Search

In this paper, a new data-driven autonomous fuzzy clustering (AFC) algorithm is proposed for static data clustering. Employing a Gaussian-type membership function, AFC firstly uses all the data samples as micro-cluster medoids to assign memberships to each other and obtains the membership matrix. Based on this, AFC chooses these data samples that represent local models of data distribution as cluster medoids for initial partition. It then continues to optimize the cluster medoids iteratively to obtain a locally optimal partition as the algorithm output. Moreover, an online extension is introduced to AFC enabling the algorithm to cluster streaming data chunk-by-chunk in a one pass manner. Numerical examples based on a variety of benchmark problems demonstrate the efficacy of the AFC algorithm in both offline and online application scenarios, proving the effectiveness and validity of the proposed concept and general principles.

We present new algorithms to classify structural ensembles of macromolecules, based on the recently proposed extended similarity measures. Molecular Dynamics provides a wealth of structural information on systems of biologically interest. As computer power increases we capture larger ensembles and larger conformational transitions between states. Typically, structural clustering provides the statistical mechanics treatment of the system to identify relevant biological states. The key advantage of our approach is that the newly introduced extended similiarity indices reduce the computational complexity of assessing the similarity of a set of structures from O(N2) to O(N). Here we take advantage of this favorable cost to develop several highly efficient techniques, including a linear-scaling algorithm to determine the medoid of a set (which we effectively use to select the most representative structure of a cluster). Moreover, we use our extended similarity indices as a linkage criterion in a novel hierarchical agglomerative clustering algorithm. We apply these new metrics to analyze the ensembles of several systems of biological interest such as folding and binding of macromolecules (peptide,protein,DNA -protein). In particular, we design a new workflow that is capable of identifying the most important conformations contributing to the protein folding process. We show excellent performance in the resulting clusters (surpassing traditional linkage criteria), along with faster performance and an efficient cost-function to identify when to merge clusters.

The latent demand to optimize costs and customer service has been fostered in the current economic situations, characterized by high competitiveness and disruption in supply chains, placing inventories as a vital sector with significant potential to implement improvements in firms. Inventory management that is done correctly has a favorable impact on logistics performance indexes. Warehousing operations account for around 15% of logistics expenditures in terms of dollars. This article employs a method based on the Partitioning Around Medoids algorithm that incorporates, in a novel way, the application of a strategy for locating the optimal picking point based on cluster classification, taking into account the qualitative and quantitative factors that have the greatest impact or priority on inventory management in the company. The results obtained with this model improve the routes of distributed materials based on the identification of their characteristics such as the frequency of collection and handling of materials, allowing for the reorganization and expansion of storage capacity of the various SKUs, moving from a classification by families to a cluster classification. This article shows a suggestion for a warehouse distribution design using data mining techniques, which uses indicators and key qualities for operational success for a case study in a corporation, as well as an approach to improve inventory management decision-making.

Efficient big data clustering is a requirement for massive data generating in this digitalized connected world. The traditional clustering algorithms do not scale over massively sized and highly unstructured big data. Thus, to obtain efficiency in clustering big data new architecture and programming paradigm is required. In this work, a novel MapReduce-based Fuzzy C-Medoids clustering algorithm is designed and experimented with to cluster big data repository of documents datasets. The performance of the proposed algorithm is experimentally evaluated for different-sized Hadoop cluster sizes and different-sized document datasets. The algorithm is found to be scalable and efficient in performing clustering jobs.

CNNs, RNNs, GCNs, and CapsNets have shown significant insights in representation learning and are widely used in various text mining tasks such as large-scale multi-label text classification. Most existing deep models for multi-label text classification consider either the non-consecutive and long-distance semantics or the sequential semantics. However, how to coherently take them into account is still far from studied. In addition, most existing methods treat output labels as independent medoids, ignoring the hierarchical relationships among them, which leads to a substantial loss of useful semantic information. In this paper, we propose a novel hierarchical taxonomy-aware and attentional graph capsule recurrent CNNs framework for large-scale multi-label text classification. Specifically, we first propose to model each document as a word order preserved graph-of-words and normalize it as a corresponding word matrix representation preserving both the non-consecutive, long-distance and local sequential semantics. Then the word matrix is input to the proposed attentional graph capsule recurrent CNNs for effectively learning the semantic features. To leverage the hierarchical relations among the class labels, we propose a hierarchical taxonomy embedding method to learn their representations, and define a novel weighted margin loss by incorporating the label representation similarity. Extensive evaluations on three datasets show that our model significantly improves the performance of large-scale multi-label text classification by comparing with state-of-the-art approaches.

A VANET or vehicular Ad Hoc Network is known for its fast topology transition and node mobility, contributing to its attributes as an ad hoc network. The aspect of gathering the nodes, making this system extremely vigorous is known as clustering. However, in certain cases, it is not possible to keep track of the nodes which will results in network issues due to energy insufficiency during execution. Hence this will lead to primary energy management problems faced during the routing protocol which take into consideration the node lifetime. To address this discrepancy, we have proposed a novel optimization technique based on clustering. It has been observed that the proposed methodology will further improve the effectiveness of V2V communication. In this paper, clustering of the vehicle nodes is done using K-Medoid clustering model and are then used to improve energy efficiency. A metaheuristic algorithm is used to establish an energy efficient communication methodology. Based on the simulation analysis performed, it is seen that this methodology requires lesser execution time and improves the nodes’ energy efficiency.

