Two-step Clustering Method Research Articles

Fatigue Evaluation of Bridges Based on Strain Influence Line Loaded by Elaborate Stochastic Traffic Flow

Stochastic traffic flow, as a type of repeated load, can cause serious high-cycle fatigue damage to bridges. In addition, the rough simulation of stochastic traffic flow and inappropriate analysis method of fatigue stresses cause the fatigue evaluation results to deviate from reality. To overcome this challenge, a probabilistic fatigue valuation method is proposed based on an elaborate simulation of the stochastic traffic flow and field-measured strain influence line. By selecting vehicle load features affecting the bridge structural fatigue as clustering parameters, the two-step clustering (TSC) method is applied to distinguish the different traffic states with the clustering numbers to be determined objectively. On this basis, the elaborate stochastic traffic flow is simulated by random sampling of vehicle feature probabilistic models for each traffic state. Subsequently, the bridge strain influence line, which is identified through synchronous monitoring of strain and vehicle positions, is loaded by the simulated traffic loads to obtain the stress history instead of the traditional finite-element model (FEM). Finally, the structural fatigue life can be probabilistically predicted through a Monte Carlo simulation. The proposed method was verified to be effective through a case study of a long-span suspension bridge. It can be concluded that distinguishing the different traffic states can improve the rationality of stochastic vehicle load simulation, and a more reasonable prediction of the vehicle-induced bridge fatigue damage can be obtained through the influence line loaded by stochastic vehicle loads.

Load pattern recognition based optimization method for energy flexibility in office buildings

Air conditioning systems are generally considered to have the greatest flexibility potential in buildings that can be flexibly regulated with thermal storage to reduce the interaction with the power grid and increase demand response benefits. In previous studies, the flexibility of air-conditioning systems was reflected through time-of-use tariffs. However, a strategy that only factors the tariffs incurs a greater operational energy consumption. In this study, a flexibility factor was established and incorporated into the multi-objective optimization process, together with the operational energy consumption, as two optimization objectives. After obtaining typical load patterns using a two-step clustering method, for multi-objective decision-making in the day-ahead operation, the entropy-grey technique for order preference by similarity to an ideal solution method is used. Considering an office building as a case study, we found that the optimized flexibility factor can reach 0.31 and 0.99 during a week of operation in winter and summer, on average, respectively, and achieved a cumulative energy-saving effect of 17.98% and 35.49%. In addition, the two-step clustering method can better demonstrate the flexibility factor than the single-step clustering.

Typologies of sport structures in writing and implementing European Projects: A two-step cluster analysis

In this paper we analyze information about the trends in sports structures in writing and implementing European funds, dividing them into three clusters, using SPSS Two-step Cluster method. When talking about sport structures and their relation with writing and implementing European projects in the field of sport, may not share all the same characteristics. This study aimed to identify typologies of sport structures who engage in writing and implementing European projects. The authors propose a method for a better understanding of the expectations of sports structures in the field of European funds and for managing future participants to European funds trainings effectively. About 433 sport structures completed an online questionnaire. Two-step cluster analysis identified three subgroups, based on projects with non-reimbursable funding that they have benefited from in the last 5 years, type of funding programs (external funds/state budget) and the presence of specialized internal human resources for writing and implementing projects inside their organisation. The largest group contains 222 respondents (53.4%), whose profile shows that they represent sport structures that have never beneficiated from European funds in the last past 5 years (100%), they are not considering hiring new human resources specialized in writing and implementing projects (100%) and don’t know a specific funding line / program (72.5%). The second group consists in 104 respondents (25%) – sport structures’ representatives that have beneficiated from European funds in the last past 5 years (99%), they are considering hiring new human resources specialized in writing and implementing projects (52.9%) and as a type of funds they are aware of the subsidies provided from the state budget. The third profile gathers 90 respondents, sport structures’ representatives that have not beneficiated from European funds in the last past 5 years (98.9%), but they are considering hiring new human resources specialized in writing and implementing projects (100%). Instead, this group doesn’t know the funding opportunities that the state or the European Commission provides for Romania. The benefit of the study is reinforcing the sport structures’ profits by managing their training in the field of European funds more effectively.

