scholarly journals Clustering stationary and non-stationary time series based on autocorrelation distance of hierarchical and k-means algorithms

2017 ◽  
Vol 3 (3) ◽  
pp. 154 ◽  
Author(s):  
Mohammad Alfan Alfian Riyadi ◽  
Dian Sukma Pratiwi ◽  
Aldho Riski Irawan ◽  
Kartika Fithriasari
Keyword(s):  
Time Series ◽  
Time Series Data ◽  
Hierarchical Cluster ◽  
Temperature Data ◽  
Data Models ◽  
Stationary Time Series ◽  
Series Data ◽  
Classification Approach ◽  
Stationary Time ◽  
Autocorrelation Distance

Observing large dimension time series could be time-consuming. One identification and classification approach is a time series clustering. This study aimed to compare the accuracy of two algorithms, hierarchical cluster and K-Means cluster, using ACF’s distance for clustering stationary and non-stationary time series data. This research uses both simulation and real datasets. The simulation generates 7 stationary data models and another 7 of non-stationary data models. On the other hands, the real dataset is the daily temperature data in 34 cities in Indonesia. As a result, K-Means algorithm has the highest accuracy for both data models.

scholarly journals System for Prediction of Non Stationary Time Series based on the Wavelet Radial Bases Function Neural Network Model

2018 ◽  
Vol 8 (4) ◽  
pp. 2327 ◽  
Author(s):  
Heni Kusdarwati ◽  
Samingun Handoyo
Keyword(s):  
Neural Networks ◽  
Time Series ◽  
Time Series Data ◽  
Linear Trend ◽  
Stationary Time Series ◽  
Series Data ◽  
Training Time ◽  
Stationary Time ◽  
Computation Process ◽  
Smooth Coefficients

This paper proposes and examines the performance of a hybrid model called the wavelet radial bases function neural networks (WRBFNN). The model will be compared its performance with the wavelet feed forward neural networks (WFFN model by developing a prediction or forecasting system that considers two types of input formats: input9 and input17, and also considers 4 types of non-stationary time series data. The MODWT transform is used to generate wavelet and smooth coefficients, in which several elements of both coefficients are chosen in a particular way to serve as inputs to the NN model in both RBFNN and FFNN models. The performance of both WRBFNN and WFFNN models is evaluated by using MAPE and MSE value indicators, while the computation process of the two models is compared using two indicators, many epoch, and length of training. In stationary benchmark data, all models have a performance with very high accuracy. The WRBFNN9 model is the most superior model in nonstationary data containing linear trend elements, while the WFFNN17 model performs best on non-stationary data with the non-linear trend and seasonal elements. In terms of speed in computing, the WRBFNN model is superior with a much smaller number of epochs and much shorter training time.

scholarly journals Comparison of outlier detection techniques in non-stationary time series data

2021 ◽  
Vol 27 (1) ◽  
pp. 55-60
Author(s):  
Sampson Twumasi-Ankrah ◽  
Simon Kojo Appiah ◽  
Doris Arthur ◽  
Wilhemina Adoma Pels ◽  
Jonathan Kwaku Afriyie ◽  
...  
Keyword(s):  
Time Series ◽  
Outlier Detection ◽  
Mahalanobis Distance ◽  
Time Series Data ◽  
Principal Component ◽  
Stationary Time Series ◽  
Series Data ◽  
Distance Method ◽  
Detection Techniques ◽  
Stationary Time

This study examined the performance of six outlier detection techniques using a non-stationary time series dataset. Two key issues were of interest. Scenario one was the method that could correctly detect the number of outliers introduced into the dataset whiles scenario two was to find the technique that would over detect the number of outliers introduced into the dataset, when a dataset contains only extreme maxima values, extreme minima values or both. Air passenger dataset was used with different outliers or extreme values ranging from 1 to 10 and 40. The six outlier detection techniques used in this study were Mahalanobis distance, depth-based, robust kernel-based outlier factor (RKOF), generalized dispersion, Kth nearest neighbors distance (KNND), and principal component (PC) methods. When detecting extreme maxima, the Mahalanobis and the principal component methods performed better in correctly detecting outliers in the dataset. Also, the Mahalanobis method could identify more outliers than the others, making it the "best" method for the extreme minima category. The kth nearest neighbor distance method was the "best" method for not over-detecting the number of outliers for extreme minima. However, the Mahalanobis distance and the principal component methods were the "best" performed methods for not over-detecting the number of outliers for the extreme maxima category. Therefore, the Mahalanobis outlier detection technique is recommended for detecting outlier in nonstationary time series data.

Implementation of Fuzzy Time Series in Forecasting of the Non-Stationary Data

2016 ◽  
Vol 15 (02) ◽  
pp. 1650009 ◽  
Author(s):  
Riswan Efendi ◽  
Mustafa Mat Deris ◽  
Zuhaimy Ismail
Keyword(s):  
Time Series ◽  
Exchange Rates ◽  
Time Series Data ◽  
Data Type ◽  
Fuzzy Time Series ◽  
Stationary Time Series ◽  
Series Data ◽  
Stationary Time ◽  
Load Demand ◽  
Electricity Load

To forecast the non-stationary data is quite difficult when compared with the stationary data time series. Because their variances are not constant and not stable like the second data type. This paper presents the implementation of fuzzy time series (FTS) into the non-stationary time series data forecasting, such as, the electricity load demand, the exchange rates, the enrollment university and others. These data forecasts are derived by implementing of the weightage and linguistic out-sample methods. The result shows that the FTS can be applied in improving the accuracy and efficiency of these non-stationary data forecasting opportunities.

scholarly journals Over-Differencing and Forecasting with Non-Stationary Time Series Data

2019 ◽  
Vol 67 (1) ◽  
pp. 21-26
Author(s):  
Zakir Hossain ◽  
Atikur Rahman ◽  
Moyazzem Hossain ◽  
Jamil Hasan Karami
Keyword(s):  
Time Series ◽  
Simulation Study ◽  
Time Series Data ◽  
House Prices ◽  
Stationary Time Series ◽  
Series Data ◽  
Common Phenomenon ◽  
Stationary Time ◽  
True Model ◽  
Simulation Results

In time series analysis, over-differencing is a common phenomenon to make the data to be stationary. However, it is not always a good idea to take over-differencing in order to ensure the stationarity of time series data. In this paper, the effect of over-differencing has been investigated via a simulation study to observe how far or how close the fitted model from the true one. Simulation results show that the fitted model is found to be different and very far from the true model because of over-differencing in most of the scenarios considered in this study. In practice, it may be worthy to consider differencing as well as suitable transformation of the time series data to make it stationary. Both transformation and differencing are used for a non-stationary time series data on average monthly house prices to ensure it to be stationary. We then analyse the data and make prediction for the future values. Dhaka Univ. J. Sci. 67(1): 21-26, 2019 (January)

Sign in / Sign up

Export Citation Format

Share Document