• ETRI Journal
• /
• 제43권6호
• /
• pp.1058-1080
• /
• 2021

Crime is not a completely random event but rather shows a pattern in space and time. Capturing the dynamic nature of crime patterns is a challenging task. Crime prediction models that rely only on neighborhood influence and demographic features might not be able to capture the dynamics of crime patterns, as demographic data collection does not occur frequently and is static. This work proposes a novel approach for crime count and hotspot prediction to capture the dynamic nature of crime patterns using taxi data along with historical crime and demographic data. The proposed approach predicts crime events in spatial units and classifies each of them into a hotspot category based on the number of crime events. Four models are proposed, which consider different covariates to select a set of independent variables. The experimental results show that the proposed combined subset model (CSM), in which static and dynamic aspects of crime are combined by employing the taxi dataset, is more accurate than the other models presented in this study.

• 한국소성가공학회:학술대회논문집
• /
• 한국소성가공학회 2001년도 추계학술대회 논문집
• /
• pp.121-124
• /
• 2001

On-line prediction model which calculate roll force, roll power and forward slip of continuous hot strip rolling was built based on the results of plane strait rigid-viscoplastic finite element process model. Using the integrated FE process model, a series of finite element simulation was conducted over the process variables, and the influence of various process conditions on non-dimensional parameters was inspected. The prediction accuracy of the proposed on-line model under front and back tension is examined through comparison with predictions from a finite element process model over the various process conditions. In addition, we examined the validity of the on-line prediction model through comparison with roll force of experiment in hot rolling.

• Structural Engineering and Mechanics
• /
• 제9권6호
• /
• pp.557-568
• /
• 2000

As time-variant reliability approaches become increasingly used for service life prediction of the aging infrastructure, the demand for computer solution methods continues to increase. Effcient computer techniques have become well established for the reliability analysis of structural systems. Thus far, however, this is largely limited to time-invariant reliability problems. Therefore, the requirements for time-variant reliability prediction of deteriorating structural systems under time-variant loads have remained incomplete. This study presents a computer program for $\underline{REL}$iability of $\underline{T}$ime-Variant $\underline{SYS}$tems, RELTSYS. This program uses a combined technique of adaptive importance sampling, numerical integration, and fault tree analysis to compute time-variant reliabilities of individual components and systems. Time-invariant quantities are generated using Monte Carlo simulation, whereas time-variant quantities are evaluated using numerical integration. Load distribution and post-failure redistribution are considered using fault tree analysis. The strengths and limitations of RELTSYS are presented via a numerical example.

• Wind and Structures
• /
• 제29권2호
• /
• pp.129-137
• /
• 2019

The maximum along-wind displacement of a considerable amount of building under simulated wind loads is computed with the aim to produce a simple prediction model using multiple regression analysis with variables transformation. The Shinozuka and Newmark methods are used to simulate the turbulent wind and to calculate the dynamic response, respectively. In order to evaluate the prediction performance of the regression model with longer degree of determination, two complex structural models were analyzed dynamically. In addition, the prediction model proposed is used to estimate and compare the maximum response of two test buildings studied with wind loads by other authors. Finally, it was proved that the prediction model is reliable to estimate the maximum displacements of structures subjected to the wind loads.

• 한국경영과학회:학술대회논문집
• /
• 한국경영과학회 1996년도 추계학술대회발표논문집; 고려대학교, 서울; 26 Oct. 1996
• /
• pp.203-206
• /
• 1996

Prediction of firm bankruptcy have been extensively studied in accounting, as all stockholders in a firm have a vested interest in monitoring its financial performance. The objective of this paper is to develop the hybrid models for bankruptcy prediction. The proposed hybrid models are two phase. Phase one are (a) DA-assisted neural network, (b) Logit-assisted neural network, and (c) Genetic-assisted neural network. And, phase two are (a) DA-assisted Case based reasoning, and (b) Genetic-assisted Case based reasoning. In the variables selection, We are focusing on three alternative methods - linear discriminant analysis, logit analysis and genetic algorithms - that can be used empirically select predictors for hybrid model in bankruptcy prediction. Empirical results using Korean medium-sized firms data show that hybrid models are very promising neural network models and case based reasoning for bankruptcy prediction in terms of predictive accuracy and adaptability.

