Search results

1 – 10 of 12
Article
Publication date: 5 February 2018

Tianxiang Yao and Hong Gao

Buffer operators can be utilized to improve the smooth degree of the raw data sequence, and to increase the simulation accuracy of the model. The purpose of this paper is…

Abstract

Purpose

Buffer operators can be utilized to improve the smooth degree of the raw data sequence, and to increase the simulation accuracy of the model. The purpose of this paper is to analyze the cause of increase in the simulation accuracy of the buffer operator.

Design/methodology/approach

This paper probed into the modeling mechanism of several typical buffer operators such as the arithmetic buffer operators, the buffer operators with monotonic function and weighted buffer operators. The paper also gives an example of the buffer operator sequence.

Findings

The results indicate that after applying an infinite buffer operator, whether the authors adopt a weakening buffer operator or a strengthen buffer operator, the raw sequence can be changed into a constant sequence. Because the discrete GM(1,1) model can completely simulate constant sequence, the simulation accuracy is 100 percent. Because the discrete GM(1,1) model is the accurate form of the GM(1,1) model, after applying an infinite buffer operator, the GM(1,1) model can have a very high simulation accuracy. The buffer operator model can increase the simulation accuracy of both the GM(1,1) model and the discrete GM(1,1) model.

Originality/value

The paper analyses the cause of increasing simulation accuracy of the buffer operator model. The paper may indicate that possible results can be studied in the future. All the buffer operator models have similar properties. After applying an infinite buffer operator, the raw sequence can be changed into a constant sequence. A fixed-point axiom may be the basic cause.

Details

Grey Systems: Theory and Application, vol. 8 no. 1
Type: Research Article
ISSN: 2043-9377

Keywords

Article
Publication date: 7 November 2016

Tianxiang Yao, Wenrong Cheng and Hong Gao

The purpose of this paper is to assess the natural disaster damage of Sichuan province and provide suggestions to prevent or decrease the loss owing to the natural disaster.

Abstract

Purpose

The purpose of this paper is to assess the natural disaster damage of Sichuan province and provide suggestions to prevent or decrease the loss owing to the natural disaster.

Design/methodology/approach

The disaster loss system of Sichuan is regarded as a grey system. Five evaluation indicators are selected such as the number of deaths, total affected area, collapsed houses, damaged houses, and the direct economic losses. Grey fixed-weight clustering approach is applied in the cluster analysis. In order to reduce the impact of human factors, grey correlation analysis method is applied to calculate the weights of grey fixed-weight clustering.

Findings

The results of this paper indicate that the frequency of occurrence of major natural disaster in Sichuan increased since 2008. The major natural disasters occurred in 2008, 2010, 2011, and 2013. In contrast, there was almost no major disaster during 2000-2007. Minor natural disaster occurred in 2002 and 2003.

Practical implications

Sichuan province is one of the provinces most affected by natural disasters in China. Natural disasters have occurred frequently in Sichuan province since 2008 and pose serious threats to life and property safety. They have become an important restricting factor for economic and social development. In order to prevent or decrease the effects of natural disasters, effective measures should be taken to protect the environment.

Originality/value

This paper first normalizes the raw sequence, calculates the weight, and then establishes the grey cluster model. A new method is applied to determine the weight when evaluating natural disaster damage.

Details

Grey Systems: Theory and Application, vol. 6 no. 3
Type: Research Article
ISSN: 2043-9377

Keywords

Article
Publication date: 6 February 2017

Hong Gao, Tianxiang Yao and Xiaoru Kang

The purpose of this paper is to predict the population of Anhui province. The authors analyze the trend of the main demographic indicators.

Abstract

Purpose

The purpose of this paper is to predict the population of Anhui province. The authors analyze the trend of the main demographic indicators.

Design/methodology/approach

On the basis of the main methods of statistics, this paper studies the tendency of the population of Anhui province. It mainly analyzes the sex structure and the age structure of the current population. Based on the GM(1,1) model, this paper forecasts the total population, the population sex structure, and the population age structure of Anhui province in the next ten years.

Findings

The results show that the total population was controlled well, but there have been many problems of the population structure, such as the aging population, high sex ratio, heavy social dependency burden, and the declining labor force.

Social implications

This paper forecasts the main indexes of the population of Anhui province and provides policy recommendations for the government and the relevant departments.

Originality/value

This paper utilizes data analysis method and the grey forecasting model to study the tendency of the population problems in Anhui province.

Details

Grey Systems: Theory and Application, vol. 7 no. 1
Type: Research Article
ISSN: 2043-9377

Keywords

Article
Publication date: 19 June 2020

Tianxiang Yao and Zihan Wang

According to the problem of crude oil price forecasting, the purpose of this paper is to propose a multi-step prediction method based on the empirical mode decomposition…

Abstract

Purpose

According to the problem of crude oil price forecasting, the purpose of this paper is to propose a multi-step prediction method based on the empirical mode decomposition, long short-term memory network and GM (1,1) model.

Design/methodology/approach

First, the empirical mode decomposition method is used to decompose the crude oil price series into several components with different frequencies. Then, each subsequence is classified and synthesized based on the specific periodicity and other properties to obtain several components with different significant characteristics. Finally, all components are substituted into a suitable prediction model for fitting. LSTM models with different parameters are constructed for predicting specific components, which approximately and respectively represent short-term market disturbance and long-term influences. Rolling GM (1,1) model is constructed to simulate a series representing the development trend of oil price. Eventually, all results obtained from forecasting models are summarized to evaluate the performance of the model.

