• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.8 no.3
• /
• pp.57-67
• /
• 2018

The ensemble is a unified approach used for getting better performance by using multiple algorithms in machine learning. In this paper, we introduce boosting and bagging, which have been widely used in ensemble techniques, and design a method using support vector regression, radial basis function network, Gaussian process, and multilayer perceptron. In addition, our experiment was performed by adding a recurrent neural network and MOHID numerical model. The drifter data used for our experimental verification consist of 683 observations in seven regions. The performance of our ensemble technique is verified by comparison with four algorithms each. As verification, mean absolute error was adapted. The presented methods are based on ensemble models using bagging, boosting, and machine learning. The error rate was calculated by assigning the equal weight value and different weight value to each unit model in ensemble. The ensemble model using machine learning showed 61.7% improvement compared to the average of four machine learning technique.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.24 no.3
• /
• pp.155-163
• /
• 2022

The optimization of long-range ensemble climate prediction for rice phenology model with advanced bias correction method is conducted. The daily long-range forecast(6-month) of mean/ minimum/maximum temperature and observation of January to October during 1991-2021 is collected for rice phenology prediction. In this study, the concept of "buffer period" is newly introduced to reduce the problem after bias correction by quantile mapping with constructing the transfer function by month, which evokes the discontinuity at the borders of each month. The four experiments with different lengths of buffer periods(5, 10, 15, 20 days) are implemented, and the best combinations of buffer periods are selected per month and variable. As a result, it is found that root mean square error(RMSE) of temperatures decreases in the range of 4.51 to 15.37%. Furthermore, this improvement of climatic variables quality is linked to the performance of the rice phenology model, thereby reducing RMSE in every rice phenology step at more than 75~100% of Automated Synoptic Observing System stations. Our results indicate the possibility and added values of interdisciplinary study between atmospheric and agriculture sciences.

• Journal of the Korean Geosynthetics Society
• /
• v.23 no.3
• /
• pp.15-22
• /
• 2024

Predicting ground settlement during the improvement of soft ground and the construction of a structure is an crucial factor. Numerous studies have been conducted, and many prediction equations have been proposed to estimate settlement. Settlement can be calculated using the compression index of clay. In this study, data on water content, void ratio, liquid limit, plastic limit, and compression index from the Busan New Port area were collected to construct a dataset. Correlation analysis was conducted among the collected data. Machine learning algorithms, including Random Forest, Neural Network, Linear Regression, Ada Boost, and Gradient Boosting, were applied using the Orange mining program to propose compression index prediction models. The models' results were evaluated by comparing RMSE and MAPE values, which indicate error rates, and R² values, which signify the models' significance. As a result, water content showed the highest correlation, while the plastic limit showed a somewhat lower correlation than other characteristics. Among the compared models, the AdaBoost model demonstrated the best performance. As a result of comparing each model, the AdaBoost model had the lowest error rate and a large coefficient of determination.

• Nuclear Engineering and Technology
• /
• v.55 no.12
• /
• pp.4357-4366
• /
• 2023

MARS-KS, a domestic regulatory confirmatory code of Republic of Korea, had been developed by integrating RELAP5/MOD2 and COBRA-TF. The integration of COBRA-TF allowed to extend the capability of MARS-KS, limited to one-dimensional analysis, to multi-dimensional analysis. The use of COBRA-TF was mainly focused on subchannel analyses for simulating multi-dimensional behavior within the reactor core. However, this feature has been remained as a legacy without ongoing maintenance. Meanwhile, MARS-KS also includes its own multidimensional component, namely MULTID, which is also feasible to simulate three-dimensional convection and diffusion. The MULTID is capable of modeling the turbulent diffusion using simple mixing length model. The implementation of the turbulent mixing is of importance for analyzing the reactor core where a disturbing cross-sectional structure of rod bundle makes the flow perturbation and corresponding mixing stronger. In addition, the presence of this turbulent behavior allows the secondary transports with net mass exchange between subchannels. However, a series of assessments performed in previous studies revealed that the turbulence model of the MULTID could not simulate the aforementioned effective mixing occurred in the subchannel-scale problems. This is obvious consequence since the physical models of the MULTID neglect the effect of mass transport and thereby, it cannot model the void drift effect and resulting phasic distribution within a bundle. Thus, in this study, the turbulence mixing model of the MULTID has been improved by means of the inter-channel mixing model, widely utilized in subchannel analysis, in order to extend the application of the MULTID to small-scale problems. A series of assessments has been performed against rod bundle experiments, namely GE 3X3 and PSBT, to evaluate the performance of the introduced mixing model. The assessment results revealed that the application of the inter-channel mixing model allowed to enhance the prediction of the MULTID in subchannel scale problems. In addition, it was indicated that the code could not predict appropriate phasic distribution in the rod bundle without the model. Considering that the proper prediction of the phasic distribution is important when considering pin-based and/or assembly-based expressions of the reactor core, the results of this study clearly indicate that the inter-channel mixing model is required for analyzing the rod bundle, appropriately.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.22 no.4
• /
• pp.312-326
• /
• 2020

