Search results

The purpose of this paper is to propose a new temporal disaggregation method for time series based on the accumulated and inverse accumulated generating operations in grey modeling and the interpolation method.

This disaggregation method includes three main steps, including accumulation, interpolation, and differentiation (AID). First, a low frequency flow series is transformed to the corresponding stock series through accumulated generating operation. Then, values of the stock series at unobserved time is estimated through appropriate interpolation method. And finally, the disaggregated stock series is transformed back to high frequency flow series through inverse accumulated generating operation.

The AID method is tested with a sales series. Results shows that the disaggregated sales data are satisfactory and reliable compared with the original data and disaggregated data using a time series model. The AID method is applicable to both long time series and grey series with insufficient information.

The AID method can be easily used to disaggregate low frequency flow series.

The AID method is a combination of grey modeling technique and interpolation method. Compared with other disaggregation methods, the AID method is simple, and does not require auxiliary information or plausible minimizing criterion required by other disaggregation methods.

The purpose of this paper is to study a fractional grey model FAGM(1,1,t^α) based on the GM(1,1,t^α) model and the fractional accumulated generating operation, and then predict the national health expenditure, the government health expenditure and the out-of-pocket health expenditure of China.

The presented univariate grey model is systematically studied by using the grey modelling technique, the fractional accumulated generating operation and the trapezoid approximation formula of definite integral. The optimal system parameters r and α are evaluated by the particle swarm optimisation algorithm.

The expressions of the time response function and the restored values of this model are derived. The GM(1,1), NGM(1,1,k,c) and GM(1,1,t^α) models are particular cases of the FAGM(1,1,t^α) model with deterministic r and α. Compared with other forecasting models, the results of the FAGM(1,1,t^α) model have higher precision.

The superiority of the new model has high potential to be used in the medicine and health fields and others. Results can provide a guideline for government decision making.

The univariate fractional grey model FAGM (1,1,t^α) successfully studies the China’s health expenditure.

The purpose of this paper is to develop a novel multivariate fractional grey model termed GM(a, n) based on the classical GM(1, n) model. The new model can provide accurate prediction with more freedom, and enrich the content of grey theory.

The GM(α, n) model is systematically studied by using the grey modelling technique and the forward difference method. The optimal fractional order a is computed by the genetic algorithm. Meanwhile, a stochastic testing scheme is presented to verify the accuracy of the new GM(a, n) model.

The recursive expressions of the time response function and the restored values of the presented model are deduced. The GM(1, n), GM(a, 1) and GM(1, 1) models are special cases of the model. Computational results illustrate that the GM(a, n) model provides accurate prediction.

The GM(a, n) model is used to predict China’s total energy consumption with the raw data from 2006 to 2016. The superiority of the GM(a, n) model is more freedom and better modelling by fractional derivative, which implies its high potential to be used in energy field.

It is the first time to investigate the multivariate fractional grey GM(α, n) model, apply it to study the effects of China’s economic growth and urbanization on energy consumption.

PM10 is one of the most dangerous air pollutants which is harmful to the ecological system and human health. Accurate forecasting of PM10 concentration makes it easier for the government to make efficient decisions and policies. However, the PM10 concentration, particularly, the emerging short-term concentration has high uncertainties as it is often impacted by many factors and also time varying. Above all, a new methodology which can overcome such difficulties is needed.

The grey system theory is used to build the short-term PM10 forecasting model. The Euler polynomial is used as a driving term of the proposed grey model, and then the convolutional solution is applied to make the new model computationally feasible. The grey wolf optimizer is used to select the optimal nonlinear parameters of the proposed model.

The introduction of the Euler polynomial makes the new model more flexible and more general as it can yield several other conventional grey models under certain conditions. The new model presents significantly higher performance, is more accurate and also more stable, than the six existing grey models in three real-world cases and the case of short-term PM10 forecasting in Tianjin China.

With high performance in the real-world case in Tianjin China, the proposed model appears to have high potential to accurately forecast the PM10 concentration in big cities of China. Therefore, it can be considered as a decision-making support tool in the near future.

This is the first work introducing the Euler polynomial to the grey system models, and a more general formulation of existing grey models is also obtained. The modelling pattern used in this paper can be used as an example for building other similar nonlinear grey models. The practical example of short-term PM10 forecasting in Tianjin China is also presented for the first time.

This paper aims to propose a hybrid method based on polynomial fitting bias self-compensation, grey forward-backward linear prediction (GFBLP) and moving average filter (MAF) for error compensation in micro-electromechanical system gyroscope signal especially under motion state.

The error compensation can be divided into two processes: bias correction and noise reduction. A polynomial drift angle fitting algorithm is used to correct bias before denoising processing. For noise reduction, operation can be taken in two stages: detection and processing. First, sample variances are used to judge motion state. According to the detection results, algorithmic system switches between grey GFBLP and MAF to ensure fast convergence rate and small steady-state error.

Experimental results show that the proposed method can correct bias effectively for practical gyroscope signal, and can eliminate noise effectively for both practical gyroscope signal and synthetic signal, which indicates the effectiveness of the proposed method.

Bias correction and noise reduction are considerations. Noise contained in practical or synthetic signal can be reduced rapidly and effectively, which benefits from the new idea of combination grey GFBLP, MAF and sample variances. And most importantly, it is applicable for signal denoising under arbitrary motion state condition, which is different from other methods where the convergence performance is seldom analyzed.

