Cluster Centroids Research Articles

Dynamic Water Stress Threshold Determination for Precision Deficit Irrigation Control using Progressive Clustering Approach

Precision deficit irrigation offers a solution to the increasing global pressure on freshwater resources occasioned by a rising demand for agricultural outputs to support a growing human population. Plant physiological responses to water deficit are describe in terms defining severity of water stress. Implementation of deficit irrigation control strategies capable of achieving the twin goals of maximizing potential yield and minimizing cumulative water consumption requires the identification of water deficit levels corresponding to significant stress thresholds to ensure memory initiation and prevent permanent damage to the crop. In this contribution machine learning approaches are implemented for dynamic identification of water stress thresholds during deficit irrigation of potted maize plants. K-means clustering is initally applied to delineate three zones of water stress described as ”no stress”, ”mild stress” and ”high stress” for chronologically segmented data points. Least squares-based polynomial curve fitting is employed to mathematically represent the dynamic progression of stress cluster centroids, with accuracy values ranging between 90% and 98%.

High-Order Semantic Decoupling Network for Remote Sensing Image Semantic Segmentation

Low-order features based on convolution kernel are easy to be distorted when encountering dramatic view angle transformation and atmospheric scattering in remote sensing images. To address this concern, this paper firstly proposes to operate semantic segmentation of remote sensing images based on the high-order information, which can represent the relative relationship of low-order features and is robust and stable when suffering feature distortion. Besides, semantic decouples have recently been well researched and have achieved significant improvement in image understanding. Thus, in this paper, a High-order Semantic Decoupling Network (HSDN) is proposed to disentangle features by semantics based on high-order features. Specifically, HSDN firstly represents each pixel by calculating the pixel-level affinity as a high-order feature and then clusters these pixels into different semantics. Afterward, an attention-like mask generation module is designed for both intra and inter semantic groups, leading to three kinds of masks, including the Semantic Decoupling Mask (SDM), which utilizes each high-order cluster centroid as a mask to compact features intra cluster and expand different inter clusters, so as to improve semantic disentangle performance to a better extent; Semantic Enhancement Mask (SEM), which records pixel-level relative correlation within a class to sufficiently exploit high-order features and could enhance feature robustness; and Boundary Supplementary Mask (BSM) which aims to process borderline pixels to reduce cluster errors. Finally, by applying masks on pixels both within classes and on borderlines, semantic decoupled features are generated and concatenated to realize segmentation. The quantitative and qualitative experiments are conducted on two large-scale fine-resolution remote sensing image datasets to demonstrate the significant performance of adopting high-order representation. Besides, we also implement numerous experiments to validate the effectiveness of the proposed semantic decouple framework in dealing with complicated and distortion-prone remote sensing image segmentation tasks.

ИЗМЕРЕНИЕ ЦЕЛЕДОСТИЖЕНИЯ СТРАН В ОБЛАСТИ УСТОЙЧИВОГО РАЗВИТИЯ В МЕЖДУНАРОДНОЙ СРЕДЕ

The paper studies the possibilities of using methods for measuring goal achievement in the field of sustainable development using the example of socio-economic systems on a global scale. Based on open access data, groups of variables were selected that characterize the development of countries in these areas for three time periods, and variables were identified that make it possible to construct the most stable and describable clusters of countries. An analysis of the shift of cluster centroids, the movement of countries across clusters was carried out, and the movement of countries towards the target state in the field of sustainable development was quantitatively measured. It has been proven that the results of economic growth in only half of countries lead to significant improvements in income distribution and the environment.

Automatically obtaining by methods of flow cytometry and cluster analysis simplified leukocyte formula

The leukocyte formula is the percentage of different groups of white blood cells. According to morphological features, three subpopulations can be distinguished among leukocytes: lymphocytes, monocytes and granulocytes. Granulocytes are divided into neutrophilic, eosinophilic, and basophilic cells. Automatic typologization of white blood cells is an unsolved problem, since at present, during cytometric research, the counting of the number of cells in various subpopulations of leukocytes is actually done manually, which in turn causes the subjectivity of the experiment and large values of errors in calculations. To solve this problem, attempts have been made repeatedly to use cluster analysis methods. In computational experiments, it was shown that the use of standard algorithms, such as the agglomerative methods, EM algorithm, DBSCAN, etc., does not allow to obtain the desired results. In recent years, a large number of research papers have been published describing specialized clustering algorithms for detecting and determining populations of white blood cells, some of them have found practical application, but the problems associated with the presence of a large amount of noise and different data density distribution during leukocyte clustering by flow cytometry methods remain relevant. The article considers an approach to constructing a strategy for automatic allocation of the main leukocyte subpopulations using a modified agglomerative centroid clustering method and discusses the results of computational experiments. The results of calculating the proportion of lymphocytes are compared “manually” and automatically using a modified centroid algorithm.

