Recent Trends in Incremental Clustering: A Review

IOSR Journal of Computer Engineering (IOSR-JCE)
e-ISSN: 2278-0661,p-ISSN: 2278-8727, Volume 19, Issue 1, Ver. I (Jan.-Feb. 2017), PP 19-24
www.iosrjournals.org
DOI: 10.9790/0661-1901011924 www.iosrjournals.org 19 | Page
Recent Trends in Incremental Clustering: A Review
Neha Chopade1
, Jitendra Sheetlani2
1
(Department of Computer Application, SIES College of Management Studies/ University of Mumbai, India)
2
(Department of Computer Science of Engineering/Sri Satya Sai Universityof Technology and Medical Sciences
India)
Abstract: This paper presents a review on recent trends in incremental clustering algorithms. It tries to focus
on both clustering based on similarity measure and clustering not based on similarity measure. In this context,
the paper is devoted to various typical incremental clustering algorithms. Mainly optimization, genetic and
fuzzy approaches of these algorithms is covered in the paper. The paper is original with respect to one aspect
that is, it provides a complete overview that is fully devoted to evolutionary algorithms for incremental
clustering. A number of references are provided that describe applications of evolutionary algorithms for
incremental clustering in different domains, such as human activity detection, online fault detection, information
security, track an object consistently throughout the network solving boundary problem etc.
Keywords: fuzzy logic, incremental clustering, natural genetics, optimization, similarity measure.
I. Introduction
With the rapid development of World Wide Web, it becomes more and more difficult for users to find
online information they need. Therefore, there is a huge potential to collect valuable information and structure
behind Web documents to improve the intelligence and efficiency of internet. Over the past few years, Web
mining techniques have shown rapid progress and been widely used. One of these techniques is document
clustering, which tries to identify inherent groupings of text documents so that a set of clusters is produced in
which clusters exhibit high intra-cluster similarity and low inter-cluster similarity. It is particularly useful in
many applications such as grouping search results, clustering Web documents, and others.There is a large body
of work that investigates clustering methods. Based on accumulation rules of data objects in clustering and
methods employing these rules, clustering methods could be divided into four types: hierarchical clustering,
partitional clustering, density & grid-based clustering and others. Hierarchical and partitional clustering methods
are used in many applications, and their representative algorithms include agglomerative hierarchical clustering
algorithm and K-Means algorithm, respectively. Currently, to meet the demands of online applications where
documents are generated in the course of using, such as blog and wiki, incremental clustering becomes a
research focus. Incremental clustering algorithms work by processing data objects one at a time, incrementally
assigning data objects to their respective clusters while they progress. Typical examples include Single-Pass
Clustering, KNearest Neighbor clustering (KNN). This paper will analyze recent representative incremental
clustering algorithms from the aspect of algorithm thinking, key techniques, advantages and disadvantages, and
compare their clustering quality by experiments on some datasets. The rest of this paper is organized as follows:
Section 2 briefly introduces the existing typical incremental clustering algorithms. Section 3 expatiates on the
experiments carried out and discusses the experimental results with conclusion.
II. Incremental Clustering Algorithms
In current Web applications, there is much User-Generated Content (UGC) which covers a range of
media content available in modern communications technologies, such as question-answer databases, digital
video, blogging, podcasting, forums, review-sites, social networking, mobile phone photography and wikis .
User-Generated Content has also been characterized as 'Conversational Media', which is a key characteristic of
so-called Web 2.0 which encourages the publishing of one's own content and commenting on other people's. In
above situations, the dataset is dynamic, so it is impossible to collect all data objects before starting clustering.
When new data comes, non-incremental clustering will have to re-cluster all the data, which certainly decreases
efficiency and wastes computing resource. On the contrary, incremental clustering just need to group new data
and update new clusters to previous clustering results. The strategy optimizes clustering process and especially
adapts to those applications where time is a critical factor for usability. However, incremental clustering faces
several challenges.The number of pioneer documents is small, so it is difficult to obtain high clustering quality
in the early stage. When more and more documents come, we will find that some previous documents were put
into wrong groups, so it might be necessary to reassign some documents to new clusters. In another word,
documents with different order could result in different clustering results. It can be seen from above analysis
that there is still much work to do, though incremental clustering seems simple. Generally, a typical documents