Context. The analytical procedures used in the audit are currently based on data mining techniques. The work solves the problem of increasing the efficiency and effectiveness of analytical audit procedures by clustering based on spectral decomposition. The object of the research is the process of auditing the compliance of payment and supply sequences for raw materials. Objective. The aim of the work is to increase the effectiveness and efficiency of the audit due to the method of spectral clustering of sequences of payment and supply of raw materials while automating procedures for checking their compliance. Method. The vectors of features are generated for the objects of the sequences of payment and supply of raw materials, which are then used in the proposed method. The created method improves the traditional spectral clustering method by automatically determining the number of clusters based on the explained and sample variance rule; automatic determination of the scale parameter based on local scaling (the rule of K-nearest neighbors is used); resistance to noise and random outliers by replacing the k-means method with a modified PAM method, i.e. replacing centroid clustering with medoid clustering. As in the traditional approach, the data can be sparse, and the clusters can have different shapes and sizes. The characteristics of evaluating the quality of spectral clustering are selected. Results. The proposed spectral clustering method was implemented in the MATLAB package. The results obtained made it possible to study the dependence of the parameter values on the quality of clustering. Conclusions. The experiments carried out have confirmed the efficiency of the proposed method and allow us to recommend it for practical use in solving audit problems. Prospects for further research may lie in the creation of intelligent parallel and distributed computer systems for general and special purposes, which use the proposed method for segmentation, machine learning and pattern recognition tasks.

Data analytics methods have been increasingly applied to understanding materials chemistry, processing due to the manufacturing approach, and uni-axial and cyclic property relationships in the highly complex space of alloy design. There are several benefits to applying data analytics to this space, including the ability to manage non-linearities in the responses of the alloy attributes and the resulting mechanical properties. However, key difficulties in applying and understanding the results of data analytics include the often lack of reported assumptions and data processing steps necessary to improve interpretation and reproducibility in derived results. In this work, the methods used to generate clustering and correlation analyses for experimental 9% Cr ferritic-martensitic steel data were investigated and the resulting implications for mechanical property predictions were assessed. This work uses principal component analysis, partitioning around medoids, t-SNE, and k-means clustering to investigate trends in composition, processing and microstructure information with creep and tensile properties, building on work done previously using a smaller version of the same dataset. The initial assumptions, preprocessing steps and methods are investigated and outlined in order to depict the fine level of detail required to convey the steps taken to process data and produce analytical results. The variations in the resulting analyses are explored due to the influence of new and more varied data.

In wireless sensor networks, sensor nodes, the miniature embedded devices, have limitation of energy, storage, computing, and etc. One of the tasks of the nodes is to use their limited resources to complete work efficiently. Choosing high quality link communication can effectively save energy. In this paper, we propose a link quality estimation model that is based on deep forest. To avoid a noise sample becoming a center point in the clustering, we use an improved K-medoids algorithm based on step increasing and optimizing medoids (INCK) when dividing the link quality grades. During the sample preprocessing stage, the Pauta criterion is used to delete the noise link samples, and we fill the mean value of each grade into the missing values. The feature extraction performance of deep forest is improved by combining the stratified sampling to change the unbalance distribution of link quality samples. And then the Stratified Sampling Cascade Forest link quality estimation (SCForest-LQE) is constructed by combining stratified sampling with cascade forest. The experiments are conducted in three real application scenarios. Compared with the existing six link quality estimation models, SCForest-LQE has better estimation performance and stability.

The k-nearest-neighbor (kNN) decision rule is a simple and robust classifier for text categorization. The performance of kNN decision rule depends heavily upon the value of the neighborhood parameter k. The method categorize a test document even if the difference between the number of members of two competing categories is one. Hence, choice of k is crucial as different values of k can change the result of text categorization. Moreover, text categorization is a challenging task as the text data are generally sparse and high dimensional. Note that, assigning a document to a predefined category for an arbitrary value of k may not be accurate when there is no bound on the margin of majority voting. A method is thus proposed in spirit of the nearest-neighbor decision rule using a medoid-based weighting scheme to deal with these issues. The method puts more weightage on the training documents that are not only lie close to the test document but also lie close to the medoid of its corresponding category in decision making, unlike the standard nearest-neighbor algorithms that stress on the documents that are just close to the test document. The aim of the proposed classifier is to enrich the quality of decision making. The empirical results show that the proposed method performs better than different standard nearest-neighbor decision rules and support vector machine classifier using various well-known text collections in terms of macro- and micro-averaged f-measure.

The wireless sensor networks have become a very hot topic of research in the recent years because of their wide range of applications such as industrial and agricultural monitoring, military surveillance, smart homes etc. These sensors can also be used in locations that are potentially hazardous to the human beings or are just out of our reach at this moment of time. A wireless sensor network is collection of large number of individual sensor nodes. A sensor usually comprises of components for sensing the environment, processing, communicating and a power supply. The major limiting factor of the wireless sensor networks is the limited amount of power that each of the sensors can carry and also the energy in these sensors cannot be replenished easily. So, the major design challenge in a wireless sensor network has always been about reduction in the consumption of energy by the sensors. Clustering is one of the popular methods to reduce energy consumption in wireless sensor networks. Here, we propose a scheme to decrease the energy consumption and prolong the lifetime of wireless sensor network. The main idea behind the scheme is that we try to minimise the communication distance between the individual sensor nodes using the clustering technique.

The aim of the work is to identify a clustering structure for the 20 Italian regions according to the main variables related to COVID-19 pandemic. Data are observed over time, spanning from the last week of February 2020 to the first week of February 2021. Dealing with geographical units observed at several time occasions, the proposed fuzzy clustering model embedded both space and time information. Properly, an Exponential distance-based Fuzzy Partitioning Around Medoids algorithm with spatial penalty term has been proposed to classify the spline representation of the time trajectories. The results show that the heterogeneity among regions along with the spatial contiguity is essential to understand the spread of the pandemic and to design effective policies to mitigate the effects.