Graph identification of proteins in tomograms (GRIP-Tomo).

In this study, we present a method of pattern mining based on network theory that enables the identification of protein structures or complexes from synthetic volume densities, without the knowledge of predefined templates or human biases for refinement. We hypothesized that the topological connectivity of protein structures is invariant, and they are distinctive for the purpose of protein identification from distorted data presented in volume densities. Three-dimensional densities of a protein or a complex from simulated tomographic volumes were transformed into mathematical graphs as observables. We systematically introduced data distortion or defects such as missing fullness of data, the tumbling effect, and the missing wedge effect into the simulated volumes, and varied the distance cutoffs in pixels to capture the varying connectivity between the density cluster centroids in the presence of defects. A similarity score between the graphs from the simulated volumes and the graphs transformed from the physical protein structures in point data was calculated by comparing their network theory order parameters including node degrees, betweenness centrality, and graph densities. By capturing the essential topological features defining the heterogeneous morphologies of a network, we were able to accurately identify proteins and homo-multimeric complexes from 10 topologically distinctive samples without realistic noise added. Our approach empowers future developments of tomogram processing by providing pattern mining with interpretability, to enable the classification of single-domain protein native topologies as well as distinct single-domain proteins from multimeric complexes within noisy volumes.

Heart Disease Risk Identification using Machine Learning Techniques for a Highly Imbalanced Dataset: a Comparative Study

Heart disease has become one of the most prevailing universal diseases in the world today. It is estimated that 32% of all deaths worldwide are caused due to heart diseases. One of the major causes for this is that its extremely difficult even for medical practitioners to predict heart diseases as heart attacks as it is a complex task which requires a great amount of knowledge and experience. The number of deaths caused by heart diseases has hugely increased in the recent past. Machine learning has become one of the most popular areas in computer science where many complex problems have been addressed successfully specially in the field of medicine. In this study we trained multiple supervised classifiers namely’; Naïve Bayes, LightGBM, Decision Trees, Random Forest, XGBoost, K Nearest Neighbours and ADABoost and we compared the accuracies and identified what models perform better for heart disease prediction. We used the Behavioral Risk Factor Surveillance System (BRFSS) 2015 Heart Disease Health Indicators Dataset which was highly imbalanced and in order to address the class imbalance problem we used methods such as Synthetic Minority Over Sampling Technique (Smote) Sampling, Adaptive Synthetic Sampling, Random Over Sampling, Random Under Sampling, TomekLink, SmoteTomek, Smoteen and Cluster Centroid. According to the results obtained, we can conclude that the hybrid models such as Smoteen and SmoteTomek performed better than the other sampling methods.

On fly hybrid swarm optimization algorithms for clustering of streaming data

Clustering is an important data analysis technique for extracting knowledge and hidden patterns in the data. Recently hybrid clustering algorithms have been proposed to solve the local optimum and poor robustness problem due to improper selection of initial cluster centroids in the traditional clustering algorithms. In hybrid algorithms, clustering is solved as an optimization problem by invoking optimization algorithms to find the optimal cluster centroid. Many hybrid clustering algorithms integrating different swarm algorithms and traditional clustering algorithms have been proposed. However, these algorithms were not designed for the on-fly clustering of streaming data. This is necessary for real-time streaming requirements in financial domains like stock markets. This work proposes an on-fly hybrid swarm optimization algorithm for the clustering of streaming data.

