Abstract: In this paper we used data mining techniques to
identify outlier patients who are using large amount of drugs over a
long period of time. Any healthcare or health insurance system
should deal with the quantities of drugs utilized by chronic diseases
patients. In Kingdom of Bahrain, about 20% of health budget is spent
on medications. For the managers of healthcare systems, there is no
enough information about the ways of drug utilization by chronic
diseases patients, is there any misuse or is there outliers patients. In
this work, which has been done in cooperation with information
department in the Bahrain Defence Force hospital; we select the data
for Cardiac patients in the period starting from 1/1/2008 to
December 31/12/2008 to be the data for the model in this paper. We
used three techniques for finding the drug utilization for cardiac
patients. First we applied a clustering technique, followed by
measuring of clustering validity, and finally we applied a decision
tree as classification algorithm. The clustering results is divided into
three clusters according to the drug utilization, for 1603 patients, who
received 15,806 prescriptions during this period can be partitioned
into three groups, where 23 patients (2.59%) who received 1316
prescriptions (8.32%) are classified to be outliers. The classification
algorithm shows that the use of average drug utilization and the age,
and the gender of the patient can be considered to be the main
predictive factors in the induced model.
Abstract: In the semiconductor manufacturing process, large
amounts of data are collected from various sensors of multiple
facilities. The collected data from sensors have several different characteristics
due to variables such as types of products, former processes
and recipes. In general, Statistical Quality Control (SQC) methods
assume the normality of the data to detect out-of-control states of
processes. Although the collected data have different characteristics,
using the data as inputs of SQC will increase variations of data,
require wide control limits, and decrease performance to detect outof-
control. Therefore, it is necessary to separate similar data groups
from mixed data for more accurate process control. In the paper,
we propose a regression tree using split algorithm based on Pearson
distribution to handle non-normal distribution in parametric method.
The regression tree finds similar properties of data from different
variables. The experiments using real semiconductor manufacturing
process data show improved performance in fault detecting ability.
Abstract: Terminal localization for indoor Wireless Local Area
Networks (WLANs) is critical for the deployment of location-aware
computing inside of buildings. A major challenge is obtaining high
localization accuracy in presence of fluctuations of the received signal
strength (RSS) measurements caused by multipath fading. This paper
focuses on reducing the effect of the distance-varying noise by spatial
filtering of the measured RSS. Two different survey point geometries
are tested with the noise reduction technique: survey points arranged
in sets of clusters and survey points uniformly distributed over the
network area. The results show that the location accuracy improves
by 16% when the filter is used and by 18% when the filter is applied
to a clustered survey set as opposed to a straight-line survey set.
The estimated locations are within 2 m of the true location, which
indicates that clustering the survey points provides better localization
accuracy due to superior noise removal.
Abstract: Clustering large populations is an important problem
when the data contain noise and different shapes. A good clustering
algorithm or approach should be efficient enough to detect clusters
sensitively. Besides space complexity, time complexity also gains
importance as the size grows. Using hierarchies we developed a new
algorithm to split attributes according to the values they have and
choosing the dimension for splitting so as to divide the database
roughly into equal parts as much as possible. At each node we
calculate some certain descriptive statistical features of the data
which reside and by pruning we generate the natural clusters with a
complexity of O(n).
Abstract: The clustering ensembles combine multiple partitions
generated by different clustering algorithms into a single clustering
solution. Clustering ensembles have emerged as a prominent method
for improving robustness, stability and accuracy of unsupervised
classification solutions. So far, many contributions have been done to
find consensus clustering. One of the major problems in clustering
ensembles is the consensus function. In this paper, firstly, we
introduce clustering ensembles, representation of multiple partitions,
its challenges and present taxonomy of combination algorithms.
Secondly, we describe consensus functions in clustering ensembles
including Hypergraph partitioning, Voting approach, Mutual
information, Co-association based functions and Finite mixture
model, and next explain their advantages, disadvantages and
computational complexity. Finally, we compare the characteristics of
clustering ensembles algorithms such as computational complexity,
robustness, simplicity and accuracy on different datasets in previous
techniques.
