• Journal of Korea Water Resources Association
• /
• v.56 no.4
• /
• pp.245-259
• /
• 2023

The agricultural reservoir is a critical water supply system in South Korea, providing approximately 60% of the agricultural water demand. However, the reservoir faces several issues that jeopardize its efficient operation and management. To address this issues, we propose a novel deep-learning-based water level recognition model that uses CCTV image data to accurately estimate water levels in agricultural reservoirs. The model consists of three main parts: (1) dataset construction, (2) image segmentation using the U-Net algorithm, and (3) CCTV-based water level recognition using either CNN or ResNet. The model has been applied to two reservoirs G-reservoir and M-reservoir with observed CCTV image and water level time series data. The results show that the performance of the image segmentation model is superior, while the performance of the water level recognition model varies from 50 to 80% depending on water level classification criteria (i.e., classification guideline) and complexity of image data (i.e., variability of the image pixels). The performance of the model can be improved if more numbers of data can be collected.

• Analytical Science and Technology
• /
• v.24 no.6
• /
• pp.533-543
• /
• 2011

The hERG (human ether-a-go-go related gene) ion channel is a main factor for cardiac repolarization, and the blockade of this channel could induce arrhythmia and sudden death. Therefore, potential hERG ion channel inhibitors are now a primary concern in the drug discovery process, and lots of efforts are focused on the minimizing the cardiotoxic side effect. In this study, $IC_{50}$ data of 202 organic compounds in HEK (human embryonic kidney) cell from literatures were used to develop predictive 2D-QSAR model. Multiple linear regression (MLR), Support Vector Machine (SVM), and artificial neural network (ANN) were utilized to predict inhibition concentration of hERG ion channel as machine learning methods. Population based-forward selection method with cross-validation procedure was combined with each learning method and used to select best subset descriptors for each learning algorithm. The best model was ANN model based on 14 descriptors ($R^2_{CV}$=0.617, RMSECV=0.762, MAECV=0.583) and the MLR model could describe the structural characteristics of inhibitors and interaction with hERG receptors. The validation of QSAR models was evaluated through the 5-fold cross-validation and Y-scrambling test.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.27 no.1
• /
• pp.13-21
• /
• 2021

The purpose of this study is to develop the ship valuation model by utilizing the neural network model. The target of the valuation was secondhand VLCC. The variables were set as major factors inducing changes in the value of ship through prior research, and the corresponding data were collected on a monthly basis from January 2000 to August 2020. To determine the stability of subsequent variables, a multi-collinearity test was carried out and finally the research structure was designed by selecting six independent variables and one dependent variable. Based on this structure, a total of nine simulation models were designed using linear regression, neural network regression, and random forest algorithm. In addition, the accuracy of the evaluation results are improved through comparative verification between each model. As a result of the evaluation, it was found that the most accurate when the neural network regression model, which consist of a hidden layer composed of two layers, was simulated through comparison with actual VLCC values. The possible implications of this study first, creative research in terms of applying neural network model to ship valuation; this deviates from the existing formalized evaluation techniques. Second, the objectivity of research results was enhanced from a dynamic perspective by analyzing and predicting the factors of changes in the shipping. market.

• Journal of Korea Water Resources Association
• /
• v.55 no.spc1
• /
• pp.1295-1303
• /
• 2022

As the role of water distribution networks (WDNs) becomes more important, identifying abnormal events (e.g., pipe burst) rapidly and accurately is required. Since existing approaches such as field equipment-based detection methods have several limitations, model-based methods (e.g., machine learning based detection model) that identify abnormal events using hydraulic simulation models have been developed. However, no previous work has examined the impact of data uncertainties on the results. Thus, this study compares the effects of measurement error-induced pressure data uncertainty in WDNs. An artificial neural network (ANN) is used to predict nodal pressures and measurement errors are generated by using cumulative density function inverse sampling method that follows Gaussian distribution. Total of nine conditions (3 input datasets × 3 output datasets) are considered in the ANN model to investigate the impact of measurement error size on the prediction results. The results have shown that higher data uncertainty decreased ANN model's prediction accuracy. Also, the measurement error of output data had more impact on the model performance than input data that for a same measurement error size on the input and output data, the prediction accuracy was 72.25% and 38.61%, respectively. Thus, to increase ANN models prediction performance, reducing the magnitude of measurement errors of the output pressure node is considered to be more important than input node.