Data mining technology for the identification and threshold of governing factors of landslide in the Three Gorges Reservoir area

Due to the complex geological conditions and external triggering factors, the deformation of landslide disaster often has spatial differences, especially in the Three Gorges Reservoir area. It is of great significance to explore the governing factors and their thresholds in different parts of landslide. In this research, the deformation of Shuping landslide is analyzed. First, 9 hydrological factors are selected for data mining analysis by comprehensive research, including 5 reservoir water factors and 4 rainfall factors. Then, the numerical variables are transformed into discrete variables by two-step clustering method, and the Apriori algorithm is utilized to deal with the classified variables to generate the correlation criterion meeting the minimum confidence, and the correlation criterions between triggering factors and landslide displacement are established. Finally, the threshold of governing factors are mined out by decision tree C5.0 models. The results indicate that governing factors controlling the deformation of different parts of landslide are distinct. Specifically, the rear landslide is jointly controlled by the reservoir water and rainfall. On the contrary, the reservoir level controls the deformation of other parts of Shuping landslide. Generally, the daily drop of water level is the most important factor causing the deformation of Shuping landslide. During the period of low water level (138.951 ~ 147.437 m), once the daily drop of water level exceeded 0.416 m/d, the landslide will show severe deformation. This research reveals that the study of association criterion and threshold is of great significance for landslide deformation analysis. Data mining technology can be better applied to the prediction of the reservoir landslide.

Clustering daily AMI data using the two-step clustering method

Analyzing advanced metering infrastructure (AMI) data is vital for consumers to reduce electric costs and for companies to plan their business models. Thus, the statistical analysis of AMI data has become popular. In this paper, we propose a two-step clustering method that considers the usage amount and AMI pattern. Compared to the existing clustering methods, the proposed method provides different clustering groups that can be further used for time-of-use rates in Korea. We also demonstrate the differences between each group based on the electricity price before and after tariff reform.

Work in Hotels Under Conditions Related to the Covid-19 Disease

Hotel employees are at increased risk of infection with SARS-Cov-2. Therefore, governments have taken many systematic measures to protect employees and employers (hoteliers). Since previous studies have almost entirely overlooked hotel employees' perspectives on the pandemic, this study determines how heterogeneously Slovenian hotel employees perceived the disease and their own work during and after the health crisis. The Two-Step and K-Means clustering methods were used to identify clusters of respondents. The One-way ANOVA with post hoc Tukey's HSD test was employed to verify the significant differences among groups/items. The sample included 301 completed questionnaires. A three-cluster solution with statistically significant differences was identified. Cluster 3, the largest, is particularly interesting, as its members are the most pessimistic of all. In contrast, Cluster 1, which is much smaller, included the most optimistic members (plain optimists). Cluster 2 is also interesting, as its members tend to be more extroverted – expressing the highest psychological burden and pessimistic views about the future provision of hotel services. Managers should provide clear instructions, education/training, tighten control, and do everything possible to prevent oversensitivity and excessively defensive responses that could hinder operational work.

Identification of novel classes for patients with lupus nephritis using two-step cluster model.

To identify and reclassify the patients in the lupus nephritis (LN) cohort, and to further analyze the prominent clinical features and clinical significance of each cluster. In this retrospective cross-sectional study, we used atwo-step clustering method to classify 635 patients with LN into different clusters, then we observed the main differences and analyzed relevant clinical significance between the clusters. Cluster1 (20.5%) presented with the highest disease severity, patients in this group had the disease for alonger duration and higher systemic lupus erythematosus disease activity index (SLEDAI) score, with multiple positive auto-antibodies and lower complement level. Patients of cluster2 (20.8%) had lower levels of IgG, IgA and IgM, with renal function being relatively worse in this cluster than in clusters1 and3. Cluster3 was the largest group (58.7%), and the patients in this group showed mild disease severity. This study reclassified LN patients in alarge cohort into three clusters. Our classification might be helpful to implement targeted therapy at various stages of systemic lupus erythematosus.

