• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.40 no.3
• /
• pp.273-283
• /
• 2020

Because of climate change, the occurrence of localized and heavy rainfall is increasing. It is important to predict floods in urban areas that have suffered inundation in the past. For flood prediction, not only numerical analysis models but also machine learning-based models can be applied. The LSTM (Long Short-Term Memory) neural network used in this study is appropriate for sequence data, but it demands a lot of data. However, rainfall that causes flooding does not appear every year in a single urban basin, meaning it is difficult to collect enough data for deep learning. Therefore, in addition to the rainfall observed in the study area, the observed rainfall in another urban basin was applied in the predictive model. The LSTM neural network was used for predicting the total overflow, and the result of the SWMM (Storm Water Management Model) was applied as target data. The prediction of the inundation map was performed by using logistic regression; the independent variable was the total overflow and the dependent variable was the presence or absence of flooding in each grid. The dependent variable of logistic regression was collected through the simulation results of a two-dimensional flood model. The input data of the two-dimensional flood model were the overflow at each manhole calculated by the SWMM. According to the LSTM neural network parameters, the prediction results of total overflow were compared. Four predictive models were used in this study depending on the parameter of the LSTM. The average RMSE (Root Mean Square Error) for verification and testing was 1.4279 ㎥/s, 1.0079 ㎥/s for the four LSTM models. The minimum RMSE of the verification and testing was calculated as 1.1655 ㎥/s and 0.8797 ㎥/s. It was confirmed that the total overflow can be predicted similarly to the SWMM simulation results. The prediction of inundation extent was performed by linking the logistic regression with the results of the LSTM neural network, and the maximum area fitness was 97.33 % when more than 0.5 m depth was considered. The methodology presented in this study would be helpful in improving urban flood response based on deep learning methodology.

• 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 Korean Society of Transportation
• /
• v.20 no.4
• /
• pp.151-162
• /
• 2002

The object of this study is to develop an operating time prediction model for expressways using toll collection data. A Prediction model based on modular neural network model was developed and tested using real data. Two toll collection system(TCS) data set. Seoul-Suwon section for short range and Seoul-Daejeon section for long range, in Kyongbu expressway line were collected and analyzed. A time series analysis on TCS data indicated that operating times on both ranges are in reasonable prediction ranges. It was also found that prediction for the long section was more complex than that for the short section. However, a long term prediction for the short section turned out to be more difficult than that for the long section because of the higher sensitivity to initial condition. An application of the suggested model produced accurate prediction time. The features of suggested prediction model are in the requirement of minimum (3) input layers and in the ability of stable operating time prediction.

• Journal of Intelligence and Information Systems
• /
• v.26 no.2
• /
• pp.1-25
• /
• 2020

In this paper, we suggest an application system architecture which provides accurate, fast and efficient automatic gasometer reading function. The system captures gasometer image using mobile device camera, transmits the image to a cloud server on top of private LTE network, and analyzes the image to extract character information of device ID and gas usage amount by selective optical character recognition based on deep learning technology. In general, there are many types of character in an image and optical character recognition technology extracts all character information in an image. But some applications need to ignore non-of-interest types of character and only have to focus on some specific types of characters. For an example of the application, automatic gasometer reading system only need to extract device ID and gas usage amount character information from gasometer images to send bill to users. Non-of-interest character strings, such as device type, manufacturer, manufacturing date, specification and etc., are not valuable information to the application. Thus, the application have to analyze point of interest region and specific types of characters to extract valuable information only. We adopted CNN (Convolutional Neural Network) based object detection and CRNN (Convolutional Recurrent Neural Network) technology for selective optical character recognition which only analyze point of interest region for selective character information extraction. We build up 3 neural networks for the application system. The first is a convolutional neural network which detects point of interest region of gas usage amount and device ID information character strings, the second is another convolutional neural network which transforms spatial information of point of interest region to spatial sequential feature vectors, and the third is bi-directional long short term memory network which converts spatial sequential information to character strings using time-series analysis mapping from feature vectors to character strings. In this research, point of interest character strings are device ID and gas usage amount. Device ID consists of 12 arabic character strings and gas usage amount consists of 4 ~ 5 arabic character strings. All system components are implemented in Amazon Web Service Cloud with Intel Zeon E5-2686 v4 CPU and NVidia TESLA V100 GPU. The system architecture adopts master-lave processing structure for efficient and fast parallel processing coping with about 700,000 requests per day. Mobile device captures gasometer image and transmits to master process in AWS cloud. Master process runs on Intel Zeon CPU and pushes reading request from mobile device to an input queue with FIFO (First In First Out) structure. Slave process consists of 3 types of deep neural networks which conduct character recognition process and runs on NVidia GPU module. Slave process is always polling the input queue to get recognition request. If there are some requests from master process in the input queue, slave process converts the image in the input queue to device ID character string, gas usage amount character string and position information of the strings, returns the information to output queue, and switch to idle mode to poll the input queue. Master process gets final information form the output queue and delivers the information to the mobile device. We used total 27,120 gasometer images for training, validation and testing of 3 types of deep neural network. 22,985 images were used for training and validation, 4,135 images were used for testing. We randomly splitted 22,985 images with 8:2 ratio for training and validation respectively for each training epoch. 4,135 test image were categorized into 5 types (Normal, noise, reflex, scale and slant). Normal data is clean image data, noise means image with noise signal, relfex means image with light reflection in gasometer region, scale means images with small object size due to long-distance capturing and slant means images which is not horizontally flat. Final character string recognition accuracies for device ID and gas usage amount of normal data are 0.960 and 0.864 respectively.