Distributed Fuzzy Clustering Analysis of Time-Lapse Electrical Resistivity Tomography for Water Inrush Monitoring in Coal Mines

The majority of water inrush accidents in coal mines are caused by mining engineering activities. To avoid water inrush accidents, the Time-lapse Electrical Resistivity Tomography (TLERT) is applied to monitor water migration in fractured zone. A great challenge for the application of TLERT monitoring is the huge and numerous time series data sets generated by monitoring systems, which are difficult to process manually. This research proposed a distributed fuzzy clustering algorithm based on kernel function estimation to analyze TLERT images automatically. The resistivity date can be classified with different cluster centroids. The fuzzy c-means algorithm was chosen to display resistivity change. The algorithm was validated using a floor water inrush model. The results indicate that the water migration in the fractured zone can be monitored automatically and the edge of the resistivity changing area can be shown clearly.

A machine learning-based approach for mapping leachate contamination using geoelectrical methods

Leachate is the main source of pollution in landfills and its negative impacts continue for several years even after landfill closure. In recent years, geophysical methods are recognized as effective tools for providing an imaging of the leachate plume. However, they produce subsurface cross-sections in terms of individual physical quantities, leaving room for ambiguities on interpretation of geophysical models and uncertainties in the definition of contaminated zones. In this work, we propose a machine learning-based approach for mapping leachate contamination through an effective integration of geoelectrical tomographic data. We apply the proposed approach for the characterization of two urban landfills. For both cases, we perform a multivariate analysis on datasets consisting of electrical resistivity, chargeability and normalized chargeability (chargeability-to-resistivity ratio) data extracted from previously inverted model sections. By executing a K-Means cluster analysis, we find that the best partition of the two datasets contains ten and eleven classes, respectively. From such classes and also introducing a distance-based colour code, we get updated cross-sections and provide an easy and less ambiguous identification of the leachate accumulation zones. The latter turn out to be characterized by coordinate values of cluster centroids<3 Ωm and >27 mV/V and 11 mS/m. Our findings, also supported by borehole data for one of the investigation sites, show that the combined use of geophysical imaging and unsupervised machine learning is promising and can yield new perspectives for the characterization of leachate distribution and pollution assessment in landfills.

A Proposed Framework for Early Prediction of Schistosomiasis.

Schistosomiasis is a neglected tropical disease that continues to be a leading cause of illness and mortality around the globe. The causing parasites are affixed to the skin through defiled water and enter the human body. Failure to diagnose Schistosomiasis can result in various medical complications, such as ascites, portal hypertension, esophageal varices, splenomegaly, and growth retardation. Early prediction and identification of risk factors may aid in treating disease before it becomes incurable. We aimed to create a framework by incorporating the most significant features to predict Schistosomiasis using machine learning techniques. A dataset of advanced Schistosomiasis has been employed containing recovery and death cases. A total data of 4316 individuals containing recovery and death cases were included in this research. The dataset contains demographics, socioeconomic, and clinical factors with lab reports. Data preprocessing techniques (missing values imputation, outlier removal, data normalisation, and data transformation) have also been employed for better results. Feature selection techniques, including correlation-based feature selection, Information gain, gain ratio, ReliefF, and OneR, have been utilised to minimise a large number of features. Data resampling algorithms, including Random undersampling, Random oversampling, Cluster Centroid, Near miss, and SMOTE, are applied to address the data imbalance problem. We applied four machine learning algorithms to construct the model: Gradient Boosting, Light Gradient Boosting, Extreme Gradient Boosting and CatBoost. The performance of the proposed framework has been evaluated based on Accuracy, Precision, Recall and F1-Score. The results of our proposed framework stated that the CatBoost model showed the best performance with the highest accuracy of (87.1%) compared with Gradient Boosting (86%), Light Gradient Boosting (86.7%) and Extreme Gradient Boosting (86.9%). Our proposed framework will assist doctors and healthcare professionals in the early diagnosis of Schistosomiasis.

Application of clustering algorithms to detect abnormal state of pumping equipment

The article is devoted to detection of an abnormal and pre-emergency state of pumping equipment using clustering and anomaly search algorithms. A background for research is the need to search for and apply methods for assessing the technical condition and identifying emerging defects in an automated mode for a wide range of equipment that give results at an earlier stage than existing ones. To achieve this goal, we consider the use of machine learning methods to analyze the parameters of equipment operation over a certain time period in order to create an algorithm for detecting anomalies in data, which in this case will be signs of abnormal operation. This article discusses the application of clustering based on the k-means method. So, in this research three normal operating modes of pumping equipment were recognized in the synthesized data. Based on the analysis of the distribution of each measurement to the corresponding nearest cluster centroid, the maximum distance from each measurement point to it was determined, which further served as a criterion for classifying a certain measurement as data outliers. As a result of the analysis, five measurements were identified that correspond to the abnormal operation of oil pumping equipment. Also, the ranges of normal operation of the equipment were compiled for each of the measured parameters of its operation, which forms the threshold values for classifying the state of the equipment as an abnormal or emergency state. The proposed approach has such advantages as the possibility of full automation, adaptation to various operating modes of the equipment, no need to share data outside the pumping station, early detection of emerging defects and the onset of an emergency.

