• Korea Trade Review
• /
• v.46 no.5
• /
• pp.65-81
• /
• 2021

The technological development in the era of the 4th industrial revolution is changing the paradigm of various industries. Various technologies such as big data, cloud, artificial intelligence, virtual reality, and the Internet of Things are used, creating synergy effects with existing industries, creating radical development and value creation. Among them, the logistics sector has been greatly influenced by quantitative data from the past and has been continuously accumulating and managing data, so it is highly likely to be linked with big data analysis and has a high utilization effect. The modern advanced technology has developed together with the data mining technology to discover hidden patterns and new correlations in such big data, and through this, meaningful results are being derived. Therefore, data mining occupies an important part in big data analysis, and this study tried to analyze data mining techniques that can contribute to the logistics field and common logistics using these data mining technologies. Therefore, by using the AHP technique, it was attempted to derive priorities for each type of efficient data mining for logisticalization, and R program and R Studio were used as tools to analyze this. Criteria of AHP method set association analysis, cluster analysis, decision tree method, artificial neural network method, web mining, and opinion mining. For the alternatives, common transport and delivery, common logistics center, common logistics information system, and common logistics partnership were set as factors.

• Journal of The Korean Association of Information Education
• /
• v.25 no.5
• /
• pp.705-712
• /
• 2021

This study aims to develop artificial intelligence education programs that can be easily applied in elementary schools according to the trend of the times called artificial intelligence. The training program designed the purpose and direction based on the analysis results of the needs of 70 elementary school teachers according to the steps of the ADDIE model. According to the survey, elementary school students developed a machine learning education program to set sound data as the theme of the most accessible in their daily lives and to learn the principles of artificial intelligence in solving problems using sound data in real life. These days, when the need for artificial intelligence education emerges, elementary machine learning education programs that solve daily life problems based on sound data developed in this study will lay the foundation for elementary artificial intelligence education.

• Journal of Korean Society of Water and Wastewater
• /
• v.29 no.3
• /
• pp.427-436
• /
• 2015

Developing two process models to simulate wastewater treatment process is needed to draw a comparison between measured BOD data and estimated process model data: a mathematical model based on the process mass-balance and an ANN (artificial neural network) model. Those two types of simulator can fit well in terms of effluent BOD data, which models are formulated based on the distinctive five parameters: influent flow rate, effluent flow rate, influent BOD concentration, biomass concentration, and returned sludge percentage. The structuralized mass-balance model and ANN modeI with seasonal periods can estimate data set more precisely, and changing optimization algorithm for the penalty could be a useful option to tune up the process behavior estimations. An complex model such as ANN model coupled with mass-balance equation will be required to simulate process dynamics more accurately.

• Transactions of Materials Processing
• /
• v.33 no.2
• /
• pp.96-102
• /
• 2024

This study addresses evaluation of performance of hardening model for a titanium alloy (Ti6Al4V) based on the artificial neural network (ANN) regarding the strain rate and the temperature. Uniaxial compression tests were carried out at different strain rates from 0.001 /s to 10 /s and temperatures from 575 ℃ To 975 ℃. Using the experimental data, ANN models were trained and tested with different hyperparameters, such as size of hidden layer and optimizer. The input features were determined with the equivalent plastic strain, strain rate, and temperature while the output value was set to the equivalent stress. When the number of data is sufficient with a smooth tendency, both the Bayesian regulation (BR) and the Levenberg-Marquardt (LM) show good performance to predict the flow behavior. However, only BR algorithm shows a predictability when the number of data is insufficient. Furthermore, a proper size of the hidden layer must be confirmed to describe the behavior with the limited number of the data.

• Korean Journal of Artificial Intelligence
• /
• v.6 no.2
• /
• pp.11-15
• /
• 2018

Breast cancer is one of the leading causes of cancer related death among women. So prediction of overall survival status is important into decided in adjuvant treatment. Deep belief network is a kind of artificial intelligence (AI). We intended to construct prediction model by deep belief network using associated clinicopathologic factors. 103881 cases were found in the Korean Breast Cancer Registry. After preprocessing of data, a total of 15733 cases were enrolled in this study. The median follow-up period was 82.4 months. In univariate analysis for overall survival (OS), the patients with advanced AJCC stage showed relatively high HR (HR=1.216 95% CI: 0.011-289.331, p=0.001). Based on results of univariate and multivariate analysis, input variables for learning model included 17 variables associated with overall survival rate. output was presented in one of two states: event or cencored. Individual sensitivity of training set and test set for predicting overall survival status were 89.6% and 91.2% respectively. And specificity of that were 49.4% and 48.9% respectively. So the accuracy of our study for predicting overall survival status was 82.78%. Prediction model based on Deep belief network appears to be effective in predicting overall survival status and, in particular, is expected to be applicable to decide on adjuvant treatment after surgical treatment.