Toward Terrain Effects on GNSS Interferometric Reflectometry Snow Depth Retrievals: Geometries, Modeling, and Applications

Accurate and high temporal-spatial resolution snow depth retrieval using the Global Navigation Satellite System Interferometric Reflectometry (GNSS-IR) has become a popular topic. The terrain is a significant issue affecting GNSS-IR snow depth retrieval. This study explores detailed information about the problems and new solutions to this issue. The main conclusions include but are not limited to the following aspects: 1) Reflections from Below the Antenna (RBA) is the primary geometrical relationship of the GNSS multipath signal for snow depth retrieval; 2) The proposed GSnow_TERR model considers the terrain effects by incorporating the surface tilt angle (γ) into the derivative of the multipath relative phase (φ) with respect to the satellite elevation angle ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">e</i> ). Unlike the previous region-by-region solutions, the new model has a definite physical meaning which considers the γ as an independent non-negligible variable; 3) The new model performs well for repeatable and non-repeatable GNSS tracks. The former agrees with the PBO H2O product with r <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> = 0.97 and a slightly 1 ~ 2 cm improvement in the RMSE. The latter agrees with the baseline two-step clustering method for GLONASS, Galileo, and BDS, with r <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> = 0.96 and RMSD = 1.11 cm. The rate of data utilization increases by a mean value of 38.21% for non-repeatable tracks. The performance of the model in practical applications is consistent with theoretical analysis. The findings of this study provide a valuable reference for future GNSS-IR snow depth research and applications.

Modifying resting-state EEG microstates with pulsed near-infrared transcranial photobiomodulation: a randomized sham-controlled crossover study

Abstract Objective: Transcranial Photobiomodulation (tPBM) is a novel noninvasive brain stimulation technique that applies near-infrared (NIR) light and influences cortical oscillation. However, the mechanism and extent of its effects are yet to be understood. In this study, we investigated the effect of active vs. sham tPBM on the temporal dynamics of large-scale brain networks using resting-state EEG microstate. Methods: Twenty healthy volunteers received 20 minutes of active or sham tPBM using 810 nm light-emitting diodes (LEDs), pulsed at 40 Hz with 50% duty cycle, delivered transcranially to the default mode network. 10-minute eyes-closed EEG recordings were collected before and after each stimulation session. The artifact-free resting-state data were used for microstate analysis, focusing on the mean duration, frequency of occurrence, and ratio of time coverage. We used the two-step k-mean clustering method to identify microstates that best describe the dataset across all subjects and conditions. Results: Our analysis identified four microstate classes (A-D) which explained 76% of the global variance. The active tPBM, showed modification of the temporal parameters of class A, with a posterior orientation of the mapped field, before and after stimulation. We found a significant increase in the duration (t=3.3, p=0.004), frequency of occurrence (t=2.7, p=0.013), and ratio of time coverage (t=3.3, p=0.001). The sham tPBM did not show any feature modification in the four microstate classes. Conclusion: For the first time, we revealed the influence of tPBM on the temporal dynamics of large-scale brain networks represented by modifications in the EEG microstates. The changes in this study were significant and occurred immediately after 20 minutes of active tPBM stimulation. Our findings provide more credibility to tPBM as an effective brain stimulation technique and warrant further research. Microstate measures can potentially be added to EEG, fMRI, and clinical assessments as tools to improve personalized treatments with tPBM. Keywords: photobiomodulation, EEG, microstate, brain networks

Investigation of accident severity in sea lanes from an emergency response perspective based on data mining technology

Due to the unobserved heterogeneity inherent in the severity data of maritime accidents, traditional methods used to investigate the severity of maritime accidents always result in hiding some underlying relationships. This paper proposes a methodology for analysing the factors affecting the severity of maritime accidents from an emergency response perspective. A two-step clustering method is first used to classify maritime accidents into two homogeneous clusters. Subsequently, multinomial ordered logit models are developed for each cluster to analyse the unobserved heterogeneity that affects the severity of the three accident consequences: ship damage, casualties, and environmental damage. Analyses are performed based on data collected from China's Maritime Safety Administration reports on maritime accidents that occurred in sea lanes of the country's maritime transportation system. The model estimation results indicate that a wide spectrum of factors affect the severity of accident consequences, including natural environmental factors, ship characteristics, accident characteristics and rescue conditions. However, the factors have different effects on the severity of accident consequences. Furthermore, variations in estimated coefficients across clusters reveal unobserved heterogeneity. The proposed methodology can effectively explore the factors affecting the severity of maritime accidents, and the results provide a decision-making strategy in maritime emergency rescue measures.

