Ensemble Methods for Binary Classifications of Airborne LIDAR Data

Nourzad, Seyed Hossein Hosseini; Pradhan, Anju

doi:10.1061/(asce)cp.1943-5487.0000276

Cited by 12 publications

(7 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The study of Niemeyer et al (2011) reported that it took 202 min and 252 min to train the CRF and MRF, respectively, with a study area of 1.93 ha. Some emerging research attempted to use ensemble learning (or multiple classifier systems) such as AdaBoost (Lodha et al, 2007;Nourzad & Pradhan, 2014), Cascade Binary Classifier (Carlberg, Gao, Chen, & Zakhor, 2009), Weighted Majority Voting (Samadzadegan et al, 2010), and Random Forests (Chehata et al, 2009;Guo et al, 2011) for both discrete return and waveform LiDAR data, which still produced desirable classification accuracy (80% to 90%).…”

Section: Classification Techniquesmentioning

confidence: 98%

Urban land cover classification using airborne LiDAR data: A review

Yan

Shaker

El-Ashmawy

2015

Remote Sensing of Environment

447

270

View full text Add to dashboard Cite

Section: Classification Techniquesmentioning

confidence: 98%

Urban land cover classification using airborne LiDAR data: A review

Yan

Shaker

El-Ashmawy

2015

Remote Sensing of Environment

447

270

View full text Add to dashboard Cite

“…Ensemble learning, also known as multiple classifier systems, has become an influential solution overshadowing not only multi-class imbalance learning but also two-class imbalance problems and standard classification, as discussed in [48] with regard to the boosting algorithms primarily designed for binary classification. In the literature, different researchers agreed on the versatility and effectiveness of ensemble-based learning techniques, where several component classifier predictions were combined to make a final prediction report, improving the performance of individual weak learners with a small training dataset to build an improved classification-learning model.…”

Section: Ensemble-based Methodsmentioning

confidence: 99%

Generation of Controlled Synthetic Samples and Impact of Hyper-Tuning Parameters to Effectively Classify the Complex Structure of Overlapping Region

Mahmood

Butt

Rehman³

et al. 2022

Applied Sciences

View full text Add to dashboard Cite

The classification of imbalanced and overlapping data has provided customary insight over the last decade, as most real-world applications comprise multiple classes with an imbalanced distribution of samples. Samples from different classes overlap near class boundaries, creating a complex structure for the underlying classifier. Due to the imbalanced distribution of samples, the underlying classifier favors samples from the majority class and ignores samples representing the least minority class. The imbalanced nature of the data—resulting in overlapping regions—greatly affects the learning of various machine learning classifiers, as most machine learning classifiers are designed to handle balanced datasets and perform poorly when applied to imbalanced data. To improve learning on multi-class problems, more expertise is required in both traditional classifiers and problem domain datasets. Some experimentation and knowledge of hyper-tuning the parameters and parameters of the classifier under consideration are required. Several techniques for learning from multi-class problems have been reported in the literature, such as sampling techniques, algorithm adaptation methods, transformation methods, hybrid methods, and ensemble techniques. In the current research work, we first analyzed the learning behavior of state-of-the-art ensemble and non-ensemble classifiers on imbalanced and overlapping multi-class data. After analysis, we used grid search techniques to optimize key parameters (by hyper-tuning) of ensemble and non-ensemble classifiers to determine the optimal set of parameters to enhance the learning from a multi-class imbalanced classification problem, performed on 15 public datasets. After hyper-tuning, 20% of the dataset samples are synthetically generated to add to the majority class of each respective dataset to make it more overlapped (complex structure). After the synthetic sample’s addition, the hyper-tuned ensemble and non-ensemble classifiers are tested over that complex structure. This paper also includes a brief description of tuned parameters and their effects on imbalanced data, followed by a detailed comparison of ensemble and non-ensemble classifiers with the default and tuned parameters for both original and synthetically overlapped datasets. We believe that the underlying paper is the first kind of effort in this domain, which will furnish various research aspects to with a greater focus on the parameters of the classifier in the field of learning from imbalanced data problems using machine-learning algorithms.

show abstract

“…On top of that, machine learning approaches also apply clustering approaches to define planar segments and further features on these planar segments (Lu et al, 2009). Most common techniques are conditional random field (Lu et al, 2009, Niemeyer et al, 2012, support vector machines (Mewhort, 2013) and random forest (Ni et al, 2017) but also ad-aBoost and bagging (Nourzad and Pradhan, 2014).…”

Section: Machine Learning Approachesmentioning

confidence: 99%

Ground Point Filtering From Airborne Lidar Point Clouds Using Deep Learning: A Preliminary Study

Janssens-Coron

Guilbert

2019

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

<p><strong>Abstract.</strong> Airborne lidar data is commonly used to generate point clouds over large areas. These points can be classified into different categories such as ground, building, vegetation, etc. The first step for this is to separate ground points from non-ground points. Existing methods rely mainly on TIN densification but there performance varies with the type of terrain and relies on the user’s experience who adjusts parameters accordingly. An alternative may be on the use of a deep learning approach that would limit user’s intervention. Hence, in this paper, we assess a deep learning architecture, PointNet, that applies directly to point clouds. Our preliminary results show mitigating classification rates and further investigation is required to properly train the system and improve the robustness, showing issues with the choices we made in the preprocessing. Nonetheless, our analysis suggests that it is necessary to enrich the architecture of the network to integrate the notion of neighbourhood at different scales in order to increase the accuracy and the robustness of the treatment as well as its capacity to treat data from different geographical contexts.</p>

show abstract

Ensemble Methods for Binary Classifications of Airborne LIDAR Data

Cited by 12 publications

References 38 publications

Urban land cover classification using airborne LiDAR data: A review

Urban land cover classification using airborne LiDAR data: A review

Generation of Controlled Synthetic Samples and Impact of Hyper-Tuning Parameters to Effectively Classify the Complex Structure of Overlapping Region

Ground Point Filtering From Airborne Lidar Point Clouds Using Deep Learning: A Preliminary Study

Contact Info

Product

Resources

About