Clustering Structure Analysis in Time-Series Data With Density-Based Clusterability Measure

Clustering is used to gain an intuition of the struc tures in the data.Most of the current clustering algorithms pro duce a clustering structure even on data that do not possess such structure.In these cases,the algorithms force a structure in the data instead of discovering one.To avoid false structures in the relations of data,a novel clusterability assessment method called density-based clusterability measure is proposed in this paper.I measures the prominence of clustering structure in the data to evaluate whether a cluster analysis could produce a meaningfu insight to the relationships in the data.This is especially useful in time-series data since visualizing the structure in time-series data is hard.The performance of the clusterability measure is evalu ated against several synthetic data sets and time-series data sets which illustrate that the density-based clusterability measure can successfully indicate clustering structure of time-series data.

Integrating petrophysical data into efficient iterative cluster analysis for electrofacies identification in clastic reservoirs

Efficient iterative unsupervised machine learning involving probabilistic clustering analysis with the expectation-maximization(EM)clustering algorithm is applied to categorize reservoir facies by exploiting latent and observable well-log variables from a clastic reservoir in the Majnoon oilfield,southern Iraq.The observable well-log variables consist of conventional open-hole,well-log data and the computer-processed interpretation of gamma rays,bulk density,neutron porosity,compressional sonic,deep resistivity,shale volume,total porosity,and water saturation,from three wells located in the Nahr Umr reservoir.The latent variables include shale volume and water saturation.The EM algorithm efficiently characterizes electrofacies through iterative machine learning to identify the local maximum likelihood estimates(MLE)of the observable and latent variables in the studied dataset.The optimized EM model developed successfully predicts the core-derived facies classification in two of the studied wells.The EM model clusters the data into three distinctive reservoir electrofacies(F1,F2,and F3).F1 represents a gas-bearing electrofacies with low shale volume(Vsh)and water saturation(Sw)and high porosity and permeability values identifying it as an attractive reservoir target.The results of the EM model are validated using nuclear magnetic resonance(NMR)data from the third studied well for which no cores were recovered.The NMR results confirm the effectiveness and accuracy of the EM model in predicting electrofacies.The utilization of the EM algorithm for electrofacies classification/cluster analysis is innovative.Specifically,the clusters it establishes are less rigidly constrained than those derived from the more commonly used K-means clustering method.The EM methodology developed generates dependable electrofacies estimates in the studied reservoir intervals where core samples are not available.Therefore,once calibrated with core data in some wells,the model is suitable for application to other wells that lack core data.

ARHCS (Automatic Rainfall Half-Life Cluster System): A Landslides Early Warning System (LEWS) Using Cluster Analysis and Automatic Threshold Definition

A significant portion of Landslide Early Warning Systems (LEWS) relies on the definition of operational thresholds and the monitoring of cumulative rainfall for alert issuance. These thresholds can be obtained in various ways, but most often they are based on previous landslide data. This approach introduces several limitations. For instance, there is a requirement for the location to have been previously monitored in some way to have this type of information recorded. Another significant limitation is the need for information regarding the location and timing of incidents. Despite the current ease of obtaining location information (GPS, drone images, etc.), the timing of the event remains challenging to ascertain for a considerable portion of landslide data. Concerning rainfall monitoring, there are multiple ways to consider it, for instance, examining accumulations over various intervals (1 h, 6 h, 24 h, 72 h), as well as in the calculation of effective rainfall, which represents the precipitation that actually infiltrates the soil. However, in the vast majority of cases, both the thresholds and the rain monitoring approach are defined manually and subjectively, relying on the operators’ experience. This makes the process labor-intensive and time-consuming, hindering the establishment of a truly standardized and rapidly scalable methodology on a large scale. In this work, we propose a Landslides Early Warning System (LEWS) based on the concept of rainfall half-life and the determination of thresholds using Cluster Analysis and data inversion. The system is designed to be applied in extensive monitoring networks, such as the one utilized by Cemaden, Brazil’s National Center for Monitoring and Early Warning of Natural Disasters.

Comparative Analysis of Differences among Northern,Jiangnan,and Lingnan Classical Private Gardens Using Principal Component Cluster Method

This paper investigates the design essence of Chinese classical private gardens,integrating their design elements and fundamental principles.It systematically analyzes the unique characteristics and differences among classical private gardens in the Northern,Jiangnan,and Lingnan regions.The study examines nine classical private gardens from Northern China,Jiangnan,and Lingnan by utilizing the advanced tool of principal component cluster analysis.Based on literature analysis and field research,273 variables were selected for principal component analysis,from which four components with higher contribution rates were chosen for further study.Subsequently,we employed clustering analysis techniques to compare the differences among the three types of gardens.The results reveal that the first principal component effectively highlights the differences between Jiangnan and Lingnan private gardens.The second principal component serves as the key to defining the types of Northern private gardens and distinguishing them from the other two types,and the third principal component indicates that Lingnan private gardens can be categorized into two distinct types as well.