Penggerombolan Sekolah pada Penerimaan Mahasiswa Baru Jalur SNMPTN di IPB Menggunakan Metode Two-Step Cluster

New student admissions are opened in three pathways including SNMPTN, SBMPTN, and Seleksi Mandiri. In order to improve the SNMPTN selection system at IPB, a study was conducted on the quality of SMA/MA which registered to IPB through school clustering. In general, cluster analysis cannot handle large and mixed-type data, so this school clustering used the Two-Step Cluster method with two alternatives, namely without handling outliers and handling 5 percent outliers. Both of these alternatives produced an average Silhouette coefficient value of 0.2 and 0.3 respectively, which was still under the good category. However, clustering without handling outliers resulted in more detailed cluster criteria with 4 optimal clusters. The criteria for these four clusters include, Cluster 1 is a category of Low Commitment, Low Quality, and Low Consistency schools, Cluster 2 and 3 are categories of schools that have special criteria in certain categories, and Cluster 4 is a category of High Commitment, High Quality, and High Consistency.

Research on big data analysis model of multi energy power generation considering pollutant emission—Empirical analysis from Shanxi Province

With the development of the integrated energy Internet, energy structure optimization and emission reduction have led to higher requirements for developing various energy sources to enable coordinated and sustainable development. However, data-mining methods are rarely used to study the coordination of multi-energy generation in published research results. In this study, from the perspective of power industry emissions, coordinated generation of various energy sources, and balance of power generation and consumption, a data-mining algorithm was used to analyze the development of thermal power, hydropower, wind power, waste heat, gas, and other power sources. The chi-square automatic interaction detection tree (CHAID), logistic regression, and two-step clustering methods were applied. The results show that: a) CO2 and SO2 emissions were mainly affected by thermal power generation, whereas NOx emissions were jointly affected by thermal power, garbage power, and gas-fired power, and the emissions of various pollutants increased with an increase in power consumption. The optimal power-generation scheme under minimum emission can be obtained. b) There was a strong correlation between thermal power generation and residential electricity consumption, and renewable energy (wind energy, photovoltaic, hydropower) exhibited the highest correlation with the electricity consumption of the tertiary industry, which indicates that renewable energy generation can be promoted by managing electricity consumption in the tertiary industry. c) When the electricity demand of all users was small, the proportion of renewable energy power generation increased; in contrast, the thermal power generation was larger. This indicates the importance of improving the sustainable and stable power supply of renewable energy. This study provides a data analysis model for the coordinated development of multiple energies, which will contribute to the decision-making basis for controlling power emissions, improving the utilization rate of renewable energy, and optimizing the energy structure.

Food Consumption and Characteristics Associated in a Brazilian Older Adult Population: A Cluster Analysis.

Epidemiological studies support diet as a factor in the prevention and treatment of non-communicable chronic diseases, whose occurrence increases with age due to the poor choices or the adoption of a monotonous diet. The aim of this study was to construct the food consumption profiles of older adults of a Brazilian city to identify the main food groups and eating habits that contribute to these profiles and to estimate its association with socioeconomic characteristics, health and use of health services, lifestyle, and anthropometric indicators. This is a population-based cross-sectional study conducted with a representative sample of 621 community-dwelling older adults (≥60 years) in Viçosa, Minas Gerais, Brazil. The food consumption profile was the dependent variable obtained from a Food Frequency Questionnaire, utilizing the two-step cluster method. The multiple multinomial logistic regression model was used to estimate the independent associations, obtaining the odds ratios and 95% confidence intervals. Three clusters were generated, namely, (1) “unhealthy” (2) “less unhealthy,” and (3) “fairly healthy.” The cluster “unhealthy” was characterized by a regular consumption of beans, fats, fatty/processed meats, and whole milk. The factors independently associated with this cluster were lower education level, lower individual income, history of at least one doctor's appointment in the year preceding this study, and being a former smoker. The cluster “less unhealthy” was characterized by a regular consumption of beans, green vegetables, vegetables and fruits, as well as fats, fatty/processed meats, and whole milk. The factors independently associated with the “less unhealthy” cluster were lower education level and history of at least six doctor's appointments in the prior year. The cluster “fairly healthy” was characterized by the same pattern of “less unhealthy,” except for skim milk and low-fat dairy products. The evidence of the associations indicates the profile of older adults who require greater attention and care related to improved nutrition. The illiterate or semi-literate aged individuals, those with low income, and those who neglect to seek medical advice must be the focus of healthy eating actions and programs.