Background: Heterogeneity in Acute Respiratory Distress Syndrome (ARDS), as a consequence of its non-specific definition, has led to a multitude of negative randomised controlled trials (RCTs). Investigators have sought to identify heterogeneity of treatment effect (HTE) in RCTs using clustering algorithms. We evaluated the proficiency of several commonly-used machine-learning algorithms to identify clusters where HTE may be detected. Methods: Five unsupervised: Latent class analysis (LCA), K-means, partition around medoids, hierarchical, and spectral clustering; and four supervised algorithms: model-based recursive partitioning, Causal Forest (CF), and X-learner with Random Forest (XL-RF) and Bayesian Additive Regression Trees were individually applied to three prior ARDS RCTs. Clinical data and research protein biomarkers were used as partitioning variables, with the latter excluded for secondary analyses. For a clustering schema, HTE was evaluated based on the interaction term of treatment group and cluster with day-90 mortality as the dependent variable. Findings: No single algorithm identified clusters with significant HTE in all three trials. LCA, XL-RF, and CF identified HTE most frequently (2/3 RCTs). Important partitioning variables in the unsupervised approaches were consistent across algorithms and RCTs. In supervised models, important partitioning variables varied between algorithms and across RCTs. In algorithms where clusters demonstrated HTE in the same trial, patients frequently interchanged clusters from treatment-benefit to treatment-harm clusters across algorithms. LCA aside, results from all other algorithms were subject to significant alteration in cluster composition and HTE with random seed change. Removing research biomarkers as partitioning variables greatly reduced the chances of detecting HTE across all algorithms. Interpretation: Machine-learning algorithms were inconsistent in their abilities to identify clusters with significant HTE. Protein biomarkers were essential in identifying clusters with HTE. Investigations using machine-learning approaches to identify clusters to seek HTE require cautious interpretation. Funding: NIGMS R35 GM142992 (PS), NHLBI R35 HL140026 (CSC); NIGMS R01 GM123193, Department of Defense W81XWH-21-1-0009, NIA R21 AG068720, NIDA R01 DA051464 (MMC)

In a centralized cooperative spectrum sensing (CSS) system, it is vulnerable to malicious users (MUs) sending fraudulent sensing data, which can severely degrade the performance of CSS system. To solve this problem, we propose sensing data fusion schemes based on K-medoids and Mean-shift clustering algorithms to resist the MUs sending fraudulent sensing data in this paper. The cognitive users (CUs) send their local energy vector (EVs) to the fusion center which fuses these EVs as an EV with robustness by the proposed data fusion method. Specifically, this method takes a Medoids of all EVs as an initial value and searches for a high-density EV by iteratively as a representative statistical feature which is robust to malicious EVs from MUs. It does not need to distinguish MUs from CUs in the whole CSS process and considers constraints imposed by the CSS system such as the lack of information of PU and the number of MUs. Furthermore, we propose a global decision framework based on fast K-medoids or Mean-shift clustering algorithm, which is unaware of the distributions of primary user (PU) signal and environment noise. It is worth noting that this framework can avoid the derivation of threshold. The simulation results reflect the robustness of our proposed CSS scheme.

In our work, we cluster the data collected on pregnancy women through hospitals, into three different categories such as elective LSCS, emergency LSCS and normal delivery. We aim to identify outliers so that we can predict the complications that can occur during pregnancy. These complications can even lead to maternal death. Clustering is performed by the aid of k-means, and k-medoid procedures which are implemented in windows form application to run in Microsoft Visual Studio, a comparison is provided on its performance and efficiency between both the algorithms and also the outlier, i.e. normal delivery cases are detected and depicted. From our work, we can clearly say that K-Means works better when the dataset is between the range of 50 – 100. Suppose the data set is greater than 500 then K-medoid works efficiently. In our work, we are considering various maternity cases. Here we are detecting normal delivery cases as an outlier.

This paper presents a data mining study and cluster analysis of social data obtained on small producers and family farmers from six country cities in Ceará state, northeast Brazil. The analyzed data involve demographic, economic, agriculture and food insecurity information. The goal of the study is to establish profiles for the small producer families that reside in the region and to identify relevant features which differentiate these profiles. Moreover, we provide an efficient data mining methodology for analysis of social data sets which is capable of handling its natural challenges, such as mixed variables and abundance of null values. We use the Silhouette method for the estimation of the best number of natural groups within the data, along with the Partitioning Around Medoids clustering algorithm in order to compute the profiles. The Correlation-Based Feature Selection method is used to identify which social criteria are the most important to differentiate the families from each profile. Classification models based on support vector machines, multilayer perceptron and decision trees were developed aiming to predict in which of the identified clusters an arbitrary family would be best fit. We obtained a good separation of the families into two clusters, and a multilayer perceptron model with approximately 93.5% prediction accuracy. Keywords: Clustering, Social data, Classification, Pam, Data mining

This study investigates the use of clustering methodologies as a means of reducing spatio-temporal wind speed data into statistically representative classes of temporal profiles for further processing and interpretation. The clustering methodologies are applied to the high-resolution spatio-temporal, meso-scale renewable energy resource dataset produced for Southern Africa by the Council of Scientific and Industrial Research. This large dataset incorporates thousands of coordinates and represents a challenge from a computational perspective. This dataset can be reduced by applying clustering techniques to classify the temporal wind speed profiles into categories with similar statistical properties. Various clustering algorithms are considered, with the view to compare the performances of these algorithms for large wind resource datasets, namely k-means, partitioning around medoids, the clustering large applications algorithm, agglomerative clustering, the divisive analysis algorithm and fuzzy c-means clustering. Two distance measures are considered, namely the Euclidean distance and Pearson correlation distance. The validation metrics evaluated in the investigation includes the silhouette coefficient, the Calinski-Harabasz index and the Dunn index. Case study results are presented for the Komsberg Renewable Energy Development Zone, located in Western Cape, South Africa. This zone is selected based on the high mean wind speed and large standard deviation exhibited by the temporal wind speed profiles associated with the zone. The effects of seasonal variation in the temporal wind speed profiles are considered by partitioning the input dataset in accordance with the low and high demand seasons defined by the Megaflex Time of Use tariff. The clustered wind resource maps produced by the proposed methodology represent a valuable input dataset for further studies such as siting and the optimal geographical allocation of wind generation capacity to reduce the variability and ramping effects that are inherent to wind energy.