Analysis of Patents Related to COVID-19-Based on Patent Clustering Model in Specific Fields

Objective To improve the efficiency of patent clustering related to COVID-19 through the topic extraction algorithm and BERT model,and to help researchers understand the patent applications for novel corona virus.Methods The weights of topic vector and BERT model vector were adjusted by cross-entropy loss algorithm to obtain joint vector.Then,k-means++algorithm was used for patent clustering after dimension reduction.Results and Conclusion The model was applied to patents for corona virus drugs,and five clustering topics were generated.Through comparison,it is proved that the clustering results of this model are more centralized and the differentiation between clusters is significant.The five clusters generated are visually analyzed to reveal the development status of patents for corona virus drugs.

Identifying a competency improvement strategy for infection prevention and control professionals:A rapid systematic review and cluster analysis

Remarkable progress has been made in infection prevention and control(IPC)in many countries,but some gaps emerged in the context of the coronavirus disease 2019(COVID-19)pandemic.Core capabilities such as standard clinical precautions and tracing the source of infection were the focus of IPC in medical institutions during the pandemic.Therefore,the core competences of IPC professionals during the pandemic,and how these contributed to successful prevention and control of the epidemic,should be studied.To investigate,using a systematic review and cluster analysis,fundamental improvements in the competences of infection control and prevention professionals that may be emphasized in light of the COVID-19 pandemic.We searched the PubMed,Embase,Cochrane Library,Web of Science,CNKI,WanFang Data,and CBM databases for original articles exploring core competencies of IPC professionals during the COVID-19 pandemic(from January 1,2020 to February 7,2023).Weiciyun software was used for data extraction and the Donohue formula was followed to distinguish high-frequency technical terms.Cluster analysis was performed using the within-group linkage method and squared Euclidean distance as the metric to determine the priority competencies for development.We identified 46 studies with 29 high-frequency technical terms.The most common term was“infection prevention and control training”(184 times,17.3%),followed by“hand hygiene”(172 times,16.2%).“Infection prevention and control in clinical practice”was the most-reported core competency(367 times,34.5%),followed by“microbiology and surveillance”(292 times,27.5%).Cluster analysis showed two key areas of competence:Category 1(program management and leadership,patient safety and occupational health,education and microbiology and surveillance)and Category 2(IPC in clinical practice).During the COVID-19 pandemic,IPC program management and leadership,microbiology and surveillance,education,patient safety,and occupational health were the most important focus of development and should be given due consideration by IPC professionals.

A Hybrid Neural Network Model for Marine Dissolved Oxygen Concentrations Time-Series Forecasting Based on Multi-Factor Analysis and a Multi-Model Ensemble

Dissolved oxygen(DO)is an important indicator of aquaculture,and its accurate forecasting can effectively improve the quality of aquatic products.In this paper,a new DO hybrid forecasting model is proposed that includes three stages:multi-factor analysis,adaptive decomposition,and an optimizationbased ensemble.First,considering the complex factors affecting DO,the grey relational(GR)degree method is used to screen out the environmental factors most closely related to DO.The consideration of multiple factors makes model fusion more effective.Second,the series of DO,water temperature,salinity,and oxygen saturation are decomposed adaptively into sub-series by means of the empirical wavelet transform(EWT)method.Then,five benchmark models are utilized to forecast the sub-series of EWT decomposition.The ensemble weights of these five sub-forecasting models are calculated by particle swarm optimization and gravitational search algorithm(PSOGSA).Finally,a multi-factor ensemble model for DO is obtained by weighted allocation.The performance of the proposed model is verified by timeseries data collected by the pacific islands ocean observing system(PacIOOS)from the WQB04 station at Hilo.The evaluation indicators involved in the experiment include the Nash–Sutcliffe efficiency(NSE),Kling–Gupta efficiency(KGE),mean absolute percent error(MAPE),standard deviation of error(SDE),and coefficient of determination(R^(2)).Example analysis demonstrates that:①The proposed model can obtain excellent DO forecasting results;②the proposed model is superior to other comparison models;and③the forecasting model can be used to analyze the trend of DO and enable managers to make better management decisions.

