• Journal of Cadastre & Land InformatiX
• /
• v.52 no.2
• /
• pp.211-231
• /
• 2022

This study attempted to identify the effects of macroeconomic variables such as the All Industry Production Index, Consumer Price Index, CD Interest Rate, and KOSPI on apartment lease prices divided into nationwide, Seoul, metropolitan, and region, and to present a methodological prediction model of apartment lease prices by region using Long Short Term Memory (LSTM). According to VAR analysis results, the nationwide apartment lease price index and consumer price index in Lag1 and 2 had a significant effect on the nationwide apartment lease price, and likewise, the Seoul apartment lease price index, the consumer price index, and the CD interest rate in Lag1 and 2 affect the apartment lease price in Seoul. In addition, it was confirmed that the wide-area apartment jeonse price index and the consumer price index had a significant effect on Lag1, and the local apartment jeonse price index and the consumer price index had a significant effect on Lag1. As a result of the establishment of the LSTM prediction model, the predictive power was the highest with RMSE 0.008, MAE 0.006, and R-Suared values of 0.999 for the local apartment lease price prediction model. In the future, it is expected that more meaningful results can be obtained by applying an advanced model based on deep learning, including major policy variables

• Journal of Information Processing Systems
• /
• v.15 no.3
• /
• pp.682-693
• /
• 2019

The traditional classification methods mostly assume that the data for class distribution is balanced, while imbalanced data is widely found in the real world. So it is important to solve the problem of classification with imbalanced data. In Mahalanobis-Taguchi system (MTS) algorithm, data classification model is constructed with the reference space and measurement reference scale which is come from a single normal group, and thus it is suitable to handle the imbalanced data problem. In this paper, an improved method of MTS-CBPSO is constructed by introducing the chaotic mapping and binary particle swarm optimization algorithm instead of orthogonal array and signal-to-noise ratio (SNR) to select the valid variables, in which G-means, F-measure, dimensionality reduction are regarded as the classification optimization target. This proposed method is also applied to the financial distress prediction of Chinese listed companies. Compared with the traditional MTS and the common classification methods such as SVM, C4.5, k-NN, it is showed that the MTS-CBPSO method has better result of prediction accuracy and dimensionality reduction.

• Wind and Structures
• /
• v.39 no.2
• /
• pp.85-100
• /
• 2024

In light of extreme value distribution probability, an improved prediction method of the Recurrence Period Wind Speed (RPWS) is constructed considering wind direction, with the Equivalent Independent Wind Direction Number (EIWDN) introduced as a parameter variable. Firstly, taking the RPWS prediction of Beijing city as an example, the traditional Cook method is used to predict the RPWS of each wind direction based on the measured wind speed data in Beijing area. On basis of the results, the empirical formulae to determine the parameter variables are fitted to construct an improved expression of the non-exceedance probability of the RPWS. In this process, the statistical model of the optimal threshold is established, and thus the independent wind speed samples exceeding the threshold are extracted and fitted to follow the Generalized Pareto Distribution (GPD) model for analysis. In addition, the Extreme Value Type I (EVT I) distribution model is used to predict and analyze the RPWS. To verify its wide applicability, the improved method is further used in cities like Jinan, Nanjing, Wuxi, Shanghai and Shenzhen to predict and analyze the RPWS of each wind direction, and the prediction results are compared against those gained via the traditional Cook method and the whole direction. Results show that the 50-year RPWS results predicted by the improved method are basically consistent with those predicted by the traditional method, and the RPWS prediction values of most wind directions are within the envelope range of the whole wind direction prediction value. Compared with the traditional method, the improved method can readily predict the RPWS under different return periods through empirical formulae, and avoid the repeated operation process and some assumptions in the traditional Cook method, and then improve the efficiency of prediction. In addition, the improved RPWS prediction results corresponding to the GPD model are slightly larger than those of the EVT I distribution model.

• Journal of the Society of Disaster Information
• /
• v.17 no.2
• /
• pp.245-253
• /
• 2021

Purpose: This study develops a risk prediction model that predicts the risk of a fire site by using initial information such as building information and reporter acquisition information, and supports effective mobilization of fire fighting resources and the establishment of damage minimization strategies for appropriate responses in the early stages of a disaster. Method: In order to identify the variables related to the fire damage scale on the fire statistics data, a correlation analysis between variables was performed using a machine learning algorithm to examine predictability, and a learning data set was constructed through preprocessing such as data standardization and discretization. Using this, we tested a plurality of machine learning algorithms, which are evaluated as having high prediction accuracy, and developed a risk prediction model applying the algorithm with the highest accuracy. Result: As a result of the machine learning algorithm performance test, the accuracy of the random forest algorithm was the highest, and it was confirmed that the accuracy of the intermediate value was relatively high for the risk class. Conclusion: The accuracy of the prediction model was limited due to the bias of the damage scale data in the fire statistics, and data refinement by matching data and supplementing the missing values was necessary to improve the predictive model performance.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.652-657
• /
• 2004

As the real-time multimedia applications through Internet increase, the bandwidth available to TCP connections is oppressed by the UDP traffic, result in the performance of overall system is extremely deteriorated. Therefore, developing a new transmission protocol is necessary. The TCP-friendly algorithm is an example meeting this necessity. The TCP-friendly (TFRC) is an UDP-based protocol that controls the transmission rate based on the available round transmission time (RTT) and the packet loss rate (PLR). In the data transmission processing, transmission rate is determined based on the conditions of the previous transmission period. If the one-step ahead predicted values of the control factors are available, the performance will be improved significantly. This paper proposes a prediction model of transmission rate control factors that will be used for the transmission rate control, which improves the performance of the networks. The model developed through this research is predicting one-step ahead variables of RTT and PLR. A multiplayer perceptron neural network is used as the prediction model and Levenberg-Marquardt algorithm is used for the training. The values of RTT and PLR were collected using TFRC protocol in the real system. The obtained prediction model is validated using new data set and the results show that the obtained model predicts the factors accurately.

