Fuzzy Clustering Analysis Research Articles

Identifying the principal driving factors of water ecosystem dependence and the corresponding indicator species in a pilot City, China

The world’s aquatic ecosystems yield numerous vital services, which are essential to human existence but have deteriorated seriously in recent years. By studying the mechanisms of interaction between ecosystems and habitat processes, the constraining factors can be identified, and this knowledge can be used to improve the success rate of ecological restoration initiatives. At present, there is insufficient data on the link between hydrological, water quality factors and the changes in the structure of aquatic communities to allow any meaningful study of driving factors of aquatic ecosystems. In this study, the typical monitoring stations were selected by fuzzy clustering analysis based on the spatial and temporal distribution characteristics of water ecology in Jinan City, the first pilot city for the construction of civilized aquatic ecosystems in China. The dominant species identification model was used to identify the dominant species of the aquatic community. The driving effect of hydrological and water quality factors on dominant species was analyzed by Canonical Correspondence Analysis. Then, the principal factors of aquatic ecosystem dependence were selected. The results showed that there were 10 typical monitoring stations out of 59 monitoring sites, which were representative of aquatic ecosystems, 9 dominant fish species, and 20 dominant invertebrate species. The selection of factors for aquatic ecosystem dependence in Jinan were highly influenced by its regional conditions. Chemical environmental parameters influence the temporal and spatial variation of invertebrate much more than that of fish in Jinan City. However, the methodologies coupling typical monitoring stations selection, dominant species determination and driving factors identification were certified to be a cost-effective way, which can provide in-deep theoretical and technical directions for the restoration of aquatic ecosystems elsewhere.

Module partition of complex mechanical products based on weighted complex networks

It is tough to build an effective mathematical model to describe the complicated relationships in complex mechanical products, which leads to the module partition of complex mechanical products and the guarantee of accurate results become more difficult. In addition, the module partition method cannot bring about a satisfactory module partition result if the scale of the products is huge and complicated. In this case, complex network theory is used to solve these problems in this paper. Firstly, a weighted complex network is established to systematically express the structure of complex mechanical products. In particular, customer demands are taken into account for module partition by introducing customer involvement. Secondly, the interval-valued intuitionistic fuzzy sets are used to calculate the relationships between parts for reducing the subjectivity of the calculation process. Afterwards, a modified GN algorithm (community detection algorithm) is proposed to achieve the module partition of complex mechanical products. Finally, the module partition of a wind turbine is carried out to verify the effectiveness of the proposed method in this paper. The result of the case study shows that the modified GN algorithm achieves better module partition performance than the classical GN algorithm and fuzzy clustering analysis method, which obtains a satisfactory result for applications.

Fuzzy Cluster Analysis of Undergraduates’ Employment Quality and Its Application

Assessment index reflects assessed contents and the choice of assessment method. A scientific assessment index system is in favor of exactly assessing the quality of talent cultivation, as well as guiding the enhancement of the quality. This paper intends to establish an index system of fuzzy assessment of undergraduates' employment quality through the theoretical approach of management science and engineering and apply it into the guidance of undergraduates' employment from Beijing University of Technology.

Model-Based Magnetization Transfer Imaging Markers to Characterize Patients and Asymptomatic Gene Carriers in Huntington's Disease.

Huntington's disease (HD) is a chronic progressive neurodegenerative disorder with a long presymptomatic period that opens a window for potential therapies aimed at neuroprotection. Neuroimaging offers the potential to monitor disease-related progression of the disease burden (DB) using model-based magnetization transfer imaging. We have conducted a cross-sectional study to stratify healthy age-matched controls, premanifest and symptomatic HD patients (n = 30) according to their macromolecular depositions in the caudate nucleus. We employed a binary spin-bath magnetization transfer (MT) method for a quantitative description of macromolecule deposits and interactions with their adjacent environment. A region-of-interest based fuzzy clustering analysis identified representative clusters for several stages of the disease course related to its progression: one cluster represented subjects with a high DB <268 that encompassed all symptomatic HD patients and one presymptomatic gene carrier. The next cluster represented the presymptomatic gene carriers with a very low DB >230 and healthy controls. Three further clusters represented transition zones between both DB levels (230-268) consisting of presymptomatic carriers with DB values increasing with decreasing distance from the cluster that indicated low DB and healthy age-matched controls. The proposed binary spin-bath MT method offers the potential to monitor DB and progression in HD. The method may augment qualitative MT techniques since it depicts tissue changes related to interactions between macromolecules and protons in disease specific brain regions that follow the neurodegenerative process.