clustering process mainly includes two components, namely a similarity measure and a clustering algorithm.
There are many methods for measuring document similarity, such as the Cosine measure, the Jaccard measure,
the Dice measure and the Overlap measure. One clustering method could choose different similarity measures,
and clustering results generated by the same method under various similarity measures could even have
significant difference. Therefore, it is very crucial to select an appropriate similarity measure.However, there are
some clustering methods that rely on the original document vectors not the pair-wise document similarity , such
as Suffix Tree Clustering (STC) and DC-Tree Clustering. In this section, we will briefly discuss following five
incremental clustering methods, covering above two categories.
2.1 Clustering based on Similarity
Reviews existing similarity measures, including the measures in the vector space model, the
information theoretic measure, the measures derived from popular retrieval functions and the OM-based
measures, and also proposes a novel measure based on the earth mover’s distance to evaluate document
similarity by allowing many-to-many matching between subtopics. When designing a clustering algorithm,
similarity measure choice is sensitive to the specific representation, which determines whether the algorithm can
accurately reflect the structure of various components in high dimensional data. However, there are many
methods to measure pair-wise document similarity and no selection criteria so that too often it is an arbitrary
choice to choose similarity measure although it is very important to a clustering algorithm.
1.1.1 Single-Pass Clustering
It is a very simple clustering method. The method makes the first object as the centroid for the first
cluster, and then calculates the similarity between the next object and each existing cluster centroid using some
similarity coefficient. If the highest value of the similarity is greater than the threshold value appointed
beforehand, the new object is added to the corresponding cluster and the centroid is updated; otherwise, the
object is put into a new cluster. The method is very efficient, but suffers from that the resulting clusters are not
independent of the object insertion order.
1.1.2 K-Nearest Neighbor Clustering
KNN is an approach to classifying objects based on closest training data in pattern recognition, and it
can also be used as a clustering method. According to this algorithm, an object is classified by a majority vote of
its neighbors, with the object being assigned to the class most common amongst its K nearest neighbors .
2.2 Clustering NOT based on Similarity
Some clustering algorithms are designed without obvious similarity measure. For example, in Suffix
Tree Clustering, documents are combined based on base clusters that indirectly measure the distance between
documents; DC-Tree Clustering is based on the B+-tree structure, and inserting a new document just involves
comparison of the document feature vector with the cluster vectors. Though there are no obvious similarity
measures in these algorithms, they actually include steps for measuring similarity indirectly. In another word,
the similarity measures of this type of clustering methods are different mainly in manifestations from methods
based on similarity. We briefly review the following three algorithms.
2.2.1Suffix Tree Clustering
Its kernel is a suffix tree which is a data structure keeping track of all n-grams of any length in a set of
word strings, while allowing strings to be inserted incrementally in time linear to the number of words in each
string . STC is composed of the following three steps: document cleaning, identifying base clusters, and
combining base clusters. The algorithm is theoretically fast, but it is just useful when there is enough memory
available to create the suffix tree. When creating a suffix tree from a large sequence database, the memory
requirement is difficult to be ensured, and the effectiveness of STC is decreased.
2.2.1Incremental DBSCAN
DBSCAN (Density-Based Spatial Clustering of Applications with Noise) is a data clustering algorithm
proposed by proposed a new document clustering approach based on graph model and enhanced incremental
DBSCAN. In their approach, a graph-based model is used for document representation instead of traditional
vector-based model. It is an effective incremental clustering algorithm suitable for mining in dynamically
changing databases, and we can easily update graph structure when a new document is added to database by
using graph model.
2.2.2 ICIB
ICIB (Incremental Clustering based on Information Bottleneck theory) is presented in 2011. The
method is designed to improve the accuracy and efficiency of document clustering, and resolve the issue that an
arbitrary choice of document similarity measure could produce an inaccurate clustering result. ICIB measures
document similarity with information bottleneck theory. A first document is selected randomly and classified as
one cluster, and then each remaining document is processed incrementally according to the mutual information
loss introduced by the merger of the document and each existing cluster. If the minimum value of mutual
information loss is below a certain threshold, the document will be added to its closest cluster; otherwise it will

