• Convergence Security Journal
• /
• v.21 no.1
• /
• pp.191-200
• /
• 2021

Artificial intelligence technology is developing in an environment where a lot of data is produced due to the development of computing technology, a cloud environment that can store data, and the spread of personal mobile phones. Among these artificial intelligence technologies, the deep neural network provides excellent performance in image recognition and image classification. There have been many studies on image detection for forest fires and fire prevention using such a deep neural network, but studies on detection of cigarette smoking were insufficient. Meanwhile, military units are establishing surveillance systems for various facilities through CCTV, and it is necessary to detect smoking near ammunition stores or non-smoking areas to prevent fires and explosions. In this paper, by reflecting experimentally optimized numerical values such as activation function and learning rate, we did the detection of smoking pictures and non-smoking pictures in two cases. As experimental data, data was constructed by crawling using pictures of smoking and non-smoking published on the Internet, and a machine learning library was used. As a result of the experiment, when the learning rate is 0.004 and the optimization algorithm Adam is used, it can be seen that the accuracy of 93% and F1-score of 94% are obtained.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.13 no.6
• /
• pp.461-469
• /
• 2020

In this paper, we propose a PCA-based feature feedback method for extracting important areas of handwritten numeric data sets and face data sets. A PCA-based feature feedback method is proposed by extending the previous LDA-based feature feedback method. In the proposed method, the data is reduced to important feature dimensions by applying the PCA technique, one of the dimension reduction machine learning algorithms. Through the weights derived during the dimensional reduction process, the important points of data in each reduced dimensional axis are identified. Each dimension axis has a different weight in the total data according to the size of the eigenvalue of the axis. Accordingly, a weight proportional to the size of the eigenvalues of each dimension axis is given, and an operation process is performed to add important points of data in each dimension axis. The critical area of the data is calculated by applying a threshold to the data obtained through the calculation process. After that, induces reverse mapping to the original data in the important area of the derived data, and selects the important area in the original data space. The results of the experiment on the MNIST dataset are checked, and the effectiveness and possibility of the pattern recognition method based on PCA-based feature feedback are verified by comparing the results with the existing LDA-based feature feedback method.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.3
• /
• pp.568-578
• /
• 2021

Patents that are research results from industry-university cooperation (IUC) are a source of innovation, and play an important role in economic growth, such as technology transfer and commercialization. For this reason, there are many efforts to revitalize IUC, but in general, company patents are achievements that can be commercialized, rather than research achievements, so not all patents are used for business, even after their creation as the outcome of IUC. Therefore, this research supports the design of measures in which IUC can ultimately be linked to successful utilization of patents by identifying the purposes of IUC, even after it has been successfully promoted, and patents have been filed as a result. To this end, first, the patents registered for industry-academia cooperation in the United States are collected, and second, a predictive model is designed, with unexpired and expired patents predicted using machine learning techniques. The final identified patents are intended to derive available factors in terms of marketability and technicality. This study is expected to help predict the utilization of unexpired and expired patents, and is expected to contribute to setting goals for research results from technical cooperation between corporate and university officials planning early IUC.

• Journal of Biomedical Engineering Research
• /
• v.42 no.3
• /
• pp.71-79
• /
• 2021

Currently, the naked eyes-based diagnosis of bone metastases on CT images relies on qualitative assessment. For this reason, there is a great need for a state-of-the-art approach that can assess and follow-up the bone metastases with quantitative biomarker. Radiomics can be used as a biomarker for objective lesion assessment by extracting quantitative numerical values from digital medical images. In this study, therefore, we evaluated the clinical applicability of non-invasive and objective bone metastases computer-aided diagnosis using radiomics-based biomarkers in CT. We employed a total of 21 approaches consist of three-classifiers and seven-feature selection methods to predict bone metastases and select biomarkers. We extracted three-dimensional features from the CT that three groups consisted of osteoblastic, osteolytic, and normal-healthy vertebral bodies. For evaluation, we compared the prediction results of the classifiers with the medical staff's diagnosis results. As a result of the three-class-classification performance evaluation, we demonstrated that the combination of the random forest classifier and the sequential backward selection feature selection approach reached AUC of 0.74 on average. Moreover, we confirmed that 90-percentile, kurtosis, and energy were the features that contributed high in the classification of bone metastases in this approach. We expect that selected quantitative features will be helpful as biomarkers in improving the patient's survival and quality of life.

• 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.