Table of Content

23 March 2021, Volume 33 Issue 1

Previous Issue    Next Issue

 Grey Exponential Cloud Decision Model for Monotonic Hesitant Fuzzy Linguistic Terms

Yuan Liu, Zhuozhuo Yang, Jinjin Zhu, Jingjing Hao, Xinwang Jiang

2021, 33(1):  1-16. 

Asbtract ( 190 )  

Related Articles | Metrics

Monotonic natural language is widely used to express experts' subjective appraisal opinions, such as "not less than," "at least," "not more than," and "at most," which covey the information of expert hidden psychological preference. A novel quantitative computational method based on the grey exponential cloud model is proposed, transforming the expert's uncertainty appraisal information into decision data by systematically mining the experts' hesitant fuzzy preference on specific linguistic options. The comprehensive meaning of monotonic hesitant fuzzy linguistic terms is introduced, and the interval grey number is used to represent the expert's grey preference and indicator weight. Additionally, a programming model is constructed by the exponential cloud model and ABC classification analysis method, which can obtain the order of alternatives related to the optimal solution. Finally, a numerical study is conducted to show the advantages and effectiveness of the new method against other comparable methods is demonstrated.

Linear Transformation Properties of Grey Model

Aiping Jiang, Xiaoling Li, Liang Zeng

2021, 33(1):  17-29. 

Asbtract ( 143 )  

Related Articles | Metrics



 GRGAL: A Grey Relational Generative Adversarial Learning Method for Image Denoising#br#

Hongjun Li, Chaobo Li, Wei Hu, Junjie Chen, Shibing Zhang

2021, 33(1):  30-42. 

Asbtract ( 199 )  

Related Articles | Metrics

Image denoising is a well-known problem in image processing. Deep networks can achieve state-of-the-art denoising results based on the quality or quantity of training samples. However, Deep networks face performance saturation when the interference of complex noise and few paired training samples. We introduce a grey relational generative adversarial learning method into the image denoising task. To solve the problem of deep network saturation caused by complex noises and the lack of paired training samples, an adversarial learning network is built to learn latent space distribution of noisy images and reconstruct the distribution of clear images. The grey relation analysis is introduced into the network to deal with the uncertainty of noisy images and improve the ability of adversarial learning. This network is optimized by a new loss function that combined the adversary and grey relation. The loss can reasonably measure the difference between the denoised images and clear images. Experiential results show the proposed method obtains the averaged PSNR of 29.67, which is 0.53 higher than the network without grey relation. Extensive experiments demonstrate the superiority of our approach in image denoising.


Integrating two stages of Malmquist index and Grey forecasting to access industrial performance: A case of Vietnamese steel industry

Nhu-Ty Nguyen

2021, 33(1):  43-58. 

Asbtract ( 161 )  

Related Articles | Metrics

Vietnam's steel industry is in its developing stage with significant progress since the openness of the economy. Many companies in this industry have adopted the development and advancement of technologies used in manufacturing. However, the productivity of the steel industry in Vietnam is still considered low compared to other countries, which leads to the decline in competitiveness in terms of Vietnam steel products to its competitors. Companies in the steel industry, as well as the government, need to know about productivity and performance in order to give out vital decisions for the development of the steel industry which is one of the prior and core industries in Vietnam. Thus, evaluation of the Vietnamese steel industry has become a significant issue. This study takes advantage of the integrated Data Envelopment Analysis model and Malmquist Productivity Index to evaluate the past-to-future performance of the Vietnam steel industry in two different timeframes; the first period was from 2014 to 2018, the second is from 2019 to 2023, which are the results from Grey system forecasting. Totally, the realistic financial reports of 16 companies are considered to be in this evaluation after the strict selection from the whole industry. Three factors are put into consideration, including efficiency change (catch-up), technical change (frontier-shift), and Malmquist productivity index are examined respectively, in each period mentioned. The results find that the performances of all companies have not shown many abrupt changes on their scores except some outstanding cases, which demonstrate the high applicable usability of the integrated methods.

 A Quality Overall Design Approach for Complex Products byintegrating Fuzzy QFD and Grey Relational Decision-making: A Quality Competitiveness Perspective

Huan Wang, Daao Wang, Zhigeng Fang, Xiaqing Liu

2021, 33(1):  59-73. 

Asbtract ( 142 )  

Related Articles | Metrics

This paper aims to propose a novel quality overall design approach for complex products. The core parameter design and scheme optimization in the perspective of quality competitiveness are deeply addressed. Integrating the fuzzy QFD approach and the grey relational decision-making model, this paper explores the uncertain analysis and multiple attribute decision-making problems for the quality overall design of complex products. The overall quality design of a civil aircraft is presented as a numerical example, and conclusions and future work are discussed.

Multi-stage Grey Intelligent Clustering Model

Dang Luo, Manman Zhang, Xiaolei Wang

2021, 33(1):  74-97. 

