• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.10
• /
• pp.8-15
• /
• 2020

A forecasting method using deep learning does not have consistent results due to the differences in the characteristics of the dataset, even though they have the same forecasting models and parameters. For example, the forecasting model X optimized with dataset A would not produce the optimized result with another dataset B. The forecasting model with the characteristics of the dataset needs to be optimized to increase the accuracy of the forecasting model. Therefore, this paper proposes novel optimization steps for outlier removal, dataset classification, and a CNN-LSTM-based hyperparameter tuning process to forecast the daily power usage of a university campus based on the hourly interval. The proposing model produces high forecasting accuracy with a 2% of MAPE with a single power input variable. The proposing model can be used in EMS to suggest improved strategies to users and consequently to improve the power efficiency.

• Journal of Korea Water Resources Association
• /
• v.51 no.6
• /
• pp.503-514
• /
• 2018

In recent, the hydrological regime of the Mekong river is changing drastically due to climate change and haphazard watershed development including dam construction. Information of hydrologic feature like streamflow of the Mekong river are required for water disaster prevention and sustainable water resources development in the river sharing countries. In this study, runoff simulations at the Kratie station of the lower Mekong river are performed using SWAT (Soil and Water Assessment Tool), a physics-based hydrologic model, and LSTM (Long Short-Term Memory), a data-driven deep learning algorithm. The SWAT model was set up based on globally-available database (topography: HydroSHED, landuse: GLCF-MODIS, soil: FAO-Soil map, rainfall: APHRODITE, etc) and then simulated daily discharge from 2003 to 2007. The LSTM was built using deep learning open-source library TensorFlow and the deep-layer neural networks of the LSTM were trained based merely on daily water level data of 10 upper stations of the Kratie during two periods: 2000~2002 and 2008~2014. Then, LSTM simulated daily discharge for 2003~2007 as in SWAT model. The simulation results show that Nash-Sutcliffe Efficiency (NSE) of each model were calculated at 0.9(SWAT) and 0.99(LSTM), respectively. In order to simply simulate hydrological time series of ungauged large watersheds, data-driven model like the LSTM method is more applicable than the physics-based hydrological model having complexity due to various database pressure because it is able to memorize the preceding time series sequences and reflect them to prediction.

• Korean Journal of Community Nutrition
• /
• v.6 no.5
• /
• pp.726-733
• /
• 2001

This study was designed to investigate the effect of iron supplementation on the iron nutritional status and anemia of high school girls in Korea. One hundred thirty-five female students residing in Ulian metropolitan city in Korea diagnosed as having anemia or iron deficiency participated in this study. One or two tablets of iron medicine(80-160 mg Fe as ferrous sulfate/day) were administered to all participants for 3 months. Subjects were evaluated with a questionaire, measurement of hematological indices before and after iron supplementation. The average height and weight of respondents were 161.62 $\pm$ 4.68 cm and 53.87 $\pm$ 6.10 kg, respectively. Daily intakes of energy were 1597.8 $\pm$ 302.35 kcal(76.0% RDA). Iron intakes were 13.72 $\pm$ 4.17 mg (76.3% of RDA) and calcium intakes were 580.74 $\pm$ 177.21(72.5% of RDA) before iron supp]ementation. At baseline, 63% of all participants had depleted store(serum ferritin 12 ug/ml and/or transferrin saturation(TS) < 14%). After iron supplementation, this proportion declined to 19.3%. 55.6% of subjects had 12 ug/m1 of basal ferritin concentration before iron supplementation, and this proportion declined to 16.3% after iron supplementation. The basal hemoglobin(Hb) concentrations were 12.13 $\pm$ 1.01 g/dl and they increased to 12.79 $\pm$ 0.81 g/dl, which showed significant difference artier iron supplementation(p < 0.001). The basal ferritin and TS(%) were 13.24 $\pm$ 11.66 ng/ml, 18.42 $\pm$ 10.12% and they significantly increased to 32.95 $\pm$ 21.14 ng/ml, 33.53 $\pm$ 16.64%, respectively(p < 0.001). The basal total iron binding protein(TIBC) were 467.81 $\pm$ 97.24 ug/dl and they significantly decreased to 325.05 $\pm$ 48.89 ug/dl(p < 0.001) after iron supplementation. The number of tablets administered was positively correlated with serum iron(t = 0.553, p < 0.01), serum ferritin(t = 0.557, p < 0.01), TS(%)(t = 0.588, p < 0.01) and negatively correlated with TIBC(t= -0.409, p <0.01). The anemia symptoms such as ‘Shortening of breath when going upstairs(p < 0.01)’, ‘Tired out easily(p < 0.01)’, ‘Feeling blue(p < 0.001)’, ‘Decreased ability to concentrate(p < 0.01)’, and ‘Poor memory(p < 0.001)’improved significantly after iron supplementation. In this study, daily iron supplementations were efficacious in improving the iron status and anemic symptoms of female high school students. Regular check-ups and nutrition education for adolescents are necessary because of their vulnerability to iron deficiency. Further studies are needed to determine the minimum effective dose of iron and to examine the adverse effect of long-term iron supplementation.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.16 no.4
• /
• pp.153-163
• /
• 2017

