• Journal of Korea Water Resources Association
• /
• v.53 no.11
• /
• pp.929-938
• /
• 2020

In this study, we estimated missing evapotranspiration (ET) data at a eddy-covariance flux tower in the Cheongmicheon farmland site using the Artificial Neural Network (ANN). The ANN showed excellent performance in numerical analysis and is expanding in various fields. To evaluate the performance the ANN-based gap-filling, ET was calculated using the existing gap-filling methods of Mean Diagnostic Variation (MDV) and Food and Aggregation Organization Penman-Monteith (FAO-PM). Then ET was evaluated by time series method and statistical analysis (coefficient of determination, index of agreement (IOA), root mean squared error (RMSE) and mean absolute error (MAE). For the validation of each gap-filling model, we used 30 minutes of data in 2015. Of the 121 missing values, the ANN method showed the best performance by supplementing 70, 53 and 84 missing values, respectively, in the order of MDV, FAO-PM, and ANN methods. Analysis of the coefficient of determination (MDV, FAO-PM, and ANN methods followed by 0.673, 0.784, and 0.841, respectively.) and the IOA (The MDV, FAO-PM, and ANN methods followed by 0.899, 0.890, and 0.951 respectively.) indicated that, all three methods were highly correlated and considered to be fully utilized, and among them, ANN models showed the highest performance and suitability. Based on this study, it could be used more appropriately in the study of gap-filling method of flux tower data using machine learning method.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.22 no.3
• /
• pp.451-457
• /
• 2018

We propose an automatic detection and classification system of sewer damage database based on artificial intelligence and deep learning. In order to optimize the performance, we implemented a robust system against various environmental variations such as illumination and shadow changes. In our proposed system, a crack detection and damage classification method using a deep learning based Convolutional Neural Network (CNN) is implemented. For optimal results, 9,941 CCTV images with $256{\times}256$ pixel resolution were used for machine learning on the damaged area based on the CNN model. As a result, the recognition rate of 98.76% was obtained. Total of 646 images of $720{\times}480$ pixel resolution were extracted from various sewage DB for performance evaluation. Proposed system presents the optimal recognition rate for the automatic detection and classification of damage in the sewer DB constructed in various environments.

• Korean Journal of Construction Engineering and Management
• /
• v.21 no.5
• /
• pp.11-19
• /
• 2020

A daily progress monitoring and further schedule management of a construction project have a significant impact on the construction manager's decision making in schedule change and controlling field operation. However, a current site monitoring method highly relies on the manually recorded daily-log book by the person in charge of the work. For this reason, it is difficult to take a detached view and sometimes human error such as omission of contents may occur. In order to resolve these problems, previous researches have developed automated site monitoring method with the object recognition-based visualization or BIM data creation. Despite of the research results along with the related technology development, there are limitations in application targeting the practical construction projects due to the constraints in the experimental methods that assume the fixed equipment at a specific location. To overcome these limitations, some smart devices carried by the field workers can be employed as a medium for data creation. Specifically, the extracted information from the site picture by object recognition technology of CNN model, and positional information by GIPS are applied to update 4D BIM data. A standard CNN model is developed and BIM data modification experiments are conducted with the collected data to validate the research suggestion. Based on the experimental results, it is confirmed that the methods and performance are applicable to the construction site management and further it is expected to contribute speedy and precise data creation with the application of automated progress monitoring methods.

• Journal of Convergence for Information Technology
• /
• v.11 no.11
• /
• pp.57-65
• /
• 2021

We propose a novel method to detect abnormal data of specific symptoms using deep learning in air pollution measurement system. Existing methods generally detect abnomal data by classifying data showing unusual patterns different from the existing time series data. However, these approaches have limitations in detecting specific symptoms. In this paper, we use DeepLab V3+ model mainly used for foreground segmentation of images, whose structure has been changed to handle one-dimensional data. Instead of images, the model receives time-series data from multiple sensors and can detect data showing specific symptoms. In addition, we improve model's performance by reducing the complexity of noisy form time series data by using 'piecewise aggregation approximation'. Through the experimental results, it can be confirmed that anomaly data detection can be performed successfully.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.18 no.4
• /
• pp.44-57
• /
• 2019

Various studies have been conducted to solve traffic congestions in many metropolitan cities through accurate traffic flow prediction. Most studies are based on the assumption that past traffic patterns repeat in the future. Models based on such an assumption fall short in case irregular traffic patterns abruptly occur. Instead, the approaches such as predicting traffic pattern through big data analytics and artificial intelligence have emerged. Specifically, deep learning algorithms such as RNN have been prevalent for tackling the problems of predicting temporal traffic flow as a time series. However, these algorithms do not perform well in terms of long-term prediction. In this paper, we take into account various external factors that may affect the traffic flows. We model the correlation between the multi-dimensional context information with temporal traffic speed pattern using deep neural networks. Our model trained with the traffic data from TOPIS system by Seoul, Korea can predict traffic speed on a specific date with the accuracy reaching nearly 90%. We expect that the accuracy can be improved further by taking into account additional factors such as accidents and constructions for the prediction.