Mapping Diversity of Publication Patterns in the Social Sciences and Humanities: An Approach Making Use of Fuzzy Cluster Analysis

Abstract Purpose To present a method for systematically mapping diversity of publication patterns at the author level in the social sciences and humanities in terms of publication type, publication language and co-authorship. Design/methodology/approach In a follow-up to the hard partitioning clustering by Verleysen and Weeren in 2016, we now propose the complementary use of fuzzy cluster analysis, making use of a membership coefficient to study gradual differences between publication styles among authors within a scholarly discipline. The analysis of the probability density function of the membership coefficient allows to assess the distribution of publication styles within and between disciplines. Findings As an illustration we analyze 1,828 productive authors affiliated in Flanders, Belgium. Whereas a hard partitioning previously identified two broad publication styles, an international one vs. a domestic one, fuzzy analysis now shows gradual differences among authors. Internal diversity also varies across disciplines and can be explained by researchers’ specialization and dissemination strategies. Research limitations The dataset used is limited to one country for the years 2000–2011; a cognitive classification of authors may yield a different result from the affiliation-based classification used here. Practical implications Our method is applicable to other bibliometric and research evaluation contexts, especially for the social sciences and humanities in non-Anglophone countries. Originality/value The method proposed is a novel application of cluster analysis to the field of bibliometrics. Applied to publication patterns at the author level in the social sciences and humanities, for the first time it systematically documents intra-disciplinary diversity.

DARS: A dynamic adaptive replica strategy under high load Cloud-P2P

In Cloud-P2P system, replica strategy is utilized for obtaining low access delay and high load balance, which requires paying more attention to the time of replica creation. Most of current replica strategies usually utilize the method of afterwards adjustment fixed threshold. However, these strategies may increase a large number of overload nodes and then lead to aggregate effect of being overloaded, especially under high load condition. To deal with the problem, this paper proposes a Dynamic Adaptive Replica Strategy (DARS) based on the node’s overheating similarity. DARS addresses the problem of replica creation time, including obtaining the replica creation opportune moment and finding the optimal replica placement node, by a decentralized self-adaptive manner. Based on the overheating similarity, DARS applies fuzzy membership function to obtain the replica creation opportune moment, which enables the node to create replica before its overload. Meanwhile, DARS adopts the fuzzy clustering analysis method to find out the node with high node degree and low load which is used as optimal placement node to store replicas. Extensive experiments demonstrate that DARS obtains superior performances in access latency around 15%∼20% on average and better load balance than other similar methods under high load condition.

Gas load forecasting based on optimized fuzzy c-mean clustering analysis of selecting similar days

Gas load forecasting based on optimized fuzzy c-mean clustering analysis of selecting similar days

A Hybrid Model for Forecasting Groundwater Levels Based on Fuzzy C-Mean Clustering and Singular Spectrum Analysis

Having the ability to forecast groundwater levels is very significant because of their vital role in basic functions related to efficiency and the sustainability of water supplies. The uncertainty which dominates our understanding of the functioning of water supply systems is of great significance and arises as a consequence of the time-unbalanced water consumption rate and the deterioration of the recharge conditions of captured aquifers. The aim of this paper is to present a hybrid model based on fuzzy C-mean clustering and singular spectrum analysis to forecast the weekly values of the groundwater level of a groundwater source. This hybrid model demonstrates how the fuzzy C-mean can be used to transform the sequence of the observed data into a sequence of fuzzy states, serving as a basis for the forecasting of future states by singular spectrum analysis. In this way, the forecasting efficiency is improved, because we predict the interval rather than the crisp value where the level will be. It gives much more flexibility to the engineers when managing and planning sustainable water supplies. A model is tested by using the observed weekly time series of the groundwater source, located near the town of Čačak in south-western Serbia.

Coherent tropical-subtropical Holocene see-saw moisture patterns in the Eastern Hemisphere monsoon systems

