SUPERIORITY OF ARTIFICIAL NEURAL NETWORK MODEL OVER MULTIPLE LINEAR REGRESSION MODEL FOR PREDICTING BROCCOLI YIELD

被引：0
|
作者：
Mishra, Minakshi [1 ]
Thakur, Ratan Kumar [1 ]
机构：
[1] Babasaheb Bhimrao Ambedkar Univ, Dept Stat, Lucknow 226025, Uttar Pradesh, India
来源：
INTERNATIONAL JOURNAL OF AGRICULTURAL AND STATISTICAL SCIENCES | 2020年 / 16卷 / 02期
关键词：
Broccoli; Artificial neural networks; Multiple linear regression; Mean absolute error;
D O I：
暂无
中图分类号：
S [农业科学];
学科分类号：
09 ;
摘要：
The present study aimed at the comparison of Artificial Neural Networks and Multiple Linear Regression models for broccoli yield prediction. In this study, the data concerning about broccoli yield and its biological parameters i.e. plant height, number of leaves per plant, length of leaves, width of leaves and stem diameter were taken. Artificial Neural Networks and Multiple Linear Regression models were fitted using the results of experiments to predict total yield of broccoli crop. The performance of Artificial Neural Networks with 10 hidden neurons was found to be more accurate with high value of R-2 (0.999) and low values of root mean squared error, mean squared error, mean absolute error, mean absolute percentage error and percentage forecast error than multiple linear regression prediction.
引用
收藏
页码：757 / 762
页数：6
相关论文
共 50 条
  • [21] Predicting Elderly Depression: An Artificial Neural Network Model
    Allahyari, Elahe
    [J]. IRANIAN JOURNAL OF PSYCHIATRY AND BEHAVIORAL SCIENCES, 2019, 13 (04)
  • [22] Artificial neural network model for predicting α-turn types
    Cai, YD
    Chou, KC
    [J]. ANALYTICAL BIOCHEMISTRY, 1999, 268 (02) : 407 - 409
  • [23] Predictive Performance of Artificial Neural Network and Multiple Linear Regression Models in Predicting Adhesive Bonding Strength of Wood
    Bardak, S.
    Tiryaki, S.
    Bardak, T.
    Aydin, A.
    [J]. STRENGTH OF MATERIALS, 2016, 48 (06) : 811 - 824
  • [24] Identification of the relevant input variables for predicting the parabolic trough solar collector's outlet temperature using an artificial neural network and a multiple linear regression model
    Ajbar, Wassila
    Parrales, A.
    Silva-Martinez, S.
    Bassam, A.
    Jaramillo, O. A.
    Hernandez, J. A.
    [J]. JOURNAL OF RENEWABLE AND SUSTAINABLE ENERGY, 2021, 13 (04)
  • [25] Predictive Performance of Artificial Neural Network and Multiple Linear Regression Models in Predicting Adhesive Bonding Strength of Wood
    S. Bardak
    S. Tiryaki
    T. Bardak
    A. Aydin
    [J]. Strength of Materials, 2016, 48 : 811 - 824
  • [26] Artificial neural network versus multiple linear regression: Predicting P/B ratios from empirical data
    Brey, T
    JarreTeichmann, A
    Borlich, O
    [J]. MARINE ECOLOGY PROGRESS SERIES, 1996, 140 (1-3) : 251 - 256
  • [27] Multiple Linear Regression Model Based on Neural Network and Its Application in the MBR Simulation
    Li, Chunqing
    Yang, Zixiang
    Deng, Yiquan
    Wang, Tao
    [J]. ABSTRACT AND APPLIED ANALYSIS, 2012,
  • [28] Development of air–soil temperature model using computational intelligence paradigms: artificial neural network versus multiple linear regression
    Salim Heddam
    [J]. Modeling Earth Systems and Environment, 2019, 5 : 747 - 751
  • [29] Simulation of artificial neural network model for trunk sap flow of Pyrus pyrifolia and its comparison with multiple-linear regression
    Liu, Xiaozhi
    Kang, Shaozhong
    Li, Fusheng
    [J]. AGRICULTURAL WATER MANAGEMENT, 2009, 96 (06) : 939 - 945
  • [30] An artificial neural network supported regression model for wear rate
    Argatov, Ivan I.
    Chai, Young S.
    [J]. TRIBOLOGY INTERNATIONAL, 2019, 138 : 211 - 214
12345