High dimensional data analysis within relational database management systems (RDBMS) is challenging because of inadequate support from SQL. Currently, subspace clustering of high dimensional data is implemented either outside DBMS using wrapper code or inside DBMS using SQL User Defined Functions/Aggregates(UDFs/UDAs). However, both these approaches have potential disadvantages from performance, resource usage, and security perspective for voluminous and frequently updated data. Hence, we propose an efficient querying system, named SubspaceDB, that implements subspace clustering directly within an RDBMS. SubspaceDB provides a novel set of query operators, each with an optimization objective, to facilitate interactive analysis for subspace clustering. The query operators focus on retrieving optimal answers to four key query types : (a) Medoid queries, (b) Neighbourhood queries, (c) Partial similarity queries, and (d) Prominence queries, that aid the formation of subspace clusters. Experimental studies on real and synthetic databases of size 15 M tuples and 104 attributes show that our proposed approach SubspaceDB can be over 10 times faster as compared to a conventional wrapper-based or SQL UDF approach. The proposed approach is also efficient in retrieving at least 50% data with performance improvement of at least 25%.

The definition of management zones (MZs) in agricultural fields has been suggested as an economically viable approach to precision agriculture. The most used methods for this task are the cluster analysis algorithms Fuzzy C-means (FCM) and K-means. However, some studies have presented that these algorithms may not provide the best classes to define MZs. Considering that these studies presented comparisons of only a few clustering methods, the objective of our research was to evaluate 20 algorithms for defining MZs, including more than 10 methods that have not been investigated in the literature for this purpose. The following algorithms were evaluated: Average Linkage, Bagged Clustering, Centroid Linkage, Clara, Complete Linkage, Diana, Fanny, FCM, Fuzzy C-shells, Hard Competitive Learning, Hybrid Hierarchical Clustering, K-means, McQuitty's Method, Median Linkage, Neural Gas, Partitioning Around Medoids, Single Linkage, Spherical K-means, Unsupervised Fuzzy Competitive Learning and Ward's Method. The evaluation was conducted with data obtained between 2010 and 2015 from three commercial agricultural fields cultivated with soya bean and maize in Brazil. The results of the analysis of variance suggested a division of the three fields into two classes with significantly different yields and a division of one of the fields into three classes. These divisions were satisfactorily performed using 17 algorithms, but McQuitty's Method and Fanny were considered to be the best choices because they produced the largest reductions in the variance of the yield in the three fields. In addition, they generated classes with high internal homogeneity and delimited MZs without spatial fragmentation.

Recently, learning only from ordinal information of the type “itemxis closer to itemythan to itemz” has received increasing attention in the machine learning community. Such triplet comparisons are particularly well suited for learning from crowdsourced human intelligence tasks, in which workers make statements about the relative distances in a triplet of items. In this paper, we systematically investigate comparison-based centrality measures on triplets and theoretically analyze their underlying Euclidean notion of centrality. Two such measures already appear in the literature under opposing approaches, and we propose a third measure, which is a natural compromise between these two. We further discuss their relation to statistical depth functions, which comprise desirable properties for centrality measures, and conclude with experiments on real and synthetic datasets for medoid estimation and outlier detection.

Sentiment analysis explores the views, perceptions and feelings of people concerning entities like subjects, goods, organizations, resources and individuals. The opinion of some people in social network influences the opinion behavior and thoughts of other people. They are known as influential user. In this article, both the sentiment analysis and identification of influential user are proposed. Initially, Twitter data are preprocessed by proposing weighted partition around medoids (WPAM) with artificial cooperative search (WPAM-ACS) which extracts topics from Twitter data through dynamic clustering (DC). For sentiment classification, NLP has been used in many works. The main issue of using NLP for sentiment classification is that many languages do not have the adequate resources to develop NLP models. So, a fuzzy deep neural network (FDNN) is proposed in this paper for sentiment classification, because FDNN effectively handles the uncertainties and noises in tweet data than other state of the arts. Emotional conformity is a metric that refers to how people from an emotional point of view agree with another person. It is given as additional input to FDNN along with the tweets for sentiment classification. Finally, influential users are detected by temporal influential model (TIM) formulated as likelihood function using incremental logistic regression (ILLR) in which user’s opinion sequence is considered for identification of influential user. In the experimental results, sentiment analysis is evaluated in terms of precision, recall and F-measure and proved that the proposed DC–FDNN sentiment classification is better than fixed clustering and NLP (FC–NLP)-based sentiment classification. Influential user detection using TIM-ILLR on opinion sequences which are identified by DC-FDNN is evaluated in terms of accuracy and proved that TIM-ILLR is better than other methods such as maximum likelihood estimation (MLE), support vector regression (SVR) and logistic regression (LR).

The Classroom Observation Protocol for Undergraduate STEM (COPUS) provides descriptive feedback to instructors by capturing student and instructor behaviors occurring in the classroom. Due to the increasing prevalence of COPUS data collection, it is important to recognize how researchers determine whether groups of courses or instructors have unique classroom characteristics. One approach uses cluster analysis, highlighted by a recently developed tool, the COPUS Analyzer, that enables the characterization of COPUS data into one of seven clusters representing three groups of instructional styles (didactic, interactive, and student centered). Here, we examine a novel 250 course data set and present evidence that a predictive cluster analysis tool may not be appropriate for analyzing COPUS data. We perform a de novo cluster analysis and compare results with the COPUS Analyzer output and identify several contrasting outcomes regarding course characterizations. Additionally, we present two ensemble clustering algorithms: 1) k-means and 2) partitioning around medoids. Both ensemble algorithms categorize our classroom observation data into one of two clusters: traditional lecture or active learning. Finally, we discuss implications of these findings for education research studies that leverage COPUS data.

e-Learning is appropriate when the learners are grouped and facilitated to learn according to their learning style and at their own pace. Elaborate researches have been proposed to categorize learners based on various e-learning parameters. Most of these researches have deployed the clustering principles for grouping eLearners, and in particular, they have utilized K-Medoid principle for better clustering. In the classical K-Medoid algorithm, predicting or determining the value of K is critical, two methods namely the Elbow and Silhouette methods are widely applied. In this paper, we experiment with the application of both these methods to determine the value of K for clustering eLearners in K-Medoid and prove that Silhouette method best predicts the value of K.

