Grey Clustering Method Research Articles

A grey convolutional neural network model for traffic flow prediction under traffic accidents

Accurate traffic flow prediction can effectively improve traffic efficiency and safety. This has become a trending topic in intelligent transportation systems. However, the occurrence of traffic accidents will cause great fluctuations of traffic flow in a short time, thus affecting the accuracy of flow prediction. This paper analyses the influence of traffic accident information on traffic flow, and proposes a grey convolutional neural network called G-CNN for traffic flow prediction. First, considering the small sample size of traffic accidents and the incomplete information description, the traffic flow and traffic speed change rate are defined to represent traffic accident grey information, and a grey fixed-weight clustering method for extracting the characteristics of traffic accident grey information is established. Second, the spatiotemporal characteristics of traffic flow are analysed, and a third-order tensor is developed to fuse them with the accident characteristics and serve as the input of the G-CNN. Then the G-CNN model is built to predict traffic flow in a traffic accident environment. The Canadian Whitemud Drive experiment on traffic flow without traffic accident information reveals that the developed G-CNN model has a better ability to predict future traffic flow with better accuracy and stability. Meanwhile, it is verified that the fluctuation of the traffic change rate will cause traffic accidents, and the probability of traffic accidents at a certain time point will be obtained through feature extraction of traffic accidents. Finally, the model is verified for the traffic flow of Hangzhou Viaduct in China, which demonstrates that the G-CNN model outperforms all of the compared models.

Developing a resilient healthcare supply chain to prevent disruption in the wake of emergency health crisis

PurposeThe study aims to identify and analyse the drivers of resilient healthcare supply chain (HCSC) preparedness in emergency health outbreaks to prevent disruption in healthcare services delivery in the context of India.Design/methodology/approachThe present study has opted for the grey clustering method to identify and analyse the drivers of resilient HCSC preparedness during health outbreaks into high, moderate and low important grey classes based on Grey-Delphi, analytic hierarchy process (AHP) and Shannon's information entropy (IE) theory.FindingsThe drivers of the resilient HCSC are scrutinised using the Grey-Delphi technique. By implementing AHP and Shannon's IE theory and depending upon structure, process and outcome measures of HCSC, eleven drivers of a resilient HCSC preparedness are clustered as highly important, three drivers into moderately important, and two drivers into a low important group.Originality/valueThe analysis and insights developed in the present study would help to plan and execute a viable, resilient emergency HCSC preparedness during the emergence of any health outbreak along with the stakeholders' coordination. The results of the study offer information, rationality, constructiveness, and universality that enable the wider application of AHP-IE/Grey clustering analysis to HCSC resilience in the wake of pandemics.

Functional Zoning and Path Selection of Land Comprehensive Consolidation Based on Grey Constellation Clustering: A Case Study of Dongying City, China.

The functional zoning of land comprehensive consolidation and the selection of consolidation paths are the key content of the current land and space planning, and it is also an important measure to achieve regional sustainable development. At present, the research system on land comprehensive consolidation is not yet mature. The previous research area is relatively small and not representative, and an effective method system has not been formed. Research on the selection of functional zoning and a consolidation path is also relatively scarce. There is an urgent need to construct the theory and method system of land comprehensive consolidation functional zoning and consolidation path selection. Taking Dongying City in China as an example, this paper constructs a zoning index system from four aspects including natural conditions, location advantages, social economy and land use. The entropy method is used to determine the weights, and GIS spatial data visualization is used to analyze the spatial distribution characteristics of the index system. Based on the analysis, the grey constellation clustering method is used to divide the study area into four types of land comprehensive consolidation functional areas, and the results of functional zoning are adjusted according to the ranking of comprehensive index values, the principle of maximum similarity, and the continuity of natural space. The research results show that: ① There are 10 functional zonings for urban development and ecological protection land consolidation, and the main consolidation path should be the ecological country park consolidation model, which can effectively serve the urban ecological construction. ② There are nine functional zonings for rural development and cultivated land conservation consolidation, and their consolidation path should be based on a comprehensive rural improvement model that enhances the quality of the village and the development, utilization and protection of cultivated land resources. ③ There are 18 functional zonings for cultivated land improvement and ecological protection land consolidation, and the main consolidation path should focus on the cultivated land ecological improvement mode that emphasizes the quality of cultivated land and the improvement of regional ecological functions. ④ There are four functional zonings for ecological conservation and fallow recuperative land consolidation, and their main consolidation path should be the land ecological restoration and improvement model of construction land reclamation, cultivated land ecological conservation, and conversion of farmland to forest and grassland. The research results can provide references for Dongying City to formulate land and space planning, and can be extended to the design of comprehensive land remediation projects in other regions. It is of great significance to promote regional sustainable and scientific development.