The concept of a Global Monsoon (GM) has been proposed based on modern precipitation observations, but its application over a wide range of temporal scales is still under debate. Here, we present a synthesis of 268 continental paleo-moisture records collected from monsoonal systems in the Eastern Hemisphere, including the East Asian Monsoon (EAsM), the Indian Monsoon (IM), the East African Monsoon (EAfM), and the Australian Monsoon (AuM) covering the last 18,000 years. The overall pattern of late Glacial to Holocene moisture change is consistent with those inferred from ice cores and marine records. With respect to the last 10,000 years (10 ka), i.e. a period that has high spatial coverage, a Fuzzy c-Means clustering analysis of the moisture index records together with “Xie-Beni” index reveals four clusters of our data set. The paleoclimatic meaning of each cluster is interpreted considering the temporal evolution and spatial distribution patterns. The major trend in the tropical AuM, EAfM, and IM regions is a gradual decrease in moisture conditions since the early Holocene. Moisture changes in the EAsM regions show maximum index values between 8 and 6 ka. However, records located in nearby subtropical areas, i.e. in regions not influenced by the intertropical convergence zone, show an opposite trend compared to the tropical monsoon regions (AuM, EAfM and IM), i.e. a gradual increase. Analyses of modern meteorological data reveal the same spatial patterns as in the paleoclimate records such that, in times of overall monsoon strengthening, lower precipitation rates are observed in the nearby subtropical areas. We explain this pattern as the effect of a strong monsoon circulation suppressing air uplift in nearby subtropical areas, and hence hindering precipitation. By analogy to the modern system, this would mean that during the early Holocene strong monsoon period, the intensified ascending airflows within the monsoon domains led to relatively weaker ascending or even descending airflows in the adjacent subtropical regions, resulting in a precipitation deficit compared to the late Holocene. Our conceptual model therefore integrates regionally contrasting moisture changes into the Global Monsoon hypothesis.

A self-learning approach for optimal detailed scheduling of multi-product pipeline

Pipeline transportation is cost-optimal in refined product transportation. However, the optimization of multi-product pipeline scheduling is rather complicated due to multi-batch sequent transportation and multi-point delivery. Even though many scholars have conducted researches on the issue, there is hardly a model settling the discontinuous constraints in the model as a result of batch interface migration. Moreover, through investigation, there is no self-learning approach to pipeline scheduling optimization at present. This paper considers batch interface migration and divides the model into time nodes sequencing issue and a mixed-integer linear programming (MILP) model with the known time node sequence. And a self-learning approach is proposed through the combination of fuzzy clustering analysis and ant colony optimization (ACO). This algorithm is capable of self-learning, which greatly improves the calculation speed and efficiency. At last, a real pipeline case in China is presented as an example to illustrate the reliability and practicability of the proposed model. • A self-learning algorithm is proposed for detailed optimal scheduling for product oil pipeline. • Two novel discontinuous process constraints are taken into consideration. • This algorithm can improve calculation speed and efficiency by itself. • A real example with six cases is given to demonstrate the method’s practicality.

Preliminary Measurements in Identifying Design Flaws

Software metrics are of great importance in object-oriented design assessment. They quantify various aspects of design entities and play an important role in predicting design quality. Despite the fact that software metrics have become increasingly useful, they raise several issues. Among them, relevant to our research are the issue of setting threshold values and the problem of measurement results interpretation. Fuzzy clustering analysis is used to overcome the limitations of the existing approaches that are using threshold values for metrics and to provide a better interpretation of the obtained measurement results. This paper focuses on metrics-based design flaw detection in object-oriented design. A new metric, Design Flaw Entropy which measures the distribution of design flaws into the analyzed system is introduced. To validate the proposed approach, a case study was also proposed.

Classification of European Countries by Economic Freedom Data

The Index of Economic Freedom is an annual index and ranking created by The Heritage Foundation and The Wall Street Journal in 1995 to measure the degree of economic freedom in the world's nations. According to the web site of Heritage Foundation, Economic freedom is defined as below: In an economically free society, individuals are free to work, produce, consume, and invest in any way they please. In economically free societies, governments allow labor, capital, and goods to move freely, and refrain from coercion or constraint of liberty beyond the extent necessary to protect and maintain liberty itself. Cluster analysis is a method for clustering a data set into groups of similar objects. It is an approach to unsupervised learning and also one of the major techniques in pattern recognition. Hard clustering methods allow each point of the data set to exactly one cluster. In fuzzy clustering, fuzzy techniques are used to cluster the data and with these techniques an object can be classified in more than one cluster. The advantage of fuzzy clustering over classical clustering methods is that it provides more detailed information on the data. In this study, European Countries has been classified with the help of Economic Freedom Data published by Heritage Foundation. Countries are classified according to a five-year period (2013 to 2017) with the help of fuzzy clustering analysis. So that european countries are divided into classes according to their economic freedoms. Also, countries with varying degrees of five-year period have been identified too.

Research on the Surface Extraction of the Point Cloud Data in Marine Surveying and Mapping

This paper firstly made analysis of the points, lines and surfaces with special curvatures in point cloud data information and classified the points according to the three eigenvalues obtained through analysis matrix. And then, it simplified the point cloud data. Data simplification was completed according to distance, surface variation, and curvature. At last, it screened, removed and classified the data based on the least square method applied in the fuzzy clustering analysis in local domain, so as to fit the point cloud surface and improve the extraction precision of the entire data.