International audience; Predicting the set of lumbers which would be obtained from sawing a log at a specific sawmill is a difficult problem, which complicates short and mid term decision making in this industry. While sawmill simulators able to simulate the sawing of a log from a 3D scan of its outer shape exist, they can be extremely computationally intensive. Several alternative approaches based on machine learning algorithms and different set of features were explored in previous works. This paper proposes the use of one hidden layer perceptrons, and a vector of features build from dissimilarities from the scans to a set of selected wood logs, chosen as the class medoids. Several architectures are tested and compared to validate the pertinence of the proposed set of medoid-based features. The lowest mean squared error was obtained for MISO neural networks with a sigmoid output activation function, to constrain the output value ranges.

Energy system models are challenged by the need for high temporal and spatial resolutions in order to appropriately depict the increasing share of intermittent renewable energy sources, storage technologies, and the growing interconnectivity across energy sectors. This study compares different temporal aggregation strategies, which reduce the number of considered time steps, to maintain computational viability of these models. The work focuses on the representation of time series by a subset of single time steps (i.e., typical time steps), or by groups of consecutive time steps (i.e., typical periods), which are commonly applied in the literature using clustering. We test these techniques for two different energy system models and benchmark the optimization results based on aggregation to those of the fully resolved models. Further, centroids and medoids are used to represent the clustered datasets and it is investigated whether the optimal aggregation method can be determined based on clustering indicators only. The results reveal that typical time steps consistently outperform typical periods with respect to clustering indicators, but do not lead to more accurate optimization results when applied to a model that takes numerous storage technologies into account. Although both aggregation techniques are capable of coupling the aggregated time steps, typical periods offer more options to depict storage operations, whereas typical time steps are more effective for models that neglect time-linking constraints. Further, this observation is independent from the choice of centroids or medoids to represent the clustered time series. In summary, the adequate choice of aggregation methods strongly depends on the mathematical structure of the considered energy system optimization model, and a priori decisions of a sufficient temporal aggregation are only possible with good knowledge of the mathematical structure of the underlying optimization problem.

In recent years, uncertain data clustering has become the subject of active research in many fields, for example, pattern recognition, and machine learning. Nowadays, researchers have committed themselves to substitute the traditional distance or similarity measures with new metrics in the existing centralized clustering algorithms in order to tackle uncertainty in data. However, in order to perform uncertain data clustering, representation plays an imperative role. In this paper, a Monte-Carlo integration is adopted and modified to express uncertain data in a probabilistic form. Then three similarity measures are used to determine the closeness between two probability distributions including one novel measure. These similarity measures are derived from the notion of Kullback-Leibler divergence and Jeffreys divergence. Finally, density-based spatial clustering of applications with noise and $k$ -medoids algorithms are modified and implemented on one synthetic database and three real-world uncertain databases. The obtained outcomes confirm that the proposed clustering technique defeats some of the existing algorithms.

In this paper we propose a robust fuzzy clustering model, the STAR-based Fuzzy C-Medoids Clustering model with Noise Cluster, to define territorial partitions of the European regions (NUTS2) according to the workplaces mobility trends for places of work provided by Google with reference to the whole COVID-19 pandemic period. The clustering model takes into account both temporal and spatial information by means of the autoregressive temporal and spatial coefficients of the STAR model. The proposed clustering model through the noise cluster is capable of neutralizing the negative effects of noisy data. The main empirical results regard the expected direct relationship between the Community mobility trend and the lockdown periods, and a clear spatial interaction effect among neighboring regions.

Grading is the process of interpreting learning competence to inform learners and instructors of the current learning ability levels and necessary improvement. For norm-referenced grading, the instructors use a conventionally statistical method, z score. It is difficult for such a method to achieve explainable grade discrimination to resolve dispute between learners and instructors. To solve such difficulty, this paper proposes a simple and efficient algorithm for explainable norm-referenced grading. Moreover, the rise of artificial intelligence nowadays makes machine learning techniques attractive to the norm-referenced grading in general. This paper also investigates two popular clustering methods, K-means and partitioning around medoids. The experiment relied on the data sets of various score distributions and a metric, namely, Davies–Bouldin index. The comparative evaluation reveals that our algorithm overall outperforms the other three methods and is appropriate for all kinds of data sets in almost all cases. Our findings however lead to a practically useful guideline for the selection of appropriate grading methods including both clustering methods and z score.

Data-driven analytical clustering and visualization techniques were applied to the dataset of 9% Cr experimental alloy data generated through the eXtremeMAT project. Techniques and results were compared with the resulting clusters obtained through similar analytical techniques on previous and reduced versions of the dataset. The principal components were generated in order to reduce the dimensionality of the complex dataset and to visualize the underlying trends in the data. Partitioning around medoids was performed on the resulting principal components to determine relevant clusters. Domain knowledge labels were further applied to the principal components to compare the labels with the trends identified through the clustering methods. The clusters can be used to compare the tensile properties of the alloys and to reduce the variation in the dataset.

Despite the expectation of heterogeneity in therapy outcomes, especially for complex diseases like cancer, analyzing differential response to experimental therapies in a randomized clinical trial (RCT) setting is typically done by dividing patients into responders and non-responders, usually based on a single endpoint. Given the existence of biological and patho-physiological differences among metastatic colorectal cancer (mCRC) patients, we hypothesized that a data-driven analysis of an RCT population outcomes can identify sub-types of patients founded on differential response to Panitumumab - a fully human monoclonal antibody directed against the epidermal growth factor receptor. Outcome and response data of the RCT population were mined with heuristic, distance-based and model-based unsupervised clustering algorithms. The population sub-groups obtained by the best performing clustering approach were then examined in terms of molecular and clinical characteristics. The utility of this characterization was compared against that of the sub-groups obtained by the conventional responders' analysis and then contrasted with aetiological evidence around mCRC heterogeneity and biological functioning. The Partition around Medoids clustering method results into the identification of seven sub-types of patients, statistically distinct from each other in survival outcomes, prognostic biomarkers and genetic characteristics. Conventional responders analysis was proven inferior in uncovering relationships between physical, clinical history, genetic attributes and differential treatment resistance mechanisms. Combined with improved characterization of the molecular subtypes of CRC, applying Machine Learning techniques, like unsupervised clustering, onto the wealth of data already collected by previous RCTs can support the design of further targeted, more efficient RCTs and better identification of patient groups who will respond to a given intervention.