Composition analysis and identification of glass products based on Pearson correlation analysis

Ancient glass objects record the cultural exchanges between East and West along the Silk Road, but they have been subjected to varying degrees of weathering over time. First, to investigate the relationship between surface weathering and glass type, decoration and color of glass artifacts, this paper investigated the correlation using Kappa consistency test and judged the difference using chi-square test, and found that there was significant correlation and difference between surface weathering and glass type. For the statistical pattern between the presence or absence of weathering on the surface and the chemical composition content, the content of each chemical composition was compared between weathered and unweathered on the surface by visualizing its chemical composition content. Secondly, to analyze the classification pattern of high potassium and lead-barium glass, it is subclassed. In this paper, the chemical constituents relevant to the classification were first selected by Pearson correlation analysis, followed by subclassification of the two types of glass artifacts by establishing a K-Means clustering subclassification model based on the elbow method to determine the number of cluster centroids. Thirdly, in order to identify the unknown types of glass artifacts, this paper establishes a random forest regression algorithm for glass type identification model and derives the results by prediction. Finally, different categories of glass artifacts are analyzed to distinguish glass from four specific categories in terms of decoration, type, color and surface weathering, and the differences in chemical composition correlation relationships between different categories are obtained by comparing the chemical composition correlation tables of different categories.

Incorporating the genetic and firefly optimization algorithms into K-means clustering method for detection of porphyry and skarn Cu-related geochemical footprints in Baft district, Kerman, Iran

For the purpose of multi-element geochemical modeling of stream sediment data, we investigate the use of unsupervised clustering analysis (CA). For the various reasons including straightforward implementation, fast computation, and scaling to big dataset, the K-means (KM) algorithm was implemented to cluster the geochemical data to reveal anomalous populations linked to porphyry and skarn Cu deposits in Baft district, NE Iran. However, one of the biggest disadvantages of KM method is the randomly selection of cluster centroids which may increase the systemic uncertainty in unsupervised geochemical modeling and also run time. To address this, genetic (GA) and firefly (FA) metaheuristic optimization algorithms were incorporated into the KM method (namely GKM and FKM models) for determination of cluster centroids, and then, optimal definition of geospatial patterns of anomaly-background classes using clr-transformed values of stream sediment geochemical data. To do so, sample catchment basins (SCBs) of anomalous geochemical dataset were used to spatially map the anomaly populations derived from KM, GKM and FKM methods. We have used the advantages of quantitative evaluation measures namely normalized density index (NDI) and success-rate curves to assess the effectiveness of multi-element geochemical anomaly in determining exploratory targets. The results not only affirms that CA is a useful method to decompose the geochemical anomaly-background populations, but also hybridization of clustering methods via optimization algorithms can efficiently increase the certainty of mineralized zones to be used in further exploration stages.

Analysis of Power Load Characteristics Based on Adaptive Ensemble Clustering Algorithm

With the growing number of power users and more flexible power consumption, how to cluster the power load curves efficiently becomes particularly important. In order to improve the accuracy, effectiveness and rapidity of load clustering, an adaptive integrated fuzzy clustering algorithm was proposed in this paper. Firstly, the initial clustering centroids were obtained by the improved DPC algorithm; then, under the dual guarantee of Euclidean distance and membership, FCM algorithm was used to cluster load curves; finally, the optimal number of clusters was obtained by the improved adaptive method in the iterative process; thus, the autonomous and accurate clustering of power load curve was realized. The proposed algorithm, DPC algorithm and FCM algorithm were applied to the load clustering experiment of power system respectively. The comparative analysis shows that this algorithm is effective and superior for load curve clustering.