Abstract: Clustering is a very well known technique in data mining. One of the most widely used clustering techniques is the kmeans algorithm. Solutions obtained from this technique depend on the initialization of cluster centers and the final solution converges to local minima. In order to overcome K-means algorithm shortcomings, this paper proposes a hybrid evolutionary algorithm based on the combination of PSO, SA and K-means algorithms, called PSO-SA-K, which can find better cluster partition. The performance is evaluated through several benchmark data sets. The simulation results show that the proposed algorithm outperforms previous approaches, such as PSO, SA and K-means for partitional clustering problem.
Abstract: A wireless sensor network with a large number of tiny sensor nodes can be used as an effective tool for gathering data in various situations. One of the major issues in wireless sensor networks is developing an energy-efficient routing protocol which has a significant impact on the overall lifetime of the sensor network. In this paper, we propose a novel hierarchical with static clustering routing protocol called Energy-Efficient Protocol with Static Clustering (EEPSC). EEPSC, partitions the network into static clusters, eliminates the overhead of dynamic clustering and utilizes temporary-cluster-heads to distribute the energy load among high-power sensor nodes; thus extends network lifetime. We have conducted simulation-based evaluations to compare the performance of EEPSC against Low-Energy Adaptive Clustering Hierarchy (LEACH). Our experiment results show that EEPSC outperforms LEACH in terms of network lifetime and power consumption minimization.
Abstract: In Multiple Sclerosis, pathological changes in the
brain results in deviations in signal intensity on Magnetic Resonance
Images (MRI). Quantitative analysis of these changes and their
correlation with clinical finding provides important information for
diagnosis. This constitutes the objective of our work. A new approach
is developed. After the enhancement of images contrast and the brain
extraction by mathematical morphology algorithm, we proceed to the
brain segmentation. Our approach is based on building statistical
model from data itself, for normal brain MRI and including clustering
tissue type. Then we detect signal abnormalities (MS lesions) as a
rejection class containing voxels that are not explained by the built
model. We validate the method on MR images of Multiple Sclerosis
patients by comparing its results with those of human expert
segmentation.
Abstract: Interpretation of aerial images is an important task in
various applications. Image segmentation can be viewed as the essential
step for extracting information from aerial images. Among many
developed segmentation methods, the technique of clustering has been
extensively investigated and used. However, determining the number
of clusters in an image is inherently a difficult problem, especially
when a priori information on the aerial image is unavailable. This
study proposes a support vector machine approach for clustering
aerial images. Three cluster validity indices, distance-based index,
Davies-Bouldin index, and Xie-Beni index, are utilized as quantitative
measures of the quality of clustering results. Comparisons on the
effectiveness of these indices and various parameters settings on the
proposed methods are conducted. Experimental results are provided
to illustrate the feasibility of the proposed approach.
Abstract: The complex hybrid and nonlinear nature of many processes that are met in practice causes problems with both structure modelling and parameter identification; therefore, obtaining a model that is suitable for MPC is often a difficult task. The basic idea of this paper is to present an identification method for a piecewise affine (PWA) model based on a fuzzy clustering algorithm. First we introduce the PWA model. Next, we tackle the identification method. We treat the fuzzy clustering algorithm, deal with the projections of the fuzzy clusters into the input space of the PWA model and explain the estimation of the parameters of the PWA model by means of a modified least-squares method. Furthermore, we verify the usability of the proposed identification approach on a hybrid nonlinear batch reactor example. The result suggest that the batch reactor can be efficiently identified and thus formulated as a PWA model, which can eventually be used for model predictive control purposes.
Abstract: Documents clustering become an essential technology
with the popularity of the Internet. That also means that fast and
high-quality document clustering technique play core topics. Text
clustering or shortly clustering is about discovering semantically
related groups in an unstructured collection of documents. Clustering
has been very popular for a long time because it provides unique
ways of digesting and generalizing large amounts of information.
One of the issues of clustering is to extract proper feature (concept)
of a problem domain. The existing clustering technology mainly
focuses on term weight calculation. To achieve more accurate
document clustering, more informative features including concept
weight are important. Feature Selection is important for clustering
process because some of the irrelevant or redundant feature may
misguide the clustering results. To counteract this issue, the proposed
system presents the concept weight for text clustering system
developed based on a k-means algorithm in accordance with the
principles of ontology so that the important of words of a cluster can
be identified by the weight values. To a certain extent, it has resolved
the semantic problem in specific areas.
