• Journal of the Korea Convergence Society
• /
• v.12 no.8
• /
• pp.279-286
• /
• 2021

The purpose of this study is to compare the predictive power of the Bagging and Boosting algorithm of ensemble method based on the motion information that occurs in woman handball matches and to analyze the availability of motion information. To this end, this study analyzed the predictive power of the result of 15 practice matches based on inertial motion by analyzing the predictive power of Random Forest and Adaboost algorithms. The results of the study are as follows. First, the prediction rate of the Random Forest algorithm was 66.9 ± 0.1%, and the prediction rate of the Adaboost algorithm was 65.6 ± 1.6%. Second, Random Forest predicted all of the winning results, but none of the losing results. On the other hand, the Adaboost algorithm shows 91.4% prediction of winning and 10.4% prediction of losing. Third, in the verification of the suitability of the algorithm, the Random Forest had no overfitting error, but Adaboost showed an overfitting error. Based on the results of this study, the availability of motion information is high when predicting sports events, and it was confirmed that the Random Forest algorithm was superior to the Adaboost algorithm.

• Journal of Korea Water Resources Association
• /
• v.55 no.12
• /
• pp.1091-1104
• /
• 2022

Climate change is predicted to increase the frequency and intensity of rainfall worldwide, and the pattern is changing due to inundation damage in urban areas due to rapid urbanization and industrialization. Accordingly, the impact assessment of climate change is mentioned as a very important factor in urban planning, and the World Meteorological Organization (WMO) is emphasizing the need for an impact forecast that considers the social and economic impacts that may arise from meteorological phenomena. In particular, in terms of traffic, the degradation of transport systems due to urban flooding is the most detrimental factor to society and is estimated to be around £100k per hour per major road affected. However, in the case of Korea, even if accurate forecasts and special warnings on the occurrence of meteorological disasters are currently provided, the effects are not properly conveyed. Therefore, in this study, high-resolution analysis and hydrological factors of each area are reflected in order to suggest the depth of flooding of urban floods and to cope with the damage that may affect vehicles, and the degree of flooding caused by rainfall and its effect on vehicle operation are investigated. decided it was necessary. Therefore, the calculation formula of rainfall-immersion depth-vehicle speed is presented using various machine learning techniques rather than simple linear regression. In addition, by applying the climate change scenario to the rainfall-inundation depth-vehicle speed calculation formula, it predicts the flooding of urban rivers during heavy rain, and evaluates possible traffic network disturbances due to road inundation considering the impact of future climate change. We want to develop technology for use in traffic flow planning.

• Journal of Korea Society of Industrial Information Systems
• /
• v.27 no.4
• /
• pp.19-27
• /
• 2022

In general, the performance of ML(Machine Learning) application is determined by various factors such as the type of ML model, the size of model (number of parameters), hyperparameters setting during the training, and training data. In particular, the recognition accuracy of ML may be deteriorated or experienced overfitting problem if the amount of dada used for training is insufficient. Existing studies focusing on image recognition have widely used open datasets for training and evaluating the proposed ML models. However, for specific applications where the sensor used, the target of recognition, and the recognition situation are different, it is necessary to build the dataset manually. In this case, the performance of ML largely depends on the quantity and quality of the data. In this paper, training data used for motion recognition application is augmented using the kernel density estimation algorithm which is a type of non-parametric estimation method. We then compare and analyze the recognition accuracy of a ML application by varying the number of original data, kernel types and augmentation rate used for data augmentation. Finally experimental results show that the recognition accuracy is improved by up to 14.31% when using the narrow bandwidth Tophat kernel.

