Fuzzy Model Optimization for Time Series Data Using a Translation in the Extent of Mean Error

Nurhayadi, Nurhayadi; Subanar, .; Abdurakhman, Abdurakhman; Abadi, Agus Maman

doi:10.3844/jmssp.2014.267.274

Cited by 6 publications

(3 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The application of the fuzzy model in forecasting time series has widespread increasingly. The researchers have also been trying to improve the forecasting time series quality in many ways [2]. Song and Chisoom have studied the fuzzy application for the university ' 'enrolment's prediction [3][4][5].…”

Section: Introductionmentioning

confidence: 99%

Implementation of Average-Based Fuzzy Time Series Model in Forecasting Product Selling at Ainaya Boutique

Ramadhani¹,

Abadi²

2021

Advances in Social Science, Education and Humanities Research

View full text Add to dashboard Cite

Demand forecasting is needed in a company to find out the estimated level of demand in the future. Forecasting cannot be considered as an absolute one because there is no accurate forecasting. The forecasting accuracy level continues to be sought through forecasting development. One of those is applied through artificial intelligence. This study discusses the application of forecasting product selling using average-based fuzzy time series in Ainaya Boutique as the case of the study. The forecasting system with average-based fuzzy time series captures patterns from past data. In this study, the data used for forecasting is monthly selling data based on the last three years. This research uses five types of products that are sold the most in the boutique. The trial result of forecasting selling products during January 2017-December 2019 that uses the average-based fuzzy time series model show the result of the next month following data: the average error for the robe is 4.81%, 11.21% for the tunic, 8.78% for pashmina, 18.35% for khimar, and 9.72% for jeans. These results show that forecasting selling products in an Ainaya Boutique using the average-based fuzzy time series model has a high accuracy level.

show abstract

Section: Introductionmentioning

confidence: 99%

Implementation of Average-Based Fuzzy Time Series Model in Forecasting Product Selling at Ainaya Boutique

Ramadhani¹,

Abadi²

2021

Advances in Social Science, Education and Humanities Research

View full text Add to dashboard Cite

show abstract

“…It has suggested that an idea of applying hybrid methods in place of AR in modelling subintervals is promising. Some of the approaches are fuzzy system as shown in work of Nurhayadi et al [34], [35] and neuro fuzzy as in Abadi et al [36].…”

Section: Arrival Time Of P and S Wave Of Mount Rinjanimentioning

confidence: 99%

Detecting P and S-wave of Mt. Rinjani seismic based on a locally stationary autoregressive (LSAR) model

Nurhaida¹,

Subanar²,

Abdurakhman³

et al. 2017

AIP Conference Proceedings

View full text Add to dashboard Cite

Abstract. Seismic data is usually modelled using autoregressive processes. The aim of this paper is to find the arrival times of the seismic waves of Mt. Rinjani in Indonesia. Kitagawa algorithm's is used to detect the seismic P and S-wave. Householder transformation used in the algorithm made it effectively finding the number of change points and parameters of the autoregressive models. The results show that the use of Box-Cox transformation on the variable selection level makes the algorithm works well in detecting the change points. Furthermore, when the basic span of the subinterval is set 200 seconds and the maximum AR order is 20, there are 8 change points which occur at 1601, 2001, 7401, 7601,7801, 8001, 8201 and 9601. Finally, The P and S-wave arrival times are detected at time 1671 and 2045 respectively using a precise detection algorithm.

show abstract

“…The research on fuzzy system that uses time series data was first conducted by Song [5]- [7] to predict the number of enrollments in a university. Other research conducted by Nurhayadi [8] is to predict the register at the Albama University. Then, Shah [9] applied fuzzy time series to predict the gross domestic capital in In fact, Lee's research [16] weighted fuzzy time series method has better accuracy than Chen's [11], Yu's [12], and Cheng's [17] method.…”

Section: Introductionmentioning

confidence: 99%

Application of Weighted Fuzzy Time Series Model to Forecast Trans Jogja’s Passengers

A’yun¹,

Abadi²,

Saptaningtyas³

2015

IJAPM

View full text Add to dashboard Cite

Trans Jogja is a public transportation in Yogyakarta which is operated by Dishubkominfo DIY. It is one of the ways to overcome transportation problems especially traffic jams. The total number of the buses until now reaches to 54. In fact, it does not significantly overcome the traffic jam problem yet. Dishubkominfo DIY always makes some efforts to improve the Trans Jogja management. One of them is by giving good services to the passengers. So, it is important to predict the amount of the passengers of Trans Jogja. This forecast uses the data from July 1 st 2014 -September 29 th 2014. This forecast is based on Weighted Fuzzy Time Series (WFTS). To forecast using WFTS, there are some important steps. There are defining the universe of discourse U, defining the fuzzy sets, establishing fuzzy logical relationship, grouping, forecasting, defuzzification, assigning weights and the last is calculating the final forecast values.

show abstract

Fuzzy Model Optimization for Time Series Data Using a Translation in the Extent of Mean Error

Cited by 6 publications

References 24 publications

Implementation of Average-Based Fuzzy Time Series Model in Forecasting Product Selling at Ainaya Boutique

Implementation of Average-Based Fuzzy Time Series Model in Forecasting Product Selling at Ainaya Boutique

Detecting P and S-wave of Mt. Rinjani seismic based on a locally stationary autoregressive (LSAR) model

Application of Weighted Fuzzy Time Series Model to Forecast Trans Jogja’s Passengers

Contact Info

Product

Resources

About