Abstract: The belief K-modes method (BKM) approach is a new
clustering technique handling uncertainty in the attribute values of
objects in both the cluster construction task and the classification one.
Like the standard version of this method, the BKM results depend on
the chosen initial modes. So, one selection method of initial modes
is developed, in this paper, aiming at improving the performances of
the BKM approach. Experiments with several sets of real data show
that by considered the developed selection initial modes method, the
clustering algorithm produces more accurate results.
Abstract: Clustering in high dimensional space is a difficult
problem which is recurrent in many fields of science and
engineering, e.g., bioinformatics, image processing, pattern
reorganization and data mining. In high dimensional space some of
the dimensions are likely to be irrelevant, thus hiding the possible
clustering. In very high dimensions it is common for all the objects in
a dataset to be nearly equidistant from each other, completely
masking the clusters. Hence, performance of the clustering algorithm
decreases.
In this paper, we propose an algorithmic framework which
combines the (reduct) concept of rough set theory with the k-means
algorithm to remove the irrelevant dimensions in a high dimensional
space and obtain appropriate clusters. Our experiment on test data
shows that this framework increases efficiency of the clustering
process and accuracy of the results.
Abstract: Selection of the best possible set of suppliers has a
significant impact on the overall profitability and success of any
business. For this reason, it is usually necessary to optimize all
business processes and to make use of cost-effective alternatives for
additional savings. This paper proposes a new efficient context-aware
supplier selection model that takes into account possible changes of
the environment while significantly reducing selection costs. The
proposed model is based on data clustering techniques while
inspiring certain principles of online algorithms for an optimally
selection of suppliers. Unlike common selection models which re-run
the selection algorithm from the scratch-line for any decision-making
sub-period on the whole environment, our model considers the
changes only and superimposes it to the previously defined best set
of suppliers to obtain a new best set of suppliers. Therefore, any recomputation
of unchanged elements of the environment is avoided
and selection costs are consequently reduced significantly. A
numerical evaluation confirms applicability of this model and proves
that it is a more optimal solution compared with common static
selection models in this field.
Abstract: Wireless Sensor Networks (WSNs) are wireless
networks consisting of number of tiny, low cost and low power
sensor nodes to monitor various physical phenomena like
temperature, pressure, vibration, landslide detection, presence of any
object, etc. The major limitation in these networks is the use of nonrechargeable
battery having limited power supply. The main cause of
energy consumption WSN is communication subsystem. This paper
presents an efficient grid formation/clustering strategy known as Grid
based level Clustering and Aggregation of Data (GCAD). The
proposed clustering strategy is simple and scalable that uses low duty
cycle approach to keep non-CH nodes into sleep mode thus reducing
energy consumption. Simulation results demonstrate that our
proposed GCAD protocol performs better in various performance
metrics.
Abstract: This paper introduces new algorithms (Fuzzy relative
of the CLARANS algorithm FCLARANS and Fuzzy c Medoids
based on randomized search FCMRANS) for fuzzy clustering of
relational data. Unlike existing fuzzy c-medoids algorithm (FCMdd)
in which the within cluster dissimilarity of each cluster is minimized
in each iteration by recomputing new medoids given current
memberships, FCLARANS minimizes the same objective function
minimized by FCMdd by changing current medoids in such away
that that the sum of the within cluster dissimilarities is minimized.
Computing new medoids may be effected by noise because outliers
may join the computation of medoids while the choice of medoids in
FCLARANS is dictated by the location of a predominant fraction of
points inside a cluster and, therefore, it is less sensitive to the
presence of outliers. In FCMRANS the step of computing new
medoids in FCMdd is modified to be based on randomized search.
Furthermore, a new initialization procedure is developed that add
randomness to the initialization procedure used with FCMdd. Both
FCLARANS and FCMRANS are compared with the robust and
linearized version of fuzzy c-medoids (RFCMdd). Experimental
results with different samples of the Reuter-21578, Newsgroups
(20NG) and generated datasets with noise show that FCLARANS is
more robust than both RFCMdd and FCMRANS. Finally, both
FCMRANS and FCLARANS are more efficient and their outputs
are almost the same as that of RFCMdd in terms of classification
rate.
