Search

The knowledge of the climate pattern for a particular region is important to alleviate the impact of climate change and protect the environment by taking appropriate actions based on geographical knowledge. It is also equally important for water resources planning and management. In this study, the regional disparities and similarities have been revealed among different climate stations or regions in Bangladesh based on different climatological factors such as rainfall, temperatures, relative humidity, sea level pressure, cloud cover, wind speed, the sunshine hour. We have selected one of the best-fitted algorithms for particular climate data from three multivariate clustering approaches named hierarchical clustering, partitioning around medoids (PAM), and K-means clustering by using different validation tests. Four homogeneity tests (Mann-Kendall Test, Pettitt's test, Buishand Range Test, Standard Normal Homogeneity Test) also have been performed for each of the clusters created based on several factors. The results suggest that the climate regions or meteorological stations of Bangladesh can be clustered into two groups based on a combination of climatological variables. According to the findings, there is a huge variation between the two groups in terms of climatological factors. The first group (cluster 1) is located in the northern part of the country that includes drought-prone and vulnerable regions, whereas, the second group (cluster 2) contains rain-prone and hilly regions, which are mostly situated in the southern part. All newly defined clusters show homogeneous behavior with few exceptions such as clusters based on sea level pressure are not homogeneous.

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.

Herein, a computational platform FluorSimStudio was developed for processing fluorescence decay curves in molecular systems, which implements the concept of complex analysis of experimental information based on the simulation modeling and data mining methods. Data analysis includes partitioning the fluorescence decay curves into clusters according to the degree of likeness in some measure of similarity, finding the median cluster members (medoids), applying the data reduction method and visualizing the experimental data in a two-dimensional space. Analysis of the decay curves is carried out by the analytical or simulation models of optical processes occurring in molecular systems. The visualization of data clusters in the original and transformed time spaces is done with the aim of user interaction. A functional scheme of the platform is proposed, the choice of software for ensuring high computing performance is substantiated, a web application of the platform is implemented ( https://dsa-cm.shinyapps.io/FluorSimStudio ), and the results of a comparative analysis of the simulation algorithms are presented. The performance of the computational platform was confirmed by examples of the analysis of data sets representing systems of free fluorophores and in the presence of the Forster electronic excitation energy transfer process. The computational platform is an open system and allows permanent addition of complex analysis models, taking into account the development of new algorithms for modeling the energy transfer processes in molecular systems, studied with the use of time-resolved fluorescence spectroscopy systems.

Energy conservation is one of the major concerns in mobile cloud sensor environment, where mobile sensing devices are capable of acquiring the sensing information and send the collaborated data to cloud hosted applications. However, they are constrained by the limited computing power and the short battery life. Hence, sensor based applications need an effective scheme to collect the sensed information and offload it to the base station in an efficient manner. In this paper, an approach named Modified Partitioning Around Medoids clustering with Threshold based Cluster Head Replacement (MPAM-TCHR), is proposed that aims for better clustering and change of cluster heads for every round of data offload to reduce the energy utilization of the sensor nodes. The proposed work divides the process into four phases namely, initialization, clustering, Cluster Head (CH) formation and transmission phases. Initially, node initialization is performed, and then the modified PAM clustering algorithm accurately estimates the medoid points based on which optimal cluster set partitioning is done. Next, the four parameters namely residual energy, signal to noise ratio (SNR) of the sensors, average path loss between the node and the other nodes and the path loss between the sensor and the base station influence the CH selection. This involves a threshold based modulation measure to identify probability effective node to become CH, iteratively changing the CH at different time intervals. Ultimately, the CH offloads the collected information to the base station (BS) with low communication cost possible during a particular time interval. Experimental results show better performances in terms of metrics like network lifetime, network utilization, and the average number of alive nodes. Thus, the proposed method performs data transmission with low energy consumption and thereby able to prolong the network lifespan.

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.