One efficient solution to solve the cold-start recommendation problem is by exploiting the user demographic information using a clustering method. As the user demographic information contains categorical data, the choice of the clustering method to be used must naturally suitable to the particular data characteristic. There are two popular heuristic categorical data clustering algorithms, i.e., centroid and medoid based. This paper conducts a comparative study towards the implementation of K-Modes of the centroid-based method and K-Approximate Modal Haplotype (K-AMH) of the medoid-based method for solving the cold-start recommendation problem. The experiment results on the MovieLens dataset show that K-AMH achieves the average performance increase of 0.51% in terms of Precision and 0.40% in terms of Normalized Discounted Cumulative Gain (NDCG) to K-Modes. Yet, K-Modes is more lenient to use due to its scalability.

The random forest algorithm is an ensemble learning method, with the decision tree as its base classifier. In the ensemble model, it is not always true that the more the base classifiers, the better the classification effect, since if there are more base classifiers with poor performance in the model, they may have negative impacts on the final classification result. In order to modify the random forest classification method under the premise of ensuring the diversity of the random forest model, based on the random forest algorithm of cluster integration selection and personal indoor thermal preference model, this paper proposes a random forest method of clustering ensemble selection with Dunn index. Considering the shortcomings of the irrevocable merging strategy of hierarchical clustering algorithm, a random forest method of hybrid clustering ensemble selection based on hierarchical clustering and k- medoids partition clustering is developed. The effectiveness of the proposed methods is verified by classifying personal indoor thermal preferences.

Missing data imputation is a critical part of data cleaning tasks and vital for learning from incomplete data. This paper proposes a novel cooperative clustering imputation (CCI) method to estimate missing values. The proposed method aims to find a better clustering model and donor for imputation, comparing with individual clustering algorithms. It makes use of agreements among different clustering algorithms to generate a set of sub-clusters, and, then, merges these sub-clusters based on the matrix of the performance measures of sub-clusters. The proposed method is evaluated using ten public datasets from UCI data repository and V2X communication data with induced missing samples, and compared with three standard clustering based imputation methods, k-means imputation, fuzzy c-means imputation, and partition around medoids imputation. Missing values are induced through each dataset by different missing mechanisms, missing rates, and missing distribution, and, thus, various incomplete datasets are generated. The performance of these methods are checked using normalized root mean square error (NRMSE). The attained experimental results indicate the effectiveness of the proposed missing values imputation method.

We propose two Modified Differential Evolution driven subspace based optimization models for anomaly detection in customer credit card churn detection, automobile insurance fraud detection and customer credit card default detection. Sparsity coefficient is chosen as the objective function for discovering anomalies. Also, we employed an external performance measure as selection constraint, namely, precision multiplied by recall at every iteration after a pre-specified iteration count. The proposed technique outperformed a bunch of baseline algorithms for anomaly detection, for example, Local Outlier Factor, Angle based Outlier Detection, K-means, Partition Around Medoids and also the proposed model without invoking the external performance measure in terms of precision and Area Under ROC Curve (AUC) indicating that the proposed method a viable alternative for anomaly detection.

Drugs Interaction (https://covid19-druginteractions.org/) is a website that allows users to select a COVID- 19 drug among the nine popular drugs with one or more drug from a different class co-medication to check for any interaction between the chosen drugs. Beyond the interaction, however, the website does not advise if the resulting class of co-medication is safe to use or otherwise along with one of the nine COVID drugs. Therefore, there exist a need to use an unsupervised clustering approach to group the COVID drugs and respective co-medications that are safe to use in the absence of interaction and vice versa. This paper focused on application of the Partitioning Around Medoid (PAM) clustering algorithm to categorize the combinations as safe or otherwise. The resulting clusters are then measured using the Silhoutte value and presented.

Clustering algorithms resume the datasets into few number of data points such as centroids or medoids, which explain the entire dataset briefly. In the domain of data-driven machine learning, the more precision with the clustering rule leads directly to more precise classification, prediction, and recognition. We propose an efficient clustering method, which applies the paradigms - mainly 3D Gaussian model - to estimate the optimum cluster number, cluster border, and congestion coordinates to model the datasets of the natural distributions. This approach considers both qualitative and quantitative features of the dataset and calculates the best scale to analyze it. We used fuzzy logic to compare the models with data, to generate and rank the hypotheses, and finally to reject or accept the assumptions. The proposed approach which is called Fuzzy Gaussian Paradigmatic Clustering (FGPC) algorithm is used as the basis of a fast (with the complexity order of O(n)) and robust algorithm for identifying fuzzy models.

Small wireless sensors are equipped with micromechanical systems, & wireless communication technologies, digital systems. A Sensor Node understands the limited area for given functionality. In order to gather information on a large area, data centers need to be collected in cooperation with a center sensor node. These co-operative functional sensors create a wireless sensor network.In the previous work, they used K-Medoids Algorithm to form the clusters and Cluster heads for databroadcast towards the base station from the source node. K-Medoid algorithms are primarily disadvantageous because they are not ideal for clustering arbitrary groups of objects. It is that they use compactness as clustering parameters, in short, rather than connectivity, to minimize differences among non-medoid objects or medoids (cluster center). The drawback, even though the first k medoids are selected randomly, can produce different results on different runs in the same dataset. These drawbacks are overcome in Fuzzy Probabilistic C-Means Algorithm & increasethe performance of the network. Simulation is performed on MATLAB tool & results show the effectiveness of the proposed work.