• Environmental Engineering Research
• /
• v.22 no.3
• /
• pp.302-311
• /
• 2017

Nowadays, with the burgeoning development of economy, $CO_2$ emissions increase rapidly in China. It has become a common concern to seek effective methods to forecast $CO_2$ emissions and put forward the targeted reduction measures. This paper proposes a novel hybrid model combined principal component analysis (PCA) with regularized extreme learning machine (RELM) to make $CO_2$ emissions prediction based on the data from 1978 to 2014 in China. First eleven variables are selected on the basis of Pearson coefficient test. Partial autocorrelation function (PACF) is utilized to determine the lag phases of historical $CO_2$ emissions so as to improve the rationality of input selection. Then PCA is employed to reduce the dimensionality of the influential factors. Finally RELM is applied to forecast $CO_2$ emissions. According to the modeling results, the proposed model outperforms a single RELM model, extreme learning machine (ELM), back propagation neural network (BPNN), GM(1,1) and Logistic model in terms of errors. Moreover, it can be clearly seen that ELM-based approaches save more computing time than BPNN. Therefore the developed model is a promising technique in terms of forecasting accuracy and computing efficiency for $CO_2$ emission prediction.

• Atmosphere
• /
• v.32 no.3
• /
• pp.191-206
• /
• 2022

Assimilation trials were performed using the Korea Institute of Atmospheric Prediction Systems (KIAPS) Korea Integrated Model (KIM) semi-operational forecast system to assess the impact of ground-based Global Navigation Satellite System (GNSS) Zenith Total Delay (ZTD) on forecast. To use the optimal observation in data assimilation of KIM forecast system, in this study, the ZTD observation were pre-processed. It involves the bias correction using long term background of KIM, the quality control based on background and the thinning of ZTD data. Also, to give the effect of observation directly to data assimilation, the observation operator which include non-linear model, tangent linear model, adjoint model, and jacobian code was developed and verified. As a result, impact of ZTD observation in both analysis and forecast was neutral or slightly positive on most meteorological variables, but positive on geopotential height. In addition, ZTD observations contributed to the improvement on precipitation of KIM forecast, specially over 5 mm/day precipitation intensity.

• Journal of Institute of Control, Robotics and Systems
• /
• v.11 no.4
• /
• pp.385-391
• /
• 2005

As the Internet real-time multimedia applications increases, the bandwidth available to TCP connections is oppressed by the UDP traffic, result in the performance of overall system is extremely deteriorated. Therefore, developing a new transmission protocol is necessary. The TCP-friendly algorithm is an example satisfying this necessity. The TCP-Friendly Rate Control (TFRC) is an UDP-based protocol that controls the transmission rate that is based on the available round trip time (RTT) and the packet loss rate (PLR). In the data transmission processing, transmission rate is determined based on the conditions of the previous transmission period. If the one-step ahead predicted values of the control factors are available, the performance will be improved significantly. This paper proposes a prediction model of transmission rate control factors that will be used in the transmission rate control, which improves the performance of the networks. The model developed through this research is predicting one-step ahead variables of RTT and PLR. A multiplayer perceptron neural network is used as the prediction model and Levenberg-Marquardt algorithm is used for the training. The values of RTT and PLR were collected using TFRC protocol in the real system. The obtained prediction model is validated using new data set and the results show that the obtained model predicts the factors accurately.

• The Journal of Korean Institute of Information Technology
• /
• v.17 no.9
• /
• pp.11-17
• /
• 2019

In recent years, damage and loss of life and property have been occurred frequently due to swelling waves in the East Sea. Swelling waves are not easy to predict because they are caused by various factors. In this research, we build a model for predicting the swelling waves occurrence in the East Coast of Korea using machine learning technique. We collect historical data of unloading interruption in the Pohang Port, and collect air pressure, wind speed, direction, water temperature data of the offshore Pohang Port. We select important variables for prediction, and test various machine learning prediction algorithms. As a result, tide level, water temperature, and air pressure were selected, and Random Forest model produced best performance. We confirm that Random Forest model shows best performance and it produces 88.86% of accuracy

• Asia-Pacific Journal of Business
• /
• v.13 no.2
• /
• pp.107-122
• /
• 2022

Purpose - This study aims to develop machine learning models to predict administrative issue designation in KOSDAQ Market using financial data. Design/methodology/approach - Employing four classification techniques including logistic regression, support vector machine, random forest, and gradient boosting to a matched sample of five hundred and thirty-six firms over an eight-year period, the authors develop prediction models and explore the practicality of the models. Findings - The resulting four binary selection models reveal overall satisfactory classification performance in terms of various measures including AUC (area under the receiver operating characteristic curve), accuracy, F1-score, and top quartile lift, while the ensemble models (random forest and gradienct boosting) outperform the others in terms of most measures. Research implications or Originality - Although the assessment of administrative issue potential of firms is critical information to investors and financial institutions, detailed empirical investigation has lagged behind. The current research fills this gap in the literature by proposing parsimonious prediction models based on a few financial variables and validating the applicability of the models.