be classified as a new cluster. The incremental clustering process is low-precision and order-dependent, which
cannot guarantee accurate clustering results. Therefore, an improved sequential clustering algorithm (SIB ) is
proposed to adjust the intermediate clustering results [1].
III. Various Techniques of Clustering
1.1 Particle Swarm Optimization (PSO)
Particle Swarm Optimization (PSO) was originally designed and introduced by Eberhart and Kennedy.
The PSO is a population based search algorithm based on the simulation of the social behavior of birds, bees or
a school of fishes. PSO originally intends to graphically simulate the graceful and unpredictable choreography
of a bird folk. Each individual within the swarm is represented by a vector in multidimensional search space.
This vector has also one assigned vector which determines the next movement of the particle and is called the
velocity vector.The PSO also determines how to update the velocity of a particle. Each particle updates its
velocity based on current velocity and the best position it has explored so far; and also based on the global best
position explored by swarm. The PSO process then is iterated a fixed number of times or until a minimum error
based on desired performance index is achieved. It has been shown that this simple model can deal with difficult
optimization problems efficiently. The PSO was originally developed for real valued spaces but many problems
are, however, defined for discrete valued spaces where the domain of the variables is finite. Classical examples
of such problems are: integer programming, scheduling and routing. In 1997, Kennedy and Eberhart introduced
a discrete binary version of PSO for discrete optimization problems. In binary PSO, each particle represents its
position in binary values which are 0 or 1. Each particle's value can then be changed (or better say mutate) from
one to zero or vice versa. In binary PSO the velocity of a particle defined as the probability that a particle might
change its state to one. Upon introduction of PSO algorithm, it was used in number of engineering applications.
Using binary PSO, proposed a high quality splitting criterion for codebooks of tree-structured vector quantizers
(TSVQ). Using binary PSO, they reduced the computation time too. Binary PSO is used to train the structure of
a Bayesian network. Although PSO is successfully used in number of engineering applications, but this
algorithm still has some shortcomings. In novel binary PSO, the velocity of a particle is its probability to change
its state from its previous state to its complement value, rather than the probability of change to 1. In this new
definition the velocity of particle and also its parameters has the same role as in real valued version of the PSO.
There are also other versions of binary PSO. authors add birth and mortality to the ordinary PSO. Also fuzzy
system can be used to improve the capability of the binary PSO [2].
1.2 Ant colony optimization
An Ant Colony Optimization algorithm (ACO) is essentially a system based on agents which simulate
the natural behavior of ants, including mechanisms of cooperation and adaptation. The use of this kind of system
as a new metaheuristic was proposed in order to solve combinatorial optimization problems. This new
metaheuristic has been shown to be both robust and versatile – in the sense that it has been successfully applied
to a range of different combinatorial optimization problems. ACO algorithms are based on the following ideas:
Each path followed by an ant is associated with a candidate solution for a given problem. When an ant follows a
path, the amount of pheromone deposited on that path is proportional to the quality of the corresponding
candidate solution for the target problem. When an ant has to choose between two or more paths, the path(s)
with a larger amount of pheromone have a greater probability of being chosen by the ant. As a result, the ants
eventually converge to a short path, hopefully the optimum or a near-optimum solution for the target problem,
as explained before for the case of natural ants. In essence, the design of an ACO algorithm involves the
specification of [2]: An appropriate representation of the problem, which allows the ants to incrementally
construct/modify solutions through the use of a probabilistic transition rule, based on the amount of pheromone
in the trail and on a local, problem-dependent heuristic. A method to enforce the construction of valid solutions,
that is, solutions those are legal in the real-world situation corresponding to the problem definition.A problem-
dependent heuristic function (h) that measures the quality of items that can be added to the current partial
solution. A rule for pheromone updating, which specifies how to modify the pheromone trail (t).A probabilistic
transition rule based on the value of the heuristic function (h) and on the contents of the pheromone trail (t) that
is used to iteratively construct a solution. Artificial ants have several characteristics similar to real ants, namely:
Artificial ants have a probabilistic preference for paths with a larger amount of pheromone. 5 Shorter paths tend
to have larger rates of growth in their amount of pheromone. The ants use an indirect communication system
based on the amount of pheromone deposited on each path [3].
1.3 Genetic algorithm
Genetic algorithms (GAs) are search and optimization procedures that are motivated by the principles
of natural selection and natural genetics. Some fundamental ideas of genetics are borrowed and used artificially
to construct search algorithms that are robust and required minimum problem information. In GAs, the role of
selection and recombination operators is very well defined. Selection operator controls the direction of search
and recombination operator generates new regions for search. Genetic algorithms are having a large amount of

