1,721,026 research outputs found
A Survey on Model Selection in Neural Networks for Prediction and Classification Problems
No full text
Simulation of queue with cyclic service in signalized intersection system
Full text linkThe simulation was implemented by modeling the queue with cyclic service in the signalized intersection system. The service policies used in this study were exhaustive and gated, the model was the M/M/1 queue, the arrival rate used was Poisson distribution and the services rate used was Exponential distribution. In the gated service policy, the server served only vehicles that came before the green signal appears at an intersection. Considered that there were 2 types of exhaustive policy in the signalized intersection system, namely normal exhaustive (vehicles only served during the green signal was still active), and exhaustive (there was the green signal duration addition at the intersection, when the green signal duration at an intersection finished). The results of this queueing simulation program were to obtain characteristics and performance of the system, i.e. average number of vehicles and waiting time of vehicles in the intersection and in the system, as well as system utilities. Then from these values, it would be known which of the cyclic service policies (normal exhaustive, exhaustive and gated) was the most suitable when applied to a signalized intersection syste
Brown’s Weighted Exponential Moving Average Implementation in Forex Forecasting
No full textIn 2016, a time series forecasting technique which combined the weighting factor calculation formula found in weighted moving average with Brown's double exponential smoothing procedures had been introduced. The technique is known as Brown's weighted exponential moving average (B-WEMA), as a new variant of double exponential smoothing method which does the exponential filter processes twice. In this research, we will try to implement the new method to forecast some foreign exchange, or known as forex data, including EUR/USD, AUD/USD, GBP/USD, USD/JPY and EUR/JPY data. The time series data forecasting results using B-WEMA then be compared with other conventional and hybrid moving average methods, such as weighted moving average (WMA), exponential moving average (EMA) and Brown's double exponential smoothing (B-DES). The comparison results show that B-WEMA has a better accuracy level than other forecasting methods used in this research
Stock Data Clustering of Food and Beverage Company
No full textAbstract
Cluster analysis can be defined as identifying groups of similar objects to discover distribution of patterns and interesting correlations in large data sets. Clustering analysis is important in the fields of pattern recognition and pattern classification. Over the years many methods have been developed for clustering data. In general, clustering methods can be categoried into two categories, i.e., fuzzy clustering and hard clustering. Fuzzy C-means is one of many methods of clustering based on fuzzy approach, while K-Means and K-Medoid are methods clustering based on crisp approach.
This study aims to apply Fuzzy C-Means, K-Means and K-Medoid methods for clustering stock data in a jbod and beverage company. The main goal is to find a clustering method that can produce optimal clusters, The resulting clusters are validated using Dunn'• Index (DI). It is expected that the result of this reseach can be used to support decision making in the food and beverage company.
Keywords : Clustering, Fuzzy C-Means, K-Means, K-Medoid, Cluster Validity, Dunn's Index (Dl
BAYESIAN ANALYSIS OF TOBIT QUANTILE REGRESSION WITH ADAPTIVE LASSO PENALTY IN HOUSEHOLD EXPENDITURE FOR CIGARETTE CONSUMPTION
Full text linkTobit Quantile Regression with Adaptive Lasso Penalty is a quantile regression model on censored data that adds Lasso's adaptive penalty to its parameter estimation. The estimation of the regression parameters is solved by Bayesian analysis. Parameters are assumed to follow a certain distribution called the prior distribution. Using the sample information along with the prior distribution, the conditional posterior distribution is searched using the Box-Tiao rule. Computational solutions are solved by the MCMC Gibbs Sampling algorithm. Gibbs Sampling can generate samples based on the conditional posterior distribution of each parameter in order to obtain a posterior joint distribution. Tobit Quantile Regression with Adaptive Lasso Penalty was applied to data on Household Expenditure for Cigarette Consumption in 2011. As a comparison for data analysis, Tobit Quantile Regression was used. The results of data analysis show that the Tobit Quantile Regression model with Adaptive Lasso Penalty is better than the Tobit Quantile Regression
THE EFFECT OF DECOMPOSITION METHOD AS DATA PREPROCESSING ON NEURAL NETWORKS MODEL FOR FORECASTING TREND AND SEASONAL TIME SERIES
No full textRecently, one of the central topics for the neural networks (NN) community is the issue of data preprocessing on the use of NN. In this paper, we will investigate this topic particularly on the effect of Decomposition method as data processing and the use of NN for modeling effectively time series with both trend and seasonal patterns. Limited empirical studies on seasonal time series forecasting with neural networks show that some find neural networks are able to model seasonality directly and prior deseasonalization is not necessary, and others conclude just the opposite. In this research, we study particularly on the effectiveness of data preprocessing, including detrending and deseasonalization by applying Decomposition method on NN modeling and forecasting performance. We use two kinds of data, simulation and real data. Simulation data are examined on multiplicative of trend and seasonality patterns. The results are compared to those obtained from the classical time series model. Our result shows that a combination of detrending and deseasonalization by applying Decomposition method is the effective data preprocessing on the use of NN for forecasting trend and seasonal time series
A New Approach of Fuzzy-Wavelet Method’s Implementation in Time Series Analysis
Full text linkAbstract— Recently, many soft computing methods have been used and implemented in time series analysis. One of the methods is fuzzy hybrid model which has been designed and developed to improve the accuracy of time series prediction.
