• Korean Journal of Environmental Agriculture
• /
• v.37 no.4
• /
• pp.251-259
• /
• 2018

BACKGROUND: Various culture media have been used for hydroponic cultures of horticultural plants under the smart greenhouses with natural and artificial light types. Management of the culture medium for the control of medium amounts and/or necessary components absorbed by plants during the cultivation period is performed with ICT (Information and Communication Technology) and/or IoT (Internet of Things) in a smart farm system. This study was conducted to develop the cloud-based data analysis system for effective management of culture medium applying to hydroponic culture and plant growth in smart greenhouses. METHODS AND RESULTS: Conventional inorganic Yamazaki and organic media derived from agricultural byproducts such as a immature fruit, leaf, or stem were used for hydroponic culture media. Component changes of the solutions according to the growth stage were monitored and plant growth was observed. Red and green lettuce seedlings (Lactuca sativa L.) which developed 2~3 true leaves were considered as plant materials. The seedlings were hydroponically grown in the smart greenhouse with fluorescent and light-emitting diodes (LEDs) lights of $150{\mu}mol/m^2/s$ light intensity for 35 days. Growth data of the seedlings were classified and stored to develop the relational database in the virtual machine which was generated from an open stack cloud system on the base of growth parameter. Relation of the plant growth and nutrient absorption pattern of 9 inorganic components inside the media during the cultivation period was investigated. The stored data associated with component changes and growth parameters were visualized on the web through the web framework and Node JS. CONCLUSION: Time-series changes of inorganic components in the culture media were observed. The increases of the unfolded leaves or fresh weight of the seedlings were mainly dependent on the macroelements such as a $NO_3-N$, and affected by the different inorganic and organic media. Though the data analysis system was developed, actual measurement data were offered by using the user smart device, and analysis and comparison of the data were visualized graphically in time series based on the cloud database. Agricultural management in data visualization and/or plant growth can be implemented by the data analysis system under whole agricultural sites regardless of various culture environmental changes.

• 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.

• Journal of Korean Society of Steel Construction
• /
• v.19 no.1
• /
• pp.107-115
• /
• 2007

In this paper, the damping ratios of two methods, namely the half-power bandwidth method and random decrement method from the vibration measurement were examined. Ambient vibration tests were conducted on two steel-framed and one composite tall building ranging from 27 to 36 stories. The performance of the half-power bandwidth method was investigated using four sample sizes, such as 1024, 2048, 4096 and 8192. Damping by the half-power bandwidth method is slightly more overestimated than the random decrement method due to insufficient record length. Damping evaluation by the half-power bandwidth method was found to be enhanced when using the narrower bandwidth with long recorded data.

• The Korean Journal of Applied Statistics
• /
• v.32 no.6
• /
• pp.795-835
• /
• 2019

Big data has been generated in various fields. Many companies have now tried to make profits by building a system capable of analyzing big data based on artificial intelligence (AI) techniques. Integrating AI technology has made analyzing and utilizing vast amounts of data increasingly valuable. In particular, demand forecasting with maximum accuracy is critical to government and business management in various fields such as finance, procurement, production and marketing. In this case, it is important to apply an appropriate model that considers the demand pattern for each field. It is possible to analyze complex patterns of real data that can also be enlarged by a traditional time series model or regression model. However, choosing the right model among the various models is difficult without prior knowledge. Many studies based on AI techniques such as machine learning and deep learning have been proven to overcome these problems. In addition, demand forecasting through the analysis of stereotyped data and unstructured data of images or texts has also shown high accuracy. This paper introduces important areas where demand forecasts are relatively active as well as introduces machine learning and deep learning techniques that consider the characteristics of each field.

• Journal of Digital Convergence
• /
• v.18 no.11
• /
• pp.259-266
• /
• 2020

Many developments have been steadily carried out by researchers with applying knowledge-based expert system or machine learning algorithms to the financial field. In particular, it is now common to perform knowledge based system trading in using stock prices. Recently, deep learning technologies have been applied to real fields of stock trading marketplace as GPU performance and large scaled data have been supported enough. Especially, LSTM has been tried to apply to stock price prediction because of its compatibility for time series data. In this paper, we implement stock price prediction using LSTM. In modeling of LSTM, we propose a fitness combination of model parameters and activation functions for best performance. Specifically, we propose suitable selection methods of initializers of weights and bias, regularizers to avoid over-fitting, activation functions and optimization methods. We also compare model performances according to the different selections of the above important modeling considering factors on the real-world stock price data of global major companies. Finally, our experimental work brings a fitness method of applying LSTM model to stock price prediction.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.38 no.3
• /
• pp.223-235
• /
• 2020