• Knowledge Management Research
• /
• v.23 no.1
• /
• pp.89-109
• /
• 2022

Due to COVID-19 and soaring participation of individual investors, large-scale transactions exceeding system capacity limits have been reported frequently in the capital market. The capital market IT systems, which the impact of system failure is very critical, have encountered unexpectedly tremendous transactions in 2020, resulting in a sharp increase in system failures. Despite the fact that many companies maintained large-scale system capacity planning policies, recent transaction influx suggests that a new approach to capacity planning is required. Therefore, this study developed capital market IT system capacity planning models using machine learning techniques and analyzed those performances. In addition, the performance of the best proposed model was improved by using sentiment index that can promptly reflect the behavior of investors. The model uses empirical data including the COVID-19 period, and has high performance and stability that can be used in practice. In practical significance, this study maximizes the cost-efficiency of a company, but also presents optimal parameters in consideration of the practical constraints involved in changing the system. Additionally, by proving that the sentiment index can be used as a major variable in system capacity planning, it shows that the sentiment index can be actively used for various other forecasting demands.

• Advanced Industrial SCIence
• /
• v.3 no.2
• /
• pp.8-16
• /
• 2024

This paper shows the system of drug classification, the goal of this is to foretell the apt drug for the patients based on their demographic and physiological traits. The dataset consists of various attributes like Age, Sex, BP (Blood Pressure), Cholesterol Level, and Na_to_K (Sodium to Potassium ratio), with the objective to determine the kind of drug being given. The models used in this paper are K-Nearest Neighbors (KNN), Logistic Regression and Random Forest. Further to fine-tune hyper parameters using 5-fold cross-validation, GridSearchCV was used and each model was trained and tested on the dataset. To assess the performance of each model both with and without hyper parameter tuning evaluation metrics like accuracy, confusion matrices, and classification reports were used and the accuracy of the models without GridSearchCV was 0.7, 0.875, 0.975 and with GridSearchCV was 0.75, 1.0, 0.975. According to GridSearchCV Logistic Regression is the most suitable model for drug classification among the three-model used followed by the K-Nearest Neighbors. Also, Na_to_K is an essential feature in predicting the outcome.

• Science of Emotion and Sensibility
• /
• v.26 no.4
• /
• pp.3-14
• /
• 2023

Recently, the effect of using social media on psychological well-being has been highlighted. However, studies exploring factors that may predict the quality of social media relationships are relatively rare. The present study investigated whether social media activity and psychological states, such as loneliness and depression, can predict the quality of social media relationships during the COVID-19 quarantine period using a machine learning technique. Ninety-five participants completed a self-report survey on loneliness, Instagram activity, quality of social media relationships, and depression at different time points (during the self-isolation and after the release of self-isolation). Similarity analyses, including multidimensional scaling (MDS), representational similarity analysis (RSA), and classification analyses, were conducted separately at each point in time. The results of MDS revealed that time spent on social media and depression were distinguished from others in the first dimension, and loneliness and passive use were distinguished from others in the second dimension. We divided the data into two groups based on the quality of social media relationships (high and low), and we conducted RSA on each group. Findings indicated an interaction between the quality of the social media relationships and the situation. Specifically, the effect of self-isolation on the high-quality social media relationship group is more pronounced than that on the low-quality group. The classification results also revealed that the predictors of social media relationships depend on whether or not they are isolated. Overall, the results of this study imply that social media relationship could be well predicted when people are not in isolated situations.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.6-7
• /
• 2021

Vegetation development in rivers is one of the important issues not only in academic fields such as geomorphology, ecology, hydraulics, etc., but also in river management practices. The problem of river vegetation is directly connected to the harmony of conflicting values of flood management and ecosystem conservation. In Korea, since the 2000s, the issue of river vegetation and land formation has been continuously raised under various conditions, such as the regulating rivers downstream of the dams, the small eutrophicated tributary rivers, and the floodplain sites for the four major river projects. In this background, this study proposes a method for classifying the distribution of vegetation in rivers based on remote sensing data, and presents the results of applying this to the Naeseong Stream. The Naeseong Stream is a representative example of the river landscape that has changed due to vegetation development from 2014 to the latest. The remote sensing data used in the study are images of Sentinel 1 and 2 satellites, which is operated by the European Aerospace Administration (ESA), and provided by Google Earth Engine. For the ground truth, manually classified dataset on the surface of the Naeseong Stream in 2016 were used, where the area is divided into eight types including water, sand and herbaceous and woody vegetation. The classification method used a random forest classification technique, one of the machine learning algorithms. 1,000 samples were extracted from 10 pre-selected polygon regions, each half of them were used as training and verification data. The accuracy based on the verification data was found to be 82~85%. The model established through training was also applied to images from 2016 to 2020, and the process of changes in vegetation zones according to the year was presented. The technical limitations and improvement measures of this paper were considered. By providing quantitative information of the vegetation distribution, this technique is expected to be useful in practical management of vegetation such as thinning and rejuvenation of river vegetation as well as technical fields such as flood level calculation and flow-vegetation coupled modeling in rivers.