Asbtract ( 157 )  

Related Articles | Metrics

In the process of grey clustering, the weights of indexes are always unknown and hard to obtain, and the decision paradox of the rule of "maximum value" often occurs. Aiming at the problems above, firstly, with the help of the Particle Swarm Optimization Algorithm, PSO-grey clustering coefficient vector is proposed to overcome the limitation of weights. Secondly, based on the theory of "entropy increasing theorem" and using the clustering weight vector group as an important tool, a multi-stage grey intelligent clustering model is established by introducing the entropy of clustering coefficient vector, which solves the decision paradox of rule of "maximum value" to a certain extent. To simplify the calculation process, the Matlab source code for this model is attached. Finally, by taking the drought risk assessment of irrigated agricultural areas in Henan Province as an example, the rationality and validity of the model are illustrated.

Grey System Model with Complex Order Accumulation

Zhengpeng Wu, Jianke Chen, Jianping Chai, Fangyuan Zhang

2021, 33(1):  98-117. 

Asbtract ( 6637 )  

Related Articles | Metrics

Based on the classical GM(1,1) model of integer (fractional) accumulation, we propose the grey model of complex accumulation (which is denoted by CAGM z(1,1) for some complex number z ∈ C ). This formulation extends the choice of Grey model's parameter from the real axis to the complex plane. We claim that all complex accumulated generating operators admit a1 dimensional additive complex Lie group's structure, which is isomorphic to C. This construction brings Lie group's theory in Grey model theory for the first time, and lays a foundation for introducing Lie group's tools in the grey system. The method of nilpotent matrix E1 of index n and Taylor series could avoid any usage of existing popular Γ functions, which also provides an efficient way for computer programming. As a novel method, accumulated generating operators of complex order could adjust weights between old information and new information, between the real part and the imaginary part simultaneously, better simulation and prediction results could be expected. The advantages of CAGM z(1,1) model are discussed with several cases, better simulation and prediction results are presented.

 Evaluation and Analysis of Smart Community Elderly Care Service Quality Based on the Two-stage Decision Model with Contents Grey Synthetic Measures under Hesitant Fuzzy Situation

Lan Xu, Yu Zhang, Yeli Wei

2021, 33(1):  118-137. 

Asbtract ( 249 )  

Related Articles | Metrics

To ensure smart elderly care service quality, this paper explores its multi-dimensional factors, and constructs an evaluation indicator system of smart community elderly care service quality based on intelligence, tangibles, responsiveness, security, reliability, and empathy. Aiming at the problem of the fuzziness of elderly's perception and the hesitation of experts’ evaluation of service quality in multi-attribute decision-making, the interval-valued intuitionistic fuzzy entropy (IVIFE) is introduced, and the evaluation method of the smart community elderly care service quality by combining the IVIFE and a two-stage decision model with grey synthetic measure is established. Four typical cities in Jiangsu Province were taken as examples to verify the feasibility of the proposed method, in order to provide a reference for promoting service standardization and reducing the difference in the level of smart community elderly care services between regions.

Evolution Mechanism of Strategic Emerging Industrial Clusters Based on Hybridization of Grey Number and Optimized Scale-Free Network 

Lirong Jian, Difei Wang, Daao Wang

2021, 33(1):  138-155. 

Asbtract ( 163 )  

Related Articles | Metrics

Strategic emerging industrial cluster network as an important form of the current industrial development, with an intensive technological innovation, prominent economies of scale and knowledge spillovers, and other characteristics, is a symbol of strategic emerging industry formation and an effective model for its development. In this paper, the Logistic model is used to characterize the strategic emerging industry cluster’s life cycle. Then, the scale-free evolution model being optimized based on the growth rate of strategic emerging industrial clusters and gray number being introduced, an evolution model of the strategic emerging industrial network is constructed considering the growth of innovators flow, the evolution process, and the stability state of the strategic emerging industrial cluster network are analyzed. Finally, an example is given to simulate and comparatively analyze the characteristics of the inflection point with the change of relevant parameters in the evolution process of the cluster network. The research results can provide some theoretical reference and guidance for the cultivation of strategic emerging

Grey Signal Predictor and Evolved Control for Practical Nonlinear Mechanical Systems

ZY Chen, Lucy Huang, Huakun Wu, Yahui Meng, Shunbo Xiang, Timothy Chen

2021, 33(1):  156-170. 

Asbtract ( 187 )  

Related Articles | Metrics

To guarantee the asymptotic stability and improve the ride comfort of vehicles, this paper develops the fuzzy neural network (NN) evolved bat algorithm (EBA) adaptive backstepping controller with grey signal predictors. To keep track of these ideal signals, Lyapunov's theory is proposed to acquire the control final laws. The gray DGM (2.1) models are also used to design suspension movements so that commands can be executed before the movement to achieve timely control. The convergence and stability of the whole system is also proven by the Lyapunov-like theory. The control expands the practices of mechanical elastic wheels (MEW) and provides a good methodical basis for a new wheel adaptation.