Article: Classification of imbalanced hyperspectral images using ensembled kernel rotational forest Journal: International Journal of Modelling, Identification and Control (IJMIC) 2023 Vol.43 No.2 pp.103 - 117 Abstract: Hyperspectral image classification suffers from an imbalance in the samples belonging to its different classes. In this paper, we propose a two-fold novel approach named oversampler + kernel rotation forest (O + KRoF). First, Synthetic minority oversampling (SMOTE) and adaptive synthetic oversampling (ADASYN) techniques are employed on original data to balance it due to their adaptive nature in the majority and minority samples. Finally, the ensembled KRoF classifier is applied, a combination of unpruned classification and regression trees (CART) as its base algorithm and kernel PCA for feature reduction and most significant nonlinear spatial-spectral feature selection. Furthermore, we designed a comparison study with frequently used oversamplers and related state-of-art tree-based classifiers. However, it is found that our ensemble model is suitable and performs better as compared to earlier works as it attains 90.92%, 97.1%, and 93.39% overall accuracies when experimented on the benchmark datasets, Indian Pines, Salinas Valley, and Pavia University, respectively. Inderscience Publishers - linking academia, business and industry through research

Title: Classification of imbalanced hyperspectral images using ensembled kernel rotational forest

Authors: Debaleena Datta; Pradeep Kumar Mallick; Mihir Narayan Mohanty

Addresses: School of Computer Engineering, Kalinga Institute of Industrial Technology, Deemed to be University, Bhubaneswar, 751024, India ' School of Computer Engineering, Kalinga Institute of Industrial Technology, Deemed to be University, Bhubaneswar, 751024, India ' Department of Electronics and Communication Engineering, ITER (FET), Siksha 'O' Anusandhan (Deemed to be University), Bhubaneswar, India

Abstract: Hyperspectral image classification suffers from an imbalance in the samples belonging to its different classes. In this paper, we propose a two-fold novel approach named oversampler + kernel rotation forest (O + KRoF). First, Synthetic minority oversampling (SMOTE) and adaptive synthetic oversampling (ADASYN) techniques are employed on original data to balance it due to their adaptive nature in the majority and minority samples. Finally, the ensembled KRoF classifier is applied, a combination of unpruned classification and regression trees (CART) as its base algorithm and kernel PCA for feature reduction and most significant nonlinear spatial-spectral feature selection. Furthermore, we designed a comparison study with frequently used oversamplers and related state-of-art tree-based classifiers. However, it is found that our ensemble model is suitable and performs better as compared to earlier works as it attains 90.92%, 97.1%, and 93.39% overall accuracies when experimented on the benchmark datasets, Indian Pines, Salinas Valley, and Pavia University, respectively.

Keywords: hyperspectral images; resampling; synthetic oversampling; tree-based classifiers; kernel rotation forest; KRoF.

DOI: 10.1504/IJMIC.2023.132599

International Journal of Modelling, Identification and Control, 2023 Vol.43 No.2, pp.103 - 117

Received: 14 Feb 2022
Received in revised form: 26 May 2022
Accepted: 30 May 2022
Published online: 30 Jul 2023 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article

Title: Classification of imbalanced hyperspectral images using ensembled kernel rotational forest

Keep up-to-date