We compare and demonstrate the effectiveness of two clustering methods with the main purpose of identifying characteristic profiles of high utilizers of health care. In this work, we use three sets of mutually independent longitudinal data that are nationally representative of the US adult working-age civilian non-institutionalized population. We compare k-means, a commonly used clustering method, with a k-medoids algorithm called Partitioning Around Medoids. We use one cohort of data to create clusters based on similar characteristics of individuals for both clustering methods. We examine these characteristic compositions of the highest three average total expenditure clusters from this cohort. We also examine the health expenditure distributions for this cohort over the following two years. We validate the approach by applying the centers of the clusters to two other cohorts of similar data. We form clusters based on demographic, economic, and health-related characteristics that are commonly used in studies of health care utilization. We demonstrate the consistency of our results across the three cohorts of data and across different types of health expenditures, such as office-based/outpatient and drug. Clusters can be formed with other more homogeneous data, such as Medicaid, Medicare, employer sponsored insurance, or individual private plans issued under the Affordable Care Act. This approach can be used to follow similar groups over time for other types of health outcomes.

A method is proposed for processing large data sets of fluorescence decay kinetic curves using data mining algorithms to determine the parameters of biophysical and optical processes in molecular systems. The idea of this method involves breaking the initial set of fluorescence decay curves into clusters in terms of some degree of similarity, finding medoids of the clusters, applying a dimensionality reduction method to the data and imaging the experimental data in two- and three-dimensional space, and analyzing the decay curves of the medoids using analytic or simulation models. The applicability of the method is examined for the example of analyzing sets of data representing systems of fluorophores. This method requires substantially less time and calculations of the analytic approximation functions, while the accuracy of the estimated parameters is higher than in the classical approach.

Today, the problem of climate change is addressed in many ways. Climate change would have a major impact on the hydrological cycle and consequently on available water resources. Therefore, the location and timing of the water resources in the world change. Water is an indispensable resource that connects all living things together and directly affects their lives. Water is a biological requirement not only for man, but also for economic, social, and cultural life itself. This study aims to identify similar countries in terms of water resources by taking into account the precipitation amounts together with climate change. For this purpose, time series clustering was conducted to precipitation amounts of 22 countries between 2000 and 2017 with the Hierarchical clustering and Partitioning Around Medoids (PAM) clustering methods based on two distance measures. Countries are divided into two clusters and they were evaluated according to their water risk levels and populations.

A nondestructive multiparametric protocol for chert investigations (NM-PCI) was developed to provide objective criteria for raw material procurements and provenance investigations of archaeological cherts. For this purpose, macroscopic and mesoscopic characteristics (structures, textures and paleontological contents) were used to describe the main visible chert features as well as colourimetric and geochemical data acquired with portable devices. Data handling was performed by means of cluster analysis multivariate statistics, with an appropriate selection of algorithms to process and visualize mixed data matrices (partitioning around medoids (PAM), t-distributed stochastic neighbor embedding (t-SNE)). The protocol was applied to chert samples from the Gargano Promontory (Italy, Apulia) mining complex located in the districts of Peschici, Vieste and Mattinata. These mines, exploited for approximately four millennia, constitute an exceptional prehistoric record of mining archaeology and, above all, a key tool to understand the Neolithisation process throughout the Adriatic region. A map of the primary and secondary chert sources of the Gargano Promontory was produced to manage field sampling of mine structures. Waste materials were selected for the geologic samples of the five mines. Due to their inaccessibility, the samples from two mines consisted exclusively of waste materials. The NM-PCI proved able to discriminate most of the analysed mines and is well suited to provenance investigations of archaeological lithic industries. Compared to previous geochemical studies, the nondestructive method proposed here improves geological resolution, allowing the discrimination of cherts within the same formation.

