One-step Clustering Research Articles

One-Step Clustering with Adaptively Local Kernels and a Neighborhood Kernel

Among the methods of multiple kernel clustering (MKC), some adopt a neighborhood kernel as the optimal kernel, and some use local base kernels to generate an optimal kernel. However, these two methods are not synthetically combined together to leverage their advantages, which affects the quality of the optimal kernel. Furthermore, most existing MKC methods require a two-step strategy to cluster, i.e., first learn an indicator matrix, then executive clustering. This does not guarantee the optimality of the final results. To overcome the above drawbacks, a one-step clustering with adaptively local kernels and a neighborhood kernel (OSC-ALK-ONK) is proposed in this paper, where the two methods are combined together to produce an optimal kernel. In particular, the neighborhood kernel improves the expression capability of the optimal kernel and enlarges its search range, and local base kernels avoid the redundancy of base kernels and promote their variety. Accordingly, the quality of the optimal kernel is enhanced. Further, a soft block diagonal (BD) regularizer is utilized to encourage the indicator matrix to be BD. It is helpful to obtain explicit clustering results directly and achieve one-step clustering, then overcome the disadvantage of the two-step strategy. In addition, extensive experiments on eight data sets and comparisons with six clustering methods show that OSC-ALK-ONK is effective.

Identification of Stopping Points in GPS Trajectories by Two-Step Clustering Based on DPCC with Temporal and Entropy Constraints

The widespread adoption of intelligent devices has led to the generation of vast amounts of Global Positioning System (GPS) trajectory data. One of the significant challenges in this domain is to accurately identify stopping points from GPS trajectory data. Traditional clustering methods have proven ineffective in accurately identifying non-stopping points caused by trailing or round trips. To address this issue, this paper proposes a novel density peak clustering algorithm based on coherence distance, incorporating temporal and entropy constraints, referred to as the two-step DPCC-TE. The proposed algorithm introduces a coherence index to integrate spatial and temporal features, and imposes temporal and entropy constraints on the clusters to mitigate local density increase caused by slow-moving points and back-and-forth movements. Moreover, to address the issue of interactions between subclusters after one-step clustering, a two-step clustering algorithm is proposed based on the DPCC-TE algorithm. Experimental results demonstrate that the proposed two-step clustering algorithm outperforms the DBSCAN-TE and one-step DPCC-TE methods, and achieves an accuracy of 95.49% in identifying stopping points.

Investigating the structural validity and reliability of the sexual health literacy for adults (SHELA) questionnaire among a sample of women in Qazvin, Iran

BackgroundThe correct measurement of sexual health literacy requires an instrument with desirable psychometric properties and fitness to the sociocultural context. Despite acceptable psychometric properties of the sexual health literacy for adults questionnaire in the mixed population of men and women, the validity and reliability of this questionnaire in the female population were not determined. Therefore, considering differences in the study population, this study aimed to determine the structural validity and reliability of the questionnaire among women.MethodsThe present study was a methodological and psychometric study of instruments conducted among 310 women referring to healthcare centers in Qazvin, Iran in 2020. Sampling was done using a one-step cluster method. We used Cronbach's alpha coefficient, Pearson correlation coefficient, and confirmatory and exploratory factor analyses to determine the reliability, convergence validity, and construct validity of the questionnaire respectively. Also, the Sexual Quality of Life-Female questionnaire (SQOL-F) and the Female Sexual Function Index (FSFI) were used to evaluate the convergence validity. Data were analyzed using SPSS 20, and STATA 13.ResultsExploratory factor analysis identified three factors including, “reading and understanding”, “evaluation and application of information”, and “skills of access” which together accounted for 70.85% of the whole variance. Based on the results of confirmatory factor analysis, this questionnaire had overall goodness of fit too. (RMSEA = 0.071, CFI = 0.928, TLI = 0.919, SRMR = 0.041, X2/df = 2.501). Convergent validity of the questionnaire showed a correlation of 0.121–0.243 between the questionnaire's dimensions with the FSFI and the SQOL-F questionnaires respectively. Also, the results showed that the questionnaire had proper internal consistency (Cronbach’s alpha was 0.981) for measuring sexual health literacy in women.ConclusionsThe 39-item sexual health literacy assessment questionnaire consisting of 3 factors in the present study was endowed with sufficient validity and reliability, and it can be used for precisely assessing women’s sexual health literacy.