Generation of weather forecasts at 100 m resolution through a statistical downscaling process was implemented by Korea Meteorological Administration Post- Processing (KMAPP) system. The KMAPP data started to be used in various industries such as hydrologic, agricultural, and renewable energy, sports, etc. Cheorwon area and Jeonbuk area have horizontal planes in a relatively wide range in Korea, where there are many complex mountainous areas. Cheorwon, which has a large number of in-situ and remotely sensed phenological data over large-scale rice paddy cultivation areas, is considered as an appropriate area for verifying KMAPP prediction performance in agricultural areas. In this study, the performance of predicting KMAPP temperature changes according to ecological changes in agricultural areas in Cheorwon was compared and verified using KMA and National Center for AgroMeteorology (NCAM) observations. Also, during the heat wave in Jeonbuk Province, solar radiation forecast was verified using Automated Synoptic Observing System (ASOS) data to review the usefulness of KMAPP forecast data as input data for application models such as livestock heat stress models. Although there is a limit to the need for more cases to be collected and selected, the improvement in post-harvest temperature forecasting performance in agricultural areas over ordinary residential areas has led to indirect guesses of the biophysical and phenological effects on forecasting accuracy. In the case of solar radiation prediction, it is expected that KMAPP data will be used in the application model as detailed regional forecast data, as it tends to be consistent with observed values, although errors are inevitable due to human activity in agricultural land and data unit conversion.

• Journal of Intelligence and Information Systems
• /
• v.23 no.1
• /
• pp.95-108
• /
• 2017

Recently, AlphaGo which is Bakuk (Go) artificial intelligence program by Google DeepMind, had a huge victory against Lee Sedol. Many people thought that machines would not be able to win a man in Go games because the number of paths to make a one move is more than the number of atoms in the universe unlike chess, but the result was the opposite to what people predicted. After the match, artificial intelligence technology was focused as a core technology of the fourth industrial revolution and attracted attentions from various application domains. Especially, deep learning technique have been attracted as a core artificial intelligence technology used in the AlphaGo algorithm. The deep learning technique is already being applied to many problems. Especially, it shows good performance in image recognition field. In addition, it shows good performance in high dimensional data area such as voice, image and natural language, which was difficult to get good performance using existing machine learning techniques. However, in contrast, it is difficult to find deep leaning researches on traditional business data and structured data analysis. In this study, we tried to find out whether the deep learning techniques have been studied so far can be used not only for the recognition of high dimensional data but also for the binary classification problem of traditional business data analysis such as customer churn analysis, marketing response prediction, and default prediction. And we compare the performance of the deep learning techniques with that of traditional artificial neural network models. The experimental data in the paper is the telemarketing response data of a bank in Portugal. It has input variables such as age, occupation, loan status, and the number of previous telemarketing and has a binary target variable that records whether the customer intends to open an account or not. In this study, to evaluate the possibility of utilization of deep learning algorithms and techniques in binary classification problem, we compared the performance of various models using CNN, LSTM algorithm and dropout, which are widely used algorithms and techniques in deep learning, with that of MLP models which is a traditional artificial neural network model. However, since all the network design alternatives can not be tested due to the nature of the artificial neural network, the experiment was conducted based on restricted settings on the number of hidden layers, the number of neurons in the hidden layer, the number of output data (filters), and the application conditions of the dropout technique. The F1 Score was used to evaluate the performance of models to show how well the models work to classify the interesting class instead of the overall accuracy. The detail methods for applying each deep learning technique in the experiment is as follows. The CNN algorithm is a method that reads adjacent values from a specific value and recognizes the features, but it does not matter how close the distance of each business data field is because each field is usually independent. In this experiment, we set the filter size of the CNN algorithm as the number of fields to learn the whole characteristics of the data at once, and added a hidden layer to make decision based on the additional features. For the model having two LSTM layers, the input direction of the second layer is put in reversed position with first layer in order to reduce the influence from the position of each field. In the case of the dropout technique, we set the neurons to disappear with a probability of 0.5 for each hidden layer. The experimental results show that the predicted model with the highest F1 score was the CNN model using the dropout technique, and the next best model was the MLP model with two hidden layers using the dropout technique. In this study, we were able to get some findings as the experiment had proceeded. First, models using dropout techniques have a slightly more conservative prediction than those without dropout techniques, and it generally shows better performance in classification. Second, CNN models show better classification performance than MLP models. This is interesting because it has shown good performance in binary classification problems which it rarely have been applied to, as well as in the fields where it's effectiveness has been proven. Third, the LSTM algorithm seems to be unsuitable for binary classification problems because the training time is too long compared to the performance improvement. From these results, we can confirm that some of the deep learning algorithms can be applied to solve business binary classification problems.