• Convergence Security Journal
• /
• v.23 no.2
• /
• pp.27-36
• /
• 2023

In recent years, ransomware attacks have become more organized and specialized, with the sophistication of attacks targeting specific individuals or organizations using tactics such as social engineering, spear phishing, and even machine learning, some operating as business models. In order to effectively respond to this, various researches and solutions are being developed and operated to detect and prevent attacks before they cause serious damage. In particular, honeypots can be used to minimize the risk of attack on IT systems and networks, as well as act as an early warning and advanced security monitoring tool, but in cases where ransomware does not have priority access to the decoy file, or bypasses it completely. has a disadvantage that effective ransomware response is limited. In this paper, this honeypot is optimized for the user environment to create a reliable real-time dynamic honeypot file, minimizing the possibility of an attacker bypassing the honeypot, and increasing the detection rate by preventing the attacker from recognizing that it is a honeypot file. To this end, four models, including a basic data collection model for dynamic honeypot generation, were designed (basic data collection model / user-defined model / sample statistical model / experience accumulation model), and their validity was verified.

• Journal of KIISE
• /
• v.44 no.1
• /
• pp.51-56
• /
• 2017

The research area for solving question answering (QA) problems using artificial intelligence models is in a methodological transition period, and one such architecture, the dynamic memory network (DMN), is drawing attention for two key attributes: its attention mechanism defined by neural network operations and its modular architecture imitating cognition processes during QA of human. In this paper, we increased accuracy of the inferred answers, by adapting an automatic data augmentation method for lacking amount of training data, and by improving the ability of time perception. The experimental results showed that in the 1K-bAbI tasks, the modified DMN achieves 89.21% accuracy and passes twelve tasks which is 13.58% higher with passing four more tasks, as compared with one implementation of DMN. Additionally, DMN's word embedding vectors form strong clusters after training. Moreover, the number of episodic passes and that of supporting facts shows direct correlation, which affects the performance significantly.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.26 no.1
• /
• pp.93-107
• /
• 2016

Game bot playing is one of the main risks in Massively Multi-Online Role Playing Games(MMORPG) because it damages overall game playing environment, especially the balance of the in-game economy. There have been many studies to detect game bot. However, the previous detection models require continuous maintenance efforts to train and learn the game bots' patterns whenever the game contents change. In this work, we have proposed a machine learning technique using the self-similarity property that is an intrinsic attribute in game bots and automated maintenance system. We have tested our method and implemented a system to major three commercial games in South Korea. As a result, our proposed system can detect and classify game bots with high accuracy.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.41 no.1
• /
• pp.1-8
• /
• 2004

According to the development of the Internet and the pervasion of Data Base, it is not easy to search for necessary information from the huge amounts of data. In order to do efficient analysis of a large amounts of data, this paper proposes a method for pattern classification based on the effective strategy for dimension reduction for narrowing down the whole data to what users wants to search for. To analyze data effectively, Radial Basis Function Networks based on VC-dimension of Support Vector Machine, a model of statistical teaming, is proposed in this paper. The model of Radial Basis Function Networks currently used performed the preprocessing of Perceptron model whereas the model proposed in this paper, performing independent analysis on VD-dimension, classifies each datum putting precise labels on it. The comparison and estimation of various models by using Machine Learning Data shows that the model proposed in this paper proves to be more efficient than various sorts of algorithm previously used.

• Journal of the Korea Convergence Society
• /
• v.10 no.9
• /
• pp.23-29
• /
• 2019

In this paper, the mood of images was classified into eight categories through a deep convolutional neural network and video was automatically generated using proper background music. Based on the collected image data, the classification model is learned using a multilayer perceptron (MLP). Using the MLP, a video is generated by using multi-class classification to predict image mood to be used for video generation, and by matching pre-classified music. As a result of 10-fold cross-validation and result of experiments on actual images, each 72.4% of accuracy and 64% of confusion matrix accuracy was achieved. In the case of misclassification, by classifying video into a similar mood, it was confirmed that the music from the video had no great mismatch with images.

• Journal of Internet Computing and Services
• /
• v.20 no.2
• /
• pp.93-100
• /
• 2019

Recently, in various business fields, companies are concentrating on providing chatbot services to various environments by adding artificial intelligence to existing messenger platforms. Organizations in the field of job placement also require chatbot services to improve the quality of employment counseling services and to solve the problem of agent management. A text-based general chatbot classifies input user sentences into learned sentences and provides appropriate answers to users. Recently, user sentences inputted to chatbots are inputted as short texts due to the activation of social network services. Therefore, performance improvement of short text classification can contribute to improvement of chatbot service performance. In this paper, we propose T-EBOW (Translation-Extended Bag Of Words), which is a method to add translation information as well as concept information of existing researches in order to strengthen the short text classification for employment chatbot. The performance evaluation results of the T-EBOW applied to the machine learning classification model are superior to those of the conventional method.