Multi-density urban hotspots detection in smart cities: A data-driven approach and experiments

The detection of city hotspots from geo-referenced urban data is a valuable knowledge support for planners, scientists, and policymakers. However, the application of classic density-based clustering algorithms on multi-density data can produce inaccurate results. Since metropolitan cities are heavily characterized by variable densities, multi-density clustering seems to be more appropriate to discover city hotspots. This paper presents CHD (City Hotspot Detector), a multi-density approach to discover urban hotspots in a city, by reporting an extensive comparative analysis with three classic density-based clustering algorithms, on both state-of-the-art and real-world datasets. The comparative experimental evaluation in an urban scenario shows that the proposed multi-density algorithm, enhanced by an additional rolling moving average technique, detects higher quality city hotspots than other classic density-based approaches proposed in literature.     

Flocking based approach for data clustering

Data clustering is a process of extracting similar groups of the underlying data whose labels are hidden. This paper describes different approaches for solving data clustering problem. Particle swarm optimization (PSO) has been recently used to address clustering task. An overview of PSO-based clustering approaches is presented in this paper. These approaches mimic the behavior of biological swarms seeking food located in different places. Best locations for finding food are in dense areas and in regions far enough from others. PSO-based clustering approaches are evaluated using different data sets. Experimental results indicate that these approaches outperform K-means, K-harmonic means, and fuzzy c-means clustering algorithms.     

Hybrid strategy for selecting compact set of clustering partitions

The selection of the most appropriate clustering algorithm is not a straightforward task, given that there is no clustering algorithm capable of determining the actual groups present in any dataset. A potential solution is to use different clustering algorithms to produce a set of partitions (solutions) and then select the best partition produced according to a specified validation measure; these measures are generally biased toward one or more clustering algorithms. Nevertheless, in several real cases, it is important to have more than one solution as the output. To address these problems, we present a hybrid partition selection algorithm, HSS, which accepts as input a set of base partitions potentially generated from clustering algorithms with different biases and aims, to return a reduced and yet diverse set of partitions (solutions). HSS comprises three steps: (i) the application of a multiobjective algorithm to a set of base partitions to generate a Pareto Front (PF) approximation; (ii) the division of the solutions from the PF approximation into a certain number of regions; and (iii) the selection of a solution per region by applying the Adjusted Rand Index. We compare the results of our algorithm with those of another selection strategy, ASA. Furthermore, we test HSS as a post-processing tool for two clustering algorithms based on multiobjective evolutionary computing: MOCK and MOCLE. The experiments revealed the effectiveness of HSS in selecting a reduced number of partitions while maintaining their quality.     

Efficient Parallel Algorithms for Hierarchical Clustering on Arrays with Reconfigurable Optical Buses

Clustering is a basic operation in image processing and computer vision, and it plays an important role in unsupervised pattern recognition and image segmentation. While there are many methods for clustering, the single-link hierarchical clustering is one of the most popular techniques. In this paper, with the advantages of both optical transmission and electronic computation, we design efficient parallel hierarchical clustering algorithms on the arrays with reconfigurable optical buses (AROB). We first design three efficient basic operations which include the matrix multiplication of two N×N matrices, finding the minimum spanning tree of a graph with N vertices, and identifying the connected component containing a specified vertex. Based on these three data operations, an O(log N) time parallel hierarchical clustering algorithm is proposed using N³ processors. Furthermore, if the connectivity of the AROB with four-port connection is allowed, two constant time clustering algorithms can be also derived using N⁴ and N³ processors, respectively. These results improve on previously known algorithms developed on various parallel computational models.     