• 한국도로학회논문집
• /
• 제20권2호
• /
• pp.57-65
• /
• 2018

PURPOSES : The study aims to predict the service life of national highway asphalt pavements through deep learning methods by using maintenance history data of the National Highway Pavement Management System. METHODS : For the configuration of a deep learning network, this study used Tensorflow 1.5, an open source program which has excellent usability among deep learning frameworks. For the analysis, nine variables of cumulative annual average daily traffic, cumulative equivalent single axle loads, maintenance layer, surface, base, subbase, anti-frost layer, structural number of pavement, and region were selected as input data, while service life was chosen to construct the input layer and output layers as output data. Additionally, for scenario analysis, in this study, a model was formed with four different numbers of 1, 2, 4, and 8 hidden layers and a simulation analysis was performed according to the applicability of the over fitting resolution algorithm. RESULTS : The results of the analysis have shown that regardless of the number of hidden layers, when an over fitting resolution algorithm, such as dropout, is applied, the prediction capability is improved as the coefficient of determination ($R^2$) of the test data increases. Furthermore, the result of the sensitivity analysis of the applicability of region variables demonstrates that estimating service life requires sufficient consideration of regional characteristics as $R^2$ had a maximum of between 0.73 and 0.84, when regional variables where taken into consideration. CONCLUSIONS : As a result, this study proposes that it is possible to precisely predict the service life of national highway pavement sections with the consideration of traffic, pavement thickness, and regional factors and concludes that the use of the prediction of service life is fundamental data in decision making within pavement management systems.

• 한국소성가공학회:학술대회논문집
• /
• 한국소성가공학회 2000년도 춘계학술대회논문집
• /
• pp.52-55
• /
• 2000

Investigated via a series of finite element process simulation is the effect of diverse process variables on some selected non-dimensional parameters characterizing the strip in hot strip rolling. Then on the basis of these parameters an on-line model is derived for the precise prediction of roll and roll power. The prediction accuracy of the proposed model is examined through comparison with predictions from a finite element process model.

• 품질경영학회지
• /
• 제21권1호
• /
• pp.152-160
• /
• 1993

In developing a quadratic regression relationship, independent variable is frequently measured with error. In this paper the integrated mean square error of prediction is developed for a quadratic functional relationship model as a measure of the effect of measurement error of the independent variable on the predicted values. The amount of the effect of error is presented and illustrated with an example.

• 한국ITS학회 논문지
• /
• 제16권4호
• /
• pp.1-12
• /
• 2017

교통사고는 인적요인, 차량요인, 환경요인이 복합적으로 작용하여 발생한다. 이 중 렌터카 교통사고는 운전자의 평소 익숙하지 않은 환경 등으로 인해 교통사고 발생 가능성과 심각도가 다른 교통사고와는 다를 것으로 예상된다. 이에 본 연구에서는 국내 대표 관광도시인 부산광역시, 강릉시, 제주시를 대상으로 최근 빅데이터 분석에 사용되는 기계학습 기법중 하나인 나이브 베이즈 분류기를 이용하여 렌터카 교통사고의 심각도를 예측하는 모형을 개발하였다. 또한, 기존 연구에 유의성이 검증된 변수와 수집 가능한 모든 변수를 이용하는 두 가지 모형에 대하여 모형의 예측 정확도를 비교하였다. 비교 결과 통계적 기법을 통해 유의성이 검증된 변수를 사용할 경우 모형이 더 높은 예측 정확도를 보이는 것으로 나타났다.

• 한국수소및신에너지학회논문집
• /
• 제33권4호
• /
• pp.419-429
• /
• 2022

Effects of operating variables on temperature profile and performance of 3 MWth chemical looping combustion system were estimated by mass and energy balance analysis based on configuration and dimension of the system determined by design tool. Air reactor gas velocity, fuel reactor gas velocity, solid circulation rate, and solid input percentage to fluidized bed heat exchanger were considered as representative operating variables. Overall heat output and oxygen concentration in the exhaust gas from the air reactor increased but temperature difference decreased as air reactor gas velocity increased. Overall heat output, required solid circulation rate, and temperature difference increased as fuel reactor gas velocity increased. However, overall heat output and temperature difference decreased as solid circulation rate increased. Temperature difference decreased as solid circulation rate through the fluidized bed heat exchanger increased. Effect of each variables on temperature profile and performance can be determined and these results will be helpful to determine operating range of each variable.