Comparative analysis of Recurrent and Finite Impulse Response Neural Networks in Time Series Prediction
Journal Title: Indian Journal of Computer Science and Engineering - Year 2012, Vol 3, Issue 1
Abstract
The purpose of this paper is to perform evaluation of two different neural network architectures used for solving temporal problems, i.e. time series prediction. The data sets in this project include Mackey-Glass, Sunspots, and Standard & Poor's 500, the stock market index. The study also presents a comparison study on the two networks and their performance.
Authors and Affiliations
Milos Miljanovic
Keywords
Related Articles
- EP ID EP119548
- DOI -
- Views 102
- Downloads 0
A Technique to improve Security of Data in Multilevel Trust
The Privacy Preserving Data Mining technique that is used widely to conserve security of data is a random perturbation method. The original data is modified and many copies are created according to the trust levels in ea...
DETECTION OF CROSS-PROJECT BENEFICIAL CLONES
Duplicate codes are also known as code clones. They are considered as one of the main factors that deteriorate the quality of software. They are usually discarded by using automatic clone detection tools. In this paper t...
PRE-IDEALS AND NEW TOPOLOGIES USING FUZZY SETS
A fuzzy ideal on a set X is a non empty collection of subsets of X with heredity property which is also closed under arbitrary union and finite intersections. In this paper, we introduce a weak form of fuzzy ideals namel...
STUDY AND PERFORMANCE ANALYSIS OF THE WYLLIE’S LIST RANKING ALGORITHM USING VARIOUS PARALLEL PROGRAMMING MODELS
The Wyllie’s list ranking algorithm takes a linked list data structure as an input and it pass the linked list successor elements to the succ1 array to find the Rank. The algorithm depends upon the Pointer jumping operat...
VARIABLE RATE STEGANOGRAPH Y IN DIGITAL IMAGES USING TWO, THREE AND FOUR NEIGHBOR PIXELS
In this paper three image steganography methods with variable rate of embedding are proposed. In the first method, called two neighbor method the two neighboring pixels such as upper and left are exploited to take embedd...