A semi-supervised approach to sentiment analysis using revised sentiment strength based on SentiWordNet

Emergence of MapReduce (MR) framework for scaling data mining and machine learning algorithms provides for Volume, while handling of Variety and Velocity needs to be skilfully crafted in algorithms. So far, scalable clustering algorithms have focused solely on Volume, taking advantage of the MR framework. In this paper we present a MapReduce algorithm—data aware scalable clustering (DASC), which is capable of handling the 3 Vs of big data by virtue of being (i) single scan and distributed to handle Volume, (ii) incremental to cope with Velocity and (iii) versatile in handling numeric and categorical data to accommodate Variety. DASC algorithm incrementally processes infinitely growing data set stored on distributed file system and delivers quality clustering scheme while ensuring recency of patterns. The up-to-date synopsis is preserved by the algorithm for the data seen so far. Each new data increment is processed and merged with the synopsis. Since the synopsis itself may grow very large in size, the algorithm stores it as a file. This makes DASC algorithm truly scalable. Exclusive clusters are obtained on demand by applying connected component analysis (CCA) algorithm over the synopsis. CCA presents subtle roadblock to effective parallelism during clustering. This problem is overcome by accomplishing the task in two stages. In the first stage, hyperclusters are identified based on prevailing data characteristics. The second stage utilizes this knowledge to determine the degree of parallelism, thereby making DASC data aware. Hyperclusters are distributed over the available compute nodes for discovering embedded clusters in parallel. Staged approach for clustering yields dual advantage of improved parallelism and desired complexity in \(\mathcal {MRC}^0\) class. DASC algorithm is empirically compared with incremental Kmeans and Scalable Kmeans++ algorithms. Experimentation on real-world and synthetic data with approximately 1.2 billion data points demonstrates effectiveness of DASC algorithm. Empirical observations of DASC execution are in consonance with the theoretical analysis with respect to stability in resources utilization and execution time.     

A flexible cluster-oriented alternative clustering algorithm for choosing from the Pareto front of solutions

Supervised alternative clustering is the problem of finding a set of clusterings which are of high quality and different from a given negative clustering. The task is therefore a clear multi-objective optimization problem. Optimizing two conflicting objectives at the same time requires dealing with trade-offs. Most approaches in the literature optimize these objectives sequentially (one objective after another one) or indirectly (by some heuristic combination of the objectives). Solving a multi-objective optimization problem in these ways can result in solutions which are dominated, and not Pareto-optimal. We develop a direct algorithm, called COGNAC, which fully acknowledges the multiple objectives, optimizes them directly and simultaneously, and produces solutions approximating the Pareto front. COGNAC performs the recombination operator at the cluster level instead of at the object level, as in the traditional genetic algorithms. It can accept arbitrary clustering quality and dissimilarity objectives and provides solutions dominating those obtained by other state-of-the-art algorithms. Based on COGNAC, we propose another algorithm called SGAC for the sequential generation of alternative clusterings where each newly found alternative clustering is guaranteed to be different from all previous ones. The experimental results on widely used benchmarks demonstrate the advantages of our approach.

     

Time series labeling algorithms based on the K-nearest neighbors’ frequencies

In the current paper, time series labeling task is analyzed and some solution algorithms are presented. In these algorithms, fuzzy c-means clustering, which is one of the unsupervised learning methods, is used to obtain the labels of the time series. Then K-nearest neighborhood (KNN) rule is performed on the labels to obtain more relevant smooth intervals.As an application, the handled labeling algorithms are performed on bispectral index (BIS) data, which are time series measures of brain activity. Finally, smoothing process is found useful in the estimation of sedation stage labels.     

A simultaneous learning framework for clustering and classification

Traditional pattern recognition generally involves two tasks: unsupervised clustering and supervised classification. When class information is available, fusing the advantages of both clustering learning and classification learning into a single framework is an important problem worthy of study. To date, most algorithms generally treat clustering learning and classification learning in a sequential or two-step manner, i.e., first execute clustering learning to explore structures in data, and then perform classification learning on top of the obtained structural information. However, such sequential algorithms cannot always guarantee the simultaneous optimality for both clustering and classification learning. In fact, the clustering learning in these algorithms just aids the subsequent classification learning and does not benefit from the latter. To overcome this problem, a simultaneous learning framework for clustering and classification (SCC) is presented in this paper. SCC aims to achieve three goals: (1) acquiring the robust classification and clustering simultaneously; (2) designing an effective and transparent classification mechanism; (3) revealing the underlying relationship between clusters and classes. To this end, with the Bayesian theory and the cluster posterior probabilities of classes, we define a single objective function to which the clustering process is directly embedded. By optimizing this objective function, the effective and robust clustering and classification results are achieved simultaneously. Experimental results on both synthetic and real-life datasets show that SCC achieves promising classification and clustering results at one time.     