Fusing Local and Global Information for One-Step Multi-View Subspace Clustering

Multi-view subspace clustering has drawn significant attention in the pattern recognition and machine learning research community. However, most of the existing multi-view subspace clustering methods are still limited in two aspects. (1) The subspace representation yielded by the self-expression reconstruction model ignores the local structure information of the data. (2) The construction of subspace representation and clustering are used as two individual procedures, which ignores their interactions. To address these problems, we propose a novel multi-view subspace clustering method fusing local and global information for one-step multi-view clustering. Our contribution lies in three aspects. First, we merge the graph learning into the self-expression model to explore the local structure information for constructing the specific subspace representations of different views. Second, we consider the multi-view information fusion by integrating these specific subspace representations into one common subspace representation. Third, we combine the subspace representation learning, multi-view information fusion, and clustering into a joint optimization model to realize the one-step clustering. We also develop an effective optimization algorithm to solve the proposed method. Comprehensive experimental results on nine popular multi-view data sets confirm the effectiveness and superiority of the proposed method by comparing it with many state-of-the-art multi-view clustering methods.

One-step multi-view spectral clustering with cluster label correlation graph

Recently, one-step clustering methods have shown good performance. However, very few one-step approaches have addressed the multi-view case, where an instance may have multiple representations. Data can be represented with multiple heterogeneous views. Clustering with multiple views faces the challenge of how to combine all the different views. A general scheme is to represent the views by view-based graphs and/or a consensus graph. Graphs can be well suited for clustering problems since they can capture the local and global structure of the data. In this paper, we present a novel approach to one-step graph-based multi-view clustering. In contrast to existing graph-based one-step clustering methods, our proposed method introduces two key innovations. First, we build an additional graph by using the cluster label correlation to the graphs associated with the data space. Second, a smoothing constraint is exploited to constrain the cluster-label matrix and make it more consistent with the original data graphs as well as with and label graphs. Experimental results on several public datasets show the efficiency of the proposed approach. All cluster evaluation metrics show significant improvement by applying our method to different types and sizes of datasets. The average improvement (across all datasets) is the difference between the indicator obtained by our approach and the indicator obtained by the most competitive method. The average improvement is approximately 4%, 2%, 3%, and 2% for the Accuracy indicator, the Normalized Mutual Information indicator, the Purity indicator, and the Adjusted Rand index, respectively.

Comparison of Feeding Behaviors in Term and Preterm Infants at Six Months Corrected Age

Background and Objectives: This study compares feeding behaviors and problems of in term Infants and preterm infants at 6 months corrected age. Subjects and Methods The study was of observational-sectional type (descriptive and analytic) and sampling was one-step cluster probability of the available population in the form of the whole number. Feeding behaviors of 90 infants, including 60 term infants and 30 preterm infants, were assessed by speech and language pathologists through interviews with parents and recorded in a questionnaire. The information in this questionnaire includes feeding behaviors, feeding problems, feeding period, infant weight at 2, 4, 6 months and the age of the child to start complementary feeding, SPSS software version 24 was used to analyze the data. In all the present study, P-value less than 5% was considered as a significant level. Results The results showed that the two groups were significantly different in the mean score of feeding behavior (P= 0.001), feeding problems (P= 0.047) and weight gain (P<0.001). While in feeding duration (P= 0.53) and Frequency of feeding (P= 0.1) there was no significant difference. Of the 90 infants studied, more than 80% of them started feeding in the form of puree in the age group of 4-6 months. Conclusion Premature infants have more feeding problems and less weight gain than normal infants. It is recommended that the speech and language pathologist evaluate and intervene appropriately for oral skills and nutrition of premature infants admitted to the neonatal intensive care unit.

