RUESVMs: An Ensemble Method to Handle the Class Imbalance Problem in Land Cover Mapping Using Google Earth Engine

Timely and accurate Land Cover (LC) information is required for various applications, such as climate change analysis and sustainable development. Although machine learning algorithms are most likely successful in LC mapping tasks, the class imbalance problem is known as a common challenge in this regard. This problem occurs during the training phase and reduces classification accuracy for infrequent and rare LC classes. To address this issue, this study proposes a new method by integrating random under-sampling of majority classes and an ensemble of Support Vector Machines, namely Random Under-sampling Ensemble of Support Vector Machines (RUESVMs). The performance of RUESVMs for LC classification was evaluated in Google Earth Engine (GEE) over two different case studies using Sentinel-2 time-series data and five well-known spectral indices, including the Normalized Difference Vegetation Index (NDVI), Green Normalized Difference Vegetation Index (GNDVI), Soil-Adjusted Vegetation Index (SAVI), Normalized Difference Built-up Index (NDBI), and Normalized Difference Water Index (NDWI). The performance of RUESVMs was also compared with the traditional SVM and combination of SVM with three benchmark data balancing techniques namely the Random Over-Sampling (ROS), Random Under-Sampling (RUS), and Synthetic Minority Over-sampling Technique (SMOTE). It was observed that the proposed method considerably improved the accuracy of LC classification, especially for the minority classes. After adopting RUESVMs, the overall accuracy of the generated LC map increased by approximately 4.95 percentage points, and this amount for the geometric mean of producer’s accuracies was almost 3.75 percentage points, in comparison to the most accurate data balancing method (i.e., SVM-SMOTE). Regarding the geometric mean of users’ accuracies, RUESVMs also outperformed the SVM-SMOTE method with an average increase of 6.45 percentage points.

Download Full-text

HCBST: An Efficient Hybrid Sampling Technique for Class Imbalance Problems

ACM Transactions on Knowledge Discovery from Data ◽

10.1145/3488280 ◽

2022 ◽

Vol 16 (3) ◽

pp. 1-37

Author(s):

Robert A. Sowah ◽

Bernard Kuditchar ◽

Godfrey A. Mills ◽

Amevi Acakpovi ◽

Raphael A. Twum ◽

...

Keyword(s):

Geometric Mean ◽

Class Imbalance ◽

Sampling Technique ◽

Data Repository ◽

Support Vector ◽

Classification Algorithms ◽

Class Imbalance Problem ◽

Imbalance Problem ◽

High Degree ◽

Hybrid Sampling

Class imbalance problem is prevalent in many real-world domains. It has become an active area of research. In binary classification problems, imbalance learning refers to learning from a dataset with a high degree of skewness to the negative class. This phenomenon causes classification algorithms to perform woefully when predicting positive classes with new examples. Data resampling, which involves manipulating the training data before applying standard classification techniques, is among the most commonly used techniques to deal with the class imbalance problem. This article presents a new hybrid sampling technique that improves the overall performance of classification algorithms for solving the class imbalance problem significantly. The proposed method called the Hybrid Cluster-Based Undersampling Technique (HCBST) uses a combination of the cluster undersampling technique to under-sample the majority instances and an oversampling technique derived from Sigma Nearest Oversampling based on Convex Combination, to oversample the minority instances to solve the class imbalance problem with a high degree of accuracy and reliability. The performance of the proposed algorithm was tested using 11 datasets from the National Aeronautics and Space Administration Metric Data Program data repository and University of California Irvine Machine Learning data repository with varying degrees of imbalance. Results were compared with classification algorithms such as the K-nearest neighbours, support vector machines, decision tree, random forest, neural network, AdaBoost, naïve Bayes, and quadratic discriminant analysis. Tests results revealed that for the same datasets, the HCBST performed better with average performances of 0.73, 0.67, and 0.35 in terms of performance measures of area under curve, geometric mean, and Matthews Correlation Coefficient, respectively, across all the classifiers used for this study. The HCBST has the potential of improving the performance of the class imbalance problem, which by extension, will improve on the various applications that rely on the concept for a solution.