Metapopulation dynamics and space use by reintroduced elk (Cervus elaphus) in central Ontario

Understanding population structure and resource selection is essential for wildlife management and conservation. We assessed the population structure of elk (Cervus elaphus L.,1758) in central Ontario. We used fuzzy and hierarchical cluster analyses to elucidate elk population structure based on spatial data collected from 41 radio-collared elk. We assessed space use between core and satellite subpopulations with the minimum convex polygon (MCP) and fixed kernel methods. Both fuzzy and hard clustering indicated that elk in this part of central Ontario occur in a metapopulation that includes five subpopulations. The largest cluster consisted of a core group containing 22 radio-collared elk located in Burwash, with several satellite subpopulations spread along a 50 km long north–south axis and a small subpopulation to the west located in Worthington. Survival rates among subpopulations were similar, ranging from 0.71 to 0.83, and anthropogenic causes of mortality were predominant only in the Burwash subpopulation. Space use and density of elk differed between core and satellite subpopulations. Understanding population structure is important to develop appropriate management plans. Our results support the conclusion that metapopulation structure can be reliably assessed using spatial data.

The index system for project selection in ecological industrial park: A China study

It is critical to extend and broaden the eco-industrial chain (EIC) by introducing new projects so that the stability of EIC network can be enhanced. At present, there is lack of effective control for project selection to eco-industrial park (EIPs) in China. This has led to low compatibility level of enterprises with the overall EIC network. By introducing the admission composite index, a framework is proposed in this study to assist the project selection in EIPs. It consists of three layers, i.e. target, criterion and variable. The preliminary index database is synthesized and simplified with Fuzzy Clustering Analysis (FCA). Fuzzy Analytic Hierarchy Process (FAHP) was employed to determine the weighting of each indicator. On the basis of the evaluation criteria, the evaluation method of the index system under two different conditions were established. This enriches the theory and methodology of ecological industry development in China. Meanwhile, the index system is effectively verified via an empirical case study. Results show that the index system is feasible, and quantitative results are consistent with the practice. These findings provide a good practical reference for the decision making of project selection in EIPs.

Strategy Implementation Style and Public Service Effectiveness, Efficiency, and Equity

Strategic decision-making theories suggest that organizations that combine rational and incremental strategy implementation styles are likely to perform better than those that emphasize a single style. To assess whether these arguments apply to the public sector; we explore the strategy implementation style and perceived service effectiveness, efficiency and equity of Turkish municipal government departments. Using fuzzy cluster analysis, we identify four distinctive though inter-related styles of strategy implementation in our sample organizations: logical-incremental; mostly rational; mostly incremental; and no clear approach. A logical-incremental and mostly rational style of implementation are associated with better effectiveness, efficiency and equity; with the absence of an implementation style associated with worse performance. Theoretical and practical implications are discussed.

Landslide Monitoring Point Optimization Deployment Based on Fuzzy Cluster Analysis

Landslide monitoring is one of the important means to landslide control. In order to do well this job in landslide monitoring work, first in ascertaining the geological conditions, then laying out a variety of professional monitoring points. This paper adopts the fuzzy cluster analysis method, and the landslide monitoring points by using fuzzy cluster analysis method, through the calculation of deformation of fuzzy clustering, finally draws the conclusion that the landslide monitoring point classification. The method for the landslide monitoring point optimization, as well as the landslide deformation monitoring plan modification and perfect have very important reference value.

Evaluation of electronic service quality using an integrated fuzzy clustering and principle component analysis approach: an empirical case study

This study uses data mining techniques to improve decision making process in various functions of electronic services provided by insurance companies. This study focuses on incentive packages recommended automatically by the system to the most qualified customers. Initially, customers are clustered based on their profiles. The fuzzy clustering techniques are used for this study. Each cluster is formed by customers with common characteristics according to their historical transactions. In each cluster, another data mining technique called principal component analysis is used to rank customers according to some variables which indicate the qualification of customer (customer satisfaction and expectation) to promote the insurance services and initiative packages.

Evaluation of electronic service quality using an integrated fuzzy clustering and principle component analysis approach: an empirical case study

This study uses data mining techniques to improve decision making process in various functions of electronic services provided by insurance companies. This study focuses on incentive packages recommended automatically by the system to the most qualified customers. Initially, customers are clustered based on their profiles. The fuzzy clustering techniques are used for this study. Each cluster is formed by customers with common characteristics according to their historical transactions. In each cluster, another data mining technique called principal component analysis is used to rank customers according to some variables which indicate the qualification of customer (customer satisfaction and expectation) to promote the insurance services and initiative packages.

Fuzzy cluster analysis for probability density functions based on width criterion

Fuzzy cluster analysis for probability density functions based on width criterion