This paper presents a clustering-based strategy to identify typical daily electricity usage (TDEU) profiles of multiple buildings. Different from the majority of existing clustering strategies, the proposed strategy consists of two levels of clustering, i.e. intra-building clustering and inter-building clustering. The intra-building clustering used a Gaussian mixture model-based clustering to identify the TDEU profiles of each individual building. The inter-building clustering used an agglomerative hierarchical clustering to identify the TDEU profiles of multiple buildings based on the TDEU profiles identified for each individual building through intra-building clustering. The performance of this strategy was evaluated using two-year hourly electricity consumption data collected from 40 university buildings. The results showed that this strategy can discover useful information related to building electricity usage, including typical patterns of daily electricity usage (DEU) and periodical variation of DEU. It was also shown that this proposed strategy can identify additional electricity usage patterns with a less computational cost, in comparison to two single-step clustering strategies including a Partitioning Around Medoids-based clustering strategy and a hierarchical clustering strategy. The results obtained from this study could be potentially used to assist in improving energy performance of university buildings and other types of buildings.

The formulation of energy policies for urban building stock frequently requires the evaluation of the energy use of large numbers of buildings. When urban energy modelling is utilised as part of this process, the identification of building groups and associated representative buildings can play a critical role. This paper outlines a novel methodology for identifying building groups and associated representative buildings in urban datasets. The methodology utilizes a combination of building classification, building clustering and predictive modelling. First, multiple urban-scale datasets are collected, and then, classification techniques and clustering algorithms are applied to identify building clusters. Next, representative buildings (medoids) in each cluster are identified. Predictive modelling is used to expand cluster membership in the case where some buildings were excluded from the previous analysis. A number of different clustering algorithms are assessed, including K-means and hierarchical (agglomerative and divisive) and partitioning around medoids. The methodology is applied to a large dataset of mixed-use buildings in the city of Geneva, Switzerland. The results, assessed by nine validation indices, indicate the capacity of the decision support framework to identify clusters and associated representative buildings. Furthermore, post-application of predictive modelling, using a random forest approach, facilitates the incorporation of a larger portion of the building stock within the established clusters with an overall average classification accuracy of 89%. A total of 67 representative buildings were identified in the urban dataset, which consisted of 13614 mixed-use buildings in the city of Geneva.

Many data exploration applications require the ability to identify the top- $k$ results according to a scoring function. We study a class of top- $k$ ranking problems where top- $k$ candidates in a dataset are scored with the assistance of another set. We call this class of workloads cross aggregate ranking . Example computation problems include evaluating the Hausdorff distance between two datasets, finding the medoid or radius within one dataset, and finding the closest or farthest pair between two datasets. In this paper, we propose a parallel and distributed solution to process cross aggregate ranking workloads. Our solution subdivides the aggregate score computation of each candidate into tasks while constantly maintains the tentative top- $k$ results as an uncertain top- $k$ result set. The crux of our proposed approach lies in our entropy-based scheduling technique to determine result-yielding tasks based on their abilities to reduce the uncertainty of the tentative result set. Experimental results show that our proposed approach consistently outperforms the best existing one in two different types of cross aggregate rank workloads using real datasets.

Hierarchical and partitional cluster analyses were used to compartmentalize Water Conservation Area 1, a managed wetland within the Arthur R. Marshall Loxahatchee National Wildlife Refuge in southeast Florida, USA, based on physical, biological, and climatic geospatial attributes. Single, complete, average, and Ward's linkages were tested during the hierarchical cluster analyses, with average linkage providing the best results. In general, the partitional method, partitioning around medoids, found clusters that were more evenly sized and more spatially aggregated than those resulting from the hierarchical analyses. However, hierarchical analysis appeared to be better suited to identify outlier regions that were significantly different from other areas. The clusters identified by geospatial attributes were similar to clusters developed for the interior marsh in a separate study using water quality attributes, suggesting that similar factors have influenced variations in both the set of physical, biological, and climatic attributes selected in this study and water quality parameters. However, geospatial data allowed further subdivision of several interior marsh clusters identified from the water quality data, potentially indicating zones with important differences in function. Identification of these zones can be useful to managers and modelers by informing the distribution of monitoring equipment and personnel as well as delineating regions that may respond similarly to future changes in management or climate.

Handling big data is one of the major issues in the field of statistical data analysis. In such investigation cluster analysis plays a vital role to deal with the large scale data. There are many clustering techniques with different cluster analysis approach. But which approach suits a particular dataset is difficult to predict. To deal with this problem a grading approach is introduced over many clustering techniques to identify a stable technique. But the grading approach depends on the characteristic of dataset as well as on the validity indices. So a two stage grading approach is implemented. In this study the grading approach is implemented over five clustering techniques like hybrid swarm based clustering (HSC), k -means, partitioning around medoids (PAM), vector quantization (VQ) and agglomerative nesting (AGNES). The experimentation is conducted over five microarray datasets with seven validity indices. The finding of grading approach that a cluster technique is significant is also established by Nemenyi post-hoc hypothetical test.

Collaborative sensing helps in achieving a more accurate sensing decision than individual sensing in cognitive radio network (CRN). In an infrastructure-based CRN, each node sends its local sensing report to the fusion center (FC), which uses a fusion rule to aggregate the local sensing reports. However, collaborative sensing is vulnerable to the spectrum sensing data falsification attack, in which a node falsifies its local sensing report before sending it to the FC with the intention of disrupting the final sensing decision of the FC. In practice, the strategy of an attacker is not known. However, the collection of sensing reports at the FC can be useful for data mining with the objective of identifying the attackers. In this paper, we present a method that uses clustering techniques for detection and isolation of such attackers. We employ two clustering techniques, viz., K -medoids clustering and agglomerative hierarchical clustering. Unlike threshold detection that requires some predefined threshold value as input, the proposed approach detects the attackers using only the collection of sensing reports at the FC. We also present how we can use the proposed approach on streaming data (sensing reports), and thus, detect and isolate attackers on the fly. Comparative numerical simulation results support the validity of the approach.