Globalization trend in integrated circuit design and manufacturing process has increased the vulnerability of integrated circuit. These vulnerabilities mainly caused by hardware Trojan have a serious impact on the security of integrated circuits. Although side-channel analysis approach is the most promising Trojan detection approach, nearly all side-channel analysis approaches rely heavily on the availability of golden chips, which are extremely difficult to obtain. In this paper, a golden layout model instead of fabricated golden chips is introduced for the practical application of hardware Trojan detection approaches. The simulated voltage variations generated from the golden layout model at different process corners serve as golden reference, thus fabricated golden chips are not required during detection. Further, silicon measurements are performed to obtain the voltage variations of fabricated chips, and a model calibration algorithm is utilized to calibrate the golden model in the presence of process variations and random noise. Finally, the Trojan detection is formulated as a two-class classification problem, and the Trojan is identified using the partitioning around medoids algorithm. Experimental results demonstrate that the similarities between the simulated traces and measured traces are greater than 98.81%, and the proposed approach distinguishes the Trojan chips correctly even under ± 15% process variation.

In finance, cluster analysis is a tool particularly useful for classifying stock market multivariate time series data related to daily returns, volatility daily stocks returns, commodity prices, volume trading, index, enhanced index tracking portfolio, and so on. In the literature, following different methodological approaches, several clustering methods have been proposed for clustering multivariate time series. In this paper by adopting a fuzzy approach and using the Partitioning Around Medoids strategy, we suggest to cluster multivariate financial time series by considering the dynamic time warping distance. In particular, we proposed a robust clustering method capable to neutralize the negative effects of possible outliers in the clustering process. The clustering method achieves its robustness by adopting a suitable trimming procedure to identify multivariate financial time series more distant from the bulk of data. The proposed clustering method is applied to the stocks composing the FTSE MIB index to identify common time patterns and possible outliers.

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).

Face recognition is itself a very challenging task and it becomes more challenging when the input images have intra class variations and inter class similarities in a large scale. Yet the recognition accuracy can be improved in some extent by supporting the system with non-matched templates. Therefore a set of cohort images is used in this regard. But all the cohort templates of the initial cohort pool may not be relevant for each and every enrolled subject. So the main focus of this work is to select a subject specific and meaningful cohort subset. This paper proposes a cohort selection method called K-medoids Cohort Selection (KMCS) to select a reference set of non-matched templates which are almost appropriate to the respective subjects. Basically, all cohort scores of a subject are clustered first using K-medoids clustering. Afterward the cluster having more scattered members/scores from its medoid is selected as a cohort subset because this cluster is constituted with the cohorts carrying more discriminative features compared to others. The SIFT points and SURF points are extracted as facial feature. The experiments are conducted on FEI, ORL and Look-alike databases of face images. The matching scores between probe and query images are normalized using T-norm, Max-Min and Aggarwal (Max rule) cohort score normalization techniques before taking the final decision of acceptance or rejection. The results obtained from the experiments show the domination of the proposed system over the non-cohort face recognition system as well as random and Top 10 cohort selection methods. There is another comparative study between k-means and K-medoids clustering for cohort selection.

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.

In the present study, parameters derived from Ice, Cloud, and land Elevation Satellite/Geoscience Laser Altimeter System (GLAS) full waveform were used for land cover classification in western part of Doon valley, Uttarakhand, India. Three parameters, viz, height, front slope angle (afslope) and canopy return ratio (rCanopy) were extracted from the returned full waveform signals. k-means (KM), partitioning around medoids (PAM), and fuzzy c-means (FCM) with different cluster sizes were used for classifying the land cover types with the help of GLAS-derived parameters. Among the clustering methods, KM performed the best. The overall accuracy (89.41 %) of all methods were quite significant with cluster size three i.e. with three classes forest, mango orchard and other class including agriculture, barren/fallow land, settlement, dry river bed, etc. The accuracy of the PAM (60 %) and the FCM (68.4 %) decreased drastically at four clusters with the separation of agriculture from barren/fallow land. The accuracy of the PAM and the FCM further decreased with increase in the number of clusters whereas KM showed reliable results for all clusters. KM with five clusters was able to distinguish five different land covers, viz, forest, mango orchard, agriculture and barren/fallow land and other class including settlement, dry river bed, etc. with an overall classification accuracy of 72.93 %. The study presents a method for classifying land cover types using GLAS full waveform data.