• Journal of Korean Society of Transportation
• /
• v.20 no.6
• /
• pp.59-68
• /
• 2002

AADT(Annual Average Daily Traffic) can be obtained by using short-term counted traffic data rather than using traffic data collected for 365 days. The process is a very important in estimating AADT using short-term traffic count data. Therefore, There have been many studies about estimating AADT. In this Paper, we tried to improve the process of the AADT estimation based on the former AADT estimation researches. Firstly, we found the factor showing differences among groups. To do so, we examined hourly variables(divided to total hours, weekday hours. Saturday hours, Sunday hours, weekday and Sunday hours, and weekday and Saturday hours) every time changing the number of groups. After all, we selected the hourly variables of Sunday and weekday as the factor showing differences among groups. Secondly, we classified 200 locations into 10 groups through cluster analysis using only monthly variables. The nile of deciding the number of groups is maximizing deviation among hourly variables of each group. Thirdly, we classified 200 locations which had been used in the second step into the 10 groups by applying statistical techniques such as Discriminant analysis and Neural network. This step is for testing the rate of distinguish between the right group including each location and a wrong one. In conclusion, the result of this study's method was closer to real AADT value than that of the former method. and this study significantly contributes to improve the method of AADT estimation.

• Journal of the Korea Concrete Institute
• /
• v.24 no.4
• /
• pp.481-490
• /
• 2012

Evaluation of chloride penetration is very important, because induced chloride ion causes corrosion in embedded steel. Diffusion coefficient obtained from rapid chloride penetration test is currently used, however this method cannot provide a correct prediction of chloride content since it shows only ion migration velocity in electrical field. Apparent diffusion coefficient of chloride ion based on simple Fick's Law can provide a total chloride penetration magnitude to engineers. This study proposes an analysis technique to predict chloride penetration using apparent diffusion coefficient of chloride ion from neural network (NN) algorithm and time-dependent diffusion phenomena. For this work, thirty mix proportions with the related diffusion coefficients are studied. The components of mix proportions such as w/b ratio, unit content of cement, slag, fly ash, silica fume, and fine/coarse aggregate are selected as neurons, then learning for apparent diffusion coefficient is trained. Considering time-dependent diffusion coefficient based on Fick's Law, the technique for chloride penetration analysis is proposed. The applicability of the technique is verified through test results from short, long term submerged test, and field investigations. The proposed technique can be improved through NN learning-training based on the acquisition of various mix proportions and the related diffusion coefficients of chloride ion.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.8
• /
• pp.21-30
• /
• 2023

