Feature extraction from 3D datasets is a current problem. Machine learning is an important tool for classification of complex 3D datasets. Machine learning classification…
Abstract
Purpose
Feature extraction from 3D datasets is a current problem. Machine learning is an important tool for classification of complex 3D datasets. Machine learning classification techniques are widely used in various fields, such as text classification, pattern recognition, medical disease analysis, etc. The aim of this study is to apply the most popular classification and regression methods to determine the best classification and regression method based on the geodesics.
Design/methodology/approach
The feature vector is determined by the unit normal vector and the unit principal vector at each point of the 3D surface along with the point coordinates themselves. Moreover, different examples are compared according to the classification methods in terms of accuracy and the regression algorithms in terms of R-squared value.
Findings
Several surface examples are analyzed for the feature vector using classification (31 methods) and regression (23 methods) machine learning algorithms. In addition, two ensemble methods XGBoost and LightGBM are used for classification and regression. Also, the scores for each surface example are compared.
Originality/value
To the best of the author’s knowledge, this is the first study to analyze datasets based on geodesics using machine learning algorithms for classification and regression.
Details
Keywords
The purpose of this study is to obtain the differential geometric analysis of autonomous wheel-legged robots and their trajectories on the terrain.
Abstract
Purpose
The purpose of this study is to obtain the differential geometric analysis of autonomous wheel-legged robots and their trajectories on the terrain.
Design/methodology/approach
The author uses a wheel using the osculating sphere of the curve on rough terrain. Additionally, the author expresses a triple osculating sphere wheel by taking advantage of differential geometry. Moreover, the author examined the consecutive wheel center-curves to obtain the optimum posture of a micro-hydraulic toolkit (MHT) robot.
Findings
The author examined the terrain path, which is crucial for trajectory planning in terms of the geometric perspective. The author designed the triple MHT wheel using the osculating sphere of the MHT robot trajectory by taking advantage of local differential geometric properties of this curve on the terrain. The consecutive wheel center-curves were expressed and studied based on differential geometry.
Originality/value
The author provides a novel approach for the optimum posture of an MHT robot using consecutive wheel-center curves and provides an original perspective to MHT robot and its trajectory by using differential geometry.
Details
Keywords
Surface curvature is needed to analyze the range data of real objects and is widely applied in object recognition and segmentation, robotics, and computer vision. Therefore, it is…
Abstract
Purpose
Surface curvature is needed to analyze the range data of real objects and is widely applied in object recognition and segmentation, robotics, and computer vision. Therefore, it is not easy to estimate the curvature of the scanned data. In recent years, machine learning classification methods have gained importance in various fields such as finance, health, engineering, etc. The purpose of this study is to classify surface points based on principal curvatures to find the best method for determining surface point types.
Design/methodology/approach
A feature selection method is presented to find the best feature vector that achieves the highest accuracy. For this reason, ten different feature selections are used and six sample datasets of different sizes are classified using these feature vectors.
Findings
The author examined the surface examples based on the feature vector using the machine learning classification methods. Also, the author compared the results for each experiment.
Originality/value
To the best of the author's knowledge, this is the first study to examine surface points according to principal curvatures using machine learning classification methods.