An automated data-driven tool to build artificial neural networks for predictive decision-making

Chun-kit Ngan

Research output: Contribution to journalArticle

Abstract

We propose the development of an automated data-driven tool to assist data analysts in building an optimal artificial neural network (ANN) model to solve their domain-specific problems for predictive decision making. The proposed approach combines the strengths of both sequential training methods and multi-hidden-layer learning algorithms to dynamically learn the best-fitted parameters, including learning rate (LR), momentum rate (MR), number of hidden layers (NHL), and number of neurons in each hidden layer (NNHL), for the given set of key input attributes and multiple output nodes. Specifically, the contributions of this work are three-fold: 1) develop the new extended algorithm, i.e., multidimensional parameter learning (MPL), to learn the optimal ANN parameters; 2) provide the user-friendly GUI tool for data analysts to maintain the data manipulations and the tool operations; 3) conduct the experimental case study, i.e., determining the severity level of Alzheimer's patients, to present the superior result (i.e., 95.33%) in terms of prediction accuracy and model complexity by using the learned parameters (i.e., LR = 0.6, MR = 0.8, NHL = 2, NNHL at the 1st layer = 28, and NNHL at the 2nd layer = 24) from the MPL algorithm.

Original languageEnglish (US)
Pages (from-to)238-255
Number of pages18
JournalInternational Journal of Applied Decision Sciences
Volume11
Issue number3
DOIs
StatePublished - Jan 1 2018

Fingerprint

Decision making
Artificial neural network
Neuron
Analysts
Learning algorithm
Momentum
Node
Prediction accuracy
Network model
Training methods
Severity
Prediction model
Manipulation

All Science Journal Classification (ASJC) codes

  • Economics and Econometrics
  • Strategy and Management
  • Management Science and Operations Research
  • Information Systems and Management

Cite this

@article{43e172417dd64c02be6c86d78b8afe58,
title = "An automated data-driven tool to build artificial neural networks for predictive decision-making",
abstract = "We propose the development of an automated data-driven tool to assist data analysts in building an optimal artificial neural network (ANN) model to solve their domain-specific problems for predictive decision making. The proposed approach combines the strengths of both sequential training methods and multi-hidden-layer learning algorithms to dynamically learn the best-fitted parameters, including learning rate (LR), momentum rate (MR), number of hidden layers (NHL), and number of neurons in each hidden layer (NNHL), for the given set of key input attributes and multiple output nodes. Specifically, the contributions of this work are three-fold: 1) develop the new extended algorithm, i.e., multidimensional parameter learning (MPL), to learn the optimal ANN parameters; 2) provide the user-friendly GUI tool for data analysts to maintain the data manipulations and the tool operations; 3) conduct the experimental case study, i.e., determining the severity level of Alzheimer's patients, to present the superior result (i.e., 95.33{\%}) in terms of prediction accuracy and model complexity by using the learned parameters (i.e., LR = 0.6, MR = 0.8, NHL = 2, NNHL at the 1st layer = 28, and NNHL at the 2nd layer = 24) from the MPL algorithm.",
author = "Chun-kit Ngan",
year = "2018",
month = "1",
day = "1",
doi = "10.1504/IJADS.2018.092795",
language = "English (US)",
volume = "11",
pages = "238--255",
journal = "International Journal of Applied Decision Sciences",
issn = "1755-8077",
publisher = "Inderscience Enterprises Ltd",
number = "3",

}

An automated data-driven tool to build artificial neural networks for predictive decision-making. / Ngan, Chun-kit.

In: International Journal of Applied Decision Sciences, Vol. 11, No. 3, 01.01.2018, p. 238-255.

Research output: Contribution to journalArticle

TY - JOUR

T1 - An automated data-driven tool to build artificial neural networks for predictive decision-making

AU - Ngan, Chun-kit

PY - 2018/1/1

Y1 - 2018/1/1

N2 - We propose the development of an automated data-driven tool to assist data analysts in building an optimal artificial neural network (ANN) model to solve their domain-specific problems for predictive decision making. The proposed approach combines the strengths of both sequential training methods and multi-hidden-layer learning algorithms to dynamically learn the best-fitted parameters, including learning rate (LR), momentum rate (MR), number of hidden layers (NHL), and number of neurons in each hidden layer (NNHL), for the given set of key input attributes and multiple output nodes. Specifically, the contributions of this work are three-fold: 1) develop the new extended algorithm, i.e., multidimensional parameter learning (MPL), to learn the optimal ANN parameters; 2) provide the user-friendly GUI tool for data analysts to maintain the data manipulations and the tool operations; 3) conduct the experimental case study, i.e., determining the severity level of Alzheimer's patients, to present the superior result (i.e., 95.33%) in terms of prediction accuracy and model complexity by using the learned parameters (i.e., LR = 0.6, MR = 0.8, NHL = 2, NNHL at the 1st layer = 28, and NNHL at the 2nd layer = 24) from the MPL algorithm.

AB - We propose the development of an automated data-driven tool to assist data analysts in building an optimal artificial neural network (ANN) model to solve their domain-specific problems for predictive decision making. The proposed approach combines the strengths of both sequential training methods and multi-hidden-layer learning algorithms to dynamically learn the best-fitted parameters, including learning rate (LR), momentum rate (MR), number of hidden layers (NHL), and number of neurons in each hidden layer (NNHL), for the given set of key input attributes and multiple output nodes. Specifically, the contributions of this work are three-fold: 1) develop the new extended algorithm, i.e., multidimensional parameter learning (MPL), to learn the optimal ANN parameters; 2) provide the user-friendly GUI tool for data analysts to maintain the data manipulations and the tool operations; 3) conduct the experimental case study, i.e., determining the severity level of Alzheimer's patients, to present the superior result (i.e., 95.33%) in terms of prediction accuracy and model complexity by using the learned parameters (i.e., LR = 0.6, MR = 0.8, NHL = 2, NNHL at the 1st layer = 28, and NNHL at the 2nd layer = 24) from the MPL algorithm.

UR - http://www.scopus.com/inward/record.url?scp=85049597799&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85049597799&partnerID=8YFLogxK

U2 - 10.1504/IJADS.2018.092795

DO - 10.1504/IJADS.2018.092795

M3 - Article

VL - 11

SP - 238

EP - 255

JO - International Journal of Applied Decision Sciences

JF - International Journal of Applied Decision Sciences

SN - 1755-8077

IS - 3

ER -