Oversampling technique based on fuzzy representativeness difference for classifying imbalanced data

Ren, Ruonan; Yang, Youlong; Sun, Liqin

doi:10.1007/s10489-020-01644-0

Cited by 18 publications

(11 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, the sampling algorithms for multi-class imbalanced data have been paid more and more attention in recent years. For example, the multiclass radial-based oversampling (MC-RBO) proposed by Krawczyk et al (2019) [23] and an oversampling technique based on fuzzy representativeness difference proposed by Ren et al (2020) [24] have attracted much observation. It can be observed that the research focus is expanding towards multi-class imbalanced data.…”

Section: Introductionmentioning

confidence: 99%

An oversampling method for multi-class imbalanced data based on composite weights

et al. 2021

View full text Add to dashboard Cite

To solve the oversampling problem of multi-class small samples and to improve their classification accuracy, we develop an oversampling method based on classification ranking and weight setting. The designed oversampling algorithm sorts the data within each class of dataset according to the distance from original data to the hyperplane. Furthermore, iterative sampling is performed within the class and inter-class sampling is adopted at the boundaries of adjacent classes according to the sampling weight composed of data density and data sorting. Finally, information assignment is performed on all newly generated sampling data. The training and testing experiments of the algorithm are conducted by using the UCI imbalanced datasets, and the established composite metrics are used to evaluate the performance of the proposed algorithm and other algorithms in comprehensive evaluation method. The results show that the proposed algorithm makes the multi-class imbalanced data balanced in terms of quantity, and the newly generated data maintain the distribution characteristics and information properties of the original samples. Moreover, compared with other algorithms such as SMOTE and SVMOM, the proposed algorithm has reached a higher classification accuracy of about 90%. It is concluded that this algorithm has high practicability and general characteristics for imbalanced multi-class samples.

show abstract

Section: Introductionmentioning

confidence: 99%

An oversampling method for multi-class imbalanced data based on composite weights

et al. 2021

View full text Add to dashboard Cite

show abstract

“…The first experiment proves the superiority of ROA against three other latest optimization algorithms AOA, GWO and WOA by applying data reduction for different 12 datasets obtained from KEEL repository [26]. In the second experiment a recent published paper [27], [28] were used in a comparison with our proposed algorithm. The last experiment was conducted on three student performance prediction data as a real-life application.…”

Section: Methodsmentioning

confidence: 88%

“…The article [27] proposed a new oversampling technique to increase the efficiency of the learning classification algorithms based on a fuzzy representativeness difference-based oversampling technique, using affinity propagation and the chromosome theory of inheritance (FRDOAC). We used our meta-heuristic optimization technique ROA for data reduction on 16 imbalanced datasets which were used in [27] as a comparison with recent published research in the second experiment. For more details for the 16 benchmark datasets and for performance evaluation matrices see [27].…”

Section: Roa For Class Imbalance Problemmentioning

confidence: 99%

Rhizostoma optimization algorithm and its application in different real-world optimization problems

Mahareek

Çifçi

El-zohni

et al. 2023

IJECE

View full text Add to dashboard Cite

<p>In last decade, numerous meta-heuristic algorithms have been proposed for dealing the complexity and difficulty of numerical optimization problems in the realworld which is growing continuously recently, but only a few algorithms have caught researchers’ attention. In this study, a new swarm-based meta-heuristic algorithm called Rhizostoma optimization algorithm (ROA) is proposed for solving the optimization problems based on simulating the social movement of Rhizostoma octopus (barrel jellyfish) in the ocean. ROA is intended to mitigate the two optimization problems of trapping in local optima and slow convergence. ROA is proposed with three different movement strategies (simulated annealing (SA), fast simulated annealing (FSA), and Levy walk (LW)) and tested with 23 standard mathematical benchmark functions, two classical engineering problems, and various real-world datasets including three widely used datasets to predict the students’ performance. Comparing the ROA algorithm with the latest meta-heuristic optimization algorithms and a recent published research proves that ROA is a very competitive algorithm with a high ability in optimization performance with respect to local optima avoidance, the speed of convergence and the exploration/exploitation balance rate, as it is effectively applicable for performing optimization tasks.</p>

show abstract

“…On the other hand, the oversampling seems not useful for scheme B which only consists of reanalysis data with coarse spatial resolution. In scheme B, a central pixel and its corresponding neighboring pixels (within 5 × 5 km) could belong to the same pixel in the data before resampling [79]. Based on the above results, the final models of schemes A and B were selected: the XGBoost models with the oversampled dataset and original dataset, respectively.…”

Section: A Performance Of the Spatially Continuous Rhns Modelsmentioning

confidence: 99%

Estimation of Spatially Continuous Near-Surface Relative Humidity Over Japan and South Korea

Park

Lee

Yoo

et al. 2021

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Near-surface relative humidity (RHns) is an essential meteorological parameter for water, carbon, and climate studies. However, spatially continuous RHns estimation is difficult due to the spatial discontinuity of in-situ observations and the cloud contamination of satellite-based data. This study proposed machine learning-based models to estimate spatially continuous daily RHns at 1 km resolution over Japan and South Korea under all sky conditions and examined the spatiotemporal patterns of RHns. All sky estimation of RHns using machine learning has been rarely conducted, and it can be an alternative to the currently available RHns data mostly from numerical models, which have relatively low spatial resolution. We combined two schemes for clear sky conditions (scheme A, which uses satellite and reanalysis data) and cloudy sky conditions (scheme B, which uses reanalysis data solely). The relatively small numbers of data in extremely low and high RHns conditions (i.e., < 30% or > 70%, respectively) were augmented by applying an oversampling method to avoid biased training. The machine learning models based on random forest and XGBoost were trained and validated using 94 in-situ observation sites from meteorological administrations of both countries from 2012 to 2017. The results showed that XGBoost produced slightly better performance than random forest, and the spatially continuous RHns model combined based on XGBoost yielded the coefficient of determination of 0.72 and a root mean square error of 10.61%. Spatiotemporal patterns of the estimated RHns agreed with in-situ observations, reflecting the effect of topography on RHns. We expect that the proposed RHns model could be used in various environmental studies that require RHns under all sky conditions as input data.

show abstract

Oversampling technique based on fuzzy representativeness difference for classifying imbalanced data

Cited by 18 publications

References 40 publications

An oversampling method for multi-class imbalanced data based on composite weights

An oversampling method for multi-class imbalanced data based on composite weights

Rhizostoma optimization algorithm and its application in different real-world optimization problems

Estimation of Spatially Continuous Near-Surface Relative Humidity Over Japan and South Korea

Contact Info

Product

Resources

About