Detection of spam reviews using hybrid grey wolf optimizer clustering method

Detection of spam reviews using hybrid grey wolf optimizer clustering method

Applying the Hierarchical Gray Relational Clustering Method to Municipal Water Use in Turkey

This study aims to compare the municipal water distribution performance and classify the municipal water distribution systems in the provinces of Turkey using the Gray Relational Hierarchical clustering method for both 2006 and 2016. A correlation analysis was used to determine the variables affecting the distributed water. The Hierarchical gray clusters and the changes during the decade are presented with spatial distribution maps using statistically significant variables. Consequently, the findings reveal that the municipalities of Istanbul, Izmir, Bursa, Gaziantep, and Kocaeli managed water distribution effectively, whereas the municipalities of Konya, Şanlıurfa, Diyarbakır, Samsun, Trabzon, and Sakarya managed it poorly.

Research on magnetizing inrush current of microgrid based on Grey identification

With the large-scale access of wind and light energy, the power system is gradually developing towards the micro grid with low inertia. AC microgrid often uses multiple parallel transformers to supply power to the load at the same time. In case of power failure due to a fault or maintenance, the parallel transformer needs to be powered on and closed without load to restore power supply. The parallel transformer is easier to saturate, the core remanence is higher, and the peak value of inrush current is larger, which has an impact on the stability of microgrid. It will also lead to misoperation of transformer differential protection and affect the safe and stable operation of power system. Therefore, a switching method of parallel transformer based on Grey recognition is proposed. Firstly, the generation mechanism of inrush current is analyzed theoretically, and then the waveform shape characteristics are analyzed. The grey whitening weight clustering method is used to identify the feature set to complete the magnetizing inrush current locking and ensure that the protection does not misoperate. Finally, the PSCAD simulation model is established to simulate the AC microgrid to verify the feasibility of this method.

The DPSIRM - Grey cloud clustering method for evaluating the water environment carrying capacity of Yangtze River economic Belt

Water Environment Carrying Capacity (WECC) is a complex system affected by society, economy, population and other factors. In this study, “Driving force- Pressure –State - Influence - Response –Management” (DPSIRM) method is introduced to analyze regional WECC, that is, WECC system is classified into six subsystems to illustrate its internal mechanism, establishing a systematic evaluation index system affecting WECC. The Fuzzy Analytic Hierarchy Process (FAHP)-Grey cloud clustering method is developed for making comprehensive WECC evaluation. Three major regions composed of 11 provinces in the Yangtze River Economic Belt (YREB) of China are selected as the study case. With regard to subsystem weights, the results show that pressure and state subsystems occupy a leading position on the whole system. For indicator weights, there are significant differences among them, and the top 5 indicators in importance are respectively: annual average total phosphorus (TP) concentration, soil erosion control rate, sediment delivery modules, wastewater effluent amount of industrial output value per 10,000 Yuan, and population density. In addition, through analyzing synthetic evaluation results, it can be found that WECC levels of different provinces present obvious spatial heterogeneity on each subsystem and overall system along the YREB, that is, they decrease along the Yangtze River from west to east except for minor deviations. Meanwhile, comprehensive scores of each regional WECC show an overall increasing trend from year 2014 to 2019, displaying significant temporal variations. Through making sensitivity analysis for WECC index system, it can be concluded that the most sensitive indicators of each subsystem are Population density, Wastewater effluent amount of industrial output value per 10,000 Yuan, Annual average TP concentration, Sediment delivery modules, Soil erosion control rate, Green coverage rate of built-up areas, respectively, which also turned out to be the top six sensitivity indicators among the whole index system. Finally, the demonstration conducted proves that the introduced DPSIRM - Grey cloud clustering method is applicable and effective to evaluate WECC at regional level.