This research is based on the previous research that personally preferred safe distance, rotating angle and speed are differentiated. Thus, we use machine learning model for recognizing maneuvering modes trained per personal or per similar driving pattern groups, and we evaluate automatic driving according to maneuvering modes. By utilizing driving knowledge, we subdivided 8 kinds of longitudinal modes and 4 kinds of lateral modes, and by combining the longitudinal and lateral modes, we build 21 kinds of maneuvering modes. we train the labeled data set per time stamp through RNN, LSTM and Bi-LSTM models by the trips of drivers, which are supervised deep learning models, and evaluate the maneuvering modes of automatic driving for the test data set. The evaluation dataset is aggregated of living trips of 3,000 populations by VTTI in USA for 3 years and we use 1500 trips of 22 people and training, validation and test dataset ratio is 80%, 10% and 10%, respectively. For recognizing longitudinal 8 kinds of maneuvering modes, RNN achieves better accuracy compared to LSTM, Bi-LSTM. However, Bi-LSTM improves the accuracy in recognizing 21 kinds of longitudinal and lateral maneuvering modes in comparison with RNN and LSTM as 1.54% and 0.47%, respectively.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.11
• /
• pp.310-318
• /
• 2018

Recently, the importance of big data analysis is increasing as a large amount of data is generated by various devices connected to the Internet with the advent of Internet of Things (IoT). Especially, it is necessary to analyze various large-scale IoT streaming sensor data generated in real time and provide various services through new meaningful prediction. This paper proposes a real-time indoor PM10 concentration prediction LSTM model based on streaming data generated from IoT sensor using AWS. We also construct a real-time indoor PM10 concentration prediction service based on the proposed model. Data used in the paper is streaming data collected from the PM10 IoT sensor for 24 hours. This time series data is converted into sequence data consisting of 30 consecutive values from time series data for use as input data of LSTM. The LSTM model is learned through a sliding window process of moving to the immediately adjacent dataset. In order to improve the performance of the model, incremental learning method is applied to the streaming data collected every 24 hours. The linear regression and recurrent neural networks (RNN) models are compared to evaluate the performance of LSTM model. Experimental results show that the proposed LSTM prediction model has 700% improvement over linear regression and 140% improvement over RNN model for its performance level.

• The Journal of the Korea Contents Association
• /
• v.19 no.9
• /
• pp.308-320
• /
• 2019

This study aims at investigating the major symptoms that help family carers detect mental illness in elderly patients. Another purpose of this study is to empirically verify the major factors determining the utilization of mental health services with a focus on family carers. The results of this study are as follows. First, the most commonly detected symptoms that caused the family carers to suspect mental illness in the elderly patients were memory decline and other forms of cognitive function decline. Second, the determinants of the elderly's utilization of mental health services included the patient's long-term care insurance level, the age of the family carer, the period of care, the level stress associated with the provision of care felt by the carer, his understanding of geriatric mental illness, and the level of perception about community mental health services. Based on these findings, this study suggests policies and practical implications for the early detection of and response to elderly mental health problems and the utilization of related services from the viewpoint of the family carers of the elderly.