Modified FDP cluster algorithm and its application in protein conformation clustering analysis

We present a modified find density peaks (MFDP) clustering algorithm. In the MFDP, a critical parameter, dc, is auto-defined by minimizing the entropy of all points. By considering both the point density, ρ, and large distance from points with higher densities, δ, the high-dimensional points are transformed into a 2D space. The halo points of the original FDP cluster algorithm are redefined, and a definition of boundary points is introduced to illustrate the intersection region between clusters. To demonstrate the clustering ability, the distance-based K-means clustering and density-based algorithms DBSCAN, original FDP are employed respectively. Four criteria are introduced to evaluate the clustering algorithms quantitatively. For most of the cases, the MFDP provides a superior clustering result than both of the typical clustering algorithms, and FDP in 20 commonly used benchmark datasets, particularly in clearly depicting the intersection region between clusters. Finally, we evaluate the performance of the MFDP in the cluster analysis of conformations in molecular dynamics (MD). In the MD clustering process, eight typical cluster center conformations are selected in six collective variable spaces. Moreover, it is in strong agreement with the experiment results. The clustering results demonstrate the potential for generalized applications of the modified algorithm to similar problems.     

Bottom-up discovery of frequent rooted unordered subtrees

In the past decade, XML has emerged as the standard language for information exchanging over the Internet. Due to its tree-structure paradigm, XML is superior for its capability of storing, querying, and manipulating complex data. Therefore, discovering frequent tree patterns over tree-structured data has become an interesting topic for XML data management. In this paper, we propose a tree mining algorithm, named BUXMiner, for finding a special class of frequent trees, called rooted unordered trees, from a tree-structured database. BUXMiner employs an efficient bottom-up approach to enumerate all candidate trees over a compact global tree guide and computes the frequent trees based on the tree guide. In addition to BUXMiner, we also propose a mining approach called BUMXMiner to discover the maximal frequent rooted unordered trees. We compare BUXMiner with previous tree-structure mining algorithms, namely XQPMinerTID and FastXMiner, which were also proposed to discover rooted unordered trees. The experimental results show that our algorithm outperforms XQPMinerTID and FastXMiner in terms of efficiency. The performance results from real-world applications also indicate the usefulness of our proposed tree mining algorithms in a variety of web applications, such as analysis of web page access patterns and mining frequent XML query patterns for caching.     

An improved,randomized algorithm for parallel selection with an experimental study

A common statistical problem is that of finding the median element in a set of data. This paper presents an efficient randomized high-level parallel algorithm for finding the median given a set of elements distributed across a parallel machine. In fact, our algorithm solves the general selection problem that requires the determination of the element of rank k, for an arbitrarily given integer k.Our general framework is an SPMD distributed-memory programming model that is enhanced by a set of communication primitives. We use efficient techniques for distributing and coalescing data as well as efficient combinations of task and data parallelism. The algorithms have been coded in the message-passing standard MPI, and our experimental results from the IBM SP-2 illustrate the scalability and efficiency of our algorithm and improve upon all the related experimental results known to the author.The main contributions of this paper are(1) New techniques for speeding the performance of certain randomized algorithms, such as selection, which are efficient with likely probability.(2) A new, practical randomized selection algorithm (UltraFast) with significantly improved convergence.     