Construction Risk Assessment of Deep Foundation Pit Projects Based on the Projection Pursuit Method and Improved Set Pair Analysis

Accurately evaluating the construction risk of deep foundation pit projects is crucial to formulate science-based risk response measures. Here, we propose a novel construction risk assessment method for deep foundation pit projects. A construction risk evaluation index system based on a work breakdown structure-risk breakdown structure matrix was established to deal with the complex risks of deep foundation pit construction. The projection pursuit method optimized by particle swarm optimization was used to extract the structural features from the evaluation data to obtain objective index weights. The calculation method of the five-element connection number in the set pair analysis was improved to evaluate the static construction risk. The partial derivatives of the five-element connection number were utilized to assess the dynamic construction risk. The Qi ‘an Fu deep foundation pit project in China was selected as a case study. The results show that the construction risk was acceptable and decreased during the construction period, which was consistent with actual conditions, demonstrating the effectiveness of this novel method. The proposed model showed better performance than classical methods (analytic hierarchy process, entropy weight method, classical set pair analysis, fuzzy comprehensive evaluation, gray clustering method, backpropagation neural network, and support vector machine).

Performance Evaluation Model of Public Resource Trading Platform Using Entropy-Based Gray Clustering Method

In order to standardize public resource trading activities and improve the operating efficiency of public resource trading platforms, this paper conducts research on the performance of public resource trading platforms. A three-level and 28-dimension performance evaluation index system for public resource trading platform is established by considering the four levels of “input-process-output-effect.” Besides, entropy weight method, gray clustering, and fuzzy comprehensive evaluation are integrated on this basis. Entropy weight method is used to determine the index weight, and the degree value of membership for indexes on gray class is determined based on gray clustering method and converted into a matrix. Then, fuzzy comprehensive evaluation method is used to determine the evaluation value and finally carry out the platform performance evaluation, which provides theoretical support for academic researchers to conduct follow-up research on the performance evaluation of public resource trading platforms.

Developing a risk assessment model for banking software development projects based on rough-grey set theory

PurposeRisk management is one of the most influential parts of project management that has a major impact on the success or failure of projects. Due to the increasing use of information technology in all fields and the high failure rate of software development projects, it is essential to predict the risk level of each project effectively before starting. Therefore, the main purpose of this paper is proposing an expert system to infer about the risk of new banking software development project.Design/methodology/approachIn this research, the risk of software developing projects is considered from four dimensions including risk of cost deviation, time deviation, quality deviation and scope deviation, which is examined by rough set theory (RST). The most important variables affecting the cost, time, quality and scope of projects are identified as condition attributes and four initial decision systems are constructed. Grey system theory is used to cluster the condition attributes and after data discretizing, eight rule models for each dimension of risk as a decision attribute are extracted using RST. The most validated model for each decision attribute is selected as an inference engine of the expert system, and finally a simple user interface is designed in order to predict the risk level of any new project by inserting the data of project attributesFindingsIn this paper, a high accuracy expert system is designed based on the combination of the grey clustering method and rough set modeling to predict the risks of each project before starting. Cross-validation of different rule models shows that the best model for determining cost deviation is Manual/Jonson/ORR model, and the most validated models for predicting the risk of time, quality and scope of projects are Entropy/Genetic/ORR, Manual/Genetic/FOR and Entropy/Genetic/ORR models; all of which are more than 90% accurateResearch limitations/implicationsIt is essential to gather data of previous cases to design a validated expert system. Since data documentation in the field of software development projects is not complete enough, grey set theory (GST) and RST are combined to improve the validity of the rule model. The proposed expert system can be used for risk assessment of new banking software projectsOriginality/valueThe risk assessment of software developing projects based on RST is a new approach in the field of risk management. Furthermore, using the grey clustering for combining the condition attributes is a novel solution for improving the accuracy of the rule models.

Safety evaluation of urban underground utility tunnel with the grey clustering method based on the whole life cycle theory

ABSTRACT The construction of urban underground utility tunnel is a complicated process. With the rapid development of urbanization in China, the safety problem of utility tunnel is becoming more and more prominent. To evaluate the safety of utility tunnel, this study proposed an evaluation model based on the whole life cycle theory. Firstly, combining with the characteristics of utility tunnel, the construction period was divided into four phases: preliminary planning, design, construction and operation and maintenance. Through literature analysis and expert investigation method, 26 evaluation indices were selected, and the whole life cycle safety evaluation index system of urban underground utility tunnel was established; Secondly, the entropy weight method was used to determine the weight of each index; Thirdly, in order to evaluate the security of the utility tunnel in the whole life cycle, a grey clustering evaluation model was constructed. Finally, a case study was conducted to explain the application of the proposed model and to verify the validity of the model, the results indicated that the model could provide a new way to evaluate the safety state of the utility tunnel project.