• Journal of Korea Water Resources Association
• /
• v.54 no.5
• /
• pp.301-309
• /
• 2021

In this study, we tried to improve the performance of the existing U-net-based deep learning rainfall prediction model, which can weaken the meaning of time series order. For this, ConvLSTM2D U-Net structure model considering temporal consistency of data was applied, and we evaluated accuracy of the ConvLSTM2D U-Net model using a RainNet model and an extrapolation-based advection model. In addition, we tried to improve the uncertainty in the model training process by performing learning not only with a single model but also with 10 ensemble models. The trained neural network rainfall prediction model was optimized to generate 10-minute advance prediction data using four consecutive data of the past 30 minutes from the present. The results of deep learning rainfall prediction models are difficult to identify schematically distinct differences, but with ConvLSTM2D U-Net, the magnitude of the prediction error is the smallest and the location of rainfall is relatively accurate. In particular, the ensemble ConvLSTM2D U-Net showed high CSI, low MAE, and a narrow error range, and predicted rainfall more accurately and stable prediction performance than other models. However, the prediction performance for a specific point was very low compared to the prediction performance for the entire area, and the deep learning rainfall prediction model also had limitations. Through this study, it was confirmed that the ConvLSTM2D U-Net neural network structure to account for the change of time could increase the prediction accuracy, but there is still a limitation of the convolution deep neural network model due to spatial smoothing in the strong rainfall region or detailed rainfall prediction.

• KIPS Transactions on Computer and Communication Systems
• /
• v.10 no.3
• /
• pp.71-80
• /
• 2021

The selection of an appropriate neural network algorithm is an important step for accurate data prediction in machine learning. Many algorithms based on basic artificial neural networks have been devised to efficiently predict future data. These networks include deep neural networks (DNNs), recurrent neural networks (RNNs), long short-term memory (LSTM) networks, and gated recurrent unit (GRU) neural networks. Developers face difficulties when choosing among these networks because sufficient information on their performance is unavailable. To alleviate this difficulty, we evaluated the performance of each algorithm by comparing their errors and processing times. Each neural network model was trained using a tax dataset, and the trained model was used for data prediction to compare accuracies among the various algorithms. Furthermore, the effects of activation functions and various optimizers on the performance of the models were analyzed The experimental results show that the GRU and LSTM algorithms yields the lowest prediction error with an average RMSE of 0.12 and an average R2 score of 0.78 and 0.75 respectively, and the basic DNN model achieves the lowest processing time but highest average RMSE of 0.163. Furthermore, the Adam optimizer yields the best performance (with DNN, GRU, and LSTM) in terms of error and the worst performance in terms of processing time. The findings of this study are thus expected to be useful for scientists and developers.

• Journal of Industrial Convergence
• /
• v.20 no.4
• /
• pp.23-30
• /
• 2022

Recently, with the development of artificial intelligence (AI) and deep learning, the importance of conversational artificial intelligence chatbots is being highlighted. In addition, chatbot research is being conducted in various fields. To build a chatbot, it is developed using an open source platform or a commercial platform for ease of development. These chatbot platforms mainly use RNN and application algorithms. The RNN algorithm has the advantages of fast learning speed, ease of monitoring and verification, and good inference performance. In this paper, a method for improving the inference performance of RNNs and applied algorithms was studied. The proposed method used the word group expansion learning technique of key words for each sentence when RNN and applied algorithm were applied. As a result of this study, the RNN, GRU, and LSTM three algorithms with a cyclic structure achieved a minimum of 0.37% and a maximum of 1.25% inference performance improvement. The research results obtained through this study can accelerate the adoption of artificial intelligence chatbots in related industries. In addition, it can contribute to utilizing various RNN application algorithms. In future research, it will be necessary to study the effect of various activation functions on the performance improvement of artificial neural network algorithms.

• Journal of Korea Entertainment Industry Association
• /
• v.15 no.5
• /
• pp.141-151
• /
• 2021

This study analyzed the meaning and functions of '-(으)ㄹ 것 같다' and '-나 보다' among the various semantic functions depending on the situation, and discussed ways to train speculative expressions more efficiently by expanding them from traditional teaching methods through visualizations applied visual thinking at real Korean language education. The speculative representation, which is the subject of this study, represents the speaker's speculation about something or situation, with slight differences in meaning depending on the basis of the speculation and the subject of the speculation. We propose a training method that can enhance the diversification and efficiency of teaching-learning through visualization of information or knowledge, speculative representations that exhibit fine semantic differences in various situations. Utilizing visual thinking in language education can simplify and provide language information through visualization of language knowledge, and learners can be efficient at organizing and organizing language knowledge. It also has the advantage of long-term memory of language information through visualization of language knowledge. Attempts of various educational methods that can be applied at the Korean language education site can contribute to establishing a more systematic and efficient education method, which is meaningful in that the visual thinking proposed in this study can give interest and efficiency to international students.