An optimal hierarchical clustering algorithm for gene expression data

Microarrays are used for measuring expression levels of thousands of genes simultaneously. Clustering algorithms are used on gene expression data to find co-regulated genes. An often used clustering strategy is the Pearson correlation coefficient based hierarchical clustering algorithm presented in [Proc. Nat. Acad. Sci. 95 (25) (1998) 14863-14868], which takes O(N³) time. We note that this run time can be reduced to O(N²) by applying known hierarchical clustering algorithms [Proc. 9th Annual ACM-SIAM Symposium on Discrete Algorithms, 1998, pp. 619-628] to this problem. In this paper, we present an algorithm which runs in O(NlogN) time using a geometrical reduction and show that it is optimal.     

Fuzzy clustering algorithms based on resolution and their application in image compression

This paper presents an idea of clustering resolution. On the basis of the idea, fuzzy clustering algorithms based on resolution are deduced, which naturally comprise a set of clustering algorithms. Thus, c-means algorithm and fuzzy c-means algorithms are actually special examples in the set. As an application for codebook design in image compression based on vector quantization, fuzzy clustering algorithms based on multiresolution are developed, which are almost prior to conventional algorithms in all aspects.     

Clustering using PK-D: A connectivity and density dissimilarity

We present a new dissimilarity, which combines connectivity and density information. Usually, connectivity and density are conceived as mutually exclusive concepts; however, we discuss a novel procedure to merge both information sources. Once we have calculated the new dissimilarity, we apply MDS in order to find a low dimensional vector space representation. The new data representation can be used for clustering and data visualization, which is not pursued in this paper. Instead we use clustering to estimate the gain from our approach consisting of dissimilarity + MDS. Hence, we analyze the partitions’ quality obtained by clustering high dimensional data with various well known clustering algorithms based on density, connectivity and message passing, as well as simple algorithms like k-means and Hierarchical Clustering (HC). The quality gap between the partitions found by k-means and HC alone compared to k-means and HC using our new low dimensional vector space representation is remarkable. Moreover, our tests using high dimensional gene expression and image data confirm these results and show a steady performance, which surpasses spectral clustering and other algorithms relevant to our work.     

GoSCAN: Decentralized scalable data clustering

Identifying clusters is an important aspect of analyzing large datasets. Clustering algorithms classically require access to the complete dataset. However, as huge amounts of data are increasingly originating from multiple, dispersed sources in distributed systems, alternative solutions are required. Furthermore, data and network dynamicity in a distributed setting demand adaptable clustering solutions that offer accurate clustering models at a reasonable pace. In this paper, we propose GoScan, a fully decentralized density-based clustering algorithm which is capable of clustering dynamic and distributed datasets without requiring central control or message flooding. We identify two major tasks: finding the core data points, and forming the actual clusters, which we execute in parallel employing gossip-based communication. This approach is very efficient, as it offers each peer enough authority to discover the clusters it is interested in. Our algorithm poses no extra burden of overlay formation in the network, while providing high levels of scalability. We also offer several optimizations to the basic clustering algorithm for improving communication overhead and processing costs. Coping with dynamic data is made possible by introducing an age factor, which gradually detects data-set changes and enables clustering updates. In our experimental evaluation, we will show that GoSCAN can discover the clusters efficiently with scalable transmission cost.     

Partitioned EDF scheduling: a closer look

The partitioned EDF scheduling of implicit-deadline sporadic task systems upon identical multiprocessor platforms is considered. The problem is known to be intractable, but many different polynomial-time algorithms have been proposed for solving it approximately. These different approximation algorithms have previously been compared using utilization bounds; they are compared here using a different metric—the speedup factor. It is shown that from the perspective of their speedup factors, the best partitioning algorithms are those that (i) assign the tasks in decreasing order of utilization; and (ii) are “reasonable” in the sense that they will assign a task if there is capacity available on some processor—such algorithms include the widely-used First-Fit Decreasing, Best-Fit Decreasing, and Worst-Fit Decreasing partitioning heuristics.     