Enhanced Firefly-K-Means Clustering with Adaptive Mutation and Central Limit Theorem for Automatic Clustering of High-Dimensional Datasets

Metaheuristic algorithms have been hybridized with the standard K-means to address the latter’s challenges in finding a solution to automatic clustering problems. However, the distance calculations required in the standard K-means phase of the hybrid clustering algorithms increase as the number of clusters increases, and the associated computational cost rises in proportion to the dataset dimensionality. The use of the standard K-means algorithm in the metaheuristic-based K-means hybrid algorithm for the automatic clustering of high-dimensional real-world datasets poses a great challenge to the clustering performance of the resultant hybrid algorithms in terms of computational cost. Reducing the computation time required in the K-means phase of the hybrid algorithm for the automatic clustering of high-dimensional datasets will inevitably reduce the algorithm’s complexity. In this paper, a preprocessing phase is introduced into the K-means phase of an improved firefly-based K-means hybrid algorithm using the concept of the central limit theorem to partition the high-dimensional dataset into subgroups of randomly formed subsets on which the K-means algorithm is applied to obtain representative cluster centers for the final clustering procedure. The enhanced firefly algorithm (FA) is hybridized with the CLT-based K-means algorithm to automatically determine the optimum number of cluster centroids and generate corresponding optimum initial cluster centroids for the K-means algorithm to achieve optimal global convergence. Twenty high-dimensional datasets from the UCI machine learning repository are used to investigate the performance of the proposed algorithm. The empirical results indicate that the hybrid FA-K-means clustering method demonstrates statistically significant superiority in the employed performance measures and reducing computation time cost for clustering high-dimensional dataset problems, compared to other advanced hybrid search variants.

Mapping Phonation Types by Clustering of Multiple Metrics

For voice analysis, much work has been undertaken with a multitude of acoustic and electroglottographic metrics. However, few of these have proven to be robustly correlated with physical and physiological phenomena. In particular, all metrics are affected by the fundamental frequency and sound level, making voice assessment sensitive to the recording protocol. It was investigated whether combinations of metrics, acquired over voice maps rather than with individual sustained vowels, can offer a more functional and comprehensive interpretation. For this descriptive, retrospective study, 13 men, 13 women, and 22 children were instructed to phonate on /a/ over their full voice range. Six acoustic and EGG signal features were obtained for every phonatory cycle. An unsupervised voice classification model created feature clusters, which were then displayed on voice maps. It was found that the feature clusters may be readily interpreted in terms of phonation types. For example, the typical intense voice has a high peak EGG derivative, a relatively high contact quotient, low EGG cycle-rate entropy, and a high cepstral peak prominence in the voice signal, all represented by one cluster centroid that is mapped to a given color. In a transition region between the non-contacting and contacting of the vocal folds, the combination of metrics shows a low contact quotient and relatively high entropy, which can be mapped to a different color. Based on this data set, male phonation types could be clustered into up to six categories and female and child types into four. Combining acoustic and EGG metrics resolved more categories than either kind on their own. The inter- and intra-participant distributional features are discussed.

A dynamic multi-objective evolutionary algorithm based on prediction

Abstract The dynamic multi-objective optimization problem (DMOP) is a common problem in optimization problems; the main reasons are the objective’s conflict and environment changes. In this paper, we provide a prediction approach based on diversity screening and special point prediction (DSSP) to tackle the dynamic optimization issue. First, we introduce a decision variable clustering and screening strategy that clusters the decision space of the non-dominated solution set to find the cluster centroids and then employs a decision variable screening strategy to filter out solutions that have an impact on the distribution of individuals. This approach can broaden the range of dynamic multi-objective optimization algorithms. Second, an approach for predicting special points is suggested. The algorithm’s convergence is improved following environmental changes by forecasting the special point tracking Pareto front in the object space. Finally, the forward-looking center points are used to predict the non-dominated solution set and eliminate the useless individuals in the population. The prediction strategy can help the solution set converge while maintaining its diversity, which is compared with the four other state-of-the-art strategies. Our experimental results demonstrate that the proposed algorithm, DSSP, can effectively tackle DMOPs.

