An Improved Algorithm for Imbalanced Data and Small Sample Size Classification

Hu, Yong; Guo, Deliang; Fan, Zengwei; Dong, Chen; Huang, Qiuhong; Xie, Shengkai; Liu, Guifang; Tan, Jing; Li, Boping; Xie, Qiwei

doi:10.4236/jdaip.2015.33004

Cited by 16 publications

(6 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Wisconsin breast cancer dataset (Ebenuwa et al, 2019) has multivariate data types, all 10 instances are integer types and it has 699 instances. Yeast dataset (Hu et al, 2015) have 8 real attributes with 1,484 instances. Various kinds of datasets from the Keel dataset repository (Verbiest et al, 2012;Ahmed et al, 2019;Gong and Kim, 2017;Jedrzejowicz et al, 2018;Fernández et al, 2017;Wang, 2019) are mostly used in handling imbalanced datasets.…”

Section: Used Dataset In Researchesmentioning

confidence: 99%

See 1 more Smart Citation

A Survey of Methods for Managing the Classification and Solution of Data Imbalance Problem

Hasib¹,

Iqbal

Shah³

et al. 2020

Journal of Computer Science

View full text Add to dashboard Cite

show abstract

Section: Used Dataset In Researchesmentioning

confidence: 99%

“…Abalone dataset (He et al, 2008) contains 4,177 instances with 8 attributes, attributes types are categorical. Glass dataset (Hu et al, 2015) with multivariate data types and 214 instances. E coli 2 dataset (Elhassan and Aljurf, 2016) carries 363 instances and 7 attributes.…”

Section: Used Dataset In Researchesmentioning

confidence: 99%

A Survey of Methods for Managing the Classification and Solution of Data Imbalance Problem

Hasib¹,

Iqbal

Shah³

et al. 2020

Journal of Computer Science

View full text Add to dashboard Cite

show abstract

“…Among the results, the city's 294,000 samples were obtained by SMOTE. It is very likely that the original characteristics of the city category will be lost, resulting in inaccuracies in the classification results [69].…”

Section: Stratified Smote Algorithmmentioning

confidence: 99%

Long Time Series Land Cover Classification in China from 1982 to 2015 Based on Bi-LSTM Deep Learning

et al. 2019

View full text Add to dashboard Cite

Land cover classification data have a very important practical application value, and long time series land cover classification datasets are of great significance studying environmental changes, urban changes, land resource surveys, hydrology and ecology. At present, the starting point of continuous land cover classification products for many years is mostly after the year 2000, and there is a lack of long-term continuously annual land cover classification products before 2000. In this study, a long time series classification data extraction model is established using a bidirectional long-term and short-term memory network (Bi-LSTM). In the model, quantitative remote sensing products combined with DEM, nighttime lighting data, and latitude and longitude elevation data were used. We applied this model in China and obtained China’s 1982–2017 0.05° land cover classification product. The accuracy assessment results of the test data show that the overall accuracy is 84.2% and that the accuracies of wetland, water, glacier, tundra, city and bare soil reach 92.1%, 92.0%, 94.3%, 94.6% and 92.4%, respectively. For the first time, this study used a variety of long time series data, especially quantitative remote sensing products, for the classification of features. At the same time, it also acquired long time series land cover classification products, including those from the year 2000. This study provides new ideas for the establishment of higher-resolution long time series land cover classification products.

show abstract

“…[20]. F-ölçütü değeri, dengesiz veri kümesinin azınlık sınıfına ait sınıflama başarısını değerlendirmek için kullanılırken, Gortalama ise tüm sınıfların geneli için değerlendirme yapmaktadır [21], [22].…”

Section: Literatür öZeti Ve Ilgili çAlışmalarunclassified

Analyzing and improving information gain of metrics used in software defect prediction in decision trees

Aydilek¹

2018

Pamukkale J Eng Sci

View full text Add to dashboard Cite

Yazılım kalitesinin somut bir şekilde ölçülebilmesi için kullanılan sayısal yazılım metrikleri içinde bilinen ve yaygın şekilde kullanılanlar arasında McCabe ve Halstead yöntem-seviye metrikleri bulunmaktadır. Yazılım hata tahmini, geliştirilecek olan yazılımda bulunan alt modüllerin hangisi veya hangilerinin daha çok hataya meyilli olabileceğini konusunda öngörüde bulunabilmektedir. Böylece işgücü ve zaman konusundaki kayıpların önüne geçilebilmektedir. Yazılım hata tahmini için kullanılan veri kümelerinde, hata var sınıflı kayıt sayısı, hata yok sınıflı kayıt sayısına göre daha az sayıda olabildiğinden bu veri kümeleri genellikle dengeli olmayan bir sınıf dağılımına sahip olmakta ve makine öğrenme yöntemlerinin sonuçlarını olumsuz etkilemektedir. Bilgi kazancı, karar ağaçları ve karar ağacı temeline dayanan kural sınıflayıcı, nitelik seçimi gibi algoritma ve yöntemlerde kullanılmaktadır. Bu çalışmada, yazılım hata tahmini için önemli bilgiler sunan yazılım metrikleri incelenmiş, NASA'nın PROMISE yazılım veri deposundan CM1, JM1, KC1 ve PC1 veri kümeleri sentetik veri artırım Smote algoritması ile daha dengeli hale getirilerek bilgi kazancı yönünden iyileştirilmiştir. Sonuçta karar ağaçlarında sınıflama başarı performansı daha yüksek yazılım hata tahmini veri kümeleri ve bilgi kazanç oranı yükseltilmiş yazılım metrik değerleri elde edilmiştir. McCabe and Halstead method-level metrics are among the well-known and widely used quantitative software metrics are used to measure software quality in a concrete way. Software defect prediction can guess which or which of the sub-modules in the software to be developed may be more prone to defect. Thus, loss of labor and time can be avoided. The datasets which are used for software defect prediction, usually have an unbalanced class distribution, since the number of records with defective class can be fewer than the number of records with not defective class and this situation adversely affect the results of the machine learning methods. Information gain is employed in decision trees and decision tree based rule classifier and attribute selection methods. In this study, software metrics that provide important information for software defect prediction have been investigated and CM1, JM1, KC1 and PC1 datasets of NASA's PROMISE software repository have been balanced with the synthetic data over-sampling Smote algorithm and improved in terms of information gain. As a result, the software defect prediction datasets with higher classification success performance and the software metrics with increased information gain ratio are obtained in the decision trees.

show abstract

An Improved Algorithm for Imbalanced Data and Small Sample Size Classification

Cited by 16 publications

References 10 publications

A Survey of Methods for Managing the Classification and Solution of Data Imbalance Problem

A Survey of Methods for Managing the Classification and Solution of Data Imbalance Problem

Long Time Series Land Cover Classification in China from 1982 to 2015 Based on Bi-LSTM Deep Learning

Analyzing and improving information gain of metrics used in software defect prediction in decision trees

Contact Info

Product

Resources

About