implicit parallelism. GAs perform search in complex, large and multimodal landscapes, and provide near-
optimal solutions for objective or fitness function of an optimization problem. In GAs, the parameters of the
search space are encoded in the form of strings (called chromosomes) and collection of such strings called a
population. Initially, a random population is created, which represents different points in the search space. An
objective and fittness function is associated with each string that represents the degree of goodness of the string.
Based on the principle of survival of the fittest, a few of the strings are selected and each is assigned a number
of copies that go into the mating pool. Biologically inspired operators like crossover and mutation are applied on
these strings to yield a new generation of strings. The process of selection, crossover and mutation continues for
a fixed number of generations or till a termination condition is satisfied.
1.3.1Applications of GA based clustering
In previous section, various GA based clustering algorithms are studied. This section provides
discussion on few of applications of GA based clustering algorithms. Paper shows application of a Genetic
Algorithm to production simulation. The simulation is treated as a detailed, stochastic, multi-modal function that
describes a performance statistic. Authors tried to optimize (or at least improve) the performance of the system.
A model of a real-world production line for printed circuit boards that has many products and must often be
retooled or reconfigured was used. Since the product line is always changing, with half of the products turning
over within a year, the job of configuring and fine-tuning the production line is never ending. This paper has
shown that a Genetic Algorithm when attached to the simulation model can provide excellent support for this
process. This combination can be used to obtain quick and stable results that do indeed indicate the direction to
improved production. In microarray data analysis, clustering is a method that groups thousands of genes by their
similarities of expression levels, helping to analyze gene expression profiles. This method has been used for
identifying unknown functions of genes. The fuzzy clustering method assigns one sample to multiple groups
according to their degrees of membership. This method was more appropriate for analyzing gene expression
profiles, because a single gene might be involved in multiple functions. An evolutionary fuzzy clustering
method with knowledge-based evaluation was proposed.The segmentation problems were formulated upon such
images as an optimization problem and adopt evolutionary strategy of Genetic Algorithms for the clustering of
small regions in colors feature space. The present approach uses k-Means unsupervised clustering methods into
Genetic Algorithms, namely for guiding this last Evolutionary Algorithm in his search for finding the optimal or
sub-optimal data partition, task that as we know, requires a non-trivial search because of its intrinsic NP-
complete nature. To solve this task, the appropriate genetic coding was also discussed. The image compression
problem using genetic clustering algorithms based on the pixels of the image was proposed. GA was used to
obtain an ordered representation of the image and then the clustering was performed to obtain the compression.
In order to solve the problem of error estimation of real life data set the optimization technique of genetic
algorithm (GA) was applied to the new adaptive cluster validity index, which is called the Gene Index (GI). The
algorithm applies GA to adjust the weighting factors of adaptive cluster validity index to train an optimal cluster
validity index. Paper presents a genetic algorithm that deals with document clustering. This algorithm calculates
an approximation of the optimum k value, and solves the best grouping of the documents into these k clusters.
This algorithm was evaluated with sets of documents that were the output of a query in a search engine. The
modified variable string length genetic algorithm (MVGA) was proposed in for text clustering. This algorithm
has been exploited for automatically evolving the optimal number of clusters as well as providing proper data
set clustering. The chromosome was encoded by a string of real numbers with special indices to indicate the
location of each gene. More effective versions of operators for selection, crossover, and mutation were
introduced in MVGA which can also automatically adjust the influence between the diversity of the population
and selective pressure during generations. GA was applied to enhance the performance of clustering algorithms
in mobile ad hoc networks. Authors have optimized recently proposed weighted clustering algorithm (WCA).
The proposed technique was such that each clusterhead handles the maximum possible number of mobile nodes
in its cluster in order to facilitate the optimal operation of the medium access control (MAC) protocol.
Consequently, it results in the minimum number of clusters and hence cluster heads. Clustering the Gene
Ontology is a difficult combinatorial problem and can be modeled as a graph partitioning problem. Additionally,
deciding the number k of clusters to use is not easily perceived and is a hard algorithmic problem. Therefore, an
approach for solving the automatic clustering of the Gene Ontology was proposed by incorporating cohesion-
and-coupling metric into a hybrid algorithm consisting of a genetic algorithm and a split-and-merge algorithm.
To solve task clustering problem on an unbounded number of processors, a new genetic algorithm approach
which has nice properties called Genetic Convex Clustering Algorithm (GCCA) was proposed. The main idea
was to assign tasks to locations in convex groups. Here arbitrary execution time was considered and a novel
crossover operator in the context of the task clustering problem was developed. Genetic algorithm with species
and sexual selection (GAS3) was proposed to solve unimodal and multi-modal function of various difficulties.
GAS3 uses sex determination method to determine the sex (male or female) of members in population. Each
female member was considered as a niche in the population and the species (cluster) formation takes place

