Online Linear Regression Based on Weighted Average

被引:0
作者
Abu-Shaira, Mohammad [1 ]
Speegle, Greg [1 ]
机构
[1] Baylor Univ, Waco, TX 76798 USA
来源
NEXT GENERATION DATA SCIENCE, SDSC 2023 | 2024年 / 2113卷
关键词
Online Machine Learning; Weighted Average; Linear Regression; Online Linear Regression; Pseudo-Inverse; Coefficient of Determination (R-squared);
D O I
10.1007/978-3-031-61816-1_7
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Machine Learning requires a large amount of training data in order to build accurate models. Sometimes the data arrives over time, requiring significant storage space and recalculating the model to account for the new data. On-line learning addresses these issues by incrementally modifying the model as data is encountered, and then discarding the data. In this study we introduce a new online linear regression approach. Our approach combines newly arriving data with a previously existing model to create a new model. The introduced model, named OLR-WA (OnLine Regression with Weighted Average) uses user-defined weights to provide flexibility in the face of changing data to bias the results in favor of old or new data. We have conducted 2-D and 3-D experiments comparing OLR-WA to a static model using the entire data set. The results show that for consistent data, OLR-WA and the static batch model perform similarly and for varying data, the user can set the OLR-WA to adapt more quickly or to resist change.
引用
收藏
页码:88 / 108
页数:21
相关论文
共 50 条
  • [21] Adaptive and optimal online linear regression on l1-balls
    Gerchinovitz, Sebastien
    Yu, Jia Yuan
    THEORETICAL COMPUTER SCIENCE, 2014, 519 : 4 - 28
  • [22] THE WEIGHTED AVERAGE REFERENCE MONTAGE
    LEMOS, MS
    FISCH, BJ
    ELECTROENCEPHALOGRAPHY AND CLINICAL NEUROPHYSIOLOGY, 1991, 79 (05): : 361 - 370
  • [23] Linear programming-based estimators in simple linear regression
    Preve, Daniel
    Medeiros, Marcelo C.
    JOURNAL OF ECONOMETRICS, 2011, 165 (01) : 128 - 136
  • [24] Linear Regression Based Clutter Reconstruction for STAP
    Zhang, Wei
    He, Zishu
    Li, Huiyong
    IEEE ACCESS, 2018, 6 : 56862 - 56869
  • [25] Linear regression based combination of neural classifiers
    Lin, XF
    Wu, YS
    Ding, XQ
    PROGRESS IN CONNECTIONIST-BASED INFORMATION SYSTEMS, VOLS 1 AND 2, 1998, : 608 - 611
  • [26] Linear regression based projections for dimensionality reduction
    Chen, Si-Bao
    Ding, Chris H. Q.
    Luo, Bin
    INFORMATION SCIENCES, 2018, 467 : 74 - 86
  • [27] Adaptive weighted learning for linear regression problems via Kullback-Leibler divergence
    Liang, Zhizheng
    Li, Youfu
    Xia, ShiXiong
    PATTERN RECOGNITION, 2013, 46 (04) : 1209 - 1219
  • [28] Online Diagnostic Method and System Design of Arc Plasma Jet Characteristics Based on Wavelet Transform and Linear Regression Theory
    Cao, Xiuquan
    Guo, Wenyu
    He, Yong
    Huang, Bo
    Wang, Lin
    Liu, Yuzhe
    PLASMA CHEMISTRY AND PLASMA PROCESSING, 2023, 43 (05) : 1217 - 1236
  • [29] Online Diagnostic Method and System Design of Arc Plasma Jet Characteristics Based on Wavelet Transform and Linear Regression Theory
    Xiuquan Cao
    Wenyu Guo
    Yong He
    Bo Huang
    Lin Wang
    Yuzhe Liu
    Plasma Chemistry and Plasma Processing, 2023, 43 : 1217 - 1236
  • [30] Visual comparison based on linear regression model and linear discriminant analysis
    Shi, Hanqin
    Tao, Liang
    JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION, 2018, 57 : 118 - 124