Download Full-text

Explicitly Identifying the Desertification Change in CMREC Area Based on Multisource Remote Data

Remote Sensing ◽

10.3390/rs12193170 ◽

2020 ◽

Vol 12 (19) ◽

pp. 3170

Author(s):

Zemeng Fan ◽

Saibo Li ◽

Haiyan Fang

Keyword(s):

Climate Change ◽

Human Activities ◽

Vegetation Index ◽

Normalized Difference Vegetation Index ◽

Net Primary Productivity ◽

Regression Tree ◽

Google Earth ◽

Classification And Regression Tree ◽

Support Vector ◽

Driving Mechanisms

Explicitly identifying the desertification changes and causes has been a hot issue of eco-environment sustainable development in the China–Mongolia–Russia Economic Corridor (CMREC) area. In this paper, the desertification change patterns between 2000 and 2015 were identified by operating the classification and regression tree (CART) method with multisource remote sensing datasets on Google Earth Engine (GEE), which has the higher overall accuracy (85%) than three other methods, namely support vector machine (SVM), random forest (RF) and Albedo-normalized difference vegetation index (NDVI) models. A contribution index of climate change and human activities on desertification was introduced to quantitatively explicate the driving mechanisms of desertification change based on the temporal datasets and net primary productivity (NPP). The results show that the area of slight desertification land had increased from 719,700 km2 to 948,000 km2 between 2000 and 2015. The area of severe desertification land decreased from 82,400 km2 to 71,200 km2. The area of desertification increased by 9.68%, in which 69.68% was mainly caused by human activities. Climate change and human activities accounted for 68.8% and 27.36%, respectively, in the area of desertification restoration. In general, the degree of desertification showed a decreasing trend, and climate change was the major driving factor in the CMREC area between 2000 and 2015.

Download Full-text

An Investigation of Imbalanced Ensemble Learning Methods for Cross-Project Defect Prediction

International Journal of Pattern Recognition and Artificial Intelligence ◽

10.1142/s0218001419590377 ◽

2019 ◽

Vol 33 (12) ◽

pp. 1959037 ◽

Cited By ~ 5

Author(s):

Shaojian Qiu ◽

Lu Lu ◽

Siyu Jiang ◽

Yang Guo

Keyword(s):

Ensemble Learning ◽

Class Imbalance ◽

Training Data ◽

Defect Prediction ◽

Class Imbalance Problem ◽

Learning Methods ◽

Imbalance Problem ◽

Intelligent Software ◽

Under Sampling ◽

Cross Project

Machine-learning-based software defect prediction (SDP) methods are receiving great attention from the researchers of intelligent software engineering. Most existing SDP methods are performed under a within-project setting. However, there usually is little to no within-project training data to learn an available supervised prediction model for a new SDP task. Therefore, cross-project defect prediction (CPDP), which uses labeled data of source projects to learn a defect predictor for a target project, was proposed as a practical SDP solution. In real CPDP tasks, the class imbalance problem is ubiquitous and has a great impact on performance of the CPDP models. Unlike previous studies that focus on subsampling and individual methods, this study investigated 15 imbalanced learning methods for CPDP tasks, especially for assessing the effectiveness of imbalanced ensemble learning (IEL) methods. We evaluated the 15 methods by extensive experiments on 31 open-source projects derived from five datasets. Through analyzing a total of 37504 results, we found that in most cases, the IEL method that combined under-sampling and bagging approaches will be more effective than the other investigated methods.

