Thai Water Buffalo Disease Analysis with the Application of Feature Selection Technique and Multi-Layer Perceptron Neural Network

This research aims to develop the analysis model for diseases in water buffalo towards the application of the feature selection technique along with the Multi-Layer Perceptron neural network. The data used for analysis was collected from books and documents related to diseases in water buffalo and the official website of the Department of Livestock Development. The data consists of the characteristics of six diseases in water buffalo, including Anthrax disease, Hemorrhagic Septicemia, Brucellosis, Foot and Mouth disease, Parasitic disease, and Mastitis. Since the amount of the collected data was limited, the Synthetic Minority Over-sampling Technique was also employed to adjust the imbalance dataset. Afterward, the adjusted dataset was used to select the disease characteristics towards the application of two feature selection techniques, including Correlation-based Feature Selection and Information Gain. Subsequently, the selected features were then used for developing the analysis model for diseases in water buffalo towards the use of Multi-Layer Perceptron neural network. The evaluation results of the model’s effectiveness, given by the 10-fold cross-validation, showed that the analysis model for diseases in water buffalo developed by Correlation-based Feature Selection and Multi-Layer Perceptron neural network provided the highest level of effectiveness with the accuracy of 99.71%, the precision of 99.70%, and the recall of 99.72%. This implies that the analysis model is effectively applicable.

Download Full-text

Multi-Layer Perceptron Neural Network Model Development for Chili Pepper Disease Diagnosis Using Filter and Wrapper Feature Selection Methods

Engineering, Technology & Applied Science Research ◽

10.48084/etasr.4383 ◽

2021 ◽

Vol 11 (5) ◽

pp. 7714-7719

Author(s):

S. Nuanmeesri ◽

W. Sriurai

Keyword(s):

Neural Network ◽

Feature Selection ◽

Information Gain ◽

Disease Diagnosis ◽

Chili Pepper ◽

Growth Stages ◽

Multi Layer Perceptron ◽

Selection Methods ◽

Diagnosis Model ◽

Wrapper Feature Selection

The goal of the current study is to develop a diagnosis model for chili pepper disease diagnosis by applying filter and wrapper feature selection methods as well as a Multi-Layer Perceptron Neural Network (MLPNN). The data used for developing the model include 1) types, 2) causative agents, 3) areas of infection, 4) growth stages of infection, 5) conditions, 6) symptoms, and 7) 14 types of chili pepper diseases. These datasets were applied to the 3 feature selection techniques, including information gain, gain ratio, and wrapper. After selecting the key features, the selected datasets were utilized to develop the diagnosis model towards the application of MLPNN. According to the model’s effectiveness evaluation results, estimated by 10-fold cross-validation, it can be seen that the diagnosis model developed by applying the wrapper method along with MLPNN provided the highest level of effectiveness, with an accuracy of 98.91%, precision of 98.92%, and recall of 98.89%. The findings showed that the developed model is applicable.

Download Full-text

An effective ensemble classification framework using random forests and a correlation based feature selection technique

Transactions in GIS ◽

10.1111/tgis.12268 ◽

2017 ◽

Vol 21 (6) ◽

pp. 1165-1178 ◽

Cited By ~ 13

Author(s):

Dibyajyoti Chutia ◽

Dhruba Kumar Bhattacharyya ◽

Jaganath Sarma ◽

Penumetcha Narasa Lakshmi Raju

Keyword(s):

Feature Selection ◽

Random Forests ◽

Ensemble Classification ◽

Feature Selection Technique ◽

Selection Technique ◽

Classification Framework ◽

Correlation Based Feature Selection

Download Full-text

Dynamic voltage stability prediction of power systems by a new feature selection technique and probabilistic neural network

European Transactions on Electrical Power ◽

10.1002/etep.444 ◽

2010 ◽

Vol 21 (1) ◽

pp. 312-328 ◽

Cited By ~ 6

Author(s):

Nima Amjady ◽

Mohammad Hossein Velayati

Keyword(s):

Neural Network ◽

Feature Selection ◽

Power Systems ◽

Probabilistic Neural Network ◽

Stability Prediction ◽

Feature Selection Technique ◽

Selection Technique ◽

Dynamic Voltage ◽

Dynamic Voltage Stability ◽

New Feature

Download Full-text

Sentiment Classification using Neural Network and Ensemble Model based on Genetic Algorithm

International Journal of Engineering and Advanced Technology - Regular Issue ◽

10.35940/ijeat.b3677.029320 ◽

2020 ◽

Vol 9 (3) ◽

pp. 1885-1891

Keyword(s):

Neural Network ◽

Genetic Algorithm ◽

Feature Selection ◽

Web Sites ◽

Information Gain ◽

Back Propagation ◽

Feature Selection Method ◽

Propagation Model ◽

Feature Selection Technique ◽

Fast Development

The fast development of web sites and the number of product on these websites are available. The purpose of classification of sentiment is to efficiently identify opinion expressed in text. This paper compares three different optimized models including genetic optimized feature selection method, Genetic Algorithm (GA), ensemble approach that uses information gain and genetic algorithm as feature selection methods incorporated SVM model, Genetic Bagging (GB) and the next method uses optimized feature selection as feature selection technique incorporated back propagation model, Genetic Neural Network (GNN) models are compared. We are tested in sentiment analysis using sample multi-domain review datasets and movie review dataset.. These approaches are tested using various quality metrics and the results show that the Genetic Bagging (GB) technique outperforms in classifying the sentiment of the multi domain reviews and movie reviews. An empirical analysis is performed to compare the level of importance of the classifiers GB, GNN methods with McNemar’s statistical method.

Download Full-text