Conference Paper

Finding the number of hidden neurons for an MLP neural network using coarse to fine search technique

Comput. Eng. Program, Univ. Malaysia Sabah, Kota Kinabalu, Malaysia
DOI: 10.1109/ISSPA.2010.5605430 Conference: Information Sciences Signal Processing and their Applications (ISSPA), 2010 10th International Conference on
Source: IEEE Xplore

ABSTRACT

Skin detection is an important preliminary process for subsequent feature extraction in image processing techniques. There are several techniques that are used for skin detection. In this work, the multi-layer perceptron (MLP) neural network is used. One of the important aspects of MLP is how to determine the network topology. The number of neurons in the inputs and output layers are determined by the number of available inputs and required outputs respectively. Thus, the only thing remaining is how to determine the number of neurons in the hidden layer. Therefore, we employed the coarse to fine search method to find the number of neurons. First, the number of hidden neurons is initially set using the binary search mode, HN=1, 2, 4, 8, 16, 32, 64 and 128, where HN indicates the number of hidden neurons. The 30 networks with these HN values are trained and their Mean Squared Error (MSE) is calculated. Then a sequential search, fine search, will be used in the neighbourhood of the HN that gave the lowest MSE. The selected number of neurons in the hidden layer is the lowest HN that gave the lowest MSE. The YCbCr colour space is used in this work due to its capability to separate the luminance and chrominance components explicitly. Several chrominance components are investigated.

Download full-text

Full-text

Available from: Jamal Dargham, Dec 21, 2015
  • [Show abstract] [Hide abstract]
    ABSTRACT: Project management (PM) is the application of knowledge, skills, tools and techniques to project activities in order to meet project requirements. The success of any project relies heavily on the initial estimation of all project parameters. Fuzzy logic is a soft-computing technique used to effectively solve uncertainties due to imprecise inputs to generate linguistic or quantitative outputs. This paper investigates the application of fuzzy logic as a feasible technique for improved estimation accuracy to all the tasks within the project management knowledge areas to ensure higher software project success rates.
    No preview · Conference Paper · Jun 2004
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper reviews methods to fix a number of hidden neurons in neural networks for the past 20 years. And it also proposes a new method to fix the hidden neurons in Elman networks for wind speed prediction in renewable energy systems. The random selection of a number of hidden neurons might cause either overfitting or underfitting problems. This paper proposes the solution of these problems. To fix hidden neurons, 101 various criteria are tested based on the statistical errors. The results show that proposed model improves the accuracy and minimal error. The perfect design of the neural network based on the selection criteria is substantiated using convergence theorem. To verify the effectiveness of the model, simulations were conducted on real-time wind data. The experimental results show that with minimum errors the proposed approach can be used for wind speed prediction. The survey has been made for the fixation of hidden neurons in neural networks. The proposed model is simple, with minimal error, and efficient for fixation of hidden neurons in Elman networks.
    Full-text · Article · Jun 2013 · Mathematical Problems in Engineering
  • [Show abstract] [Hide abstract]
    ABSTRACT: Froth flotation is one of the most frequently used processes for separation of valuable from gangue minerals. Modeling and simulation of the flotation process is a difficult task because of non?linear and dynamic nature of the process. In this contribution, the relationship between the process variables (i.e., gas flow rate, slurry solids%, frother/collector dosages and pH) and the metallurgical parameters (i.e., copper/mass/water recoveries and concentrate grade) in the batch flotation of a copper sulfide ore is discussed and modeled. Statistical (i.e., non?linear regression) and intelligent (i.e., neural network and adaptive neuro?fuzzy) techniques are applied to model the process behavior at different conditions. The results indicate that intelligent approaches are more efficient tools for modeling of the complicated process like flotation, which are of central importance for development of the model?based control systems.
    No preview · Article · Nov 2014 · Chemical Engineering Communications
Show more