• Journal of Intelligence and Information Systems
• /
• v.19 no.2
• /
• pp.1-20
• /
• 2013

Nowadays, social network is a huge communication platform for providing people to connect with one another and to bring users together to share common interests, experiences, and their daily activities. Users spend hours per day in maintaining personal information and interacting with other people via posting, commenting, messaging, games, social events, and applications. Due to the growth of user's distributed information in social network, there is a great potential to utilize the social data to enhance the quality of recommender system. There are some researches focusing on social network analysis that investigate how social network can be used in recommendation domain. Among these researches, we are interested in taking advantages of the interaction between a user and others in social network that can be determined and known as social relationship. Furthermore, mostly user's decisions before purchasing some products depend on suggestion of people who have either the same preferences or closer relationship. For this reason, we believe that user's relationship in social network can provide an effective way to increase the quality in prediction user's interests of recommender system. Therefore, social relationship between users encountered from social network is a common factor to improve the way of predicting user's preferences in the conventional approach. Recommender system is dramatically increasing in popularity and currently being used by many e-commerce sites such as Amazon.com, Last.fm, eBay.com, etc. Collaborative filtering (CF) method is one of the essential and powerful techniques in recommender system for suggesting the appropriate items to user by learning user's preferences. CF method focuses on user data and generates automatic prediction about user's interests by gathering information from users who share similar background and preferences. Specifically, the intension of CF method is to find users who have similar preferences and to suggest target user items that were mostly preferred by those nearest neighbor users. There are two basic units that need to be considered by CF method, the user and the item. Each user needs to provide his rating value on items i.e. movies, products, books, etc to indicate their interests on those items. In addition, CF uses the user-rating matrix to find a group of users who have similar rating with target user. Then, it predicts unknown rating value for items that target user has not rated. Currently, CF has been successfully implemented in both information filtering and e-commerce applications. However, it remains some important challenges such as cold start, data sparsity, and scalability reflected on quality and accuracy of prediction. In order to overcome these challenges, many researchers have proposed various kinds of CF method such as hybrid CF, trust-based CF, social network-based CF, etc. In the purpose of improving the recommendation performance and prediction accuracy of standard CF, in this paper we propose a method which integrates traditional CF technique with social relationship between users discovered from user's behavior in social network i.e. Facebook. We identify user's relationship from behavior of user such as posts and comments interacted with friends in Facebook. We believe that social relationship implicitly inferred from user's behavior can be likely applied to compensate the limitation of conventional approach. Therefore, we extract posts and comments of each user by using Facebook Graph API and calculate feature score among each term to obtain feature vector for computing similarity of user. Then, we combine the result with similarity value computed using traditional CF technique. Finally, our system provides a list of recommended items according to neighbor users who have the biggest total similarity value to the target user. In order to verify and evaluate our proposed method we have performed an experiment on data collected from our Movies Rating System. Prediction accuracy evaluation is conducted to demonstrate how much our algorithm gives the correctness of recommendation to user in terms of MAE. Then, the evaluation of performance is made to show the effectiveness of our method in terms of precision, recall, and F1-measure. Evaluation on coverage is also included in our experiment to see the ability of generating recommendation. The experimental results show that our proposed method outperform and more accurate in suggesting items to users with better performance. The effectiveness of user's behavior in social network particularly shows the significant improvement by up to 6% on recommendation accuracy. Moreover, experiment of recommendation performance shows that incorporating social relationship observed from user's behavior into CF is beneficial and useful to generate recommendation with 7% improvement of performance compared with benchmark methods. Finally, we confirm that interaction between users in social network is able to enhance the accuracy and give better recommendation in conventional approach.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.22 no.2
• /
• pp.91-99
• /
• 2014

