• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.50 no.3
• /
• pp.147-155
• /
• 2022

The accumulated ice and snow during the operation of aircraft and railway vehicles can degrade aerodynamic performance or damage the major components of vehicles. Therefore, it is crucial to predict the temporal growth of ice for operational safety. Numerical simulation of ice is widely used owing to the fact that it is economically cheaper and free from similarity problems compared to experimental methods. However, numerical simulation of ice generally divides the analysis into multi-step and assumes the quasi-steady assumption that considers every time step as steady state. Although this method enables efficient analysis, it has a disadvantage in that it cannot track continuous ice evolution. The purpose of this study is to construct a surrogate model that can predict the temporal evolution of ice shape using reduced-order modeling. Reduced-order modeling technique was validated for various ice shape generated under 100 different icing conditions, and the effect of the number of training data and the icing conditions on the prediction error of model was analyzed.

• The Journal of the Korea Contents Association
• /
• v.20 no.3
• /
• pp.424-431
• /
• 2020

This paper focused on the development of sports robot that detects a human player and shots a serve ball automatically. When robot technologies apply to the sports machine, the domain problems occurs such as outdoor environments and playing condition to recognize the visual and the vocal modalities. Gaussian mixture model and Kalman filter are used to detect the player's position in the left, right, and depth direction and to avoid the noises caused by the player's posture variation around the net. The sports robot is designed by the pan-tilt structure to shot a serve ball by pneumatic control under the multi layered software architecture. Finally, the proposed tracking and the machine performance are discussed by experimental results.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.28 no.10
• /
• pp.794-801
• /
• 2017

In this paper, we proposed airborne target recognition using multi-channel combining method in DTV-based passive radar. By combining multi-channel signals, we obtained the HRRP with sufficient range resolution. HRRP was obtained by AR method or zero-padding. From the obtained HRRP, we extracted scattering centers by CLEAN algorithm using the gradient descent. We extracted feature vectors and performed target recognition after training neural network using the extracted feature vectors. To verify performance of proposed methods, we assumed frequency bands of three broadcasting transmitters operated in Korea(Mt. Gwan-ak, Mt. Yong-moon, Kyeon-wol-ak) and used full scale 3D CAD model of four targets. Also we compared the target recognition performance of the proposed method with that of using only single-channel of three broadcasting transmitters. As a result, proposed methods showed better performance than using only single-channel at three broadcasting transmitters.

• Structural Engineering and Mechanics
• /
• v.84 no.2
• /
• pp.143-154
• /
• 2022

Corrosion of steel reinforcement is considered as the main cause of concrete structures deterioration, especially those under humid environmental conditions. Hence, fiber reinforced polymer (FRP) bars are being increasingly used as a replacement for conventional steel owing to their non-corrodible characteristics. However, predicting the shear strength of beams reinforced with FRP bars still challenging due to the lack of robust shear theory. Thus, this paper aims to develop an explicit data driven based model to predict the shear strength of FRP reinforced beams using multi-objective evolutionary polynomial regression analysis (MOGA-EPR) as data driven models learn the behavior from the input data without the need to employee a theory that aid the derivation, and thus they have an enhanced accuracy. This study also evaluates the accuracy of predictive models of shear strength of FRP reinforced concrete beams employed by different design codes by calculating and comparing the values of the mean absolute error (MAE), root mean square error (RMSE), mean (𝜇), standard deviation of the mean (𝜎), coefficient of determination (R²), and percentage of prediction within error range of ±20% (a20-index). Experimental database has been developed and employed in the model learning, validation, and accuracy examination. The statistical analysis illustrated the robustness of the developed model with MAE, RMSE, 𝜇, 𝜎, R², and a20-index of 14.6, 20.8, 1.05, 0.27, 0.85, and 0.61, respectively for training data and 10.4, 14.1, 0.98, 0.25, 0.94, and 0.60, respectively for validation data. Furthermore, the developed model achieved much better predictions than the standard predictive models as it scored lower MAE, RMSE, and 𝜎, and higher R² and a20-index. The new model can be used in future with confidence in optimized designs as its accuracy is higher than standard predictive models.

• Journal of Korea Water Resources Association
• /
• v.52 no.7
• /
• pp.475-482
• /
• 2019

Subseasonal-to-Seasonal (S2S) prediction information which have 2 weeks to 2 months lead time are expected to be used through many parts of industry fields, but utilizability is not reached to expectation because of lower predictability than weather forecast and mid- /long-term forecast. In this study, we used multi-layer perceptron (MLP) which is one of machine learning technique that was built for regression training in order to improve predictability of S2S precipitation data at South Korea through post-processing. Hindcast information of ECMWF was used for MLP training and the original data were compared with trained outputs based on dichotomous forecast technique. As a result, Bias score, accuracy, and Critical Success Index (CSI) of trained output were improved on average by 59.7%, 124.3% and 88.5%, respectively. Probability of detection (POD) score was decreased on average by 9.5% and the reason was analyzed that ECMWF's model excessively predicted precipitation days. In this study, we confirmed that predictability of ECMWF's S2S information can be improved by post-processing using MLP even the predictability of original data was low. The results of this study can be used to increase the capability of S2S information in water resource and agricultural fields.

