A novel framework for parameter selection of the Autocorrelation Change detection method using 250m MODIS time-series data in the Gauteng province of South Africa

This article firstly uses svm to forecast cashmere price time series. The forecasting result mainly depends on parameter selection. The normal parameter selection is based on k-fold cross validation. The k-fold cross validation is suitable for classification. In this essay, k-fold cross validation is improved to ensure that only the older data can be used to forecast latter data to improve prediction accuracy. This essay trains the cashmere price time series data to build mathematical model based on SVM. The selection of the model parameters are based on improved cross validation. The price of Cashmere can be forecasted by the model. The simulation results show that support vector machine has higher fitting precision in the situation of small samples. It is feasible to forecast cashmere price based on SVM.

Download Full-text

An Anomaly Detection Method with Exemplar Subsequence for Time Series Data

IEEJ Transactions on Electronics Information and Systems ◽

10.1541/ieejeiss.136.363 ◽

2016 ◽

Vol 136 (3) ◽

pp. 363-372

Author(s):

Takaaki Nakamura ◽

Makoto Imamura ◽

Masashi Tatedoko ◽

Norio Hirai

Keyword(s):

Time Series ◽

Anomaly Detection ◽

Time Series Data ◽

Detection Method ◽

Series Data

Download Full-text

A Novel Heuristic Approach for the Simultaneous Selection of the Optimal Clustering Method and Its Internal Parameters for Time Series Data

Advances in Intelligent Systems and Computing - 14th International Conference on Soft Computing Models in Industrial and Environmental Applications (SOCO 2019) ◽

10.1007/978-3-030-20055-8_17 ◽

2019 ◽

pp. 179-189 ◽

Cited By ~ 1

Author(s):

Adriana Navajas-Guerrero ◽

Diana Manjarres ◽

Eva Portillo ◽

Itziar Landa-Torres

Keyword(s):

Time Series ◽

Time Series Data ◽

Heuristic Approach ◽

Series Data ◽

Clustering Method ◽

Internal Parameters ◽

Simultaneous Selection ◽

Selection Of

Download Full-text

How applicable is export-led growth and import-led growth hypotheses to South African economy?

Journal of Governance and Regulation ◽

10.22495/jgr_v4_i2_p2 ◽

2015 ◽

Vol 4 (2) ◽

pp. 15-24

Author(s):

Ntebogang Dinah Moroke ◽

Molebogeng Manoto

Keyword(s):

Economic Growth ◽

South Africa ◽

Adverse Effect ◽

Time Series ◽

South African ◽

Time Series Data ◽

Series Data ◽

Long Run ◽

Reserve Bank ◽

Equilibrium Relationship

This paper investigated exports, imports and the economic growth nexus in the context of South Africa. The paper sets out to examine if long-run and causal relationships exist between these variables. Quarterly time series data ranging between 1998 and 2013 obtained from the South African Reserve Bank and Quantec databases was employed. Initial data analysis proved that the variables are integrated at their levels. The results further indicated that exports, imports and economic growth are co-integrated, confirming an existence of a long-run equilibrium relationship. Granger causal results were shown running from exports and imports to GDP and from imports to exports, validating export-led and import-led growth hypotheses in South Africa. A significant causality running from imports to exports, suggests that South Africa imported finished goods in excess. If this is not avoided, lots of problems could be caused. A suggestion was made to avoid such problematic issues as they may lead to replaced domestic output and displacement of employees. Another dreadful ramification may be an adverse effect on the economy which may further be experienced in the long-run.

Download Full-text

Transient dynamic phenotypes as criteria for model discrimination: fold-change detection in Rhodobacter sphaeroides chemotaxis

Journal of The Royal Society Interface ◽

10.1098/rsif.2012.0935 ◽

2013 ◽

Vol 10 (80) ◽

pp. 20120935 ◽

Cited By ~ 15

Author(s):

Abdullah Hamadeh ◽

Brian Ingalls ◽

Eduardo Sontag

Keyword(s):

Time Series ◽

Change Detection ◽

Rhodobacter Sphaeroides ◽

Time Series Data ◽

Series Data ◽

Transient Dynamic ◽

Experimental Time ◽

Theoretical Assumptions ◽

Experimental Time Series ◽

Fold Change Detection

The chemotaxis pathway of the bacterium Rhodobacter sphaeroides shares many similarities with that of Escherichia coli . It exhibits robust adaptation and has several homologues of the latter's chemotaxis proteins. Recent theoretical results have correctly predicted that the E. coli output behaviour is unchanged under scaling of its ligand input signal; this property is known as fold-change detection (FCD). In the light of recent experimental results suggesting that R. sphaeroides may also show FCD, we present theoretical assumptions on the R. sphaeroides chemosensory dynamics that can be shown to yield FCD behaviour. Furthermore, it is shown that these assumptions make FCD a property of this system that is robust to structural and parametric variations in the chemotaxis pathway, in agreement with experimental results. We construct and examine models of the full chemotaxis pathway that satisfy these assumptions and reproduce experimental time-series data from earlier studies. We then propose experiments in which models satisfying our theoretical assumptions predict robust FCD behaviour where earlier models do not. In this way, we illustrate how transient dynamic phenotypes such as FCD can be used for the purposes of discriminating between models that reproduce the same experimental time-series data.

Download Full-text