Development of Predictive Model for the Number of Potholes Using Multi Regression Analysis

Lee, Sang-Yum; Kim, Do Wan; Choi, Yonghyun

doi:10.9798/kosham.2014.14.3.91

Cited by 3 publications

(4 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…To verify the reliability of the derived multi-linear regression equation, correlation coefficient, decision coefficient, adjusted R-square and error were calculated. The error is RMSE and is given by the following Equation (5) [ 9 ]:

…”

Section: Applicability Of the 2 Mhz Side Scan Sonarmentioning

confidence: 99%

Development of a 2 MHz Sonar Sensor for Inspection of Bridge Substructures

Park¹,

Kim²,

Lee³

et al. 2018

Sensors

View full text Add to dashboard Cite

Hydraulic factors account for a large part of the causes of bridge collapse. Due to the nature of the underwater environment, quick and accurate inspection is required when damage occurs. In this study, we developed a 2 MHz side scan sonar sensor module and effective operation technique by improving the limitations of existing sonar. Through field tests, we analyzed the correlation of factors affecting the resolution of the sonar data such as the angle of survey, the distance from the underwater structure and the water depth. The effect of the distance and the water depth and the structure on the survey angle was 66~82%. We also derived the relationship between these factors as a regression model for effective operating techniques. It is considered that application of the developed 2 MHz side scan sonar and its operation method could contribute to prevention of bridge collapses and disasters by quickly and accurately checking the damage of bridge substructures due to hydraulic factors.

show abstract

…”

Section: Applicability Of the 2 Mhz Side Scan Sonarmentioning

confidence: 99%

Development of a 2 MHz Sonar Sensor for Inspection of Bridge Substructures

Park¹,

Kim²,

Lee³

et al. 2018

Sensors

View full text Add to dashboard Cite

show abstract

“…The coefficient of correlation used in this study is coefficient of determination and adjusted -square, and the coefficient of determination can be expressed as the square of the correlation coefficient [13]. In addition, to prevent the correlation adj 2 from increasing because of the addition of a relatively low independent variable, the coefficient of determination after adjustment was used [14]. This is shown in the following:…”

Section: Journal Of Sensorsmentioning

confidence: 99%

“…As a result of analysis, the distance between water depth and structure showed a major influence on angle of the towfish. In this case, since the value, which is probability of significance, indicates the degree of rejection of the null hypothesis that the independent variable affects the dependent variable, it can be judged that the smaller the value is, the more significant it is [14,16]. The larger value and the more independent variables affect the dependent variable because the standardization factor ( ) is an indicator of the influence of each independent variable on the dependent variable [17].…”

Section: Journal Of Sensorsmentioning

confidence: 99%

A Study for Optimum Survey Method of Underwater Structure Using the Dual Sonar Sensor

Kim¹,

Lee²,

Park³

et al. 2017

Journal of Sensors

View full text Add to dashboard Cite

We have developed dual sonar equipment and an improved operating method for improving resolution in order to solve the problems of limitations of the optical equipment and the application method of SSS (side scan sonar) in the investigation of damage of underwater structures. We analyzed the influence factors of the resolution of sonar data through the comparison of resolution and data quality in indoor test. Also we confirmed the problems about the overlapping area of the dual sonar. Depth and distance were analyzed as major influencing factors for survey angle. Specimens were scanned while adjusting distance and towfish angle according to depth change in order to verify applicability of the developed dual sonar in the field experiment. Optimal resolution was found to be 3 cm in specimen spacing, and 20 sample data items were extracted. We developed the regression model based on the multiple regression analysis and developed the RealDualSONAR-DAQ tool, the dual sonar optimum operating method program based on proposed correlation equations. We can use the developed tools to get the value of the major influencing factors for dual sonar operation and obtain high quality sonar data to analyze damage of underwater structures.

show abstract

“…6. Pothole Occurrence Analysis기존 연구(Kim, Han et al, 2014)에서는 포트홀 발생에 대한 예측은 기상 및 교통량에 관련된다는 결론을 내렸다(Lee et al, 2014;Lee et al, 2017). 개설해 다양한 정보를 제공하고 있다.…”

unclassified

Predictive Modeling of Pavement Damage Using Machine Learning and Big Data Processing

Kim¹,

Jeon²,

Kim³

2019

J. Korean Soc. Hazard Mitig

View full text Add to dashboard Cite

Potholes, soil settlement, and road subsidence have become major road safety hazards in South Korea. Such problems not only impede driver and pedestrian safety but also cause secondary accidents, economic losses, and damage the nation's image. To this end, we developed local predictive models that can be extrapolated to national estimation models. These models were developed from a specific area (Seoul Metropolitan City) that has the highest occurrences of potholes and road subsidence. This research utilized big data and artificial intelligence techniques to develop these models. The first step involved the dimensional reduction of independent variables using a mechanical-statistical approach. A data standardization process was then used for reducing the uncertainty of these variables. A total of 19 machine learning optimization methods were used to train the standardized variables. The optimized models were finally determined by an error comparison. As a result, the optimized prediction models for potholes, soil settlement, and road subsidence were found to be multiple regression analysis that showed an accuracy of 70% and robust regression analysis that showed an accuracy of 73%.

show abstract

Development of Predictive Model for the Number of Potholes Using Multi Regression Analysis

Cited by 3 publications

References 3 publications

Development of a 2 MHz Sonar Sensor for Inspection of Bridge Substructures

Development of a 2 MHz Sonar Sensor for Inspection of Bridge Substructures

A Study for Optimum Survey Method of Underwater Structure Using the Dual Sonar Sensor

Predictive Modeling of Pavement Damage Using Machine Learning and Big Data Processing

Contact Info

Product

Resources

About