Clustering Complex Chronic Patients: A Cross-Sectional Community Study From the General Practitioner's Perspective.

Objective:Characterize subgroups of Complex Chronic Patients (CCPs) with cluster analysis from the general practitioner’s perspective.Study design:Cross-sectional population-based study.Setting:Three Primary Care urban centres for a reference population of 43,647 inhabitants over 14 years old in Sabadell, Catalonia, Spain.Methods:Complexity is defined by the independent clinical judgment of general practitioners with the aid of complexity domains (both clinical and social). We used a Two-Step Cluster method to identify relevant subgroups of CCPs.Results:Three relevant subgroups were identified. The first one was mainly managed by primary care professionals, and 63% of its CCPs belonged to the high-risk stratum of the Adjusted Morbidity Groups (GMA). The second subgroup included younger patients than the other two clusters, and showed the highest ratios of social deprivation and severe mental disease; 48% of its CCPs belonged to the high-risk stratum of the GMA. A third cluster included patients who belonged to the high-risk stratum of the GMA. Their age was similar to that of the patients in the first cluster, but they showed the highest values in the following areas: (i) risk of admission; (ii) proportion of advanced chronic disease and limited-life prognosis; (iii) functional loss and (iv) geriatric syndromes, along with special uncertainty in decision-making and clinical management.Conclusions:Characterization of CCPs shows clearly distinct profiles of needs, which provides an improved epidemiological picture by identifying clusters of patients who are likely to benefit from targeted interventions.

Research on Weighted Cluster Analysis Method of Panel Data

Panel data is composed of three dimensions: object, index and time, it has no mature clustering algorithm because of its complexity and dynamic data structure. Two clustering methods for multi index panel data are proposed in this paper. These two methods are respectively weighted from the index perspective and time perspective, and on this basis, the two-step clustering method is used for clustering. Then these methods are applied to cluster analysis of regional economy. The empirical results show that these two methods can effectively complete the clustering of the research objects, and have their own emphasis on the feature extraction angle of the panel data.

Research on Hierarchical Clustering Method of Urban Rail Transit Passengers Based on Individual Portrait

The travel behavior of urban rail transit passengers has spatial-temporal differences, which increases difficulties of accurately grasping the evolution of passenger flow and achieving accurate short-term travel forecasts. Therefore, it’s particularly significant to deeply analyze passenger travel spatial-temporal characteristics and to achieve refined passenger classification. Using the AFC data of the urban rail transit system, this paper focuses on the construction of individual travel spatial-temporal portraits. An improved DBSCAN-based method for extracting individual travel spatial-temporal characteristics is proposed, and Python software is used to realize the visual drawing of individual portraits, so as to dig out potential passenger travel rules. Furthermore, a hierarchical clustering method of passengers based on individual portraits is proposed, and the quantified extracted individual travel feature values are clustered through the two-step clustering method, and the refined classification of passengers is realized layer by layer. Finally, the passengers are divided into four categories: definite passengers, flexible passengers, random passengers and one-way ticket passengers. The rationality and accuracy of the classification results are verified from multiple angles. The study clarifies the travel spatial-temporal characteristics of different types of passengers, improves the objectivity of passenger classification, and lays the foundation for short-term travel prediction.

