• The Sea:JOURNAL OF THE KOREAN SOCIETY OF OCEANOGRAPHY
• /
• v.27 no.2
• /
• pp.71-86
• /
• 2022

The water quality index (WQI) has been widely used to evaluate marine water quality. The WQI in Korea is categorized into five classes by marine environmental standards. But, the WQI calculation on huge datasets is a very complex and time-consuming process. In this regard, the current study proposed machine learning (ML) based models to predict WQI class by using water quality datasets. Sihwa Lake, one of specially-managed coastal zone, was selected as a modeling site. In this study, adaptive boosting (AdaBoost) and tree-based pipeline optimization (TPOT) algorithms were used to train models and each model performance was evaluated by metrics (accuracy, precision, F1, and Log loss) on classification. Before training, the feature importance and sensitivity analysis were conducted to find out the best input combination for each algorithm. The results proved that the bottom dissolved oxygen (DO_Bot) was the most important variable affecting model performance. Conversely, surface dissolved inorganic nitrogen (DIN_Sur) and dissolved inorganic phosphorus (DIP_Sur) had weaker effects on the prediction of WQI class. In addition, the performance varied over features including stations, seasons, and WQI classes by comparing spatio-temporal and class sensitivities of each best model. In conclusion, the modeling results showed that the TPOT algorithm has better performance rather than the AdaBoost algorithm without considering feature selection. Moreover, the WQI class for unknown water quality datasets could be surely predicted using the TPOT model trained with satisfactory training datasets.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.11
• /
• pp.147-155
• /
• 2022

In this study, we developed a system to dynamically balance a daily stock portfolio and performed trading simulations using gradient boosting and genetic algorithms. We collected various stock market data from stocks listed on the KOSPI and KOSDAQ markets, including investor-specific transaction data. Subsequently, we indexed the data as a preprocessing step, and used feature engineering to modify and generate variables for training. First, we experimentally compared the performance of three popular gradient boosting algorithms in terms of accuracy, precision, recall, and F1-score, including XGBoost, LightGBM, and CatBoost. Based on the results, in a second experiment, we used a LightGBM model trained on the collected data along with genetic algorithms to predict and select stocks with a high daily probability of profit. We also conducted simulations of trading during the period of the testing data to analyze the performance of the proposed approach compared with the KOSPI and KOSDAQ indices in terms of the CAGR (Compound Annual Growth Rate), MDD (Maximum Draw Down), Sharpe ratio, and volatility. The results showed that the proposed strategies outperformed those employed by the Korean stock market in terms of all performance metrics. Moreover, our proposed LightGBM model with a genetic algorithm exhibited competitive performance in predicting stock price movements.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.2
• /
• pp.99-110
• /
• 2023

This study proposed a classification of malicious network traffic using the cyber threat framework(Mitre ATT&CK) and machine learning to solve the real-time traffic detection problems faced by current security monitoring systems. We applied a network traffic dataset called UNSW-NB15 to the Mitre ATT&CK framework to transform the label and generate the final dataset through rare class processing. After learning several boosting-based ensemble models using the generated final dataset, we demonstrated how these ensemble models classify network traffic using various performance metrics. Based on the F-1 score, we showed that XGBoost with no rare class processing is the best in the multi-class traffic environment. We recognized that machine learning ensemble models through Mitre ATT&CK label conversion and oversampling processing have differences over existing studies, but have limitations due to (1) the inability to match perfectly when converting between existing datasets and Mitre ATT&CK labels and (2) the presence of excessive sparse classes. Nevertheless, Catboost with B-SMOTE achieved the classification accuracy of 0.9526, which is expected to be able to automatically detect normal/abnormal network traffic.