• Journal of Intelligence and Information Systems
• /
• v.19 no.2
• /
• pp.39-54
• /
• 2013

Recent explosive increase of electronic commerce provides many advantageous purchase opportunities to customers. In this situation, customers who do not have enough knowledge about their purchases, may accept product recommendations. Product recommender systems automatically reflect user's preference and provide recommendation list to the users. Thus, product recommender system in online shopping store has been known as one of the most popular tools for one-to-one marketing. However, recommender systems which do not properly reflect user's preference cause user's disappointment and waste of time. In this study, we propose a novel recommender system which uses data mining and multi-model ensemble techniques to enhance the recommendation performance through reflecting the precise user's preference. The research data is collected from the real-world online shopping store, which deals products from famous art galleries and museums in Korea. The data initially contain 5759 transaction data, but finally remain 3167 transaction data after deletion of null data. In this study, we transform the categorical variables into dummy variables and exclude outlier data. The proposed model consists of two steps. The first step predicts customers who have high likelihood to purchase products in the online shopping store. In this step, we first use logistic regression, decision trees, and artificial neural networks to predict customers who have high likelihood to purchase products in each product group. We perform above data mining techniques using SAS E-Miner software. In this study, we partition datasets into two sets as modeling and validation sets for the logistic regression and decision trees. We also partition datasets into three sets as training, test, and validation sets for the artificial neural network model. The validation dataset is equal for the all experiments. Then we composite the results of each predictor using the multi-model ensemble techniques such as bagging and bumping. Bagging is the abbreviation of "Bootstrap Aggregation" and it composite outputs from several machine learning techniques for raising the performance and stability of prediction or classification. This technique is special form of the averaging method. Bumping is the abbreviation of "Bootstrap Umbrella of Model Parameter," and it only considers the model which has the lowest error value. The results show that bumping outperforms bagging and the other predictors except for "Poster" product group. For the "Poster" product group, artificial neural network model performs better than the other models. In the second step, we use the market basket analysis to extract association rules for co-purchased products. We can extract thirty one association rules according to values of Lift, Support, and Confidence measure. We set the minimum transaction frequency to support associations as 5%, maximum number of items in an association as 4, and minimum confidence for rule generation as 10%. This study also excludes the extracted association rules below 1 of lift value. We finally get fifteen association rules by excluding duplicate rules. Among the fifteen association rules, eleven rules contain association between products in "Office Supplies" product group, one rules include the association between "Office Supplies" and "Fashion" product groups, and other three rules contain association between "Office Supplies" and "Home Decoration" product groups. Finally, the proposed product recommender systems provides list of recommendations to the proper customers. We test the usability of the proposed system by using prototype and real-world transaction and profile data. For this end, we construct the prototype system by using the ASP, Java Script and Microsoft Access. In addition, we survey about user satisfaction for the recommended product list from the proposed system and the randomly selected product lists. The participants for the survey are 173 persons who use MSN Messenger, Daum Caf$\acute{e}$, and P2P services. We evaluate the user satisfaction using five-scale Likert measure. This study also performs "Paired Sample T-test" for the results of the survey. The results show that the proposed model outperforms the random selection model with 1% statistical significance level. It means that the users satisfied the recommended product list significantly. The results also show that the proposed system may be useful in real-world online shopping store.

• International Journal of Internet, Broadcasting and Communication
• /
• v.12 no.4
• /
• pp.232-237
• /
• 2020

Given the recent pace of development and expansion of Artificial Intelligence (AI) technology, the influence and ripple effects of AI technology on the whole of our lives will be very large and spread rapidly. The National Artificial Intelligence R&D Strategy, published in 2019, emphasizes the importance of artificial intelligence education for K-12 students. It also mentions STEM education, AI convergence curriculum, and budget for supporting the development of teaching materials and tools. However, it is necessary to create a new type of curriculum at a time when artificial intelligence curriculum has never existed before. With many attempts and discussions going very fast in all countries on almost the same starting line. Also, there is no suitable professor for K-12 students, and it is difficult to make K-12 students understand the concept of AI. In particular, it is difficult to teach elementary school students through professional programming in AI education. It is also difficult to learn tools that can teach AI concepts. In this paper, we propose an educational model for elementary school students to improve their understanding of AI through play or experience. This an experiential education model that combineds exploratory learning and discovery learning using multi-intelligence and the PLAY teaching-learning model to undertand the importance of data training or data required for AI education. This educational model is designed to learn how a computer that knows only binary numbers through UA recognizes images. Through code.org, students were trained to learn AI robots and configured to understand data bias like play. In addition, by learning images directly on a computer through TeachableMachine, a tool capable of supervised learning, to understand the concept of dataset, learning process, and accuracy, and proposed the process of AI inference.

