SOM learning is influenced by the se-quence of learning data and the initial feature map. In conventional method, ini-tial value of feature map has set at ran-dom, so a different mapping appears even by same input data, so different impres-sions could be increased to the same data in different diagnosis....

This paper deals with Gross Error Detection using a signal-based approach and proposes an algorithm to be applied in industrial processes. The developed algorithm is used in some industrial software platforms to detect sensor outliers. A validation of this algorithm through computer simulations is shown....

SKK Migas has mission to supervise and control activities of upstream Oil & Gas. It is believed that by knowing efficiency level of each PSC Contractor, improvement programs can be more effective and directly hit the objective. This paper discusses research proposal on efficiency metrics using data mining...

We propose a statistical approach with which to identify the indexes crucial to classifying Chinese yams by shape. The proposed approach comprises two steps. The first step is to estimate the diameters indicating the shapes of yams along their length, and the second step is to characterize the shapes...

The impacts of franchise business to the economic are proven globally. In order to increase the company value the company value and to keep competitive, companies need to understand the customers and its business environment. The impact of in-formation system is proven that give positive impact to companies....

Many diabetic patients eventually develop foot ulcers are at risk for further infection and subsequent amputation if they are not treated promptly. Hence, this study is focused on identifying wild type strain bacteria and standard ATCC bacte-ria using e-nose which are PEN3 and Cyranose320. Data collected...

This paper presents the estimation of pu-rity of honey using Artificial Neural Network (ANN). ANN method was used to automate the decision of estimation, replacing the manual human approximate method. A total of 21 honey purity sam-ples from various concentrations of pure honey, adulterated honey and...

Face recognition is an ever changing and evolving domain for research. However, the application of face recognition is still new and not commonly used in this country as opposed to other biometric identifications. This paper seeks to find out the effectiveness and weaknesses of face recognition approach...

Back-Propagation Neural Network (BPNN) algorithm is a widely used technique implemented in many engineering disciplines. Despite solving several practical problems around the globe, BPNN still faces problems like slow convergence, network stagnancy and convergence to local minima. Many alternative ways...

RNNs have local feedback loops within the network which allows them to shop earlier accessible patterns. This network can be educated with gradient descent back propagation and optimization technique such as second-order methods; conjugate gradient, quasi-Newton, Levenberg- Marquardt have also been used...

A duffing system under approximate sawtooth wave excitation obtained by a relaxation oscillator is proposed, and its dynamic properties (including phase trajectory, time evolution, bifurcation diagram) are analyzed, also the impact of excitation magnitude change on phase trajectory is discussed. The...

Having a significance vulnerability clas-sification is important in developing a strong confidence in choosing the damag-ing cases associated with testing prob-lems. The accurate classification helps to explain the belonging of vulnerability. The current research failed to empirically describe these...

Numerical techniques are applied to a set of experimental data to study depolymerization process of xenobiotic polymers. The molecular factor of the degradation rate is obtained numerically from the weight distribution before and after cultivation of microorganisms. The temporal factor of the degradation...

Path planning algorithm is compulsory for establishing autonomous Unmanned Aerial Vehicle (UAV). The dynamic path planning based on linear and Modified Dubins algorithm was introduced. The path planning is used for intercepting a moving target. In order to obtain optimum path, decision making has to...