The common-rail injectors are the most critical component of the CRDI diesel engines that dominantly affect engine performances through high pressure injection with exact control. Thus, from now on the advanced combustion technologies for common-rail diesel injection engine require high performance fuel injectors. Accordingly, the previous studies on the numerical and experimental analysis of the diesel injector have focused on a optimum geometry to induce proper injection rate. In this study, computational predictions of performance of the diesel injector have been performed to evaluate internal flow characteristics for various needle lift and the spray pattern at the nozzle exit. To our knowledge, three-dimensional computational fluid dynamics (CFD) model of the internal flow passage of an entire injector duct including injection and return routes has never been studied. In this study, major design parameters concerning internal routes in the injector are optimized by using a CFD analysis and Response Surface Method (RSM). The computational prediction of the internal flow characteristics of the common-rail diesel injector was carried out by using STAR-CCM+7.06 code. In this work, computations were carried out under the assumption that the internal flow passage is a steady-state condition at the maximum needle lift. The design parameters are optimized by using the L16 orthogonal array and polynomial regression, local-approximation characteristics of RSM. Meanwhile, the optimum values are confirmed to be valid in 95% confidence and 5% significance level through analysis of variance (ANOVA). In addition, optimal design and prototype design were confirmed by calculating the injection quantities, resulting in the improvement of the injection performance by more than 54%.

• The Journal of the Acoustical Society of Korea
• /
• v.42 no.1
• /
• pp.7-15
• /
• 2023

Recently, as interest in air quality in vehicles increases, the use of fine dust detection sensors for air quality measurement is becoming common. An axial-flow fan is inserted in the fine dust sensor installed in the air conditioning system in the vehicle to prevent dust from sinking directly on the sensor. When the sensor operates, the flow noise caused by the rotation of the axial-flow fan acts as a major noise source of the fine dust sensor. flow noise is recognized as one of the product competitiveness of fine dust sensors. In this study, the noise was gradually reduced at the same flow rate by improving the flow performance of the small axial flow fan. First, a virtual fan performance tester consisting of about 20 million grids was developed to analyze the aerodynamic performance of the target small axial-flow fan. In addition, the flow field was simulated by using compressible Large Eddy Simulation for direct computation of flow noise as well as high-accurate prediction of flow rate. The validity of numerical method are confirmed through the comparison of predicted results with experimental ones. After the effects of pitch angle on flow performance were analyzed using the verified numerical method, the pitch angle was determined to maximize the flow rate. It was found that the flow rate was increased by 8.1 % and noise was reduced by 0.8 dBA when the axial-flow fan with the optimum pitch angle was used.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.15 no.1
• /
• pp.593-601
• /
• 2014

In this study, we investigated the methods of improving the capturing ability of acid fume by assessing the performance of slot-type external hood installed on both sides of an open surface tank for acid washing process. A field survey and the results of computational fluid dynamics revealed that capturing performance of existing hoods is very poor. To solve such problem, 'push-pull hood' that pushes from one side of an open surface tank and pulls on the other side was suggested. The initial prediction was that if a push-pull hood is used, the acid fume of an acid-washing tank surface could be moved towards the hood through the push flow. However, this study has confirmed that if the push flow velocity becomes too high, it could spread to other areas due to flooding from the hood. Therefore, if the push air supply is maintained at around 25 $m^3/min$(push 10 m/s), proper control flow is formed on the surface of a tank and acid fume that stayed at the upper part of the tank is smoothly captured toward the hood, significantly enhancing the capturing performance.