Popoola has developed a fuzzy hybrid model which using wavelet transformation as a pre-processing tool, and commonly known as fuzzy-wavelet method. In this thesis, a new approach of fuzzy-wavelet method has been introduced. If in Popoola’s fuzzy-wavelet, a fuzzy inference system is built for each decomposition data, then on the new approach only two fuzzy inference systems will be needed. By that way, the computation needed in time series analysis can be pressed.
The research is continued by making new software that can be used to analyze any given time series data based on the forecasting method applied. As a comparison there are three forecasting methods implemented on the software, i.e. fuzzy conventional method, Popoola’s fuzzy-wavelet, and the new approach of fuzzy-wavelet method. The software can be used in short-term forecasting (single-step forecast) and long-term forecasting. There are some limitation to the software, i.e. maximum data can be predicted is 300, maximum interval can be built is 7, and maximum transformation level can be used is 10. Furthermore, the accuracy and robustness of the proposed method will be compared to the other forecasting methods, so that can give us a brief description about the accuracy and robustness of the proposed method.
Keywords— fuzzy, wavelet, time series, soft computin
INFERENSI BAYESIAN DALAM WAVELET SHRINKAGE
No full textIn this paper, we discuss the Bayesian inference in wavelet nonparametric problems. In most areas of application, there is a need for a shrinkage procedure to (i) adapt to data and (ii) use prier information. The Bayesian paradigm provides a natural terrain for both of these goals. •
In 1.oavelet domain, the Bayes rules §"(d) under the squared error loss function with selecti.on prior distribution 1r(fJ) for ()
whose symmetric property i.e TC(B) = rc(-B), in fact mjmic
'shrinkers', such that can be solved with wavelet shrinkage. In case the prior distribution for B with symmetric property and satisfies E(B) = 0, such that the shrinkage rules to wavelet coefficients
toward the prior mean can be solved
THE EFFECT OF DECOMPOSITION METHOD AS DATA PREPROCESSING ON NEURAL NETWORKS MODEL FOR FORECASTING TREND AND SEASONAL TIME SERIES
No full textRecently, one of the central topics for the neural networks (NN) community is the issue of data preprocessing on the use of NN. In this paper, we will investigate this topic particularly on the effect of Decomposition method as data processing and the use of NN for modeling effectively time series with both trend and seasonal patterns. Limited empirical studies on seasonal time series forecasting with neural networks show that some find neural networks are able to model seasonality directly and prior deseasonalization is not necessary, and others conclude just the opposite. In this research, we study particularly on the effectiveness of data preprocessing, including detrending and deseasonalization by applying Decomposition method on NN modeling and forecasting performance. We use two kinds of data, simulation and real data. Simulation data are examined on multiplicative of trend and seasonality patterns. The results are compared to those obtained from the classical time series model. Our result shows that a combination of detrending and deseasonalization by applying Decomposition method is the effective data preprocessing on the use of NN for forecasting trend and seasonal time series
- …