The application of ACO-based algorithms in data mining has been growing over the last few years, and several supervised and unsupervised learning algorithms have been developed using this bio-inspired approach. Most recent works about unsupervised learning have focused on clustering, showing the potential of ACO-based techniques. However, there are still clustering areas that are almost unexplored using these techniques, such as medoid-based clustering. Medoid-based clustering methods are helpful—compared to classical centroid-based techniques—when centroids cannot be easily defined. This paper proposes two medoid-based ACO clustering algorithms, where the only information needed is the distance between data: one algorithm that uses an ACO procedure to determine an optimal medoid set (METACOC algorithm) and another algorithm that uses an automatic selection of the number of clusters (METACOC-K algorithm). The proposed algorithms are compared against classical clustering approaches using synthetic and real-world datasets.

This paper presents a partitioning around medoid (PAM)-based novel method to realize the recognition of the tool wear state in milling. In PAM, the representative objects called medoids are used to define clusters and average dissimilarities are applied to assess the medoids, which make PAM robust to outliers and therefore improve the clustering performance. Meanwhile, locality preserving projections (LPP) method is utilized to further increase the clustering accuracy by dimension reduction. To show the effectiveness of the proposed method, end milling experiment of Ti-6Al-4V alloy were carried out and the commonly used k-means and fuzzy c-means (FCM) algorithm are introduced to make a comparison with PAM algorithm by using five clustering evaluation indicators. The results show that PAM performs higher accuracy and robustness than the other two clustering algorithm.

Dividing a geographical region into some subregions with common characteristics is an important research topic, and has been studied in many research fields such as urban planning and transportation planning. In this paper, by network analysis approach, we attempt to extract functionally similar regions, each of which consists of functionally similar nodes of a road network. For this purpose, we previously proposed the Functional Cluster Extraction method, which takes a large amount of computation time to output clustering results because it treats too many high-dimensional vectors. To overcome this difficulty, we also previously proposed a transfer learning-based clustering method that selects approximate medoids from the target network using the K medoids of a previously clustered network and divides all the nodes into K clusters. If we select an appropriate network with similar structural characteristics, this method produces highly accurate clustering results. However it is difficult to preliminarily know which network is appropriate. In this paper, we extend this method to ensure accuracy using the K medoids of multiple networks rather than a specific network. Using actual urban streets, we evaluate our proposed method from the viewpoint of the improvement degree of clustering accuracy and computation time.

This paper addresses the problem of insufficient performance of statistical classification with the medium-sized database (thousands of classes). Each object is represented as a sequence of independent segments. Each segment is defined as a random sample of independent features with the distribution of multivariate exponential type. To increase the speed of the optimal Kullback–Leibler minimum information discrimination principle, we apply the clustering of the training set and an approximate nearest neighbor search of the input object in a set of cluster medoids. By using the asymptotic properties of the Kullback–Leibler divergence, we propose the maximal likelihood search procedure. In this method the medoid to check is selected from the cluster with the maximal joint density (likelihood) of the distances to the previously checked medoids. Experimental results in image recognition with artificially generated dataset and Essex facial database prove that the proposed approach is much more effective, than an exhaustive search and the known approximate nearest neighbor methods from FLANN and NonMetricSpace libraries.