• Journal of Internet Computing and Services
• /
• v.24 no.4
• /
• pp.57-64
• /
• 2023

The ROK military faces a significant challenge in its vigilance mission due to demographic problems, particularly the current aging population and population cliff. This study demonstrates the crucial role of the 4th industrial revolution and its core artificial intelligence algorithm in maximizing work efficiency within the Command&Control room by mechanizing simple tasks. To achieve a fully developed military surveillance system, we have chosen multi-object tracking (MOT) technology as an essential artificial intelligence component, aligning with our goal of an intelligent and automated surveillance system. Additionally, we have prioritized data visualization and user interface to ensure system accessibility and efficiency. These complementary elements come together to form a cohesive software application. The CCTV video data for this study was collected from the CCTV cameras installed at the 1st and 2nd main gates of the 00 unit, with the cooperation by Command&Control room. Experimental results indicate that an intelligent and automated surveillance system enables the delivery of more information to the operators in the room. However, it is important to acknowledge the limitations of the developed software system in this study. By highlighting these limitations, we can present the future direction for the development of military surveillance systems.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.15-17
• /
• 2022

In the aftermath of the avian influenza that occurred from the second half of 2020 to the beginning of 2021, 17.8 million laying hens were slaughtered. Although the government invested more than 100 billion won for egg imports as a measure to stabilize prices, the effort was not that easy. The sharp volatility of egg prices negatively affected both consumers and poultry farmers, so measures were needed to stabilize egg prices. To this end, the egg prices were successfully predicted in this study by using the analysis algorithm of a machine learning regression. For price prediction, a total of 8 independent variables, including monthly broiler chicken production statistics for 2012-2021 of the Korean Poultry Association and the slaughter performance of the national statistics portal (kosis), have been selected to be used. The Root Mean Square Error (RMSE), which indicates the difference between the predicted price and the actual price, is at the level of 103 (won), which can be interpreted as explaining the egg prices relatively well predicted. Accurate prediction of egg prices lead to flexible adjustment of egg production weeks for laying hens, which can help decision-making about stocking of laying hens. This result is expected to help secure egg price stability.

• Korean Journal of Remote Sensing
• /
• v.37 no.2
• /
• pp.321-335
• /
• 2021

Particulate matter (PM10 and PM2.5 with a diameter less than 10 and 2.5 ㎛, respectively) can be absorbed by the human body and adversely affect human health. Although most of the PM monitoring are based on ground-based observations, they are limited to point-based measurement sites, which leads to uncertainty in PM estimation for regions without observation sites. It is possible to overcome their spatial limitation by using satellite data. In this study, we developed machine learning-based retrieval algorithm for ground-level PM10 and PM2.5 concentrations using aerosol parameters from Geostationary Ocean Color Imager (GOCI) satellite and various meteorological parameters from a numerical weather prediction model during January to December of 2019. Gradient Boosted Regression Trees (GBRT) and Light Gradient Boosting Machine (LightGBM) were used to estimate PM concentrations. The model performances were examined for two types of feature sets-all input parameters (Feature set 1) and a subset of input parameters without meteorological and land-cover parameters (Feature set 2). Both models showed higher accuracy (about 10 % higher in R2) by using the Feature set 1 than the Feature set 2. The GBRT model using Feature set 1 was chosen as the final model for further analysis(PM10: R2 = 0.82, nRMSE = 34.9 %, PM2.5: R2 = 0.75, nRMSE = 35.6 %). The spatial distribution of the seasonal and annual-averaged PM concentrations was similar with in-situ observations, except for the northeastern part of China with bright surface reflectance. Their spatial distribution and seasonal changes were well matched with in-situ measurements.