around these niches. Species formation was based on Euclidean distance between female and male members.
Each species contains one female member and zero or more male members. Parameter-less cluster formation
technique was used. Merging of clusters takes place based on performance evaluation criterion [4].
1.4 Fuzzy Logic
Lets consider an example, a bank wants to classify their customers into two grups as rich and poor
customers. Obviously there is no crisp separation between rich and poor in a way that customers own less than 2
million SEK are poor while they own a fortune of 2million SEK or more are rich. So according to the above
explanation a person with a fortune of 2.1 million SEK is considered as reasonably rich but still a little bit poor.
The indicator for similarity in fuzzy sets is called membership degree µ ={0,.....,1}. A membership degree µ =1
indicates that an object completely belongs to set and a membership degree µ =0 shows a total dissimilarity
between an object and a set. In our example, the customer with 2.1million SEK may have membership degrees
of µ rich 1.2(millionSEK) = 65.0 to the set rich and 1.2(millionSEK) = 35.0 µ poor to the set poor. This indicates
that the customer is rich but not extremely wealthy. However a customer having 30billion SEK would surely
have memberships of 1(billionSEK) = 0.1 µ rich and 0.0 µ poor 1(billionSEK) = o.o. There is probabilistic
uncertainity neither about the fortune of the customer who is having 2.1million SEK nor about the rules for how
to classify him into one or other of the two sets [5].
IV. Related Work and Conclusion
Xizhe Yin et al. [2016] This paper presents our recent work on human activity detection based on smart
phone sensors and incremental clustering algorithms. The proposed unsupervised (clustering) activity detection
scheme works in an incremental manner, which contains two stages. In the first stage, streamed sensor data will
be processed. A single-pass clustering algorithm is used in order to generate pre-clustered results for the next
stage. In the second stage,pre-clustered results will be refined to form the final clusters, which means the
clusters are built incrementally adding one cluster at a time [6].
Ming Hou et al. [2016] In this paper, we present a computationally efficient online tensor regression
algorithm, namely incremental higher-order partial least squares (IHOPLS), for adapting HOPLS to the setting
of infinite time-dependent tensor streams. By incrementally clustering the projected latent variables in latent
space and summarizing the previous data, IHOPLS is able to recursively update the projection matrices and core
tensors over time, resulting in greatly reduced costs in terms of both memory and running time while
maintaining high prediction accuracy. To show the effectiveness and scalability of our approach for large
databases, we apply IHOPLS to two real-life applications as reconstruction of 3D motion trajectories from video
and ECoG streaming signals [7].
Theodora Kontogianni et al. [2016] In this paper, we address the problem of object discovery in time-
varying, large-scale image collections. A core part of our approach is a novel Limited Horizon Minimum
Spanning Tree (LH-MST) structure that closely approximates the Minimum Spanning Tree at a small fraction of
the latter’s computational cost. Our proposed tree structure can be created in a local neighborhood of the
matching graph during image retrieval and can be efficiently updated whenever the image database is extended.
We show how the LH-MST can be used within both single-link hierarchical agglomerative clustering and the
Iconoid Shift framework for object discovery in image collections, resulting in significant efficiency gains and
making both approaches capable of incremental clustering with online updates [8].
Jueun Kwak et al. [2015] In this paper, we propose an online fault detection algorithm based on
incremental clustering. The algorithm accurately finds wafer faults even in severe class distribution skews and
efficiently processes massive sensor data in terms of reductions in the required storage. We tested our algorithm
on illustrative examples and an industrial example. The algorithm performed well with the illustrative examples
that included imbalanced class distributions of Gaussian and non Gaussian types and process drifts. In the
industrial example, which simulated real data from a plasma etcher, we verified that the performance of the
algorithm was better than that of the standard support vector machine (SVM), one-class SVM and three
instance-based fault detection algorithms that are typically used in the literature. Most standard classification
algorithms, such as support vector machines, can handle moderate sizes of training data and assume balanced
class distributions. When the class sizes are highly imbalanced, the standard algorithms tend to strongly favor
the majority class and provide a notably low detection of the minority class as a result [9].
Mahmuda Akter et al. [2015] In this paper, an Incremental Clustering Algorithm is proposed in
conjunction with Static Clustering Technique to track an object consistently throughout the network solving
boundary problem. The proposed research follows a Gaussian Adaptive Resonance Theory (GART) based
Incremental Clustering that creates and updates clusters incrementally to incorporate incessant motion pattern
without defiling the previously learned clusters. The objective of this research is to continue tracking at the
boundary region in an energy-efficient way as well as to ensure robust and consistent object tracking throughout
the network. The network lifetime performance metric has shown significant improvements for Incremental
Static Clustering at the boundary regions than that of existing clustering techniques. Emerging significance of

