Loading...

Table of Content

    25 December 2022, Volume 34 Issue 4
    A Framework of Grey Prediction Models on China's Population Aging Under the Perspective of Regional Differences 
    Weiliang Zhang, Sifeng Liu, Junliang Du, Lianyi Liu, Xiaojun Guo, Zurun Xu
    2022, 34(4):  1. 
    Asbtract ( 359 )  
    Related Articles | Metrics
    Population aging is a major social problem that China is facing. Scientific prediction and correct analysis of population aging are important for resource allocation, policy formulation, and service provision. To this end, this paper proposes a population prediction framework based on grey models to predict and analyze regional differences in China's aging status. Firstly, we construct three indicators, i.e., total population, aged population, and proportion of the aged population, to reflect the aging status of a region. Secondly, we develop a grey model framework to predict and analyze aging differences in the eastern, central, and western regions of China. Finally, according to the prediction and analysis results of the three aging indicators, we suggest some corresponding countermeasures to address the challenges of China's future aging problem.
    A Vetoed Multi-objective Grey Target Decision Model with Application in Supplier Choice 
    Baoan Huang, Jianjun Miao, Qingsheng Li
    2022, 34(4):  15. 
    Asbtract ( 173 )  
    Related Articles | Metrics
    A vetoed multi-attribute grey target decision method is proposed and demonstrated with a practical case study. Firstly, a classical multi-objective grey target decision model is introduced, then a veto function is defined with a hesitant region, which can accommodate some vagueness in the decision maker’s specification of this level to reject a scheme. Secondly, a vetoed synthetic effect measure matrix is obtained based on the veto function and the uniform effect measure. Finally, the proposed model is applied to a supplier selection problem for official vehicles. The decision method proposed in this study, which is expressed by the vetoed synthetic effect measure, is reasonable and useful in decision-making practice. 
    A Novel Option Pricing Approach Using the Black-Scholes Model and Grey Forecasting Method 
    Xuemei Li, Hang Wang, Yun Cao
    2022, 34(4):  28. 
    Asbtract ( 165 )  
    Related Articles | Metrics
    China’s options market has developed rapidly since 2015, and options have become an important financial derivative. Accurate pricing of options is an important prerequisite for options hedging, risk management, and other functions. There is much uncertain information interference in the traditional option pricing process, which will cause large errors between the pricing result and the actual market delivery price: because grey system theory has a natural advantage in dealing with uncertain information, based on the classic Black–Scholes (B-S) option pricing model and grey forecasting method, a comprehensive option pricing B-S- RGM model is developed, and Shanghai Stock Exchange 50ETF data in China are selected as a case for empirical analysis. The empirical results show that the proposed B-S-RGM model herein can mine the uncertain information in the process of option pricing. Compared with the classic B-S model, the B-S-RGM pricing model has more accurate pricing results. The average relative errors of the B-S models in Sample A and Sample B are 10.37% and 18.29%, respectively, while the average relative errors of the four B-S-RGM models are all stable and within 5%. In addition, the stability of the B-S-RGM model is discussed. The B-S option pricing model suffers from instability, with the pricing errors increasing in pricing intervals further from the expiration date while the B-S-RGM pricing model maintains a high degree of stability in pricing intervals both further and closer to maturity. The conclusions have important applications for option pricing, and can broaden the application scope of grey system theory. 
    A Grey Relational Analysis Method for Structural Stability Sensitivity of Cable-Suspended Camera Robots Including Presence of Cable Mass 
    Peng Liu, Xuhui Zhang, Xinzhou Qiao, Yuanying Qiu
    2022, 34(4):  47. 
    Asbtract ( 128 )  
    Related Articles | Metrics
    A cable-suspended camera robot with a large workspace is employed to realize mobile photographs, while the large-span cables with unilateral driving properties introduce many new challenges that need to be addressed, whose structural stability is one of the most critical challenges. As a result, this paper first presents a stability measure method for camera robots while considering the cable mass and sags. Moreover, a stability sensitivity evaluation model for the robot is established with grey relational degree, where the relationship between the stability of the robot and the influencing factors (the cable tensions and the positions of the camera platform) is explored. Finally, the proposed models are supported by doing some simulation studies on a cable-suspended camera robot. The results show that the cable sags of the large-span cables have significant effects on both the cable tensions and the structural stability of the robot, while the stability sensitivity evaluation results indicate the cable tensions have a more important influence on the stability of the camera robot than the positions of the camera platform. 
    Prediction and Analysis of Agricultural Eco-Efficiency in Henan Province Based on GM-BP Neural Network 
    Bingjun Li, Wenyan Li, Yifan Zhang
    2022, 34(4):  71. 
    Asbtract ( 105 )  
    Related Articles | Metrics
    The grey GM(1, 1) model is widely used due to its relatively simple structure, few parameters, easy training, and considering the grey characteristics of known information and unknown information. However, the GM(1, 1) model is weak in mining complex information, and it is difficult to deal with sequences with both linear and nonlinear characteristics. In response to this problem, the BP neural network is introduced, and the combination model of the GM-BP neural network is constructed by using the powerful nonlinear data mining ability of the BP neural network. And the GM-BP neural network is used to predict the agricultural eco-efficiency of Henan province. On this basis, the development trend of agricultural eco-efficiency in Henan is analyzed. The results show that the GM-BP neural network model can describe the complex changes in agricultural eco-efficiency in Henan and has a good prediction effect. The agricultural eco-efficiency in Henan from 2020 to 2025 is effective, with a continuous upward trend, but the increasing rate has slowed down. In space, the agricultural eco-efficiency of Henan shows the characteristics of gradually increasing from north to south, high in the east and west, low in the middle, and slightly higher in the west than in the east. 