The New York Times Annotated Corpus, the ACM Digital Library, and PubMed are three prototypical examples of document collections in which each document is tagged with keywords or phrases. Such collections can be viewed as high-dimensional document cubes against which browsers and search systems can be applied in a manner similar to online analytical processing against data cubes. After examining the tagging patterns in these collections, a partial materialization strategy is developed to provide efficient storage and access to centroids for document subsets that are defined through queries over tags. By adopting this strategy, summary measures dependent on centroids (including measures involving medoids, sets of representative documents, or sets of representative terms) can be efficiently computed. The proposed design is evaluated on the three collections and on several synthetically generated collections to validate that it outperforms alternative storage strategies.

In this paper, following a partitioning around medoids approach, a fuzzy clustering model for interval-valued data, i.e., FCMd-ID, is introduced. Successively, for avoiding the disruptive effects of possible outlier interval-valued data in the clustering process, a robust fuzzy clustering model with a trimming rule, called Trimmed Fuzzy $$C$$ C -medoids for interval-valued data (TrFCMd-ID), is proposed. In order to show the good performances of the robust clustering model, a simulation study and two applications are provided.

We propose a robust fuzzy clustering model for classifying time series, considering the autoregressive metric based. In particular, we suggest a clustering procedure which: 1) considers an autoregressive parameterization of the time series, capable of representing a large class of time series; 2) inherits the benefits of the partitioning around medoids approach, classifying time series in classes characterized by prototypal observed time series (the “medoid” time series), which synthesize the structural information of each cluster; 3) inherits the benefits of the fuzzy approach, capturing the vague (fuzzy) behaviour of particular time series, such as “middle” time series (time series with middle features in respect of the considered clusters in all time period) and “switching” time series (time series with a pattern typical of a given cluster during a certain time period and a completely different pattern, similar to another cluster, in another time period); 4) is capable of suitably neutralizing the negative influence of the presence of “outlier” time series in the clustering procedure, i.e., the “outlier” time series are classified in the so-called “noise cluster” and therefore cluster structure is not altered. To illustrate the effectiveness of the proposed model, a simulation study and an application to real time series are carried out.

The research presented in this article focuses on the development of a multi-objective optimization algorithm based on the differential evolution (DE) concept combined with Mamdani-type fuzzy logic controllers (FLCs) and $$K$$ K -medoids clustering. The FLCs are used for adaptive control of the DE parameters; $$K$$ K -medoids clustering enables the algorithm to perform a more guided search by evolving neighboring vectors, i.e., vectors that belong to the same cluster. A modified version of the $$DE/best/1/bin$$ D E / b e s t / 1 / b i n algorithm is adopted as the core search component of the multi-objective optimizer. The FLCs utilize Pareto dominance and cluster-related information as input in order to adapt the algorithmic parameters dynamically. The proposed optimization algorithm is tested using a number of problems from the multi-objective optimization literature in order to investigate the effect of clustering and parameter adaptation on the algorithmic performance under various conditions, e.g., problems of high dimensionality, problems with non-convex Pareto fronts, and problems with discontinuous Pareto fronts. A detailed performance comparison between the proposed algorithm with state-of-the-art multi-objective optimizers is also presented.

Similarity plays an important role in many data mining tasks and information retrieval processes. Most of the supervised, semi-supervised, and unsupervised learning algorithms depend on using a dissimilarity function that measures the pair-wise similarity between the objects within the dataset. However, traditionally most of the similarity functions fail to adequately treat all the spatial attributes of the geospatial polygons due to the incomplete quantitative representation of structural and topological information contained within the polygonal datasets. In this paper, we propose a new dissimilarity function known as the polygonal dissimilarity function (PDF) that comprehensively integrates both the spatial and the non-spatial attributes of a polygon to specifically consider the density, distribution, and topological relationships that exist within the polygonal datasets. We represent a polygon as a set of intrinsic spatial attributes, extrinsic spatial attributes, and non-spatial attributes. Using this representation of the polygons, PDF is defined as a weighted function of the distance between two polygons in the different attribute spaces. In order to evaluate our dissimilarity function, we compare and contrast it with other distance functions proposed in the literature that work with both spatial and non-spatial attributes. In addition, we specifically investigate the effectiveness of our dissimilarity function in a clustering application using a partitional clustering technique (e.g. $$k$$ k -medoids) using two characteristically different sets of data: (a) Irregular geometric shapes determined by natural processes, i.e., watersheds and (b) semi-regular geometric shapes determined by human experts, i.e., counties.

