Solving multiple linear regression problem using artificial neural network

Khrisat, Mohammad S.; Alqadi, Ziad

doi:10.11591/ijece.v12i1.pp770-775

Cited by 8 publications

(8 citation statements)

References 12 publications

(14 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A pollution input data set was selected [2]- [5]. This data set contains a 2D matrix with 8 rows and 508 columns, each column represents the values of PM (temperature, relative humidity, carbon monoxide, sulfur dioxide, nitrogen dioxide, hydrocarbons, ozone) [24], [25], The target data is a 2D matrix with 3 rows and 508 column, each row represents the values of the pollution negative effects (total mortality, respiratory mortality, cardiovascular mortality), Figure 5 shows a sample of the input data set. The input data set was divided into 3 parts: training, testing and validating data, the various ANN architectures were selected to be trained and used as a prediction tool.…”

Section: Methodsmentioning

confidence: 99%

Autoregressive prediction analysis using machine deep learning

Khrisat

Alabadi

Khawatreh

et al. 2022

IJEECS

Self Cite

View full text Add to dashboard Cite

Regression analysis, in statistic a modelling, is a set of statical processes that can be used to estimate the relationship between a dependent variable, commonly known as the outcome or response, and more independent variables generally called predictors of covariant. On the other hand, autoregression, which is based on regression equations, is a sequential model that uses time to predict the next step data from the previous step. Given the importance of accurate modelling and reliable predictions. in this paper we have analyzed the most popular methods used for data prediction. Nonlinear autoregressive methods were introduced, and then the machine deep learning approach was used to apply prediction based on a selected input data set. The mean square error was calculated for various artificial neural networks architecture to reach the optimal architecture, which minimized the error. Different artificial neural network (ANN) architectures were trained, tested, and validated using various regressive models, a recommendation was raised according to the obtained and analyzed experimental results. It was shown that using the concepts of machine deep learning will enhance the response of the prediction model.

show abstract

Section: Methodsmentioning

confidence: 99%

Autoregressive prediction analysis using machine deep learning

Khrisat

Alabadi

Khawatreh

et al. 2022

IJEECS

Self Cite

View full text Add to dashboard Cite

show abstract

“…Additionally, linear regression cannot represent complex models with many inputs. When the model becomes complex, it can lead to overfitting [15], [16].…”

Section: Multiple Linear Regression Problemmentioning

confidence: 99%

Predicting ICO Prices Using Artificial Neural Network and Ridge Regression Algorithm

Toại

Hạn

Huân

2023

J Syst Eng Inf Technol

View full text Add to dashboard Cite

An Initial Coin Offering (ICO) is a method of raising funds for digital currency projects. Investors purchase these coins at a very low initial price before they are released. These coins are then listed on the trading platform, and their prices may increase rapidly if the currency performs well. After six months of release, ICO evaluation is the expected time for investors to profit. A dataset consisting of 109 ICOs was constructed from reputable websites after data preprocessing. Correlation analysis of 12 inputs revealed issues of multicollinearity, leading to biased regression model results. Overfitting occurred when using the regression model. To address these limitations, the Ridge regression method resolved the issues with the ICO data. An artificial neural network model addressed the complex nonlinear relationships between inputs and ICO prices. By adjusting parameters to achieve the best performance according to the Root Mean Square Error, R-squares, and Mean Absolute Error metrics, the results showed that the Ridge regression algorithm with a test set of three ICOs achieved accuracy ranging from 63% to 92% of ICO prices, while the artificial neural network model predicted with 98% accuracy depending on the metric used.

show abstract

“…the second function computes the output of the neuron which depends on an activation function [20,21] chosen for the neuron with specified layer. The following steps should be followed for the classification of FFANN (see Figure 5) [22][23][24]:…”

Section: Classification Using Artificial Neural Networkmentioning

confidence: 99%

Optimal Solution of Classification (Prediction) Problem

Khrisat¹

2022

RIA

Self Cite

View full text Add to dashboard Cite

Classification or prediction problem is how to solve it using a specific feature to obtain the predicted class. A wheat seeds specifications 4 3 classes of seeds will be used in a prediction process. A multi-linear regression will be built, and a prediction error ratio will be calculated. To enhance the prediction ratio an ANN model will be built and trained. The obtained results will be examined to show how to make a prediction tool capable to compute a predicted class number very close to the target class number.

show abstract

Solving multiple linear regression problem using artificial neural network

Cited by 8 publications

References 12 publications

Autoregressive prediction analysis using machine deep learning

Autoregressive prediction analysis using machine deep learning

Predicting ICO Prices Using Artificial Neural Network and Ridge Regression Algorithm

Optimal Solution of Classification (Prediction) Problem

Contact Info

Product

Resources

About