Machine Learning improvements to the accuracy of predicting Specific Language Impairment

被引:0
|
作者
Huang, George [1 ]
Cheng, Andrew [2 ]
Gao, Yujie [3 ]
机构
[1] Wellington Coll Int Shanghai, Shanghai 200126, Peoples R China
[2] Basis Int Sch Shenzhen, Shenzhen, Guangdong, Peoples R China
[3] Pierce Coll, Puyallup, WA 98498 USA
来源
2022 INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, COMPUTER VISION AND MACHINE LEARNING (ICICML) | 2022年
关键词
Specific Language Impairment; Imbalanced data; AUC (F1 and Recall) Scores; Logistic regression model; AdaBoost model; Random Forest model; BPNN model; Principal Component Analysis;
D O I
10.1109/ICICML57342.2022.10009881
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Specific Language Impairment (SLI) has been a main obstacle of children's growth in the long-run. To diagnose this by applying Machine Learning (ML), we argue that it is crucial to understand which models should use to generate an accurate result. The key to this is the identification of positive between a large number of children, which relates to the big data that the machine has to read. In ML, the accuracy can be affected by the accidental delete of important data, failure of interpreting positive due to the random selection, imbalanced data and incorrect expression of specific features like the probability set. These problems might affect the overall accuracy in machine. Based on these issues, we gave a series of models that might be capable of solving it and train them in ML, then we can determine which model gives the best accuracy. We then consider that the big data might affect our results on accuracy, and therefore we introduced PCA. Generally speaking, we theoretically present the effectiveness of implementing different algorithms and models, which leads to the conclusion that the usefulness of application in models to the problem of diagnosing SLI.
引用
收藏
页码:553 / 566
页数:14
相关论文
共 50 条
  • [21] Statistical Learning in Specific Language Impairment: A Meta-Analysis
    Lammertink, Imme
    Boersma, Paul
    Wijnen, Frank
    Rispens, Judith
    JOURNAL OF SPEECH LANGUAGE AND HEARING RESEARCH, 2017, 60 (12): : 3474 - 3486
  • [22] Using Learning Potential to Evaluate Children with Specific Language Impairment
    Auxiliadora Robles-Bello, Ma
    Dolores Calero Garcia, Ma
    SPANISH JOURNAL OF PSYCHOLOGY, 2013, 16
  • [23] Procedural Learning in Specific Language Impairment: Effects of Sequence Complexity
    Gabriel, Audrey
    Maillart, Christelle
    Stefaniak, Nicolas
    Lejeune, Caroline
    Desmottes, Lise
    Meulemans, Thierry
    JOURNAL OF THE INTERNATIONAL NEUROPSYCHOLOGICAL SOCIETY, 2013, 19 (03) : 264 - 271
  • [24] Is There a Global Procedural Learning Deficit in Children with Specific Language Impairment?
    Desmottes, L.
    Maillart, C.
    Meulemans, T.
    ARCHIVES OF CLINICAL NEUROPSYCHOLOGY, 2014, 29 (06)
  • [25] Sequence- specific procedural learning deficits in children with specific language impairment
    Hsu, Hsinjen Julie
    Bishop, Dorothy V. M.
    DEVELOPMENTAL SCIENCE, 2014, 17 (03) : 352 - 365
  • [26] Learning and memory performance of children with Specific Language Impairment (SLI)
    Riccio, Cynthia A.
    Cash, Deborah L.
    Cohen, Morris J.
    APPLIED NEUROPSYCHOLOGY, 2007, 14 (04): : 255 - 261
  • [27] Relations between specific language impairment and specific learning disorder in Italian sample
    Costa, C. D'agostini
    Salvadore, I.
    Penge, R.
    EUROPEAN CHILD & ADOLESCENT PSYCHIATRY, 2015, 24 : S163 - S163
  • [28] Learning and Overnight Retention in Declarative Memory in Specific Language Impairment
    Lukacs, Agnes
    Kemeny, Ferenc
    Lum, Jarrad A. G.
    Ullman, Michael T.
    PLOS ONE, 2017, 12 (01):
  • [29] Predicting cognitive impairment in outpatients with epilepsy using machine learning techniques
    Lin, Feng
    Han, Jiarui
    Xue, Teng
    Lin, Jilan
    Chen, Shenggen
    Zhu, Chaofeng
    Lin, Han
    Chen, Xianyang
    Lin, Wanhui
    Huang, Huapin
    SCIENTIFIC REPORTS, 2021, 11 (01)
  • [30] Predicting cognitive impairment in outpatients with epilepsy using machine learning techniques
    Feng Lin
    Jiarui Han
    Teng Xue
    Jilan Lin
    Shenggen Chen
    Chaofeng Zhu
    Han Lin
    Xianyang Chen
    Wanhui Lin
    Huapin Huang
    Scientific Reports, 11