TIME-SERIES MODELI NG AND FAULT FORECAST STUDY ON SPECTRAL ANALYSIS OF LUBRICATING OIL

The application of ti me-series modeling and forecasting method to the spectral analysis for lubricat ing oil of mechanical equipment is discussed. The AR model is used to perform a time-series modeling and forecasting analysis for the spectral analysis data co llected from aero-engines. In the oil condition monitoring field of mechanical equipment, the use of the method of time-series analysis has rarely been report ed. As indicated in the satisfactory example, a practical method for condition m onitoring and fault forecasting of mechanical equipment has been achieved.

Time-series analysis of the characteristic pressure fluctuations in a conical fluidized bed with negative pressure

The negative pressure conical fluidized bed is widely used in the pharmaceutical industry.In this study,experiments based on the negative pressure conical fluidized bed are carried out by changing the material mass and particle size.The pressure fluctuation signals are analyzed by the time and the frequency domain methods.A method for absolutely characterizing the degree of the energy concentration at the main frequency is proposed,where the calculation is to divide the original power spectrum by the average signal power.A phenomenon where the gas velocity curve temporarily stops growing is observed when the material mass is light,and the particle size is small.The standard deviation and kurtosis both rapidly change at the minimum fluidization velocity and thus can be used to determine the flow regime,and the variation rule of the kurtosis is independent of both the material mass and particle size.In the initial fluidization stage,the dominant pressure signal comes from the material movement;with the increase in the gas velocity,the power of a 2.5 Hz signal continues to increase.A method of dividing the main frequency by the average cycle frequency can conveniently determine the fluidized state,and a novel concept called stable fluidized zone proposed in this paper can be obtained.Controlling the gas velocity within the stable fluidized zone ensures that the fluidized bed consistently remains in a stable fluidized state.

Variation and Cluster Analysis on Leaf Characters from Different Provenance Sources of Polygonum multiflorum Thunb

[Objective] The aim was to study the variation of leaf characters from different provenance sources of Polygonum multiflorum Thunb,as well as to carry out cluster analysis on P.multiflorum from different provenance sources to provide basis for the classification,identification,breeding and improved variety selection of P.multiflorum.[Method] Leaf shape characters of 31 copies of germplasm resources in the major distribution region of the whole country were determined,and the genetic variation of P.multiflorum leaves from different producing areas was analyzed.[Result] The leaf characters of single plant of the same experimental provenance source of P.multiflorum were relatively stable,the variation was mainly found on the single leaf area,1/2 leaf width,leaf width and other indicators;the variation of each leaf character among different provenance sources was obvious,and the variation was mainly found on the single leaf weight,leaf area,1/2 leaf width,leaf length and other indicators.The correlation analysis of each leaf character in P.multiflorum suggested that the single leaf area and single leaf weight showed extremely significant positive correlation with leaf length,1/2 leaf width,leaf width,leaf thickness and leaf stem length,while the single leaf area and single leaf weight showed significant negative correlation with WWR（leaf width/1/2 leaf width）and LWR（leaf length/1/2 leaf length）,in addition,several macroscopic leaf characters such as leaf length,1/2 leaf width,leaf width,leaf stem length showed extremely positive correlation.The main component analysis result suggested that the contribution rate of accumulation variance of the front three main components was up to 97.4%,which could better reflect the comprehensive performance of leaf characters of different provenance sources of P.multiflorum.The cluster analysis showed that the experimental 31 copies of P.multiflorum provenance sources should be divided into three classes,the first class was distributed in the Middle,Western of Guizhou,northwestern of Guangxi and western areas with higher altitude;the second class was distributed in Hunan,Hubei,Sichuan,Guangdong and the most area of Guangxi;the third class was distributed in Anhui,Jiangsu and Henan and Shandong.[Conclusion] Cluster analysis of leaf characters indicated that the kinds of provenance sources which the geographical position was closer could be got together.The study had provided a certain basis for the classification of P.multiflorum.

Application of cluster analysis and stepwise regression in predicting the traffic volume of lanes

Because of the difficulty to obtain the traffic flow information of lanes at non-detector intersections in most metropolises of the world,based on the relationships between the lanes of signal-controlled intersections,cluster analysis and stepwise regression are integrated to predict the traffic volume of lanes at non-detector isolated controlled intersections.First cluster analysis is used to cluster the lanes of non-detector isolated signal-controlled intersections and the lanes of all signal-controlled intersections with detectors.Then, by the results of cluster analysis,the traffic volume samples are selected randomly and stepwise regression is used to predict the traffic volume of lanes at non-detector isolated signal-controlled intersections.The method is tested by the traffic volume data of lanes of the road network of Nanjing city.The problem of predicting the traffic volume of lanes at non-detector isolated signal-controlled intersections was resolved and can be widely used in urban traffic flow guidance and urban traffic control in cities without enough intersections equipped with detectors.