In order to make sense of the sheer volume of metabolomic data that can be generated using current technology, robust data analysis tools are essential. We propose the use of the growing self-organizing map (GSOM) algorithm and by doing so demonstrate that a deeper analysis of metabolomics data is possible in comparison to the widely used batch-learning self-organizing map, hierarchical cluster analysis and partitioning around medoids algorithms on simulated and real-world time-course metabolomic datasets. We then applied GSOM to a recently published dataset representing metabolome response patterns of three wheat cultivars subject to a field simulated cyclic drought stress. This novel and information rich analysis provided by the proposed GSOM framework can be easily extended to other high-throughput metabolomics studies.

An emergency response system (ERS) can assist a municipality or government in improving its capabilities to respond urgent and severe events. The responsiveness and effectiveness of an ERS relies greatly on its data acquisition and processing system, which has been evolved with information technology (IT). With the rapid development of sensor networks and cloud computing, the emerging Internet of things (IoT) tends to play an increasing role in ERSs; the networks of sensors, public services, and experts are able to interact with each other and make scientific decisions to the emergencies based on real-time data. When group decision making is required in an ERS, one critical challenge is to obtain the good understanding of massive and diversified data and make consensus group decisions under a high-level stress and strict time constraint. Due to the nature of unorganized data and system complexity, an ERS depends on the perceptions and judgments of experts from different domains; it is challenging to assess the consensus of understanding on the collected data and response plans before appropriate decisions can be reached for emergencies. In this paper, the group decision-making to emergency situations is formulated as a multiple attribute group decision making (MAGDM) problem, the consensus among experts is modeled, and a new methodology is proposed to reach the understanding of emergency response plans with the maximized consensus in course of decision-making. In the implementation, the proposed methodology in integrated with computer programs and encapsulated as a service on the server. The objectives of the new methodology are (i) to enhance the comprehensive group cognizance on emergent scenarios and response plans and (ii) to accelerate the consensus for decision making with an intelligent clustering algorithm, (iii) to adjust the experts' opinions without affecting the reliability of the decision when the consensus cannot be reached from the preliminary decision-making steps. Partitioning Around Medoids (PAM) has been applied as the clustering algorithm, Particle Swarm Optimization (PSO) is deployed to adjust evaluation values automatically. The methodology is applied in a case study to illustrate its effectiveness in converging group opinions and promoting the consensus of understanding on emergencies.

Clustering remains one of the most difficult challenges in data mining. This paper proposes a new algorithm, CLAM, using a hybrid metaheuristic between VNS and Tabu Search to solve the problem of k-medoid clustering. The new technique is compared to the well-known CLARANS. Experimental results show that, given the same computation times, CLAM is more effective.

In the setting of multi-instance learning, each object is represented by a bag composed of multiple instances instead of by a single instance in a traditional learning setting. Previous works in this area only concern multi-instance prediction problems where each bag is associated with a binary (classification) or real-valued (regression) label. However, unsupervised multi-instance learning where bags are without labels has not been studied. In this paper, the problem of unsupervised multi-instance learning is addressed where a multi-instance clustering algorithm named Bamic is proposed. Briefly, by regarding bags as atomic data items and using some form of distance metric to measure distances between bags, Bamic adapts the popular k -Medoids algorithm to partition the unlabeled training bags into k disjoint groups of bags. Furthermore, based on the clustering results, a novel multi-instance prediction algorithm named Bartmip is developed. Firstly, each bag is re-represented by a k-dimensional feature vector, where the value of the i-th feature is set to be the distance between the bag and the medoid of the i-th group. After that, bags are transformed into feature vectors so that common supervised learners are used to learn from the transformed feature vectors each associated with the original bag's label. Extensive experiments show that Bamic could effectively discover the underlying structure of the data set and Bartmip works quite well on various kinds of multi-instance prediction problems.