In this study, we propose an approach for calibrating the elevation of a DEM (Digital Elevation Model), one of the key data in realizing unmanned aerial vehicle image-based precision agriculture. First of all, radiometric correction is performed on the orthophoto, and then ExG (Excess Green) is generated. The non-vegetation area is extracted based on the threshold value estimated by applying the Otsu method to ExG. Subsequently, the elevation of the DEM corresponding to the location of the non-vegetation area is extracted as EIFs (Elevation Invariant Features), which is data for elevation correction. The normalized Z-score is estimated based on the difference between the extracted EIFs to eliminate the outliers. Then, by constructing a linear regression model and correcting the elevation of the DEM, high-quality DEM is produced without GCPs (Ground Control Points). To verify the proposed method using a total of 10 DEMs, the maximum/minimum value, average/standard deviation before and after elevation correction were compared and analyzed. In addition, as a result of estimating the RMSE (Root Mean Square Error) by selecting the checkpoints, an average RMSE was derivsed as 0.35m. Comprehensively, it was confirmed that a high-quality DEM could be produced without GCPs.

• Journal of Intelligence and Information Systems
• /
• v.29 no.1
• /
• pp.107-119
• /
• 2023

The technology that recognizes a soldier's motion and movement status has recently attracted large attention as a combination of wearable technology and artificial intelligence, which is expected to upend the paradigm of troop management. The accuracy of state determination should be maintained at a high-end level to make sure of the expected vital functions both in a training situation; an evaluation and solution provision for each individual's motion, and in a combat situation; overall enhancement in managing troops. However, when input data is given as a timer series or sequence, existing feedforward networks would show overt limitations in maximizing classification performance. Since human behavior data (3-axis accelerations and 3-axis angular velocities) handled for military motion recognition requires the process of analyzing its time-dependent characteristics, this study proposes a high-performance data-driven classifier which utilizes the long-short term memory to identify the order dependence of acquired data, learning to classify eight representative military operations (Sitting, Standing, Walking, Running, Ascending, Descending, Low Crawl, and High Crawl). Since the accuracy is highly dependent on a network's learning conditions and variables, manual adjustment may neither be cost-effective nor guarantee optimal results during learning. Therefore, in this study, we optimized hyperparameters using Bayesian optimization for maximized generalization performance. As a result, the final architecture could reduce the error rate by 62.56% compared to the existing network with a similar number of learnable parameters, with the final accuracy of 98.39% for various military operations.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.88-88
• /
• 2021