Application of Improved Fuzzy-Set Pair Analysis in Mine Water Environmental Quality Evaluation

Mine water is an important water resource, mine water resource is of great significance to realize the sustainable development of economy and society, and the evaluation of water quality is an important link of mine water resource. This paper will be improved in Nemerow index method is applied to the fuzzy-set pair analysis method of composite algorithm, and the water quality evaluation of Kongzhuang Mine in Xuzhou is carried out. Finally, compared with the evaluation results of set pair analysis method and grey clustering method, it is shown that the evaluation results of this method are reasonable and scientific, which can provide reliable basis for the utilization of mine water resources.

Application of fuzzy evaluation technique and grey clustering method for water quality assessment of the coastal and estuaries of selected rivers in Sarawak

BackgroundEstuarine and marine water quality has remarkable importance because these water resources are used for multiple reasons for instance: transportation, tourism, recreation, and other human or economic ways to use water. The objective of the study was to assess the water quality of the coastal and estuaries of the Rambungan, Sibu, Salak, and Santubong rivers in Sarawak, Malaysia. Water samples were collected from 10 locations and analyzed by employing standard techniques. A fuzzy comprehensive evaluation, grey clustering evaluation methods, Thailand Marine Water Classification System, and the Malaysian Marine Water Quality Index (MMWQI) and its classification system were applied to compute the index of each water quality parameter.ResultsThe results showed that all the analyzed water quality parameters were within the allowable threshold levels. The results obtained by the application of fuzzy comprehensive evaluation and grey clustering evaluation methods proved that the coastal and the estuaries waters were clean with exception of coastal location CZ9 and the estuary of Salak river which showed slight pollution. Based on the Malaysian Marine Water Quality Index, it was observed that all the locations were in the classification group of moderate (i.e. 50–79%). This suggests that the estuaries of selected rivers can be used for natural resource conservation, while the coastal regions are good for fish farming.ConclusionIt can be deduced that the suggested techniques were workable and logical. The method developed and the information in this study can serve as a reference and decision support for scientists and policymakers of concern.

Evaluation of coalbed methane resources in the Huainan-Huaibei coalfield of Anhui Province, China, using an analytic hierarchy process and grey cluster method

Evaluation of coalbed methane resources in the Huainan-Huaibei coalfield of Anhui Province, China, using an analytic hierarchy process and grey cluster method

An Integrated Entropy Weight and Grey Clustering Method–Based Evaluation to Improve Safety in Mines

An Integrated Entropy Weight and Grey Clustering Method–Based Evaluation to Improve Safety in Mines

Water Quality Analysis in Mantaro River, Peru, Before and After the Tailing’s Accident Using the Grey Clustering Method

Problems with environmental accidents are increasing worldwide, which generates great damage to the environment. In fact, in July 2019, a tailing spill occurred that flowed into the Mantaro River, contaminating it with thousands of liters of waste. This had environmental consequences and social ones since there were people for and against mining, which is the principal economic activity in the area. In this way, this study proposes to quantify the damage caused by the tailing spill using the grey clustering method, which is based on grey systems theory. For this purpose, two sampling points were chosen for data collection and evaluation both before and after the accident, which allowed to measure the impact of metal concentrations and other physical-chemical parameters caused by accident. The results obtained from the study revealed increases in the concentration levels of metals such as aluminum, arsenic, among others, in some cases very high that exceeded the maximum permitted limits. Such findings could help local and national government authorities, people living and transiting near the river, and activities related to the use of the water in this river; since the quality of the river water can be lethal if the necessary measures are not taken. In addition, the method used in this study showed to be very practical and efficient during its application. Finally, it is advised that future research investigate each point along the Mantaro River and show the areas where the disaster had the most impact to develop some mitigating techniques.

Urban ecological security evaluation and spatial correlation research-----based on data analysis of 16 cities in Hubei Province of China

As artificial ecosystems with high population concentrations, the security of urban ecosystems is more fragile than that of natural ecosystems. This paper aims to construct the methodology of an urban ecological security evaluation system. Firstly, based on the “driver–pressure–state–impact–response” (DPSIR) model, an evaluation index system of urban ecological security is established. Then gray clustering method is introduced to build an evaluation model of urban ecological security. A spatial autocorrelation analysis is also adopted to explore the spatial mechanism that affects the changes of urban ecological differences. Results indicate that the average level of ecological security in these 16 cities from 2007 to 2016 was between 0.535 and 0.647, and the southwest region is better than the northeast region. The results of the spatial analysis suggest that the surrounding areas easily affected the city's ecological security, showing a clustering effect. This study provides a theoretical reference for decision making of urban sustainable development.