Besides traditional domains (e.g., resource allocation, data mining applications), algorithms for medoid computation and related problems will play an important role in numerous emerging fields, such as location based services and sensor networks. Since the k-medoid problem is NP-hard, all existing work deals with approximate solutions on relatively small datasets. This paper aims at efficient methods for very large spatial databases, motivated by: (1) the high and ever increasing availability of spatial data, and (2) the need for novel query types and improved services. The proposed solutions exploit the intrinsic grouping properties of a data partition index in order to read only a small part of the dataset. Compared to previous approaches, we achieve results of comparable or better quality at a small fraction of the CPU and I/O costs (seconds as opposed to hours, and tens of node accesses instead of thousands). In addition, we study medoid-aggregate queries, where k is not known in advance, but we are asked to compute a medoid set that leads to an average distance close to a user-specified value. Similarly, medoid-optimization queries aim at minimizing both the number of medoids k and the average distance. We also consider the max version for the aforementioned problems, where the goal is to minimize the maximum (instead of the average) distance between any object and its closest medoid. Finally, we investigate bichromatic and weighted medoid versions for all query types, as well as, maximum capacity and dynamic medoids.

We propose a hybrid genetic algorithm for k-medoids clustering. A novel heuristic operator is designed and integrated with the genetic algorithm to fine-tune the search. Further, variable length individuals that encode different number of medoids (clusters) are used for evolution with a modified Davies-Bouldin index as a measure of the fitness of the corresponding partitionings. As a result the proposed algorithm can efficiently evolve appropriate partitionings while making no a priori assumption about the number of clusters present in the datasets. In the experiments, we show the effectiveness of the proposed algorithm and compare it with other related clustering methods.

One of the fundamental challenges in crime mapping and analysis is pattern recognition. Efforts and methods to detect crime hot-spots, or geographic areas of elevated criminal activity, are wide ranging. For aggregate data, such as total crime events in a census tract(s), measures of spatial autocorrelation have proven useful. For disaggregate data (i.e. individual crime events), kernel density smoothing and non-hierarchical cluster analysis (e.g. k-means), are widely used. Non-hierarchical techniques are particularly effective in delineating geographic space into areas of higher or lower crime concentrations, because each observation is assigned to one and only one cluster. The resulting set of partitions provides clear-cut spatial boundaries that can be used for hot-spot evaluation and interpretation. However, the strength of non-hierarchical methods can also be viewed as a weakness. Although the hard-clustering of observations into a set of discrete clusters is helpful, there are many cases where ambiguity exists in the data. In such cases, a more generalized approach for hot-spot detection would be helpful. The purpose of this paper is to explore the use of a generalized partitioning method known as fuzzy clustering for hot-spot detection. Functional and visual comparisons of fuzzy clustering and two hard-clustering approaches (medoid and k-means), across a range of cluster values are analyzed. The empirical results suggest that a fuzzy clustering approach is better equipped to handle intermediate cases and spatial outliers.

In this paper we present a method for clustering geo-referenced data suitable for applications in spatial data mining, based on the medoid method. The medoid method is related to k -MEANS, with the restriction that cluster representatives be chosen from among the data elements. Although the medoid method in general produces clusters of high quality, especially in the presence of noise, it is often criticized for the Ω(n 2 ) time that it requires. Our method incorporates both proximity and density information to achieve high-quality clusters in subquadratic time; it does not require that the user specify the number of clusters in advance. The time bound is achieved by means of a fast approximation to the medoid objective function, using Delaunay triangulations to store proximity information.