Characterizing heterogeneity in vehicular traffic speed using two-step cluster analysis

In order to analyze the heterogeneity in vehicular traffic speed, a new method that integrates cluster analysis and probability distribution function fitting is presented. First, for identifying the optimal number of clusters, the two-step cluster method is applied to analyze actual speed data, which suggests that dividing speed data into two clusters can best reflect the intrinsic patterns of traffic flows. Such information is then taken as guidance in probability distribution function fitting. The normal, skew-normal and skew-t distribution functions are used to fit the probability distribution of each cluster respectively, which suggests that the skew-t distribution has the highest fitting accuracy; the second is skew-normal distribution; the worst is normal distribution. Model analysis results demonstrate that the proposed mixture model has a better fitting and generalization capability than the conventional single model. In addition, the new method is more flexible in terms of data fitting and can provide a more accurate model of speed distribution.

Genetic Diversity and Clustering Analysis of 48Cultivars of Olea euyopaea L.

Inter-simple sequence repeat（ISSR） molecular markers were applied to analyze the genetic diversity and clustering of 48 introduced and bred cultivars of Olea euyopaea L. Totally 106 DNA bands were amplified by 11 screened primers, including 99 polymorphic bands; the percentage of polymorphic loci was 93.40%, indicating a rich genetic diversity in Olea euyopaea L. germplasm resources. Based on Nei＇s genetic distances between various cultivars, a dendrogram of 48 cultivars of Olea euyopaea L. was constructed using unweighted pair-group（UPMGA）method,which showed that 48 cultivars were clustered into four main categories; 84.6% of native cultivars were clustered into two categories; most of introduced cultivars were clustered based on their sources and main usages but not on their geographic origins. This study will provide references for the utilization and further genetic improvement of Olea euyopaea L. germplasm resources.

Cluster Analysis of Morphologic Characteristic of Eight Geographical Populations of Rana Dybowskii

[ObJective] The research aimed to determine the geographic distribution map of system of Rana dybowskii. [Method] Four morphologic indices （body length, body weight, forelimb length, hindlimb length） of eight geographical populations of R.dybowskii which naturally distribute in Changhai Mountain and Xiaoxing＇an Mountain were measured. Measure results were variance analyzed and cluster analyzed. [Result] Variance analysis showed： the genetic branching among the Dongfanghong male population（ belongs to Wandashan） and Xiaoxing＇an Mountain male population and Changbai Mountain male population were significantly different （P〈0.05） ; the genetic branching between the Hebei female population （belongs to Xiaoxing＇an Mountain） and Changbai Mountain female population was significantly different （P〈0.05 ）. Cluster analysis showed ： male R.dybowskii can be divided into three groups ： the first group included Quanyang, Tianbei, Chaoyang and Ddkouqin, the second group included Tieli and Anshan, the third group included Dongfanghong; and the female R. dybowskii can be divided into three groups ： the first group included Quanyang and Chaoyang, the second group included Tianbei and Dakouqin, the third group included Hebei. [Condusion] The paper deduced that the Sanjiang Plain was the geographical origin center ofR. dybowskii which radiated to Changbai Mountain and Xiaoxing＇an Mountain along the adverse current of Songhua River basin, therefore, the current distribution pattern of R. dybowskii was formed.

Clustering analysis algorithm for security supervising data based on semantic description in coal mines

In order to mine production and security information from security supervising data and to ensure security and safety involved in production and decision-making,a clustering analysis algorithm for security supervising data based on a semantic description in coal mines is studied.First,the semantic and numerical-based hybrid description method of security supervising data in coal mines is described.Secondly,the similarity measurement method of semantic and numerical data are separately given and a weight-based hybrid similarity measurement method for the security supervising data based on a semantic description in coal mines is presented.Thirdly,taking the hybrid similarity measurement method as the distance criteria and using a grid methodology for reference,an improved CURE clustering algorithm based on the grid is presented.Finally,the simulation results of a security supervising data set in coal mines validate the efficiency of the algorithm.