The Study on Credit Risk Warning of Regional Listed Companies in China Based on Logistic Model

The paper aims to propose a new method to state the credit risk characteristics of the regional listed companies in China and makes the listed companies avoid involving in credit crisis. The paper selects fifty-four listed companies of Hebei Province as the research sample and establishes the index system of listed company’s credit risk evaluation from four financial index categories which included profitability, operating capacity, solvency, and growth capability. The paper first filtrates fifteen indexes by using the gray clustering method from the four financial categories and finds out the effective variables of the prediction model. Then the paper predicates the credit risk probability of the listed companies by using the logistic regression model. Finally, by analyzing the financial data of annual reports of fifty-four listed companies in Hebei Province from 2012 to 2017 as sample data, the simulation experiment empirical test is carried out by using SPSS software. The results show that the logistic regression model with gray clustering analysis has high predictive accuracy and has a strong predictive ability to evaluate the credit risk of listed companies. The gray logistics evaluation plays a very good role in financial early warning for regional listed companies in China.

Evaluation Analysis of Forest Ecological Security in 11 Provinces (Cities) of the Yangtze River Economic Belt

The forest ecological security of the Yangtze River Economic Belt has an important influence on improving the regional environment and promoting the sustainable development of the social economy. Therefore, the aim of this paper is to provide countermeasures and suggestions for improving the level of regional ecological security by quantitatively analyzing the forest ecological security status of the Yangtze River Economic Belt and the tributaries of the Yangtze River. Using three main aspects, i.e., resources, socio-economic pressure and maintenance response, the study established 26 indicators that affect the forest ecological security of 11 provinces (cities) in the Yangtze River Economic Belt. The index weights were determined by principal component analysis, and the forest ecological security levels of 11 provinces (cities) in the Yangtze River Economic Belt were classified and evaluated by the grey clustering method. The results show the following: (1) the principal component analysis determined the weight of the three aspect indicators. The order is as follows: resource index > socio-economic pressure index > maintenance response index. This means that the basic environmental condition which the forest growth depends on and quality and quantity of forest is most important, and the maintenance activities performed by human beings in forest resources need to be strengthened. (2) The level of the forest ecological security in all the provinces (cities) of the Yangtze River Economic Belt is relatively good, with an upward trend. The level of forest ecological security in each province (city) decreases from the upper reaches of the Yangtze River basin to the lower reaches, and the level of forest ecological security in the central cities is lower. (3) The resource index, socio-economic pressure index and maintenance response index of all the provinces and cities showed an upward trend in these four years. The provinces with a significantly higher forest resource index include Yunnan and Guizhou. Shanghai, Chongqing, Sichuan, Hunan and Jiangxi were the provinces with significantly higher socio-economic pressure values; Yunnan province, Shanghai, Jiangxi Province and Hubei province were the provinces with higher forest maintenance response values.

Large-scale group decision-making based on Pythagorean linguistic preference relations using experts clustering and consensus measure with non-cooperative behavior analysis of clusters

To represent qualitative aspect of uncertainty and imprecise information, linguistic preference relation (LPR) is a powerful tool for experts expressing their opinions in group decision-making (GDM) according to linguistic variables (LVs). Since for an LV, it generally means that membership degree is one, and non-membership and hesitation degrees of the experts cannot be expressed. Pythagorean linguistic numbers/values (PLNs/PLVs) are novel choice to address this issue. The aim of this paper which we propose a GDM problem involved a large number of the experts is called large-scale GDM (LSGDM) based on Pythagorean linguistic preference relation (PLPR) with a consensus model. Sometimes, the experts do not modify their opinions to achieve consensus. Therefore, the experts’ proper opinions’ management with their non-cooperative behaviors (NCBs) is necessary to establish a consensus model. At the same time, it is essential to ensure the proper adjustment of the credibility information. The proposed model using grey clustering method is divided with the experts’ similar evaluations into a subgroup. Then, we aggregate the experts’ evaluations in each cluster. A cluster consensus index (CCI) and a group consensus index (GCI) are presented to measure consensus level among the clusters. Then, we provide a mechanism for managing the NCBs of the clusters, which contain two parts: (1) NCB degree is defined using CCI and GCI for identifying the NCBs of the clusters; (2) implemented the weight punishment mechanism of the NCBs clusters to consensus improvement. Finally, an example is offered for usefulness of the proposed approach.