Global and Local Structure Preservation for Nonlinear High-dimensional Spectral Clustering

Abstract Spectral clustering is widely applied in real applications, as it utilizes a graph matrix to consider the similarity relationship of subjects. The quality of graph structure is usually important to the robustness of the clustering task. However, existing spectral clustering methods consider either the local structure or the global structure, which can not provide comprehensive information for clustering tasks. Moreover, previous clustering methods only consider the simple similarity relationship, which may not output the optimal clustering performance. To solve these problems, we propose a novel clustering method considering both the local structure and the global structure for conducting nonlinear clustering. Specifically, our proposed method simultaneously considers (i) preserving the local structure and the global structure of subjects to provide comprehensive information for clustering tasks, (ii) exploring the nonlinear similarity relationship to capture the complex and inherent correlation of subjects and (iii) embedding dimensionality reduction techniques and a low-rank constraint in the framework of adaptive graph learning to reduce clustering biases. These constraints are considered in a unified optimization framework to result in one-step clustering. Experimental results on real data sets demonstrate that our method achieved competitive clustering performance in comparison with state-of-the-art clustering methods.

Towards Optimized One-Step Clustering Approach in Wireless Sensor Networks

This paper introduces a nonlinear integer programming model for the clustering problem in wireless sensor networks, with a threefold contribution. First, all factors that may influence the energy consumption of clustering protocols, such as cluster-heads selection and distribution, are considered implicitly in the model. Second, an innovative fitness function that directly maximizes the WSN lifetime is proposed. Finally, a global optimum of the whole network lifespan clustering schemes is targeted. The proposed model is then solved by a particle swarm optimization meta-heuristic based algorithm. This algorithm follows a centralized one-step off-line approach, in which the clustering schemes of the whole network lifetime and their associated durations are computed at the initialization of the network operations. The one-step approach is enabled by an energy prediction mechanism that allows to reduce the costs of the periodic network re-clustering. Simulation results show clear enhancement in network lifespan and number of received data packets as compared to some state-of-the-art clustering approaches.

Comparison of the Effectiveness of Compassion-based Therapy and Acceptance-based Therapy and Commitment to Self-care Behavior and Glycosylated Hemoglobin in Patients With Type 2 Diabetes

Background: Diabetes is one of the most common diseases affecting peoplechr('39')s mental health and the body. Therefore, psychological interventions seem necessary to solve the problems caused by this disease. Objective: The present study aimed to compare the effectiveness of Compassion-focused Therapy (CFT) and Acceptance and Commitment Therapy (ACT), and commitment to self-care behavior and glycosylated hemoglobin in patients with type 2 diabetes at Tonekabon City Hospital. Materials and Methods: This clinical trial was a one-step cluster sampling study, including 200 patients who were randomly selected from all patients with type 2 diabetes in Tonekabon City Hospital and, at the same time, the scale of self-care behavior of Tobert, Glasgow, and Hamspon (2002). A total of 45 people were randomly selected and divided into three groups of 15 people, including two intervention groups and one control group, 12 compassionate therapy sessions, and 12 admission-based treatment sessions, each lasting 45 minutes. Meetings for each intervention were performed twice a week with an interval of 3 days. At the end of treatment, all three groups were retested. Results: Due to the comparison of the mean differences between the two treatment groups for self-care and glycosylated hemoglobin (5.012) (-2.145), respectively, Acceptance and Commitment Therapy was more effective than compassion-focused therapy. Conclusion: The results owed a positive trend and increased self-care behavior and balanced glycosylated hemoglobin level in the follow-up and effectiveness of both approaches and the superiority of the acceptance and commitment-based treatment approach. Therefore, this treatment can be used in different conditions to improve the lives of patients with type 2 diabetes.