    A Self-Adaptive Grey DBSCAN Clustering Method
    Shizhan Lu, Longsheng Cheng, Zudi Lu, Qifa Huang, Bilal Ahmed Khan
    2022, 34(4):  90. 
    Asbtract ( 151 )  
    Related Articles | Metrics
    Clustering analysis, as a classical issue in data mining, is widely applied in various research areas. This article proposes a self-adaptive grey DBSCAN (SAG-DBSCAN) clustering algorithm by introducing a grey relational matrix to obtain the grey local density indicator. We then apply this local indicator to have self-adaptive noise identification to gain a dense subset of the clustering data set. An advantage of this algorithm is that it can automatically estimate the parameters utilized to cluster the dense subset. Several frequently-used data sets are further examined to compare the performance and effectiveness of our proposed clustering algorithm with those of other state-of-the-art algorithms. The comparisons indicate that our new method outperforms other common methods. 
    Dynamic Credit Evaluation Method for Small and Medium-sized Enterprises Based on Grey Cloud Similarity Analysis 
    Yeqing Guan, Yingjun Dai, Haotian Wu, Naiming Xie
    2022, 34(4):  103. 
    Asbtract ( 84 )  
    Related Articles | Metrics
    The solution of financing demand is one of the driving forces for the growth of small and medium-sized enterprises, and scientific and reasonable credit evaluation is an important way to alleviate the difficulty and expensive financing of enterprises. To address the uncertainty in enterprise credit evaluation, a dynamic evaluation method based on grey cloud similarity is proposed by combining grey incidence analysis and cloud model theory. Firstly, combining the expectation, entropy, and hyper entropy of the cloud model, the grey cloud similarity based on the inner or outer boundary curve is defined by drawing on the concept of the degree of grey incidence and the feature of the grey cloud similarity that can take the three digital characteristics of the cloud model into account, low computational complexity and high stability are summarized. Then, a multi-attribute comprehensive evaluation method is established considering randomness, fuzziness, and dynamic, and the dynamic evaluation information is aggregated by time-series weights to assess the rating of the evaluated object over a period of time. Finally, the feasibility and effectiveness of the proposed method are verified by the credit rating evaluation case of 10 small and medium-sized listed enterprises in the Growth Enterprise Market of Shenzhen Stock Exchange. 
    The Application of Adaptive Generalized NGBM(1,1) To Sales Forecasting: A Case Study of an Underwear Shop 
    Ssu-Han Chen, Guo-Wei Chen, Yi-Ching Liaw, Jin-Kwan Lin, Shang-En Hsu
    2022, 34(4):  130. 
    Asbtract ( 105 )  
    Related Articles | Metrics
    This study develops a model to predict the weekly sales of an underwear shop in New Taipei City, Taiwan. Most commonly employed prediction methods failed when applied to the sales patterns of the case company and could not create an appropriate ordering strategy. This study is based on the assumption that the choice of a predictive model may need to be matched to the fluctuation structure of the data sequence. Not all data sequences are suitable for a single prediction model. An adaptive generalized Nonlinear Grey Bernoulli Model (NGBM(1,1)) is proposed for the case company. The training data sequences are fed into an Adaptive Resonance Theory 2 (ART2) model to generate typical templates. Simultaneously, the generalized NGBM(1,1) model is associated with the Real-valued Genetic Algorithm (RGA) to identify the best hyper-parameters for each training data sequence. The relationships between the typical templates and the 24 model types are mapped. In the testing stage, each data sequence is allocated to the most similar typical template using ART2 and mapped to the corresponding suitable model type, which makes a one-step-ahead prediction. The four-year weekly sales data of an underwear shop were empirically analyzed. The proposed method was compared with traditional prediction models. The experimental results show that the proposed method can provide more precise predictions. 
    Security Risk Assessment for Trusted Chain Optimizing Based on Grey Fixed Weight Clustering
    Guna Duan , Lizhong Duan , Wenan Zhou
    2022, 34(4):  147. 
    Asbtract ( 96 )  
    Related Articles | Metrics

    Trusted computing has received further attention as an effective technique to safeguard information systems, and it has been widely applied in various fields. Trusted chain establishment, as an essential model of trusted computing technology which ensures the credibility of computing platform, still brings poor system efficiency due to the complex environment of the platform. To optimize the procedure of trusted chain establishment for trusted computing platforms, our research improved traditional trusted chain establishment from static to dynamic with additional security risk level assessment step during trusted chain establishment innovatively. First, we comprehensively analyzed threats and their source for platforms. Based on main indicators of the platform, fixed weight clustering evaluation method in the grey system theory was used to evaluate security risk level for platforms. With the recorded data of software and hardware changes for the platform, we assessed the security risk level for this platform and demonstrated the clustering results and improved measurement strategy for platform during trusted chain establishment. It is more systematic and more efficient than the traditional static trusted chain establishment method, which could find more files tampered during measurement procedure.