Task assignment algorithms for two-type heterogeneous multiprocessors

Consider the problem of assigning implicit-deadline sporadic tasks on a heterogeneous multiprocessor platform comprising two different types of processors—such a platform is referred to as two-type platform. We present two low degree polynomial time-complexity algorithms, SA and SA-P, each providing the following guarantee. For a given two-type platform and a task set, if there exists a task assignment such that tasks can be scheduled to meet deadlines by allowing them to migrate only between processors of the same type (intra-migrative), then (i) using SA, it is guaranteed to find such an assignment where the same restriction on task migration applies but given a platform in which processors are $1+\frac{\alpha}{2}$ times faster and (ii) SA-P succeeds in finding a task assignment where tasks are not allowed to migrate between processors (non-migrative) but given a platform in which processors are 1+α times faster. The parameter 0<α≤1 is a property of the task set; it is the maximum of all the task utilizations that are no greater than 1. We evaluate average-case performance of both the algorithms by generating task sets randomly and measuring how much faster processors the algorithms need (which is upper bounded by $1+\frac{\alpha}{2}$ for SA and 1+α for SA-P) in order to output a feasible task assignment (intra-migrative for SA and non-migrative for SA-P). In our evaluations, for the vast majority of task sets, these algorithms require significantly smaller processor speedup than indicated by their theoretical bounds. Finally, we consider a special case where no task utilization in the given task set can exceed one and for this case, we (re-)prove the performance guarantees of SA and SA-P. We show, for both of the algorithms, that changing the adversary from intra-migrative to a more powerful one, namely fully-migrative, in which tasks can migrate between processors of any type, does not deteriorate the performance guarantees. For this special case, we compare the average-case performance of SA-P and a state-of-the-art algorithm by generating task sets randomly. In our evaluations, SA-P outperforms the state-of-the-art by requiring much smaller processor speedup and by running orders of magnitude faster.     

HC_AB: A new heuristic clustering algorithm based on Approximate Backbone

Clustering is an important research area with numerous applications in pattern recognition, machine learning, and data mining. Since the clustering problem on numeric data sets can be formulated as a typical combinatorial optimization problem, many researches have addressed the design of heuristic algorithms for finding sub-optimal solutions in a reasonable period of time. However, most of the heuristic clustering algorithms suffer from the problem of being sensitive to the initialization and do not guarantee the high quality results. Recently, Approximate Backbone (AB), i.e., the commonly shared intersection of several sub-optimal solutions, has been proposed to address the sensitivity problem of initialization. In this paper, we aim to introduce the AB into heuristic clustering to overcome the initialization sensitivity of conventional heuristic clustering algorithms. The main advantage of the proposed method is the capability of restricting the initial search space around the optimal result by defining the AB, and in turn, reducing the impact of initialization on clustering, eventually improving the performance of heuristic clustering. Experiments on synthetic and real world data sets are performed to validate the effectiveness of the proposed approach in comparison to three conventional heuristic clustering algorithms and three other algorithms with improvement on initialization.     

Incremental K-clique clustering in dynamic social networks

Clustering entities into dense parts is an important issue in social network analysis. Real social networks usually evolve over time and it remains a problem to efficiently cluster dynamic social networks. In this paper, a dynamic social network is modeled as an initial graph with an infinite change stream, called change stream model, which naturally eliminates the parameter setting problem of snapshot graph model. Based on the change stream model, the incremental version of a well known k-clique clustering problem is studied and incremental k-clique clustering algorithms are proposed based on local DFS (depth first search) forest updating technique. It is theoretically proved that the proposed algorithms outperform corresponding static ones and incremental spectral clustering algorithm in terms of time complexity. The practical performances of our algorithms are extensively evaluated and compared with the baseline algorithms on ENRON and DBLP datasets. Experimental results show that incremental k-clique clustering algorithms are much more efficient than corresponding static ones, and have no accumulating errors that incremental spectral clustering algorithm has and can capture the evolving details of the clusters that snapshot graph model based algorithms miss.