few years, various contributions have been made in the literature on the comparison of FIR filter using neural network. Accurate analysis of comparison of different
RFID AND FACE RECOGNITION BASED ACCESS CONTROL SYSTEM 1Kenward Dzvifu, 2T Chakavarika Department of Information Security & Assurance, Harare Institute of Technology, Zimbabwe 1kenwarddzvifu@gmail.com 2ttchaka@gmail.com School of Information Science and Technology, Harare Institute of Technology, Zimbabwe ABSTRACT— The Radio frequency identification (RFID) technology has been broadly adopted in access control systems. This technology is based on the use of a card or tag and has some major
Hydraulics of Submerged Radial Gates with a Sill Abstract In this paper the submerged flow through radial gates with and without a gate sill was experimentally investigated. The effect of different gate sill heights on contraction coefficient, discharge coefficient, submerged jump length, backup water depth, flow energy dissipation, and velocity distribution with different hydraulic parameters were analyzed and graphically presented. A combination of dimensional and regression analysis tools was
objective of this review paper is to summarize and compare some of the well-known methods and application used in pattern recognition system. Keywords- Pattern recognition, classification, clustering, machine learning, error estimation, neural networks. Introduction A pattern is an entity, that could be given a name and pattern recognition is the study of how machines can observe the environment and make sense of it by differentiating between patterns. Humans are best pattern recognizers but
Extreme Learning Machine (ELM) Extreme Learning Machine is a feedforward neural network for the regression, sparse approximation, feature learning, compression, clustering and for classification with a single or multi layers of hidden nodes in which the parameters are randomly generated and they are need not be changed. The hidden nodes are assigned randomly and are never updated. But they can be inherited from their ancestors. In many cases the output weights of hidden nodes are generally learned
fuzzy rough set theory. This research solves the diagnostic breast cancer problems via a proposed hybrid model of fuzzy rough feature selection and rough neural networks. The medical data is preprocessed by the fuzzy rough feature selection algorithm to remove unnecessary attributes. The reduced data set is applied to the rough neural network to learn the connection weights iteratively. The test data set are used to measure the proposed model accuracy and time complexities. Lower and upper approximations
The Fourier series for a periodic function f(t) with fundamental frequency ω can be presented as: ft= C0+ n=1∞Cncos(nωt+θn) Equation 1 Fourier series for a periodic function The coefficients Cn and phase angles n for n-th harmonic are given by: Cn= An2+ Bn2 Equation 2 θn= tan-1-BnAn Equation 3 where T=2π/ω and C0 is the dc component of the function. The rms value of ft is defined as: An= 2T0Tf(t)cos(nωt)dt Equation 4 Bn= 2T0Tf(t)sin(nωt)dt
performance analysis of various neural networks (NN) for short term price forecasting. Several NN models are trained and tested on the half-hourly data from Australian Energy Market and their performances have been compared. Overall findings suggest that the value of mean absolute percentage Error (MAPE) in the case of 3-Layered cascaded neural network (CNN) is better than other proposed models. Keywords— Short term price forecasting, Cascaded Neural Network,
Data mining is the process of discovering patterns, trends, correlations from large amounts of data stored electronically in repositories, using statistical methods, mathematical formulas, and pattern recognition technologies (Sharma n.d.). The main idea is to analyze data from different perspectives and discover useful trends, patterns and associations. As discussed in the previous chapter, the healthcare organizations are producing massive amounts of electronic medical records, which are impossible
Extreme learning machine proposed by\cite{elm,elms} is a feed forward neural network classifier with single hidden layer in which the weights between input and hidden layer are initialized randomly. ELM uses analytical approach to compute weights between hidden and output layer\cite{elm} ,which makes it faster compared to other gradient based classifiers. ELM fails to handle class imbalance problem effectively. Many variants of Extreme Learning Machine like Weighted Extreme Learning Machine(WELM)\cite{WELM}