Principal Component Analysis and Cluster Analysis of Fagopyrum tataricum Varieties(Lines)

In order to reveal the genetic differences and agronomic traits of Fagopy-rum tataricum_ varieties （lines） intuitively, explore good resources and avoid the blindness of parent selection during the breeding process, six primary agronomic traits of 45 F. tataricum_ varieties （lines） that came from the eleven buckwheat breeding departments across the country were analyzed with principal component analysis and cluster analysis. The results of principal component analysis showed that the six agronomic traits could be simplified into three principal components, and the cumulative contribution rate reached 83%. The results of cluster analysis showed that the 45 F. tataricum varieties （lines） were classified into four groups：high stalk, medium yield and smal grain type, medium stalk, high yield and large grain type, medium stalk, low yield and smal grain type and high stalk, medium yield and medium grain type. Among them, performance of comprehensive trait of the second type was better than that of the other types. Thus, the F. tataricum_va-rieties （lines） that were classified into the second type could be considered as good varieties （lines） or breeding materials. The genetic differences among F. tataricum_varieties （lines） had no necessary correlations with origin and geographical distance. ln addition to complementary traits and geographical distance, genetic distances （dif-ferent populations） should be taken into consideration during parent selection in cross breeding.

Clustering Analysis on Large Grained Brassica napus Materials Based on the Optimized ACGM Markers

[Objective] This study aimed to develop ACGM markers for the clustering analysis of large grained Brassica napus materials. [Method] A total of 44 pairs of ACGM primers were designed according to 18 genes related to Arabidopsis grain development and their homologous rape EST sequences. After electrophoresis, 18 pairs of ACGM primers were selected for the clustering analysis of 16 larger grained samples and four fine grained samples of rapeseed. [Result] PCR result showed that 2-6 specific bands were respectively amplified by each pair of primes, and all the bands were polymorphic and repeatable, suggesting that the optimized ACGM markers were useful for clustering analysis of B. napus species. Clustering analysis revealed that the 20 rapeseed samples were divided into three clusters A, B, and C at similarity coefficient 0.6. Then, the clusters A and B were further divided into five sub clusters A1, A2, A3, B1 and B2 at similarity coefficient 0.67. [Conclusion] This study will provide theoretical and practical values for rape breeding.

Cluster Analysis of Characteristics of Different Sweet Cherry Varieties

In order to compare the characteristics of different varieties of sweet cherry and to formulate corresponding pruning scheme, hierarchical cluster analysis was conducted for the 14 sweet cherry varieties that were mainly planted in Shanxi Province. The results showed that the 14 varieties of sweet cherry could be divided into two types, Hongmanao and Rainier. Fruit setting rate, branching rate, medium fruit shoot proportion, spur proportion and yield per plant were significantly different between these two types of sweet cherry. The key points of pruning management, to improve the yield of Rainier type, were to increase the fruit setting rate and spur proportion, and to control properly the long and medium fruit shoot proportion.

Study on FTIR Spectra of Corn Germs and Endosperms of Three Different Colors Combining with Cluster Analysis

[Objective] This research aimed to study the FTIR spectra of corn germs and endosperms so as to provide a scientific way for identifying corn of different types. [Method] The corn germs and endosperms of three types were studied by using Fourier transform infrared spectroscopy（FTIR） technology, combined with cluster analysis. [Result] The overall characteristics of original FTIR spectra were basically similar within the range of 700-1 800 cm^-1. The FTIR spectra were mainly composed by the absorption peaks of polysaccharides, proteins and lipids. Within the wavelength range of 700-1 800 cm^-1, there were only tiny differences in original FTIR spectra among the corn germs and endosperms of three different types. The spectra were then processed by using first derivative and second derivative. The second derivative spectra were used for hierarchical cluster analysis（HCA）. The results showed that with the wavelength range of 700-1 800 cm^-1, the second derivative spectra of the 52 samples could be better clustered according to the tree types and corn germ and corn endosperm. The clustering correct rate reached 96.1%.[Conclusion] FTIR technology, combined with cluster analysis, can be used to identify different types of corn germs and endosperms, and it is characterized by convenience and rapidness.

Study on Trace Elements in Rehmannia glutinosa Libosch. by Principal Component Analysis and Clustering Analysis

[Objective] This study aimed to investigate the trace elements in Rehman- nia glutinosa Libosch. by using principal component analysis and clustering analysis. [Method] Principal component analysis and clustering analysis of R. glutinosa medicinal materials from different sources were conducted with contents of six trace elements as indices. [Result] The principal component analysis could comprehen- sively evaluate the quality of R. glutinosa samples with objective results which was consistent with the results of clustering analysis. [Conclusion] Principal component analysis and clustering analysis methods can be used for the quality evaluation of Chinese medicinal materials with multiple indices.