moving object tracking has been actively pursued in the Wireless Sensor Network (WSN) community for the
past decade. As a consequence, a number of methods from different angle of assessment have been developed
while relatively satisfying performance. Amongst those, clustering based object tracking has shown significant
results, which in term provides the network to be scalable and energy efficient for large-scale WSNs. As of now,
static cluster based object tracking is the most common approach for large-scale WSN. However, as static
clusters are restricted to share information globally, tracking can be lost at the boundary region of static clusters
[10].Teena Ajayan et al. [2015] in this paper, the key idea is to find multiple representative sequences like
medoids to represent a cluster in a chunk and final DNA analysis is carried out based on those identified
medoids from all the chunks. The main advantage of this incremental clustering is that it uses multiple medoids
to represent each cluster in each chunk which captures the pattern structure more accurately. Not only that it
overcomes the disadvantages of existing techniques but also has the mechanism to make use of DNA sequence
relationship among those identified medoids that serves as a side information to help the final DNA sequence
clustering. The proposed incremental approach outperforms existing clustering approaches in terms of clustering
accuracy [11].
Jafar Boostanpour et al. [2015] In this paper, to overcome the aforementioned obstacles, a two-step
algorithm is proposed which in first step, a fast spherical interpolation (SI) method is utilized to prepare an
appropriate initial guess for the MLE algorithm. In the second step, a clustering-based network is described to
attain less power consumption across the WSN. Furthermore, to increase the probability of convergence, a
cooperative incremental clusterbased estimation strategy is proposed. In addition, major issues that can affect
the performance of the proposed method are investigated. Simulation results prove the capability of this method
and support the claims [12]. Puma Chandra Sethi et al. [2014] In this paper, EHMA is implemented in two tiers,
but this paper considers the implementation of EHMA in three tiers. It follows incremental clustering algorithm
for grouping clusters according to their impact factors. This three tier implementation of EHMA improves the
security of the information as it uses SHA-256 for security. - In the present scenario, most of the computing
operations are performed over the Internet. Many companies provide their services using Internet, so networking
services becomes more important these days. Hence, there is high demand for secured management of