Making decisions in finance have been regarded as one of the biggest challenges in the modern economy today; especially, analysing and forecasting unstable data patterns with limited sample observations under the numerous economic policies and reforms. The purpose of this paper is to propose suitable forecasting approach based on grey methods in short-term predictions.

High volatile fluctuations with instability patterns are the common phenomenon in the Colombo Stock Exchange (CSE), Sri Lanka. As a subset of the literature, very few studies have been focused to find the short-term forecastings in CSE. So, the current study mainly attempted to understand the trends and suitable forecasting model in order to predict the future behaviours in CSE during the period from October 2014 to March 2015. As a result of non-stationary behavioural patterns over the period of time, the grey operational models namely GM(1,1), GM(2,1), grey Verhulst and non-linear grey Bernoulli model were used as a comparison purpose.

The results disclosed that, grey prediction models generate smaller forecasting errors than traditional time series approach for limited data forecastings.

Finally, the authors strongly believed that, it could be better to use the improved grey hybrid methodology algorithms in real world model approaches.

However, for the large sample of data forecasting under the normality assumptions, the traditional time series methodologies are more suitable than grey methodologies; especially GM(1,1) give some dramatically unsuccessful results than auto regressive intergrated moving average in model pre-post stage.

The purpose of this paper is to derive the analytical expression of fractional order reducing generation operator (or inverse accumulating generating operation) and study its properties.

This disaggregation method includes three main steps. First, by utilizing Gamma function expanded for integer factorial, this paper expands one order reducing generation operator into integer order reducing generation operator and fractional order reducing generation operator, and gives the analytical expression of fractional order reducing generation operator. Then, studies the commutative law and exponential law of fractional order reducing generation operator. Lastly, gives several examples of fractional order reducing generation operator and verifies the commutative law and exponential law of fractional order reducing generation operator.

The authors pull the analytical expression of fractional order reducing generation operator and verify that fractional order reducing generation operator satisfies commutative law and exponential law.

Expanding the reducing generation operator would help develop grey prediction model with fractional order operators and widen the application fields of grey prediction models.

The analytical expression of fractional order reducing generation operator, properties of commutative law and exponential law for fractional order reducing generation operator are first studied.

The system with partial unknown structure, parameters and characteristics is called a grey system. Grey system theory is a newly developed theory to deal with the problem of uncertainties in the case with “poor” information and has widely been used in many fields. The grey prediction SCGM(1,1) model has been used widely. In this paper, the characteristics of SCGM(1,1) model are systematically studied. Some new existing forms of SCGM(1,1) are derived including exponential form, α, β parameter form, scale form and recursive form. The parameter range suitable for SCGM(1,1) modeling has been studied based on strict proof. The prohibited area and the area not suitable or suitable for modeling of SCGM(1,1) model are divided clearly according to the developing coefficient a. Then, the discrete form of developing coefficient a is given. Based on the discrete form of developing coefficient a, a new grey modeling method avoiding complex matrix calculation is presented.

The time series forecasting is an essential methodology which can be used for analysing time series data in order to extract meaningful statistics based on the information obtained from past and present. These modelling approaches are particularly complicated when the available resources are limited as well as anomalous. The purpose of this paper is to propose a new hybrid forecasting approach based on unbiased GM(1,1) and artificial neural network (UBGM_BPNN) to forecast time series patterns to predict future behaviours. The empirical investigation was conducted by using daily share prices in Colombo Stock Exchange, Sri Lanka.

The methodology of this study is running under three main phases as follows. In the first phase, traditional grey operational mechanisms, namely, GM(1,1), unbiased GM(1,1) and nonlinear grey Bernoulli model, are used. In the second phase, the new proposed hybrid approach, namely, UBGM_BPNN was implemented successfully for forecasting short-term predictions under high volatility. In the last stage, to pick out the most suitable model for forecasting with a limited number of observations, three model-accuracy standards were employed. They are mean absolute deviation, mean absolute percentage error and root-mean-square error.

The empirical results disclosed that the UNBG_BPNN model gives the minimum error accuracies in both training and testing stages. Furthermore, results indicated that UNBG_BPNN affords the best simulation result than other selected models.

The authors strongly believe that this study will provide significant contributions to domestic and international policy makers as well as government to open up a new direction to develop investments in the future.

The new proposed UBGM_BPNN hybrid forecasting methodology is better to handle incomplete, noisy, and uncertain data in both model building and ex post testing stages.

The purpose of this paper is to examine the effectiveness of an improved dummy variables control grey model (DVCGM) considering the hysteresis effect of government policies in China's energy intensity (EI) forecasting.

Energy consumption is considered as an important driver of economic development. China has introduced policies those aim at the optimization of energy structure and EI. In this study, EI is forecasted by an improved DVCGM, considering the hysteresis effect of energy-saving policies of the government. A nonlinear optimization method based on particle swarm optimization (PSO) algorithm is constructed to calculate the hysteresis parameter. A one-step rolling mechanism is applied to provide input data of the prediction model. Grey model (GM) (1, N), DVCGM (1, N) and ARIMA model are applied to test the accuracy of the improved DVCGM (1, N) model prediction.

The results show that the improved DVCGM provides reliable results and works well in simulation and predictions using multivariable data in small sample size and time-lag virtual variable. Accordingly, the improved DVCGM notes the hysteresis effect of government policies and significantly improves the prediction accuracy of China's EI than the other three models.

This study estimates the EI considering the hysteresis effect of energy-saving policies in China by using an improved DVCGM. The main contribution of this paper is to propose a model to estimate EI, considering the hysteresis effect of energy-saving policies and improve forecasting accuracy.