Findings

The model is respectively applied to simulate daily, weekly and monthly WTI crude oil price sequences. The results show that the model has high accuracy on the prediction, especially in terms of series representing long-term influences with lower frequency. GM (1,1) model has excellent performance on fitting the trend of crude oil price.

Originality/value

This paper combines GM (1,1) model with LSTM network to forecast WTI crude oil price series. According to the different characteristics of different sequences, suitable forecasting models are constructed to simulate the components.

Details

Grey Systems: Theory and Application, vol. 11 no. 1
Type: Research Article
ISSN: 2043-9377

Keywords

Article
Publication date: 27 January 2012

Tianxiang Yao, Jeffery Forrest and Zaiwu Gong

The purpose of this paper is to expand discrete GM (1,1) model and solve the problem of non‐equidistance grey prediction problem with integral interval or digital interval.

1157

Abstract

Purpose

The purpose of this paper is to expand discrete GM (1,1) model and solve the problem of non‐equidistance grey prediction problem with integral interval or digital interval.

Design/methodology/approach

Discrete GM (1,1) model can be utilized to simulate exponential sequence without errors, but it can't be utilized to simulate non‐equidistance data sequence. This paper applied optimization theories to establish generalized discrete GM (1,1) model. First, this paper established the time response of simulation sequence directly. Second, this paper established the steps of non‐equidistance data sequence. Finally, this paper utilized examples to test the method put forward.

Findings

The results indicate the generalized discrete GM (1,1) (GDGM) model can perfectly simulate non‐equidistance exponential series. Discrete GM (1,1) model is only the special form of GDGM model.

Practical implications

Though grey forecasting models are widely used, most of the forecasting models are based on the equal distance sequence. Due to many reasons, the raw data available usually is incomplete. There are mainly four reasons which caused non‐equidistance sequence. So generalized discrete GM (1,1) model can be utilized to simulate non‐equidistance sequence and has great application values.

Originality/value

The paper succeeds in establishing a generalized discrete GM (1,1) model which can be utilized to solve non‐equidistance data sequence forecasting. The GDGM model can be solved by MATLAB or other corresponding software.

Details

Grey Systems: Theory and Application, vol. 2 no. 1
Type: Research Article
ISSN: 2043-9377

Keywords

Article
Publication date: 2 February 2015

Tianxiang Yao and Wenrong Cheng

The purpose of this paper is to find a method that has high precision to forecast the energy consumption of China’s manufacturing industry. The authors hope the predicted…

Abstract

Purpose

The purpose of this paper is to find a method that has high precision to forecast the energy consumption of China’s manufacturing industry. The authors hope the predicted data can provide references to the formulation of government’s energy strategy and the sustained growth of economy in China.

Design/methodology/approach

First, the authors respectively make use of regression prediction model and grey system theory GM(1,1) model to construct single model based the data of 2001-2010, analyze the advantages and disadvantages of single prediction models. The authors use the data of 2011 and 2012 to test the model. Second, the authors propose combination forecasting model of manufacturing’s energy consumption in China by using standard variance to allocate the weight. Finally, this model is applied to forecast China’s manufacturing energy consumption during 2013-2016.

Findings

The result shows that the combination model is a better one with higher accuracy; the authors can take the model as an effective tool to predict manufacturing’s energy consumption in China. And the energy consumption of China’s manufacturing industry continued to show a steady incremental trend.

Originality/value

This method takes full advantages of the effective information reflected by the single model and improves the prediction accuracy.

Details

Grey Systems: Theory and Application, vol. 5 no. 1
Type: Research Article
ISSN: 2043-9377

Keywords

Content available
Article
Publication date: 30 September 2014

4

Abstract

Details

Journal of Manufacturing Technology Management, vol. 25 no. 8
Type: Research Article
ISSN: 1741-038X

Content available
Article
Publication date: 17 August 2012

404

Abstract

Details

Grey Systems: Theory and Application, vol. 2 no. 2
Type: Research Article
ISSN: 2043-9377

Article
Publication date: 8 June 2022

Guo Chen, Jiabin Peng, Tianxiang Xu and Lu Xiao

Problem-solving” is the most crucial key insight of scientific research. This study focuses on constructing the “problem-solving” knowledge graph of scientific domains by…

Abstract

Purpose

Problem-solving” is the most crucial key insight of scientific research. This study focuses on constructing the “problem-solving” knowledge graph of scientific domains by extracting four entity relation types: problem-solving, problem hierarchy, solution hierarchy and association.

Design/methodology/approach

This paper presents a low-cost method for identifying these relationships in scientific papers based on word analogy. The problem-solving and hierarchical relations are represented as offset vectors of the head and tail entities and then classified by referencing a small set of predefined entity relations.

Findings

This paper presents an experiment with artificial intelligence papers from the Web of Science and achieved good performance. The F1 scores of entity relation types problem hierarchy, problem-solving and solution hierarchy, which were 0.823, 0.815 and 0.748, respectively. This paper used computer vision as an example to demonstrate the application of the extracted relations in constructing domain knowledge graphs and revealing historical research trends.

Originality/value

This paper uses an approach that is highly efficient and has a good generalization ability. Instead of relying on a large-scale manually annotated corpus, it only requires a small set of entity relations that can be easily extracted from external knowledge resources.

Details

Aslib Journal of Information Management, vol. ahead-of-print no. ahead-of-print
Type: Research Article
ISSN: 2050-3806

Keywords

1 – 10 of 12