The study proposes a model that utilizes Python-based deep learning text classification techniques to detect the legality of illegal financial advertising posts on the internet. These posts aim to promote unlawful financial activities, including the trading of bank accounts, credit card fraud, cashing out through mobile payments, and the sale of personal credit information. Despite the efforts of financial regulatory authorities, the prevalence of illegal financial activities persists. By applying this proposed model, the intention is to aid in identifying and detecting illicit content in internet-based illegal financial advertisining, thus contributing to the ongoing efforts to combat such activities. The study utilizes convolutional neural networks(CNN) and recurrent neural networks(RNN, LSTM, GRU), which are commonly used text classification techniques. The raw data for the model is based on manually confirmed regulatory judgments. By adjusting the hyperparameters of the Korean natural language processing and deep learning models, the study has achieved an optimized model with the best performance. This research holds significant meaning as it presents a deep learning model for discerning internet illegal financial advertising, which has not been previously explored. Additionally, with an accuracy range of 91.3% to 93.4% in a deep learning model, there is a hopeful anticipation for the practical application of this model in the task of detecting illicit financial advertisements, ultimately contributing to the eradication of such unlawful financial advertisements.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.35 no.5
• /
• pp.423-430
• /
• 2017

Recently, data analysis research has been carried out using the deep learning technique in various fields such as image interpretation and/or classification. Various types of algorithms are being developed for many applications. In this paper, we propose a precipitation prediction algorithm based on deep learning with high accuracy in order to take care of the possible severe damage caused by climate change. Since the geographical and seasonal characteristics of Korea are clearly distinct, the meteorological factors have repetitive patterns in a time series. Since the LSTM (Long Short-Term Memory) is a powerful algorithm for consecutive data, it was used to predict precipitation in this study. For the numerical test, we calculated the PWV (Precipitable Water Vapor) based on the tropospheric delay of the GNSS (Global Navigation Satellite System) signals, and then applied the deep learning technique to the precipitation prediction. The GNSS data was processed by scientific software with the troposphere model of Saastamoinen and the Niell mapping function. The RMSE (Root Mean Squared Error) of the precipitation prediction based on LSTM performs better than that of ANN (Artificial Neural Network). By adding GNSS-based PWV as a feature, the over-fitting that is a latent problem of deep learning was prevented considerably as discussed in this study.

• Environmental Engineering Research
• /
• v.14 no.2
• /
• pp.111-119
• /
• 2009

A prototype GIS-based decision support system (DSS) was developed by using a database management system (DBMS), a model management system (MMS), a knowledge-based system (KBS), a graphical user interface (GUI), and a geographical information system (GIS). The method of selecting a dispersion model or a modeling scheme, originally devised by Park and Seok, was developed using our GIS-based DSS. The performances of candidate models or modeling schemes were evaluated by using a single index(statistical score) derived by applying fuzzy inference to statistical measures between the measured and predicted concentrations. The fumigation dispersion model performed better than the models such as industrial source complex short term model(ISCST) and atmospheric dispersion model system(ADMS) for the prediction of the ground level $SO_2$ (1 hr) concentration in a coastal area. However, its coincidence level between actual and calculated values was poor. The neural network models were found to improve the accuracy of predicted ground level $SO_2$ concentration significantly, compared to the fumigation models. The GIS-based DSS may serve as a useful tool for selecting the best prediction model, even for complex terrains.

• Journal of Electrical Engineering and Technology
• /
• v.13 no.3
• /
• pp.1089-1098
• /
• 2018

This study aims at developing and applying a hybrid model to the wind power prediction (WPP). The hybrid model for a very-short-term WPP (VSTWPP) is achieved through analytical data, multiple linear regressions and least square methods (MLR&LS). The data used in our hybrid model are based on the historical records of wind power from an offshore region. In this model, the WPP is achieved in four steps: 1) transforming historical data into ratios; 2) predicting the wind power using the ratios; 3) predicting rectification ratios by the total wind power; 4) predicting the wind power using the proposed rectification method. The proposed method includes one-step and multi-step predictions. The WPP is tested by applying different models, such as the autoregressive moving average (ARMA), support vector machine (SVM), and artificial neural network (ANN). The results of all these models confirmed the validity of the proposed hybrid model in terms of error as well as its effectiveness. Furthermore, forecasting errors are compared to depict a highly variable WPP, and the correlations between the actual and predicted wind powers are shown. Simulations are carried out to definitely prove the feasibility and excellent performance of the proposed method for the VSTWPP versus that of the SVM, ANN and ARMA models.