Diffuse reflectance spectroscopy based rapid coal rank estimation: A machine learning enabled framework.

This research aims at studying the ability of using diffuse reflectance spectroscopy (DRS) for discriminating or classifying coal samples into different ranks. Spectral characteristics such as the shape of the spectral profile, slope, absorption intensity of coal samples of different ranks ranging from lignite A to semi-anthracite were studied in the Vis-NIR-SWIR (350-2500 nm) range. A number of classification algorithms (Logistic Regression, Random Forest, and SVM) were trained using the DRS dataset of coal samples. Class imbalances present in the dataset were handled using different approaches (SMOTE and Oversampling of minority classes), which improved the classification accuracy. Coal samples were initially classified into broad classes viz., lignite, sub-bituminous, bituminous, and anthracite with an accuracy of 0.98 and F1 score of 0.75. Later, the same samples were further classified into sub-class levels. The sub-class level classification also obtained good results with an accuracy of 0.77 and F1 score of 0.64. The results demonstrate the effectiveness of rapid coal classification systems based on DRS dataset in combination with different machine learning-based classification algorithms.

Performance analysis of different surface reconstruction algorithms for 3D reconstruction of outdoor objects from their digital images.

3D reconstruction of geo-objects from their digital images is a time-efficient and convenient way of studying the structural features of the object being modelled. This paper presents a 3D reconstruction methodology which can be used to generate photo-realistic 3D watertight surface of different irregular shaped objects, from digital image sequences of the objects. The 3D reconstruction approach described here is robust, simplistic and can be readily used in reconstructing watertight 3D surface of any object from its digital image sequence. Here, digital images of different objects are used to build sparse, followed by dense 3D point clouds of the objects. These image-obtained point clouds are then used for generation of photo-realistic 3D surfaces, using different surface reconstruction algorithms such as Poisson reconstruction and Ball-pivoting algorithm. Different control parameters of these algorithms are identified, which affect the quality and computation time of the reconstructed 3D surface. The effects of these control parameters in generation of 3D surface from point clouds of different density are studied. It is shown that the reconstructed surface quality of Poisson reconstruction depends on Samples per node (SN) significantly, greater SN values resulting in better quality surfaces. Also, the quality of the 3D surface generated using Ball-Pivoting algorithm is found to be highly depend upon Clustering radius and Angle threshold values. The results obtained from this study give the readers of the article a valuable insight into the effects of different control parameters on determining the reconstructed surface quality.