• Journal of Korea Water Resources Association
• /
• v.56 no.5
• /
• pp.311-323
• /
• 2023

In order to reduce disaster damage by localized heavy rains, floods, and urban inundation, it is important to know in advance whether natural disasters occur. Currently, heavy rain watch and heavy rain warning by the criteria of the Korea Meteorological Administration are being issued in Korea. However, since this one criterion is applied to the whole country, we can not clearly recognize heavy rain damage for a specific region in advance. Therefore, in this paper, we tried to reset the current criteria for a special weather report which considers the regional characteristics and to predict the damage caused by rainfall after 1 hour. The study area was selected as Gyeonggi-province, where has more frequent heavy rain damage than other regions. Then, the rainfall inducing disaster or hazard-triggering rainfall was set by utilizing hourly rainfall and heavy rain damage data, considering the local characteristics. The heavy rain damage prediction model was developed by a decision tree model and a random forest model, which are machine learning technique and by rainfall inducing disaster and rainfall data. In addition, long short-term memory and deep neural network models were used for predicting rainfall after 1 hour. The predicted rainfall by a developed prediction model was applied to the trained classification model and we predicted whether the rain damage after 1 hour will be occurred or not and we called this as 1ST-Model. The 1ST-Model can be used for preventing and preparing heavy rain disaster and it is judged to be of great contribution in reducing damage caused by heavy rain.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.18 no.2
• /
• pp.185-195
• /
• 2018

As machines have been automated in the field of industries in recent years, it is a paramount importance to manage and maintain the automation machines. When a fault occurs in sensors attached to the machine, the machine may malfunction and further, a huge damage will be caused in the process line. To prevent the situation, the fault of sensors should be monitored, diagnosed and classified in a proper way. In the paper, we propose a sensor fault detection scheme based on SVM and CNN to detect and classify typical sensor errors such as erratic, drift, hard-over, spike, and stuck faults. Time-domain statistical features are utilized for the learning and testing in the proposed scheme, and the genetic algorithm is utilized to select the subset of optimal features. To classify multiple sensor faults, a multi-layer SVM is utilized, and ensemble technique is used for CNN. As a result, the SVM that utilizes a subset of features selected by the genetic algorithm provides better performance than the SVM that utilizes all the features. However, the performance of CNN is superior to that of the SVM.

• KIPS Transactions on Software and Data Engineering
• /
• v.8 no.6
• /
• pp.251-256
• /
• 2019

A capsule endoscopy is a medical device that can capture an entire digestive organ from the esophagus to the anus at one time. It produces a vast amount of images consisted of about 8~12 hours in length and more than 50,000 frames on a single examination. However, since the analysis of endoscopic images is performed manually by a medical imaging specialist, the automation requirements of the analysis are increasing to assist diagnosis of the disease in the image. Among them, this study focused on automatic detection of polyp images. A polyp is a protruding lesion that can be found in the gastrointestinal tract. In this paper, we propose a weighted-image generation method to enhance the polyp image learning by multi-scale analysis. It is a way to extract the suspicious region of the polyp through the multi-scale analysis and combine it with the original image to generate a weighted image, that can enhance the polyp image learning. We experimented with SVM and RF which is one of the machine learning methods for 452 pieces of collected data. The F1-score of detecting the polyp with only original images was 89.3%, but when combined with the weighted images generated by the proposed method, the F1-score was improved to about 93.1%.