• Wind and Structures
• /
• v.36 no.4
• /
• pp.237-247
• /
• 2023

The emergence of high-rise buildings has necessitated frequent structural health monitoring and maintenance for safety reasons. Wind causes damage and structural changes on tall structures; thus, safe structures should be designed. The pressure developed on tall buildings has been utilized in previous research studies to assess the impacts of wind on structures. The wind tunnel test is a primary research method commonly used to quantify the aerodynamic characteristics of high-rise buildings. Wind pressure is measured by placing pressure sensor taps at different locations on tall buildings, and the collected data are used for analysis. However, sensors may malfunction and produce erroneous data; these data losses make it difficult to analyze aerodynamic properties. Therefore, it is essential to generate missing data relative to the original data obtained from neighboring pressure sensor taps at various intervals. This study proposes a deep learning-based, deep convolutional generative adversarial network (DCGAN) to restore missing data associated with faulty pressure sensors installed on high-rise buildings. The performance of the proposed DCGAN is validated by using a standard imputation model known as the generative adversarial imputation network (GAIN). The average mean-square error (AMSE) and average R-squared (ARSE) are used as performance metrics. The calculated ARSE values by DCGAN on the building model's front, backside, left, and right sides are 0.970, 0.972, 0.984 and 0.978, respectively. The AMSE produced by DCGAN on four sides of the building model is 0.008, 0.010, 0.015 and 0.014. The average standard deviation of the actual measures of the pressure sensors on four sides of the model were 0.1738, 0.1758, 0.2234 and 0.2278. The average standard deviation of the pressure values generated by the proposed DCGAN imputation model was closer to that of the measured actual with values of 0.1736,0.1746,0.2191, and 0.2239 on four sides, respectively. In comparison, the standard deviation of the values predicted by GAIN are 0.1726,0.1735,0.2161, and 0.2209, which is far from actual values. The results demonstrate that DCGAN model fits better for data imputation than the GAIN model with improved accuracy and fewer error rates. Additionally, the DCGAN is utilized to estimate the wind pressure in regions of buildings where no pressure sensor taps are available; the model yielded greater prediction accuracy than GAIN.

• The Korean Journal of Applied Statistics
• /
• v.36 no.2
• /
• pp.141-166
• /
• 2023

This paper investigates synthetic data generation methods and their evaluation measures. There have been increasing demands for releasing various types of data to the public for different purposes. At the same time, there are also unavoidable concerns about leaking critical or sensitive information. Many synthetic data generation methods have been proposed over the years in order to address these concerns and implemented in some countries, including Korea. The current study aims to introduce and compare three representative synthetic data generation approaches: Sequential regression, nonparametric Bayesian multiple imputations, and deep generative models. Several evaluation metrics that measure the utility and disclosure risk of synthetic data are also reviewed. We provide empirical comparisons of the three synthetic data generation approaches with respect to various evaluation measures. The findings of this work will help practitioners to have a better understanding of the advantages and disadvantages of those synthetic data methods.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.31-31
• /
• 2023

During December 2022, the northeast monsoon, which dominates the south and the Gulf of Thailand, had significant rainfall that impacted the lower southern region, causing flash floods, landslides, blustery winds, and the river exceeding its bank. The Golok River, located in Narathiwat, divides the border between Thailand and Malaysia was also affected by rainfall. In flood management, instruments for measuring precipitation and water level have become important for assessing and forecasting the trend of situations and areas of risk. However, such regions are international borders, so the installed measuring telemetry system cannot measure the rainfall and water level of the entire area. This study aims to predict 72 hours of water level and evaluate the situation as information to support the government in making water management decisions, publicizing them to relevant agencies, and warning citizens during crisis events. This research is applied to machine learning (ML) for water level prediction of the Golok River, Lan Tu Bridge area, Sungai Golok Subdistrict, Su-ngai Golok District, Narathiwat Province, which is one of the major monitored rivers. The eXtreme Gradient Boosting (XGBoost) algorithm, a tree-based ensemble machine learning algorithm, was exploited to predict hourly water levels through the R programming language. Model training and testing were carried out utilizing observed hourly rainfall from the STH010 station and hourly water level data from the X.119A station between 2020 and 2022 as main prediction inputs. Furthermore, this model applies hourly spatial rainfall forecasting data from Weather Research and Forecasting and Regional Ocean Model System models (WRF-ROMs) provided by Hydro-Informatics Institute (HII) as input, allowing the model to predict the hourly water level in the Golok River. The evaluation of the predicted performances using the statistical performance metrics, delivering an R-square of 0.96 can validate the results as robust forecasting outcomes. The result shows that the predicted water level at the X.119A telemetry station (Golok River) is in a steady decline, which relates to the input data of predicted 72-hour rainfall from WRF-ROMs having decreased. In short, the relationship between input and result can be used to evaluate flood situations. Here, the data is contributed to the Operational support to the Special Water Resources Management Operation Center in Southern Thailand for flood preparedness and response to make intelligent decisions on water management during crisis occurrences, as well as to be prepared and prevent loss and harm to citizens.

