Handling Autism Imbalanced Data using Synthetic Minority Over-Sampling Technique (SMOTE)

被引：0
|
作者：
El-Sayed, Asmaa Ahmed [1 ]
Meguid, Nagwa Abdel [2 ]
Mahmood, Mahmood Abdel Manem [1 ]
Hefny, Hesham Ahmed [3 ,4 ]
机构：
[1] Cairo Univ, Comp Sci, Dept Comp Sci, ISSR, Cairo, Egypt
[2] Natl Res Ctr, Human Genet, Res Children Special Needs Dept, Cairo, Egypt
[3] Cairo Univ, Comp Sci, ISSR, Cairo, Egypt
[4] Cairo Univ, ISSR, Cairo, Egypt
来源：
PROCEEDINGS OF 2015 THIRD IEEE WORLD CONFERENCE ON COMPLEX SYSTEMS (WCCS) | 2015年
关键词：
autism spectrum disorder (ASD); autism diagnostic interview-revised (ADI-R); Over-sampling; machine learning; support vector machine; Decision tree; navebayes; Cross-Validation;
D O I：
暂无
中图分类号：
TP301 [理论、方法];
学科分类号：
081202 ;
摘要：
The autism diagnostic interview-revised (ADI-R) is a semi-structured interview designed to assess the three core aspects of autism spectrum disorder (ASD). In this research a synthetic minority over-sampling technique (SMOT) was presented for handling autism imbalanced data to increase accuracy credibility. SMOT can potentially lead to over fitting on multiple copies of minority class examples. The autism data collected from National Research Center in Egypt (NRC). The experimental dataset applied on several machine learning algorithms and compared the accuracy before and after over-sampling techniques. The result show that over-sampling for imbalanced data making accuracy realistic and non-deceptive and can be Reliable.
引用
收藏
页数：5
相关论文
共 50 条
  • [41] An Over-Sampling Technique with Rejection for Imbalanced Class Learning
    Lee, Jaedong
    Kim, Noo-ri
    Lee, Jee-Hyong
    ACM IMCOM 2015, PROCEEDINGS, 2015,
  • [42] A Novel Synthetic Over-Sampling Technique for Imbalanced Classification of Gene Expressions Using Autoencoders and Swarm Optimization
    Daoud, Maisa
    Mayo, Michael
    AI 2018: ADVANCES IN ARTIFICIAL INTELLIGENCE, 2018, 11320 : 603 - 615
  • [43] Multi-fidelity model based on synthetic minority over-sampling technique
    Song, Jiuxiang
    Liu, Jizhong
    MULTIMEDIA TOOLS AND APPLICATIONS, 2024, 83 (11) : 33123 - 33139
  • [44] SMOTEFUNA: Synthetic Minority Over-Sampling Technique Based on Furthest Neighbour Algorithm
    Tarawneh, Ahmad S.
    Hassanat, Ahmad B. A.
    Almohammadi, Khalid
    Chetverikov, Dmitry
    Bellinger, Colin
    IEEE ACCESS, 2020, 8 (08) : 59069 - 59082
  • [45] Learning from Imbalanced Data Using Over-Sampling and the Firefly Algorithm
    Czarnowski, Ireneusz
    COMPUTATIONAL COLLECTIVE INTELLIGENCE (ICCCI 2021), 2021, 12876 : 373 - 386
  • [46] ANALYSIS AND SIMULATION OF ACCURACY OF CREDIT STATUS CLASSIFICATION WITH BOOTSTRAP AGGREGATING (BAGGING) AND SYNTHETIC MINORITY OVER-SAMPLING (SMOTE)
    Efendi, Achmad
    Amrullah, Ahmad A. N.
    Fitriani, Rahma
    Rahayudi, Bayu
    INTERNATIONAL JOURNAL OF AGRICULTURAL AND STATISTICAL SCIENCES, 2021, 17 : 925 - 938
  • [47] Deep Over-sampling Framework for Classifying Imbalanced Data
    Ando, Shin
    Huang, Chun Yuan
    MACHINE LEARNING AND KNOWLEDGE DISCOVERY IN DATABASES, ECML PKDD 2017, PT I, 2017, 10534 : 770 - 785
  • [48] Robust diabetic prediction using ensemble machine learning models with synthetic minority over-sampling technique
    Sampath, Pradeepa
    Elangovan, Gurupriya
    Ravichandran, Kaaveya
    Shanmuganathan, Vimal
    Pasupathi, Subbulakshmi
    Chakrabarti, Tulika
    Chakrabarti, Prasun
    Margala, Martin
    SCIENTIFIC REPORTS, 2024, 14 (01):
  • [49] A priori synthetic over-sampling methods for increasing classification sensitivity in imbalanced data sets
    Rivera, William A.
    Xanthopoulos, Petros
    EXPERT SYSTEMS WITH APPLICATIONS, 2016, 66 : 124 - 135
  • [50] Over-sampling methods for mixed data in imbalanced problems
    Alonso, Hugo
    da Costa, Joaquim Fernando Pinto
    COMMUNICATIONS IN STATISTICS-SIMULATION AND COMPUTATION, 2024,
12345