Prediction of Size of Buried Objects using Ground Penetrating Radar and Machine Learning Techniques

被引：0

作者：

Barkataki, Nairit ^{[1
,2
]}

Mazumdar, Sharmistha ^{[1
,2
]}

Talukdar, Rajdeep ^{[1
,2
]}

Chakraborty, Priyanka ^{[1
,2
]}

Tiru, Banty ^{[3
]}

Sarma, Utpal ^{[1
,2
]}

机构：

[1] Gauhati Univ, Dept Instrumentat, Gauhati, India

[2] Gauhati Univ, USIC, Gauhati, India

[3] Gauhati Univ, Dept Phys, Gauhati, India

来源：

2020 INTERNATIONAL CONFERENCE ON COMPUTATIONAL PERFORMANCE EVALUATION (COMPE-2020) | 2020年

关键词：

machine learning; classification; object size prediction; ground penetrating radar;

D O I：

暂无

中图分类号：

TP39 [计算机的应用];

学科分类号：

081203 ; 0835 ;

摘要：

Ground penetrating radar (GPR) uses electromagnetic (EM) wave to detect the subsurface objects. Interpretation and analysis of GPR signals are still challenging tasks as it requires skilled user (geologists in most cases). Particularly difficult is the prediction of the object sizes. This paper proposes a new method for predicting size of buried objects. First, standard scaling pre-processing techniques are used to optimise the B-Scan data. The features are then supplied to Random Forest (RF) and Support Vector Machine (SVM) classifiers to automatically predict the size of the buried object. The proposed feature based RF classifier shows similar performance in the accuracy of classification compared to SVM (Radial Basis Function kernel) system.

引用

页码：781 / 785

页数：5

共 14 条

[1] Integrated condition rating and forecasting method for bridge decks using Visual Inspection and Ground Penetrating Radar [J].