of trend for input data is considered is shown to offer advantage in both learning and prediction capability. This research regards CD(Critical Dimension) that is considerable in high integrated circuit as output variable of the prediction model.