Variational Deep Clustering of Wafer Map Patterns

In semiconductor manufacturing, several measurement data called wafer maps are obtained in the metrology steps, and the variations in the process are detected by analyzing the wafer map data. Hidden processes or equipment affecting the process quality variations can be found by comparing the process tracking history and clustered groups of similar wafer maps; thus, clustering analysis is very important to reduce the process quality variations. Currently, clustering wafer maps are becoming more difficult as the wafer maps are formed into more complex patterns along with high-dimensional data. For more effective clustering of complex and high-dimensional wafer maps, we implement a Gaussian mixture model to a variational autoencoder framework to extract features that are more suitable to the clustering environment, and a Dirichlet process is further applied in the variational autoencoder mixture framework for automated one-step clustering. The proposed method is validated using a real dataset from a global semiconductor manufacturing company, and we demonstrate that it is more effective than other competitive methods in determining the number of clusters and clustering wafer map patterns.

One-step spectral clustering based on self-paced learning

Aiming at traditional spectral clustering method still suffers from the following issues: 1) unable to handle the incomplete data, 2) two-step clustering strategies tend to perform poorly due to the heterogeneity between the similarity matrix learning model and the clustering model, 3) constructing the affinity matrix from original data which often contains noises and outliers. To address these issues, this paper proposes a robust one-step clustering method based on self-paced learning. Specifically, this paper first designs a missing value mapping matrix to handle missing data, and then employs self-paced regularizer to sort the importance of samples, reduce the interference of noise and outliers of the model, second, fusing affinity matrix learning and spectral decomposition into one model to achieve the purpose of one-step clustering. Experimental results on 8 real data sets, verified the effectiveness of our proposed one-step spectral clustering method, compared to state-of-the-art methods.

Spectral representation learning for one-step spectral rotation clustering

Conventional spectral clustering is generally divided into two main steps, 1) constructing a reliable spectral representation by similarity matrix or Laplacian matrix; 2) performing K-means clustering on the spectral representation. In this paper, we propose a novel spectral clustering algorithm to improve clustering performance by separately improving these two steps in a same learning framework. Specifically, we first utilize two dimensionality reduction methods to learn the robust low-dimensional spectral representation, and a hypergraph structure to make the spectral representation keep the high-order relation of original data. Furthermore, a spectral rotation clustering method is embedded into the spectral representation learning model to conduct one-step clustering, which effectively reduces the deviation of clustering and obtains a reliable clustering performance. Besides, an effective optimization algorithm is further proposed to solve the objective problem to have a fast convergence. Experimental analysis on real data sets showed that our proposed clustering method outperformed the classical and state-of-the-art spectral clustering methods in terms of four frequently-used clustering metrics.

Prevalence of violence against older adults and associated factors in Çanakkale, Turkey: A cross-sectional study.

This study was designed to determine the prevalence of domestic violence against older adults and the associated risk factors in Çanakkale, Turkey. A cross-sectional, population-based study was carried out, including 1230 individuals aged ≥65 years living in the city of Çanakkale, Turkey. The population of the study consisted of 73 367 individuals aged ≥65 years, living in Çanakkale. Sample selection was made with the one-step cluster sampling method. The data were collected by face-to-face interview. The study was approved by the local ethics committee, and written consent was taken from the participants. Of the participants, 4.1% had experienced physical violence, 2.5% were subjected to sexual abuse, 23.5% had undergone psychological violence and 12.2% had a history of economic violence. The exposure to any of the given violence types was 28.5%. Risk factors related to violence were being married, having children, educated partner, lack of economic independence, poor self-perceived health, administration of medications by others, feeling lonely, dissatisfaction with life, poor perception of family relations and not participating in family decisions. These results show that violence against older adults is a significant problem in a city in western Turkey. Therefore, an in-depth evaluation of the determined risk factors related to violence and actions for its prevention are warranted. Geriatr Gerontol Int 2020; 20: 66-71.