• Ecology and Resilient Infrastructure
• /
• v.10 no.3
• /
• pp.73-84
• /
• 2023

The objective of this study was to evaluate biodiversity and natural habitat environment of freshwater ecosystem. Our aim was therefore to produce a set of biodiversity and habitat indicators based on multi-parameters of water quality and biodiversity by analyzing the characteristics of the results by indicators. We selected four indicators a) anthropogenic disturbance, b) habitat diversity, c) biodiversity, d) ecosystem structure. The fishes cohabiting with Brachymystax lenok tsinlingensis were Rhynchocypris kumgangensis and Zacco koreanus. As a result of the anthropogenic disturbance evaluation, it was analyzed that vegetation embankment showed a more stable environment in the tributary than the main stream, and other disturbance was not confirmed As a result of the habitat diversity evaluation, it was analyzed that habitat evaluation index showed a high score of 200 more on average, showing an optimal habitat condition. As a result of the biodiversity evaluation, it was analyzed as a clean habitat condition with a high proportion of sensitive species, abundant dissolved oxygen, and little pollutants. As a results of the ecosystem structure, the ecological health condition metrics and appearance of endangered species showed large score deviation, but it was analyzed that the stream ecosystem health was generally excellent. There was a slight correlation between the habitat environment and the results of the nature habitat evaluation according to the appearance of the B. lenok tsinlingensis.

• Journal of the Korea Society for Simulation
• /
• v.19 no.4
• /
• pp.139-149
• /
• 2010

Internet was designed for network scalability and best-effort service which makes all hosts connected to Internet to be vulnerable against attack. Many papers have been proposed about attack detection algorithms against the attack using IP spoofing and DoS/DDoS attack. Purpose of DoS/DDoS attack is achieved in short period after the attack begins. Therefore, DoS/DDoS attack should be detected as soon as possible. Attack detection algorithms using false alarm rates consist of the false negative rate and the false positive rate. Moreover, they are important metrics to evaluate the attack detections. In this paper, we analyze the performance of the attack detection algorithms using the impact of false negative rate and false positive rate variation to the normal traffic and the attack traffic by simulations. As the result of this, we find that the number of passed attack packets is in the proportion to the false negative rate and the number of passed normal packets is in the inverse proportion to the false positive rate. We also analyze the limits of attack detection due to the relation between the false negative rate and the false positive rate. Finally, we propose a solution to minimize the limits of attack detection algorithms by defining the network state using the ratio between the number of packets classified as attack packets and the number of packets classified as normal packets. We find the performance of attack detection algorithm is improved by passing the packets classified as attacks.

• Geophysics and Geophysical Exploration
• /
• v.26 no.3
• /
• pp.126-137
• /
• 2023

In this study, a recurrent neural network (RNN) was employed as a methodological approach to classify dolphin click signals derived from ocean monitoring data. To improve the accuracy of click signal classification, the single time series data were transformed into fractional domains using fractional Fourier transform to expand its features. Transformed data were used as input for three RNN models: long short-term memory (LSTM), gated recurrent unit (GRU), and bidirectional LSTM (BiLSTM), which were compared to determine the optimal network for the classification of signals. Because the fractional Fourier transform displayed different characteristics depending on the chosen angle parameter, the optimal angle range for each RNN was first determined. To evaluate network performance, metrics such as accuracy, precision, recall, and F1-score were employed. Numerical experiments demonstrated that all three networks performed well, however, the BiLSTM network outperformed LSTM and GRU in terms of learning results. Furthermore, the BiLSTM network provided lower misclassification than the other networks and was deemed the most practically appliable to field data.

• Journal of the Korean Society for information Management
• /
• v.40 no.1
• /
• pp.1-21
• /
• 2023

This study specifically reviewed the performance of the ranking schemes as an efficient feature selection method for text classification. Until now, feature ranking schemes are mostly based on document frequency, and relatively few cases have used the term frequency. Therefore, the performance of single ranking metrics using term frequency and document frequency individually was examined as a feature selection method for text classification, and then the performance of combination ranking schemes using both was reviewed. Specifically, a classification experiment was conducted in an environment using two data sets (Reuters-21578, 20NG) and five classifiers (SVM, NB, ROC, TRA, RNN), and to secure the reliability of the results, 5-Fold cross-validation and t-test were applied. As a result, as a single ranking scheme, the document frequency-based single ranking metric (chi) showed good performance overall. In addition, it was found that there was no significant difference between the highest-performance single ranking and the combination ranking schemes. Therefore, in an environment where sufficient learning documents can be secured in text classification, it is more efficient to use a single ranking metric (chi) based on document frequency as a feature selection method.