최근 수자원과 수질관리 분야에 자료기반 머신러닝 모델과 딥러닝 모델의 활용이 급증하고 있다. 그러나 딥러닝 모델은 Blackbox 모델의 특성상 고전적인 질량, 운동량, 에너지 보존법칙을 고려하지 않고, 데이터에 내재된 패턴과 관계를 해석하기 때문에 물리적 법칙을 만족하지 않는 예측결과를 가져올 수 있다. 또한, 딥러닝 모델의 예측 성능은 학습데이터의 양과 변수 선정에 크게 영향을 받는 모델이기 때문에 양질의 데이터가 제공되지 않으면 모델의 bias와 variation이 클 수 있으며 정확도 높은 예측이 어렵다. 최근 이러한 자료기반 모델링 방법의 단점을 보완하기 위해 프로세스 기반 수치모델과 딥러닝 모델을 결합하여 두 모델링 방법의 장점을 활용하는 연구가 활발히 진행되고 있다(Read et al., 2019). Process-Guided Deep Learning (PGDL) 방법은 물리적 법칙을 반영하여 딥러닝 모델을 훈련시킴으로써 순수한 딥러닝 모델의 물리적 법칙 결여성 문제를 해결할 수 있는 대안으로 활용되고 있다. PGDL 모델은 딥러닝 모델에 물리적인 법칙을 해석할 수 있는 추가변수를 도입하며, 딥러닝 모델의 매개변수 최적화 과정에서 Cost 함수에 물리적 법칙을 위반하는 경우 Penalty를 추가하는 알고리즘을 도입하여 물리적 보존법칙을 만족하도록 모델을 훈련시킨다. 본 연구의 목적은 대청호의 수심별 수온을 예측하기 위해 역학적 모델과 딥러닝 모델을 융합한 PGDL 모델을 개발하고 적용성을 평가하는데 있다. 역학적 모델은 2차원 횡방향 평균 수리·수질 모델인 CE-QUAL-W2을 사용하였으며, 대청호를 대상으로 2017년부터 2018년까지 총 2년간 수온과 에너지 수지를 모의하였다. 기상(기온, 이슬점온도, 풍향, 풍속, 운량), 수문(저수위, 유입·유출 유량), 수온자료를 수집하여 CE-QUAL-W2 모델을 구축하고 보정하였으며, 모델은 저수위 변화, 수온의 수심별 시계열 변동 특성을 적절하게 재현하였다. 또한, 동일기간 대청호 수심별 수온 예측을 위한 순환 신경망 모델인 LSTM(Long Short-Term Memory)을 개발하였으며, 종속변수는 수온계 체인을 통해 수집한 수심별 고빈도 수온 자료를 사용하고 독립 변수는 기온, 풍속, 상대습도, 강수량, 단파복사에너지, 장파복사에너지를 사용하였다. LSTM 모델의 매개변수 최적화는 지도학습을 통해 예측값과 실측값의 RMSE가 최소화 되로록 훈련하였다. PGDL 모델은 동일 기간 LSTM 모델과 동일 입력 자료를 사용하여 구축하였으며, 역학적 모델에서 얻은 에너지 수지를 만족하지 않는 경우 Cost Function에 Penalty를 추가하여 물리적 보존법칙을 만족하도록 훈련하고 수심별 수온 예측결과를 비교·분석하였다.

• Journal of Navigation and Port Research
• /
• v.46 no.6
• /
• pp.517-524
• /
• 2022

This paper analyzes wave measurement using X-band navigation (ship) radar, changes in radar signal due to snowfall and precipitation, and factors that obstruct wave measurement. Data obtained from the radar installed at Sokcho Beach were used, and data from the Korea Meteorological Administration and the Korea Hydrographic and Oceanographic Agency were used for the meteorological data needed for comparative verification. Data from the Korea Meteorological Administration are measured at Sokcho Meteorological Observatory, which is about 7km away from the radar, and data from the Korea Hydrographic and Oceanographic Agency are measured at a buoy about 3km away from the radar. To this point, changes in radar signals due to rainfall or snowfall have been transmitted empirically, and there is no case of an analysis comparing the results to actual weather data. Therefore, in this paper, precipitation, snowfall data, CCTV, and radar signals from the Korea Meteorological Administration were comprehensively analyzed in time series. As a result, it was confirmed that the wave height measured by the radar according to snowfall and rainfall was reduced compared to the actual wave height, and a decrease in the radar signal strength according to the distance was also confirmed. This paper is meaningful in that it comprehensively analyzes the decrease in the signal strength of radar according to snowfall and rainfall.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.27 no.5
• /
• pp.574-583
• /
• 2021

Predicting shipping markets is an important issue. Such predictions form the basis for decisions on investment methods, fleet formation methods, freight rates, etc., which greatly affect the profits and survival of a company. To this end, in this study, we propose a shipping freight rate prediction model for container ships using gated recurrent units (GRUs) and long short-term memory structure. The target of our freight rate prediction is the China Container Freight Index (CCFI), and CCFI data from March 2003 to May 2020 were used for training. The CCFI after June 2020 was first predicted according to each model and then compared and analyzed with the actual CCFI. For the experimental model, a total of six models were designed according to the hyperparameter settings. Additionally, the ARIMA model was included in the experiment for performance comparison with the traditional analysis method. The optimal model was selected based on two evaluation methods. The first evaluation method selects the model with the smallest average value of the root mean square error (RMSE) obtained by repeating each model 10 times. The second method selects the model with the lowest RMSE in all experiments. The experimental results revealed not only the improved accuracy of the deep learning model compared to the traditional time series prediction model, ARIMA, but also the contribution in enhancing the risk management ability of freight fluctuations through deep learning models. On the contrary, in the event of sudden changes in freight owing to the effects of external factors such as the Covid-19 pandemic, the accuracy of the forecasting model reduced. The GRU1 model recorded the lowest RMSE (69.55, 49.35) in both evaluation methods, and it was selected as the optimal model.