Regularization Activation Function for Extreme Learning Machine
Journal Title: International Journal of Advanced Computer Science & Applications - Year 2019, Vol 10, Issue 3
Abstract
Extreme Learning Machine (ELM) algorithm based on single hidden layer feedforward neural networks has shown as the best time series prediction technique. Furthermore, the algorithm has a good generalization performance with extremely fast learning speed. However, ELM facing overfitting problem that can affect the model quality due to the implementation using empirical risk minimization scheme. Therefore, this study aims to improve ELM by introducing an Activation Functions Regularization in ELM called RAF-ELM. The experiment has been conducted in two phases. First, investigating the modified RAF-ELM performance using four type of activation functions which is Sigmoid, Sine, Tribas and Hardlim. In this study, input weight and bias for hidden layers are randomly selected, whereas the best neurons number of hidden layer is determined from 5 to 100. This experiment used UCI benchmark datasets. The number of neurons (99) using Sigmoid activation function shown the best performance. The proposed methods has improved the accuracy performance and learning speed up to 0.016205 MAE and processing time 0.007 seconds respectively compared with conventional ELM and has improved up to 0.0354 MSE for accuracy performance compare with state of the art algorithm. The second experiment is to validate the proposed RAF-ELM using 15 regression benchmark dataset. RAF-ELM has been compared with four neural network techniques namely conventional ELM, Back Propagation, Radial Basis Function and Elman. The results show that RAF-ELM technique obtain the best performance compared to other techniques in term of accuracy for various time series data that come from various domain.
Authors and Affiliations
Noraini Ismail, Zulaiha Ali Othman, Noor Azah Samsudin
Keywords
Related Articles
- EP ID EP498526
- DOI 10.14569/IJACSA.2019.0100331
- Views 75
- Downloads 0
Real-Time Analysis of Students’ Activities on an E-Learning Platform based on Apache Spark
Real time analytics is the capacity to extract valuables insights from data that comes continuously from activities on the web or network sensors. It is largely used in web based business to drive decisions based on user...
Effective Calibration and Evaluation of Multi-Camera Robotic Head
The paper deals with appropriate calibration of multispectral vision systems and evaluation of the calibration and data-fusion quality in real-world indoor and outdoor conditions. Checkerboard calibration pattern develop...
Grid Color Moment Features in Glaucoma Classification
Automated diagnosis of glaucoma disease is focused on the analysis of the retinal images to localize, perceive and evaluate the optic disc. Clinical decision support system (CDSS) is used for glaucoma classification in h...
Intruder Attacks on Wireless Sensor Networks: A Soft Decision and Prevention Mechanism
Because of the wide-ranging of applications in a variety of fields, such as medicine, environmental studies, robotics, warfare and security, and so forth, the research on wireless sensor networks (WSNs) has attracted muc...
Interaction Protocols in Multi-Agent Systems based on Agent Petri Nets Model
This paper deals with the modeling of interaction between agents in Multi Agents System (MAS) based on Agent Petri Nets (APN). Our models are created based on communicating agents. Indeed, an agent initiating a conversat...