• Proceedings of the Computational Structural Engineering Institute Conference
• /
• 2006.04a
• /
• pp.248-255
• /
• 2006

Among a variety of influencing components, time-variant seepage and long-term underground motion are important to understand the abnormal behavior of tunnels. Excessiveness of these two components could be the direct cause of severe damage on tunnels. however, it is not easy to quantify the effect of these on the behavior of tunnels. These parameters can be estimated by using inverse methods once the appropriate relationship between inputs and results are clarified. Various inverse methods or parameter estimation techniques such as artificial neural network and least square method can be used depending on the characteristics of given problems. Numerical analyses, experiments, or monitoring results are frequently used to prepare a set of inputs and results to establish the back analysis models. In this study, a back analysis method has been developed to estimate geotechnically hard-to-known parameters such as permeability of tunnel filter, underground water table, long-term rock mass load, size of damaged zone associated with seepage and long-term underground motion. The artificial neural network technique is adopted and the numerical models developed in the firstpart are used to prepare a set of data for learning process. Tunnel behavior especially the displacements of the lining has been exclusively investigated for the back analysis.

• Bulletin of the Korean Chemical Society
• /
• v.29 no.4
• /
• pp.833-841
• /
• 2008

Principal component-genetic algorithm-multiparameter linear regression (PC-GA-MLR) and principal component-genetic algorithm-artificial neural network (PC-GA-ANN) models were applied for prediction of melting point for 323 drug-like compounds. A large number of theoretical descriptors were calculated for each compound. The first 234 principal components (PC’s) were found to explain more than 99.9% of variances in the original data matrix. From the pool of these PC’s, the genetic algorithm was employed for selection of the best set of extracted PC’s for PC-MLR and PC-ANN models. The models were generated using fifteen PC’s as variables. For evaluation of the predictive power of the models, melting points of 64 compounds in the prediction set were calculated. Root-mean square errors (RMSE) for PC-GA-MLR and PC-GA-ANN models are 48.18 and $12.77{^{\circ}C}$, respectively. Comparison of the results obtained by the models reveals superiority of the PC-GA-ANN relative to the PC-GA-MLR and the recently proposed models (RMSE = $40.7{^{\circ}C}$). The improvements are due to the fact that the melting point of the compounds demonstrates non-linear correlations with the principal components.

• Geomechanics and Engineering
• /
• v.31 no.4
• /
• pp.353-364
• /
• 2022

This study presents a hybrid algorithm for classifying the rock joints, where the improved artificial bee colony (IABC) and the fuzzy C-means (FCM) clustering algorithms are incorporated to take advantage of the artificial bee colony (ABC) algorithm by tuning the FCM clustering algorithm to obtain the more reasonable and stable result. A coefficient is proposed to reduce the amount of blind random searches and speed up convergence, thus achieving the goals of optimizing and improving the ABC algorithm. The results from the IABC algorithm are used as initial parameters in FCM to avoid falling to the local optimum in the local search, thus obtaining stable classifying results. Two validity indices are adopted to verify the rationality and practicability of the IABC-FCM algorithm in classifying the rock joints, and the optimal amount of joint sets is obtained based on the two validity indices. Two illustrative examples, i.e., the simulated rock joints data and the field-survey rock joints data, are used in the verification to check the feasibility and practicability in rock engineering for the proposed algorithm. The results show that the IABC-FCM algorithm could be applicable in classifying the rock joint sets.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.25 no.3
• /
• pp.300-310
• /
• 2022

A vast amount of labeled data is required for deep neural network training. A typical strategy to improve the performance of a neural network given a training data set is to use data augmentation technique. The goal of this work is to offer a novel image augmentation method for improving object detection accuracy. An object in an image is removed, and a similar object from the training data set is placed in its area. An in-painting algorithm fills the space that is eliminated but not filled by a similar object. Our technique shows at most 2.32 percent improvements on mAP in our testing on a military vehicle dataset using the YOLOv4 object detector.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2018.05a
• /
• pp.351-354
• /
• 2018

본 연구에서는 일 증발접시 증발량 모델링을 위한 다변량 적응 회귀 스플라인 (multivariate adaptive regression splines, MARS) 모델의 성능을 평가하였다. 모델 입력변수 집합은 부산 관측소 (기상청)로부터 수집된 기상자료를 활용하여 증발접시 증발량과의 상관성이 높은 변수들의 조합으로 구성되었으며, 일사량, 일조시간, 평균지상온도, 최대기온의 조합으로 구성된 세 가지 입력집합이 결정되었다. MARS 모델의 성능은 네 가지의 모델성능평가지표를 활용하여 정량적으로 산출되었으며, 그 결과를 인공신경망 (artificial neural network, ANN) 모델과 비교하였다. 입력변수로서 일사량 및 일조시간을 가지는 Set 1의 경우 MARS1 모델이 ANN1 모델보다 우수한 성능을 나타내었으며, Set 2 (일사량, 일조시간, 평균지상온도)의 경우 ANN2 모델, Set 3 (일사량, 일조시간, 평균지상온도, 최대기온)의 경우 MARS3 모델이 상대적으로 우수한 모델 성능을 나타내었다. 모든 분석 모델들을 비교하였을 때, MARS3, ANN2, ANN3, MARS2, MARS1, ANN1 모델의 순서로 우수한 모델 성능을 나타내었으며, 특히 MARS3 모델은 CE = 0.790, $r^2=0.800$, RMSE = 0.762, MAE = 0.587로서 가장 우수한 일 증발접시 증발량 모델링 성능을 나타내었다. 따라서 본 연구에서 적용한 MARS 모델은 지상관측 기상자료를 활용한 일 증발접시 증발량 모델링에서 효과적인 대안이 될 수 있을 것으로 판단된다.