Allocation of soil profiles to one or another soil class depends on the surveyor's experience and knowledge. Inconsistent class designations can affect the downstream uses of soil information such as hydrological and ecological applications. Therefore, numerical classifications can be useful in creating property-based soil clusters. Quantitative classification of soil horizons can also be beneficial for guiding physicochemical thresholds used in taxonomic criteria. This study aimed at taking a step in applying numerical classification techniques to the South African soil legacy database to quantitatively cluster horizons. For each master horizon, the database was clustered into new “diagnostic” horizons through Partitioning Around Medoids (PAM) implemented in the Clustering Large Applications algorithm (CLARA). This algorithm has the benefit of using multiple subsets of the data making a more reliable initiation of medoids and it is a non-parametric approach making it more robust to outliers. To determine the optimal number of clusters, the silhouette width for 1 through 11 clusters was calculated. The number of clusters with the largest silhouette width was taken as the optimal number of clusters. The results of this study show that for O, E, and G (gleyed) horizons, the algorithm performs relatively well with the first two principle components capturing almost half of the variation in the data. However, for the A, B, and C horizons, the algorithm struggled to separate clusters sufficiently. The A horizon clusters only broadly corresponded to environmental factors (geography, climate, elevation, and geology) and the large clusters straddled numerous taxonomic thresholds. Moreover, the B horizon clusters correspond relatively well with environmental factors. Limitations identified, include bias in geographic location of modal soil profiles of the database, bias in the South African classification system, how to handle non-globular clusters, and outliers which add leverage to the clusters.

COVID-19 was discovered near the end of 2019 in Wuhan, China. In a short period, the virus had spread throughout the entire world. One of the primary concerns of managers and decision-makers in all types of hospitals nowadays is to implement detection plans for status of patient (Negative, Positive) in order to provide enough care at the proper moment. To reduce a pandemic of COVID-19, improving health care quality could be advantageous. Making clusters of patients with similar features and symptoms supplies an overview of health quality given to similar patients. In the scope of medical machine learning, the K-means and Partitioning Around Medoids (PAM) clustering algorithms are usually used to produce clusters depend on similarity and to detect helpful patterns from sizes of data. In this paper, we proposed a hybrid algorithm of K-Means and Partitioning Around Medoids (PAM) called K-MP to take benefits of both PAM and K-Means to construct an efficient model for predicting patient status. The suggested model for the real dataset was collected from 400 patients in the many Iraqi clinics using a questionnaire. We evaluated the proposed K-MP by using true negative rate, balance accuracy, precision, accuracy, recall, mean absolute error, F1 score, and root mean square error. From these performance measures, we found that K-MP is more efficient in discovering patient status comparing to K-Means and PAM.

Aside from anthropometric data tables, 3D shape models of the human body are becoming increasingly common and call for new product sizing methods based on 3D anthropometry. Though some shape model-based methods exist, most of them focus on mathematical clustering and do not discuss the usability of the clustering results for product design. In this paper, a new shape-model based clustering method for product sizing is presented that takes into account both shape information and usability for designers. The new method, called constrained k -medoids clustering, is applied on a shape model of 100 human heads. It is compared to a partitioning around medoid (PAM) clustering of anthropometric measurements of the same 100 heads (i.e., feature-based), as well as to PAM clustering of the shape model (i.e., shape based). Results show that both shape-based and constrained clustering perform better than feature-based clustering, with an average size-weighted variance (SWV) of 62 × 1 0 3 ± 16 × 1 0 3 and 66 × 1 0 3 ± 26 × 1 0 3 as compared to 72 × 1 0 3 ± 12 × 1 0 3 , respectively. The average point-to-point distances in shape-based and constrained k -medoids were found to be similar to those of feature-based k -medoids, indicating that using 3D-anthropometry for product sizing will not have a negative impact on designer workload and/or a higher cost to implement more sizes. The results suggest that for head-based products, which require accurate shape and size fit, sizing systems should be created using either shape-based or constrained k -medoids, with the latter being slightly less accurate but more intuitive for further design and verification.

Purpose The purpose of this paper is to detect the existence of unknown wireless devices which could result negative means to the privacy. The perceptual layer of internet of things (IoTs) suffers the most significant privacy disclosing because of limited hardware resources, huge quantity and wide varieties of sensing equipment. Determining whether there are unknown wireless devices in the communicating environment is an effective method to implement the privacy protection for the perceptual layer of IoTs. Design/methodology/approach The authors use horizontal hierarchy slicing (HHS) algorithm to extract the morphology feature of signals. Meanwhile, partitioning around medoids algorithm is used to cluster the HHS curves and agglomerative hierarchical clustering algorithm is utilized to distinguish final results. Link quality indicator (LQI) data are chosen as the network parameters in this research. Findings Nowadays data encryption and anonymization are the most common methods to protect private information for the perceptual layer of IoTs. However, these efforts are ineffective to avoid privacy disclosure if the communication environment exists unknown wireless nodes which could be malicious devices. How to detect these unknown wireless devices in the communication environment is a valuable topic in the further research. Originality/value The authors derive an innovative and passive unknown wireless devices detection method based on the mathematical morphology and machine learning algorithms to detect the existence of unknown wireless devices which could result negative means to the privacy. The simulation results show their effectiveness in privacy protection.

Background/Objectives: The emergence of Cloud computing in recent times as a globally accepted data and activity management platform is phenomenal, albeit with few clutches not only related with the data integrity and their privacy but also of their geographical location. The gravity of the issue arises with the plethora of guidelines and variations in legal procedures in storing the data and getting access to them in diverse geographical areas. The aim of present investigation is to figure-out a potentially effective method that can help detect a forged server with better location coordinates than the currently employed methods. Methods/Statistical Analysis: In this study we developed a made use of an established method to check the position of the files at a specified place as claimed by service provider. The main means employed during the course of this investigation is K-Medoid Algorithm for finding the server's geographical location putting emphasis on putative adverse outcome. Findings: The greatness of K-Medoid Algorithm is to detect a potentially forged location and also to identify the possible elements involved in forgery. This work involved the use of Tulip Dataset and Implementation in NS3 for validating algorithm modified by us to detect the forged location and possible location of involved adversaries. The investigation during this work culminated in proposing a modified K-Medoid algorithm for helping a user to find the Cloud file system which verifies the storage location with very high efficiency. Improvements/Applications: Through our research technique, user able to detect faked location and identify the dishonest service provider. Our work culminated in the best estimation of the location of server for a cloud service provider within a less distance than the previous work.