Abstract: This paper presents a new approach for image
segmentation by applying Pillar-Kmeans algorithm. This
segmentation process includes a new mechanism for clustering the
elements of high-resolution images in order to improve precision and
reduce computation time. The system applies K-means clustering to
the image segmentation after optimized by Pillar Algorithm. The
Pillar algorithm considers the pillars- placement which should be
located as far as possible from each other to withstand against the
pressure distribution of a roof, as identical to the number of centroids
amongst the data distribution. This algorithm is able to optimize the
K-means clustering for image segmentation in aspects of precision
and computation time. It designates the initial centroids- positions
by calculating the accumulated distance metric between each data
point and all previous centroids, and then selects data points which
have the maximum distance as new initial centroids. This algorithm
distributes all initial centroids according to the maximum
accumulated distance metric. This paper evaluates the proposed
approach for image segmentation by comparing with K-means and
Gaussian Mixture Model algorithm and involving RGB, HSV, HSL
and CIELAB color spaces. The experimental results clarify the
effectiveness of our approach to improve the segmentation quality in
aspects of precision and computational time.
Abstract: The present study presents a new approach to automatic
data clustering and classification problems in large and complex
databases and, at the same time, derives specific types of explicit rules
describing each cluster. The method works well in both sparse and
dense multidimensional data spaces. The members of the data space
can be of the same nature or represent different classes. A number
of N-dimensional ellipsoids are used for enclosing the data clouds.
Due to the geometry of an ellipsoid and its free rotation in space
the detection of clusters becomes very efficient. The method is based
on genetic algorithms that are used for the optimization of location,
orientation and geometric characteristics of the hyper-ellipsoids. The
proposed approach can serve as a basis for the development of
general knowledge systems for discovering hidden knowledge and
unexpected patterns and rules in various large databases.
Abstract: The prediction of Software quality during development life cycle of software project helps the development organization to make efficient use of available resource to produce the product of highest quality. “Whether a module is faulty or not" approach can be used to predict quality of a software module. There are numbers of software quality prediction models described in the literature based upon genetic algorithms, artificial neural network and other data mining algorithms. One of the promising aspects for quality prediction is based on clustering techniques. Most quality prediction models that are based on clustering techniques make use of K-means, Mixture-of-Guassians, Self-Organizing Map, Neural Gas and fuzzy K-means algorithm for prediction. In all these techniques a predefined structure is required that is number of neurons or clusters should be known before we start clustering process. But in case of Growing Neural Gas there is no need of predetermining the quantity of neurons and the topology of the structure to be used and it starts with a minimal neurons structure that is incremented during training until it reaches a maximum number user defined limits for clusters. Hence, in this work we have used Growing Neural Gas as underlying cluster algorithm that produces the initial set of labeled cluster from training data set and thereafter this set of clusters is used to predict the quality of test data set of software modules. The best testing results shows 80% accuracy in evaluating the quality of software modules. Hence, the proposed technique can be used by programmers in evaluating the quality of modules during software development.
Abstract: Cancer classification to their corresponding cohorts has been key area of research in bioinformatics aiming better prognosis of the disease. High dimensionality of gene data has been makes it a complex task and requires significance data identification technique in order to reducing the dimensionality and identification of significant information. In this paper, we have proposed a novel approach for classification of oral cancer into metastasis positive and negative patients. We have used significance analysis of microarrays (SAM) for identifying significant genes which constitutes gene signature. 3 different gene signatures were identified using SAM from 3 different combination of training datasets and their classification accuracy was calculated on corresponding testing datasets using k-Nearest Neighbour (kNN), Fuzzy C-Means Clustering (FCM), Support Vector Machine (SVM) and Backpropagation Neural Network (BPNN). A final gene signature of only 9 genes was obtained from above 3 individual gene signatures. 9 gene signature-s classification capability was compared using same classifiers on same testing datasets. Results obtained from experimentation shows that 9 gene signature classified all samples in testing dataset accurately while individual genes could not classify all accurately.