Data clustering using leaders and followers optimization and differential evolution

Data clustering is an important research topic in data mining. Although cluster analysis based on optimization algorithms has attracted great attention, optimization-based techniques face difficulties due to the non-linear objective function and complicated search space. Leaders and followers optimization (LaF) introduced in the 2015 IEEE Congress on Evolutionary Computation, and differential evolution algorithm (DE) are two efficient evolutionary computation methods, and they own some special advantages. The key power of LaF is the exploration in multi-modal search spaces, but it has a poor performance in the exploitation. On the other hand, DE based on the DE/best/1 mutation operator significantly promotes the exploitation process. In this study, the strong properties of LaF and DE are combined to balance exploration and exploitation in the search space to discover the cluster centroids. Besides, the proposed clustering method, i.e., LaF-DE, does not need parameter settings, unlike the existing optimization-based partitional clustering methods. Hence, this study proposes a straightforward, parameter-free, and efficient novel hybrid algorithm for the optimization-based partitional data clustering problem. Many experiments on the functions from CEC2017 test suite show that LaF-DE has better optimization performance and higher stability than the state-of-the-art metaheuristic algorithms. LaF-DE has been compared with well-known clustering techniques on the UCI and Shape datasets. The experimental results and statistical tests indicate that LaF-DE outperforms the well-known partitional clustering methods on 8 of 12 datasets in terms of internal performance metrics. Besides, LaF-DE performs better than density peaks clustering on 9 of 12 datasets in terms of external performance metrics.

Facial expression recognition is linked to clinical and neurofunctional differences in autism

BackgroundDifficulties in social communication are a defining clinical feature of autism. However, the underlying neurobiological heterogeneity has impeded targeted therapies and requires new approaches to identifying clinically relevant bio-behavioural subgroups. In the largest autism cohort to date, we comprehensively examined difficulties in facial expression recognition, a key process in social communication, as a bio-behavioural stratification biomarker, and validated them against clinical features and neurofunctional responses.MethodsBetween 255 and 488 participants aged 6–30 years with autism, typical development and/or mild intellectual disability completed the Karolinska Directed Emotional Faces task, the Reading the Mind in the Eyes Task and/or the Films Expression Task. We first examined mean-group differences on each test. Then, we used a novel intersection approach that compares two centroid and connectivity-based clustering methods to derive subgroups based on the combined performance across the three tasks. Measures and subgroups were then related to clinical features and neurofunctional differences measured using fMRI during a fearful face-matching task.ResultsWe found significant mean-group differences on each expression recognition test. However, cluster analyses showed that these were driven by a low-performing autistic subgroup (~ 30% of autistic individuals who performed below 2SDs of the neurotypical mean on at least one test), while a larger subgroup (~ 70%) performed within 1SD on at least 2 tests. The low-performing subgroup also had on average significantly more social communication difficulties and lower activation in the amygdala and fusiform gyrus than the high-performing subgroup.LimitationsFindings of autism expression recognition subgroups and their characteristics require independent replication. This is currently not possible, as there is no other existing dataset that includes all relevant measures. However, we demonstrated high internal robustness (91.6%) of findings between two clustering methods with fundamentally different assumptions, which is a critical pre-condition for independent replication.ConclusionsWe identified a subgroup of autistic individuals with expression recognition difficulties and showed that this related to clinical and neurobiological characteristics. If replicated, expression recognition may serve as bio-behavioural stratification biomarker and aid in the development of targeted interventions for a subgroup of autistic individuals.

State-monitoring for abnormal vibration of bridge cables focusing on non-stationary responses: From knowledge in phenomena to digital indicators

Input-output characteristics in an event of the abnormal vibration of a kilometer-level railway-highway-combined cable-stayed bridge's cables under in-service winds are deeply investigated. The knowledge of commonality that cables' abnormal vibration exists multiple independent non-stationary sections in time series with high-amplitude and quasi-single-frequency is summarized. An automatic extraction of non-stationary section of abnormal vibration is conducted via Gaussian mixture modeling of the envelope of time series signal. A new process of modal parameter identification is presented using the data of non-stationary section after bandpass filtering and its last descent. It is demonstrated that the identified damping ratio of cables with abnormal vibration will be below 0.05%. Each abnormal non-stationary vibration's frequency, damping ratio, and wind speed are clustered into corresponding natural vibration modes. Correlation model of wind speed-vibration frequency is fitted by data centroid of clusters to predict the possible-occurrence frequency of an abnormal non-stationary vibration before it is fully completed.