Relationship Between Participatory Management With Organizational Citizenship Behavior and Organizational Commitment of Nurses in Hospitals Affiliated With Mashhad University of Medical Sciences

Aims The present research was conducted in 2017-2018 with an aim to determin the relationship of participatory management style with Organizational Citizenship Behavior and organizational commitment of nurses in hospitals affiliated with Mashhad University of Medical Sciences. Methods & Materials The present research was a descriptive-correlational applied study. The statistical population of the study included all nurses working in hospitals affiliated with Mashhad University of Medical Sciences and it was comprised of 3538 members. A one-step cluster sampling was used in the present research. Using Cochran formula, 347 members of this community were selected as samples. In order to collect data, standard participatory management (Choopani), Organizational Citizenship Behavior (Organ and Konovsky), and organizational commitment (Allen and Meyer) questionnaires were used. Cronbach’s Alpha showed that the values for reliability of the three questionnaire were 0.902, 0.7140 and 0.795, respectively. The validities of the three questionnaires were confirmed by content validity and construct validity. SPSS18 and LISREL software were used to analyze the data. Findings The findings of the research showed that the relationship between participatory management style and organizational citizenship behavior was positive and significant (P=0.62), and the relationship between participatory management style and organizational commitment was also positive and significant (p=0.48). Considering the value of path coefficient, it was concluded that politeness dimension and respect dimension of organizational citizenship behavior (P=0.65) and emotional commitment dimension (P=0.53) have the most intense relationships with participatory management style. Conclusion The final results of the research suggested that participatory management was in a significant positive relationship with all dimensions of citizenship behavior an also, with the three dimensions of organizational commitment. therefore, it is recommended that the managers of treatment and healthcare centers adopt participatory management style.

An active learning brain storm optimization algorithm with a dynamically changing cluster cycle for global optimization

An active learning brain storm optimization (ALBSO) algorithm with a dynamically changing cluster cycle is proposed to enhance the performance of BSO algorithm. In the original BSO, a new individual is generated only by simply choosing one individual or two individuals from one cluster or two clusters with a certain probability. Although the diversity of the population is well maintained, owing to this way of random selection, it seriously affects the performance of BSO. In machine learning, instead of learning from random samples, a learner with active learning has the ability to select its own training data, such as the data of best value or mean value. Referring to the idea of active learning, the active learning strategy with intra-cluster learning and inter-cluster learning is integrated into BSO to elevate the solution accuracy and the convergence speed. In addition, to reduce the time burden of clustering operation, a dynamically changing cluster cycle with one-step clustering is adopted in the proposed ALBSO. Through experimental analysis by utilizing the active learning strategy with the dynamically changing cluster cycle, on the basis of the original diversity maintenance framework, the proposed ALBSO can balance the relationship of diversification and intensification, meanwhile, the time complexity is remarkably reduced. The experimental study on a set of 38 test functions and two real-world problems shows that the performance of BSO is significantly improved, and ALBSO is an effective method to optimize complex unimodal and multimodal functions in comparison with several other well-known algorithms.

Bioinspired "Active" Stealth Magneto-Nanomicelles for Theranostics Combining Efficient MRI and Enhanced Drug Delivery.

The mononuclear phagocyte system (MPS) with key roles in recognition and clearance of foreign particles, is a major constraint to nanoparticle-based delivery systems. The desire to improve the delivery efficiency has prompted the search for stealthy long-circulating nanoplatforms. Herein, we design an antiphagocytic delivery system with "active" stealth behavior for cancer theranostics combining efficient MRI and enhanced drug delivery. We modify self-peptide, a synthetic peptide for active immunomodulation, to biodegradable poly(lactide-glycolide)-poly(ethylene glycol) (PLGA-PEG), then utilize the self-assembly properties of PLGA-PEG to form nanomicelles that encapsulating iron oxide (IO) nanoparticles and anticancer drug paclitaxel (PTX). Through the interaction of self-peptide with the receptor SIRPα, which is expressed on phagocytes, the as-prepared nanomicelles can disguise as "self" to avoid being recognized as foreign particles by MPS, leading to improved blood circulation time and delivery efficiency. Compared to the "passive" stealth effect generating by PEG or zwitterionic polymers that only passively delay the physisorption of serum proteins to nanocarriers, the "active self" nanomicelles can more efficiently inhibit the MPS-mediated immune clearance and reduce "accelerated blood clearance" phenomenon. Furthermore, this one-step clustering of IO nanoparticles and loading of PTX endow the resulted magneto-nanomicelles with enhanced T2 MRI contrast performance and antitumor effect. We believe that this study provides a novel approach in designing of efficient stealth antiphagocytic delivery systems that resisting the MPS-mediated clearance for cancer theranostics.