• Journal of Bio-Environment Control
• /
• v.28 no.2
• /
• pp.95-103
• /
• 2019

Temperature and relative humidity are important factors in crop cultivation and should be properly controlled for improving crop yield and quality. In order to control the environment accurately, we need to predict how the environment will change in the future. The objective of this study was to predict air temperature and relative humidity at a future time by using a multilayer perceptron (MLP). The data required to train MLP was collected every 10 min from Oct. 1, 2016 to Feb. 28, 2018 in an eight-span greenhouse ($1,032m^2$) cultivating mango (Mangifera indica cv. Irwin). The inputs for the MLP were greenhouse inside and outside environment data, and set-up and operating values of environment control devices. By using these data, the MLP was trained to predict the air temperature and relative humidity at a future time of 10 to 120 min. Considering typical four seasons in Korea, three-day data of the each season were compared as test data. The MLP was optimized with four hidden layers and 128 nodes for air temperature ($R^2=0.988$) and with four hidden layers and 64 nodes for relative humidity ($R^2=0.990$). Due to the characteristics of MLP, the accuracy decreased as the prediction time became longer. However, air temperature and relative humidity were properly predicted regardless of the environmental changes varied from season to season. For specific data such as spray irrigation, however, the numbers of trained data were too small, resulting in poor predictive accuracy. In this study, air temperature and relative humidity were appropriately predicted through optimization of MLP, but were limited to the experimental greenhouse. Therefore, it is necessary to collect more data from greenhouses at various places and modify the structure of neural network for generalization.

• Journal of Intelligence and Information Systems
• /
• v.24 no.4
• /
• pp.111-136
• /
• 2018

In this paper, we propose a methodology to extract answer information about queries from various types of unstructured documents collected from multi-sources existing on web in order to expand knowledge base. The proposed methodology is divided into the following steps. 1) Collect relevant documents from Wikipedia, Naver encyclopedia, and Naver news sources for "subject-predicate" separated queries and classify the proper documents. 2) Determine whether the sentence is suitable for extracting information and derive the confidence. 3) Based on the predicate feature, extract the information in the proper sentence and derive the overall confidence of the information extraction result. In order to evaluate the performance of the information extraction system, we selected 400 queries from the artificial intelligence speaker of SK-Telecom. Compared with the baseline model, it is confirmed that it shows higher performance index than the existing model. The contribution of this study is that we develop a sequence tagging model based on bi-directional LSTM-CRF using the predicate feature of the query, with this we developed a robust model that can maintain high recall performance even in various types of unstructured documents collected from multiple sources. The problem of information extraction for knowledge base extension should take into account heterogeneous characteristics of source-specific document types. The proposed methodology proved to extract information effectively from various types of unstructured documents compared to the baseline model. There is a limitation in previous research that the performance is poor when extracting information about the document type that is different from the training data. In addition, this study can prevent unnecessary information extraction attempts from the documents that do not include the answer information through the process for predicting the suitability of information extraction of documents and sentences before the information extraction step. It is meaningful that we provided a method that precision performance can be maintained even in actual web environment. The information extraction problem for the knowledge base expansion has the characteristic that it can not guarantee whether the document includes the correct answer because it is aimed at the unstructured document existing in the real web. When the question answering is performed on a real web, previous machine reading comprehension studies has a limitation that it shows a low level of precision because it frequently attempts to extract an answer even in a document in which there is no correct answer. The policy that predicts the suitability of document and sentence information extraction is meaningful in that it contributes to maintaining the performance of information extraction even in real web environment. The limitations of this study and future research directions are as follows. First, it is a problem related to data preprocessing. In this study, the unit of knowledge extraction is classified through the morphological analysis based on the open source Konlpy python package, and the information extraction result can be improperly performed because morphological analysis is not performed properly. To enhance the performance of information extraction results, it is necessary to develop an advanced morpheme analyzer. Second, it is a problem of entity ambiguity. The information extraction system of this study can not distinguish the same name that has different intention. If several people with the same name appear in the news, the system may not extract information about the intended query. In future research, it is necessary to take measures to identify the person with the same name. Third, it is a problem of evaluation query data. In this study, we selected 400 of user queries collected from SK Telecom 's interactive artificial intelligent speaker to evaluate the performance of the information extraction system. n this study, we developed evaluation data set using 800 documents (400 questions * 7 articles per question (1 Wikipedia, 3 Naver encyclopedia, 3 Naver news) by judging whether a correct answer is included or not. To ensure the external validity of the study, it is desirable to use more queries to determine the performance of the system. This is a costly activity that must be done manually. Future research needs to evaluate the system for more queries. It is also necessary to develop a Korean benchmark data set of information extraction system for queries from multi-source web documents to build an environment that can evaluate the results more objectively.