Download Full-text

Biased support vector machine and weighted-smote in handling class imbalance problem

International Journal of Advances in Intelligent Informatics ◽

10.26555/ijain.v4i1.146 ◽

2018 ◽

Vol 4 (1) ◽

pp. 21 ◽

Cited By ~ 21

Author(s):

Hartono Hartono ◽

Opim Salim Sitompul ◽

Tulus Tulus ◽

Erna Budhiarti Nababan

Keyword(s):

Machine Learning ◽

Support Vector Machine ◽

Data Distribution ◽

Class Imbalance ◽

Support Vector ◽

Class Imbalance Problem ◽

Precise Method ◽

Imbalance Problem

Class imbalance occurs when instances in a class are much higher than in other classes. This machine learning major problem can affect the predicted accuracy. Support Vector Machine (SVM) is robust and precise method in handling class imbalance problem but weak in the bias data distribution, Biased Support Vector Machine (BSVM) became popular choice to solve the problem. BSVM provide better control sensitivity yet lack accuracy compared to general SVM. This study proposes the integration of BSVM and SMOTEBoost to handle class imbalance problem. Non Support Vector (NSV) sets from negative samples and Support Vector (SV) sets from positive samples will undergo a Weighted-SMOTE process. The results indicate that implementation of Biased Support Vector Machine and Weighted-SMOTE achieve better accuracy and sensitivity.

Download Full-text

CoGBUS- Center of Gravity based under Sampling Method for Imbalanced Data Classification

International Journal of Recent Technology and Engineering - 2 ◽

10.35940/ijrte.b2077.078219 ◽

2019 ◽

Vol 8 (2) ◽

pp. 2463-2468

Keyword(s):

Learning Community ◽

Sampling Method ◽

Class Imbalance ◽

Imbalanced Data ◽

Center Of Gravity ◽

Classification Algorithms ◽

Class Imbalance Problem ◽

Imbalance Problem ◽

Imbalanced Data Classification ◽

Under Sampling

Learning of class imbalanced data becomes a challenging issue in the machine learning community as all classification algorithms are designed to work for balanced datasets. Several methods are available to tackle this issue, among which the resampling techniques- undersampling and oversampling are more flexible and versatile. This paper introduces a new concept for undersampling based on Center of Gravity principle which helps to reduce the excess instances of majority class. This work is suited for binary class problems. The proposed technique –CoGBUS- overcomes the class imbalance problem and brings best results in the study. We take F-Score, GMean and ROC for the performance evaluation of the method.

Download Full-text

Pulsar candidate classification using generative adversary networks

Monthly Notices of the Royal Astronomical Society ◽

10.1093/mnras/stz2975 ◽

2019 ◽

Vol 490 (4) ◽

pp. 5424-5439 ◽

Cited By ~ 3

Author(s):

Ping Guo ◽

Fuqing Duan ◽

Pei Wang ◽

Yao Yao ◽

Qian Yin ◽

...

Keyword(s):

Class Imbalance ◽

Feature Learning ◽

Computer Experiments ◽

Support Vector ◽

Data Sets ◽

Class Imbalance Problem ◽

Generative Adversarial Network ◽

Feature Representations ◽

Adversarial Network ◽

Imbalance Problem

ABSTRACT Discovering pulsars is a significant and meaningful research topic in the field of radio astronomy. With the advent of astronomical instruments, the volume and rate of data acquisition have grown exponentially. This development necessitates a focus on artificial intelligence (AI) technologies that can mine large astronomical data sets. Automatic pulsar candidate identification (APCI) can be considered as a task determining potential candidates for further investigation and eliminating the noise of radio-frequency interference and other non-pulsar signals. As reported in the existing literature, AI techniques, especially convolutional neural network (CNN)-based techniques, have been adopted for APCI. However, it is challenging to enhance the performance of CNN-based pulsar identification because only an extremely limited number of real pulsar samples exist, which results in a crucial class imbalance problem. To address these problems, we propose a framework that combines a deep convolution generative adversarial network (DCGAN) with a support vector machine (SVM). The DCGAN is used as a sample generation and feature learning model, and the SVM is adopted as the classifier for predicting the label of a candidate at the inference stage. The proposed framework is a novel technique, which not only can solve the class imbalance problem but also can learn the discriminative feature representations of pulsar candidates instead of computing hand-crafted features in the pre-processing steps. The proposed method can enhance the accuracy of the APCI, and the computer experiments performed on two pulsar data sets verified the effectiveness and efficiency of the proposed method.

Download Full-text