• Korean Journal of Biological Psychiatry
• /
• v.27 no.1
• /
• pp.18-26
• /
• 2020

Objectives The aim was to find effective vectorization and classification models to predict a psychiatric diagnosis from text-based medical records. Methods Electronic medical records (n = 494) of present illness were collected retrospectively in inpatient admission notes with three diagnoses of major depressive disorder, type 1 bipolar disorder, and schizophrenia. Data were split into 400 training data and 94 independent validation data. Data were vectorized by two different models such as term frequency-inverse document frequency (TF-IDF) and Doc2vec. Machine learning models for classification including stochastic gradient descent, logistic regression, support vector classification, and deep learning (DL) were applied to predict three psychiatric diagnoses. Five-fold cross-validation was used to find an effective model. Metrics such as accuracy, precision, recall, and F1-score were measured for comparison between the models. Results Five-fold cross-validation in training data showed DL model with Doc2vec was the most effective model to predict the diagnosis (accuracy = 0.87, F1-score = 0.87). However, these metrics have been reduced in independent test data set with final working DL models (accuracy = 0.79, F1-score = 0.79), while the model of logistic regression and support vector machine with Doc2vec showed slightly better performance (accuracy = 0.80, F1-score = 0.80) than the DL models with Doc2vec and others with TF-IDF. Conclusions The current results suggest that the vectorization may have more impact on the performance of classification than the machine learning model. However, data set had a number of limitations including small sample size, imbalance among the category, and its generalizability. With this regard, the need for research with multi-sites and large samples is suggested to improve the machine learning models.

• Korean Journal of Remote Sensing
• /
• v.34 no.5
• /
• pp.811-827
• /
• 2018

The purpose of this study is to compare machine learning algorithm and deep learning algorithm in crop classification using multi-temporal remote sensing data. For this, impacts of machine learning and deep learning algorithms on (a) hyper-parameter and (2) training sample size were compared and analyzed for Haenam-gun, Korea and Illinois State, USA. In the comparison experiment, support vector machine (SVM) was applied as machine learning algorithm and convolutional neural network (CNN) was applied as deep learning algorithm. In particular, 2D-CNN considering 2-dimensional spatial information and 3D-CNN with extended time dimension from 2D-CNN were applied as CNN. As a result of the experiment, it was found that the hyper-parameter values of CNN, considering various hyper-parameter, defined in the two study areas were similar compared with SVM. Based on this result, although it takes much time to optimize the model in CNN, it is considered that it is possible to apply transfer learning that can extend optimized CNN model to other regions. Then, in the experiment results with various training sample size, the impact of that on CNN was larger than SVM. In particular, this impact was exaggerated in Illinois State with heterogeneous spatial patterns. In addition, the lowest classification performance of 3D-CNN was presented in Illinois State, which is considered to be due to over-fitting as complexity of the model. That is, the classification performance was relatively degraded due to heterogeneous patterns and noise effect of input data, although the training accuracy of 3D-CNN model was high. This result simply that a proper classification algorithms should be selected considering spatial characteristics of study areas. Also, a large amount of training samples is necessary to guarantee higher classification performance in CNN, particularly in 3D-CNN.

• Journal of Korean Society on Water Environment
• /
• v.24 no.1
• /
• pp.91-98
• /
• 2008

This work was performed to develop a model possible to predict the influent flow and influent components, which are one of main disturbances causing process problems at the operation of municipal wastewater treatment plant. In this study, artificial neural network (ANN) was used in order to develop a model that was able to predict the influent flow, $COD_{Mn}$, SS, TN 1 day-ahead, 2day-ahead and 3 day ahead. Multi-layer feed-forward back-propagation network was chosen as neural network type, and tanh-sigmoid function was used as activation function to transport signal at the neural network. And Levenberg-Marquart (LM) algorithm was used as learning algorithm to train neural network. Among 420 data sets except missing data, which were collected between 2005 and 2006 at field plant, 210 data sets were used for training, and other 210 data sets were used for validation. As result of it, ANN model for predicting the influent flow and components 1-3day ahead could be developed successfully. It is expected that this developed model can be practically used as follows: Detecting the fault related to effluent concentration that can be happened in the future by combining with other models to predict process performance in advance, and minimization of the process fault through the establishment of various control strategies based on the detection result.