LINEAR DISCRIMINANT ANALYSIS VERSUS ARTIFICIAL NEURAL NETWORK AS CLASSIFIERS FOR ELBOW ANGULAR POSITION RECOGNITION PURPOSES

ABSTRACT The present study aimed at evaluating the heterotic group formation in guava based on quantitative descriptors and using artificial neural network (ANN). For such, we evaluated eight quantitative descriptors. Large genetic variability was found for the eight quantitative traits in the 138 genotypes of guava. The artificial neural network technique determined that the optimal number of groups was three. The grouping consistency was determined by linear discriminant analysis, which obtained classification percentage of the groups, with a value of 86 %. It was concluded that the artificial neural network method is effective to detect genetic divergence and heterotic group formation.

Download Full-text

Slum Dwellers Perception Towards Ujjwala Yojana, a Government-Lead LPG Intervention Programme in India: An Empirical Investigation

Journal of Social Inclusion Studies ◽

10.1177/23944811211020379 ◽

2021 ◽

pp. 239448112110203

Author(s):

Koustubh Kanti Ray

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

Discriminant Analysis ◽

Support Vector ◽

Intervention Programme ◽

Linear Discriminant ◽

Customer Perception ◽

Slum Dwellers ◽

Functional Factors ◽

Artificial Neural

Numerous studies are available in the academic literature that investigates the customer perception under different contexts. In the present research the researcher tries to investigate the customer perception towards the Indian Government-sponsored social programme from the slum dwellers’ prospective. The author believes that the customer perception towards the government-lead liquefied petroleum gas intervention programme is influenced by multiple functional factors. The functional factors include both process or delivery variables and the outcome factors. In order to test the hypothesis, machine learning binary classifiers like logit, support vector machine, linear discriminant analysis, quadratic discriminant analysis and artificial neural network models are adopted. The binary classifier model efficiencies are analysed with multiple performance measurement parameters like accuracy rate, error rate, F-score, precision, kappa coefficient, Matthews correlation coefficient and area under receiver operating characteristic. While evaluating between the degree of accuracy between actual and predicted cases, the model efficiency results indicate a better predictive power of the classifier models. In relative performance of classifier models, artificial neural network outperformed the other models adopted in the empirical research.

Download Full-text

Face Recognition Using Principal Component Analysis-Fuzzy Linear Discriminant Analysis and Dynamic Fuzzy Neural Network

Lecture Notes in Electrical Engineering - Future Wireless Networks and Information Systems ◽

10.1007/978-3-642-27323-0_73 ◽

2012 ◽

pp. 577-586 ◽

Cited By ~ 1

Author(s):

Sai Wang ◽

Huiwen Deng

Keyword(s):

Neural Network ◽

Principal Component Analysis ◽

Face Recognition ◽

Discriminant Analysis ◽

Linear Discriminant Analysis ◽

Fuzzy Neural Network ◽

Principal Component ◽

Component Analysis ◽

Linear Discriminant ◽

Fuzzy Neural

Download Full-text

Human body activity recognition using wearable inertial sensors integrated with a feature extraction–based machine-learning classification algorithm

Proceedings of the Institution of Mechanical Engineers Part B Journal of Engineering Manufacture ◽

10.1177/0954405420937894 ◽

2020 ◽

pp. 095440542093789

Author(s):

Chih-Ta Yen ◽

Jia-De Lin

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

Feature Extraction ◽

Discriminant Analysis ◽

Activity Recognition ◽

Inertial Sensors ◽

Recognition Accuracy ◽

Daily Activities ◽

Linear Discriminant ◽

Wearable Inertial Sensors

This study employed wearable inertial sensors integrated with an activity-recognition algorithm to recognize six types of daily activities performed by humans, namely walking, ascending stairs, descending stairs, sitting, standing, and lying. The sensor system consisted of a microcontroller, a three-axis accelerometer, and a three-axis gyro; the algorithm involved collecting and normalizing the activity signals. To simplify the calculation process and to maximize the recognition accuracy, the data were preprocessed through linear discriminant analysis; this reduced their dimensionality and captured their features, thereby reducing the feature space of the accelerometer and gyro signals; they were then verified through the use of six classification algorithms. The new contribution is that after feature extraction, data classification results indicated that an artificial neural network was the most stable and effective of the six algorithms. In the experiment, 20 participants equipped the wearable sensors on their waists to record the aforementioned six types of daily activities and to verify the effectiveness of the sensors. According to the cross-validation results, the combination of linear discriminant analysis and an artificial neural network was the most stable classification algorithm for data generalization; its activity-recognition accuracy was 87.37% on the training data and 80.96% on the test data.

Download Full-text