information, along with faster processing of operations. Due to increased demand for network services, there is a
need to increase the performance of these services [13].
References
[1]. Yongli Liu, Qianqian Guo, Lishen Yang, Yingying Li “Research on Incremental Clustering” 978-1-4577-1415-3/12/$26.00 ©2012
IEEE.
[2]. Amreen Khan, Prof. Dr. N.G.Bawane, Prof. Sonali Bodkhe “An Analysis of Particle Swarm Optimization with Data Clustering-
Technique for Optimization in Data Mining.” International Journal on Computer Science and Engineering Vol. 02, No. 04, 2010,
1363-1366.
[3]. Rafael S. Parpinelli, Heitor S. Lopes, and Alex A. Freitas “Data Mining with an Ant Colony Optimization Algorithm”2010.
[4]. Rahila H. Sheikh, M. M.Raghuwanshi, Anil N. Jaiswal “Genetic Algorithm Based Clustering: A Survey” First International
Conference on Emerging Trends in Engineering and Technology, 2008 IEEE.
[5]. Md. Ehsanul Karim Feng Yun Sri Phani Venkata Siva Krishna Madani “Fuzzy Clustering Analysis” April 2010.
[6]. Xizhe Yin, Weiming Shen, Xianbin Wang “Incremental Clustering for Human Activity Detection Based on Phone Sensor Data”
2016 IEEE.
[7]. Ming Hou, Brahim Chaib-draa “ONLINE INCREMENTAL HIGHER-ORDER PARTIAL LEAST SQUARES REGRESSION
FOR FAST RECONSTRUCTION OF MOTION TRAJECTORIES FROM TENSOR STREAMS”2016 IEEE.
[8]. Theodora Kontogianni, Markus Mathias, Bastian Leibe “Incremental Object Discovery in Time-Varying Image Collections” 2016
IEEE.
[9]. Jueun Kwak, Taehyung Lee and Chang Ouk Kim “An Incremental Clustering-Based Fault Detection Algorithm for Class-
Imbalanced Process Data”, IEEE TRANSACTIONS ON SEMICONDUCTOR MANUFACTURING, VOL. 28, NO. 3 , 2015
IEEE.
[10]. Mahmuda Akter, Md. Obaidur Rahman, Md. Nazrul Islam and Md. Ahsan Habib “Incremental Clustering-based Object Tracking in
Wireless Sensor Networks” 2015 IEEE.
[11]. Teena Ajayan, Sony P, Janu R Panicker, Shailesh S “Clustering DNA Sequences Of Aspergillus fumigatus Using Incremental
Multiple Medoids” 2015 IEEE Fifth International Conference on Advances in Computing and Communications.
[12]. Jafar Boostanpour, Sayed Mostafa Taheri, Hossein Zamiri-Jafarian “Cluster-Based Two-Step Target Localization with Incremental
Cooperation” 2015 IEEE.
[13]. Puma Chandra Sethi, Prafulla Kumar Behera “Secured Packet Inspection with Hierarchical Pattern Matching implemented using
Incremental Clustering Algorithm” 978-1-4799-5958-7/14/$31.00 ©20 14 IEEE.

Recent Trends in Incremental Clustering: A Review

More Related Content

What's hot (20)

Similar to Recent Trends in Incremental Clustering: A Review (20)

More from IOSRjournaljce (20)

Recently uploaded (20)

Recent Trends in Incremental Clustering: A Review