A robust methodology for modal parameters estimation applied to SHM

The subject of structural health monitoring is drawing more and more attention over the last years. Many vibration-based techniques aiming at detecting small structural changes or even damage have been developed or enhanced through successive researches. Lately, several studies have focused on the use of raw dynamic data to assess information about structural condition. Despite this trend and much skepticism, many methods still rely on the use of modal parameters as fundamental data for damage detection. Therefore, it is of utmost importance that modal identification procedures are performed with a sufficient level of precision and automation. To fulfill these requirements, this paper presents a novel automated time-domain methodology to identify modal parameters based on a two-step clustering analysis. The first step consists in clustering modes estimates from parametric models of different orders, usually presented in stabilization diagrams. In an automated manner, the first clustering analysis indicates which estimates correspond to physical modes. To circumvent the detection of spurious modes or the loss of physical ones, a second clustering step is then performed. The second step consists in the data mining of information gathered from the first step. To attest the robustness and efficiency of the proposed methodology, numerically generated signals as well as experimental data obtained from a simply supported beam tested in laboratory and from a railway bridge are utilized. The results appeared to be more robust and accurate comparing to those obtained from methods based on one-step clustering analysis.

Image Cosegmentation via Saliency-Guided Constrained Clustering with Cosine Similarity

Cosegmentation jointly segments the common objects from multiple images. In this paper, a novel clustering algorithm, called Saliency-Guided Constrained Clustering approach with Cosine similarity (SGC3), is proposed for the image cosegmentation task, where the common foregrounds are extracted via a one-step clustering process. In our method, the unsupervised saliency prior is utilized as a partition-level side information to guide the clustering process. To guarantee the robustness to noise and outlier in the given prior, the similarities of instance-level and partition-level are jointly computed for cosegmentation. Specifically, we employ cosine distance to calculate the feature similarity between data point and its cluster centroid, and introduce a cosine utility function to measure the similarity between clustering result and the side information. These two parts are both based on the cosine similarity, which is able to capture the intrinsic structure of data, especially for the non-spherical cluster structure. Finally, a K-means-like optimization is designed to solve our objective function in an efficient way. Experimental results on two widely-used datasets demonstrate our approach achieves competitive performance over the state-of-the-art cosegmentation methods.

Prevalence of Confirmed Immediate Type Drug Hypersensitivity Reactions Among School Children

M Erkocoglu, A Kaya, E Civelek. Pediatr Allergy Immunol . 2013;24(2):160–167 To determine the frequency of immediate-type drug hypersensitivity reactions (iDHR) among children with parent-reported drug allergies. Eligible participants included all students attending grades 6 through 8 in 34 randomly selected schools in Ankara, Turkey, during the 2010–2011 school year. Investigators conducted a cross-sectional survey of students attending grades 6 through 8 to assess the prevalence of confirmed iDHR. One-step cluster sampling design was used to randomly select the 34 schools participating in …

ENTANGLEMENT GENERATION WITH GEOMETRIC OPERATIONS IN CAVITY QED

We propose a one-step cluster state generation scheme via atomic cavity QED. The current scheme is insensitive to the cavity mode thermal state as well as the atomic spontaneous emission since the gate operations are independent of the cavity mode states and laser power is sufficiently weak. In addition, the needed operation is of geometric nature, so it is robust against random operation errors.