Robustness-Improved Method for Measurement-Based Equivalent Modeling of Active Distribution Network

Accurate equivalent model can be efficient to analyze the dynamic properties of active distribution network (ADN) as well as assess their impacts on stabilities of interconnected power system. However, due to the stochastic nature of renewable resources and time-varying configurations of load conditions, traditional ADN equivalent model may not be robust enough to different operation conditions. To overcome the limitations, this article proposed a robustness-improved method for dynamic equivalent modeling of ADN. To sketch out the most representative operation conditions of ADN, two-step clustering method with fisher discriminant analysis are used for grouping of operation conditions featured characteristic data sets. With the key parameter based identification technique applied, the multiple solution issue in parameter identification process could be effectively avoided. To further enhance the robustness of equivalent model, long short-term memory neural network is adopted to generalize the identified parameters. The performance of proposed modeling method is comprehensively evaluated by an actual ADN based verification cases.

Self-adaptive trajectory prediction for improving traffic safety in cloud-edge based transportation systems

Intelligent transportation brings huge benefits to humans’ life and Industrial production in terms of vehicle control and traffic management. Now, the development of edge-cloud computing has once again promoted intelligent transportation into a new era. However, the development of intelligent transportation inevitably produces a large amount of data, which brings new challenges to data privacy protection and security. In this paper, we propose to develop an improved trajectory prediction framework based on the self-adaptive trajectory prediction model (SATP), which could significantly enhance traffic safety in transportation systems. The proposed framework is capable of guaranteeing the accurate trajectory prediction of moving target under different application scenarios. In particular, to reduce the size of original trajectory point data collected by sensors, the angle change and minimum description length (MDL) principle are first combined to remove the redundant points in raw trajectories. The obtained points can then be reduced for model using the two-step clustering method. To further enhance the prediction performance, we add the “self-transfer” to the original model to solve the problems that the state of original SATP model may be discontinuous. Furthermore, we propose to develop a trajectory complementation method based on Bezier curve to improve the prediction accuracy. Finally, by comparing the two-step clustering method with the commonly-used SinglePass and density-based clustering method (DBCM) algorithms, the proposed two-step clustering policy greatly reduce the time cost of clustering. At the same time, by comparing the improved SATP model with the original model, the results show that the improved SATP method can greatly improve the speed of prediction model.

A Typology of Winery SME Brand Strategies with Implications for Sustainability Communication and Co-Creation

The article explores SME (Small and Medium Sized Enterprises) brand strategies as a means to position and successfully engage in competitive markets. A derived typology of brand strategy types deals with social profiling and sheds light on brand strategy internalization of two current managerial paradigms—sustainability and co-creation. N = 895 German SME wineries were examined, leaning on a netnographic analysis of predominantly websites and social media interactions. A two-step clustering method thereby identified eight winery SME brand strategy types. The importance of sustainability across the identified eight brand strategy types is significant. Co-creation turned out to be a key profiling trait characterizing one brand strategy type. The typology illustrates strategic richness, with brand strategies leaning predominantly on traditional values, on sustainability, on external reputation, or on more innovative customer centric concepts such as co-creation. Hereby, the typology and the identified brand levers invite to strategically design brand management, governance, and sustainability. Wineries which focus on traditional positioning and legitimacy were found to be cautious in deploying co-creation through social media. Winery brands that are characterized by engagement in digital co-creation apparently either tend to expand their scope or partially combine it with traditional values, making them the most diverse type identified. Sustainability obviously needs to be addressed by all brand strategies. Despite industry and country focus, the analyses illustrate the relevance of socially-oriented profiling and highlights that sustainability has reached a status of a fundamental business approach still allowing to differentiate thereon. Furthermore, the business models of the SMEs need to deliver communicated values.

A Performance Guarantee for Spectral Clustering

The two-step spectral clustering method, which consists of the Laplacian eigenmap and a rounding step, is a widely used method for graph partitioning. It can be seen as a natural relaxation to the NP-hard minimum ratio cut problem. In this paper, we study the following central question: When is spectral clustering able to find the global solution to the minimum ratio cut problem? First, we provide a condition that naturally depends on the intra- and intercluster connectivities of a given partition under which we may certify that this partition is the solution to the minimum ratio cut problem. Then, we develop a deterministic two-to-infinity norm perturbation bound for the invariant subspace of the graph Laplacian that corresponds to the $k$ smallest eigenvalues. Finally, by combining these two results we give a condition under which spectral clustering is guaranteed to output the global solution to the minimum ratio cut problem, which serves as a performance guarantee for spectral clustering.