Evaluation of k-modes-type Algorithms for Clustering Y-Short Tandem Repeats Data

Seman, Ali; Bakar, Zainab Abu; Isa, Mohamed Nizam

doi:10.3923/tb.2012.47.52

Cited by 6 publications

(8 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In all situations the average recovery rates were larger for data generated from the Beta distribution. The best results were achieved for k=2 and degrees 1 ). When k=2 and the degree of overlapping increased to 3 and 4, the ARR values dropped down ranging from 51.07 to 76.46% (Beta data) and 50 to 64.1% (Uniform data).…”

Section: Resultsmentioning

confidence: 99%

“…So me of these algorith ms are d irect variations of the k-modes or fu zzy k-mod es (see [4] an d [5], fo r examp les). The variat ions include changing the dissimilarity measure used to co mpare the objects to the cluster centroids or the cluster centroids themselves by adding mo re informat ion fro m the data set in their defin ition b es id es o f us in g th e hard mod e. The k-representativ es [12] and the k-popu lat ions ( [9], [1]) are exa mp les o f fu zzy k -mo d es v ariatio ns . A mo n g the algorith ms based on different concepts to cluster data we find the h ierarchical method ROCK [17], wh ich uses the number o f links between objects to identify which are neighbors and belong to the same cluster; the entropy-based algorith ms LIMBO [13] and COOLCAT [14]; STIRR [16] based on nonlinear dynamical systems fro m mu ltip le instances of weighted hypergraphs; GoM a parametric procedure based on the assumption that the data follow a mu ltivariate mu ltino mial distribution ( [3], [25])); MADE [3] which uses concepts of the rough set theory to handle uncertainty of the partition; CACTUS [18] based on the idea of co-occurrence between attributes and pairs defin ing a cluster in terms of a cluster´s 2D project ions; the subspace algorith ms SUBCAD [11] and CLICK [7] whose main goal is to locate clusters in different subspaces of the data set with the purpose of overcome the difficulties found in clustering high-dimensional data; many other algorith ms can be found.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Clustering Algorithms for Categorical Data: A Monte Carlo Study

Mingoti¹,

Matos²

2012

STATISTICS

View full text Add to dashboard Cite

In this paper the clustering algorith ms: average linkage, ROCK, k-modes, fuzzy k-modes and k-populations were co mpared by means of Monte Carlo simulat ion. Data were simu lated fro m Beta and Uniform distributions considering factors such as clusters overlapping, number of groups, variables and categories. A total of 64 population structures of clusters were simu lated considering smaller and higher degree of overlapping, nu mber o f clusters, variables and categories. The results showed that overlapping was the factor with major impact in the algorith m's accuracy which decreases as the number of clusters increases. In general, ROCK presented the best performance considering overlapping and non-overlapping cases followed by k-modes and fuzzy k-Modes. The k-populations algorithm showed better accuracy only in cases where there was a s mall degree of overlapping with performance similar to the average linkage. The superiority of k-populations algorithm over k-modes and fu zzy k-modes presented in previous studies, which were based only in benchmark data, was not confirmed in this simulat ion study.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Clustering Algorithms for Categorical Data: A Monte Carlo Study

Mingoti¹,

Matos²

2012

STATISTICS

View full text Add to dashboard Cite

show abstract

“…Furthermore, the Y-STR data and their clustering results have also been published in a journal called Journal of Genetic Genealogy, a journal of genetic genealogical community [13]. A more comprehensive benchmark, involving six Y-STR dataset items and eight existing partitional algorithms, has also been reported [14]. The outcomes of this result indicate that the Y-STR data are quite unique compared to other categorical data, characterizing many similar and almost similar objects.…”

Section: Introductionmentioning

confidence: 99%

First Y-Short Tandem Repeat Categorical Dataset for Clustering Applications

Seman

Bakar

Isa³

2013

Dataset Papers in Biology

Self Cite

View full text Add to dashboard Cite

The Y-chromosome short tandem repeat (Y-STR) data are mainly collected for a performance benchmarking result in clustering methods. There are six Y-STR dataset items, divided into two categories: Y-STR surname and Y-haplogroup data presented here. The Y-STR data are categorical, unique, and different from the other categorical data. They are composed of a lot of similar and almost similar objects. This characteristic of the Y-STR data has caused certain problems of the existing clustering algorithms in clustering them.

show abstract

“…[13-19] used partitional clustering techniques to group Y-STR data by the number of repeats, a method used in genetic genealogy applications. In this study, we continue efforts to partition the Y-STR data based on the partitional clustering approaches carried out in [13-19]. Recently, we have also evaluated eight partitional clustering algorithms over six Y-STR datasets [19].…”

Section: Introductionmentioning

confidence: 99%

“…In this study, we continue efforts to partition the Y-STR data based on the partitional clustering approaches carried out in [13-19]. Recently, we have also evaluated eight partitional clustering algorithms over six Y-STR datasets [19]. As a result, we found that there is scope to propose a new partitioning algorithm to improve the overall clustering results for the same datasets.…”

Section: Introductionmentioning

confidence: 99%

An efficient clustering algorithm for partitioning Y-short tandem repeats data

2012

Self Cite

View full text Add to dashboard Cite

BackgroundY-Short Tandem Repeats (Y-STR) data consist of many similar and almost similar objects. This characteristic of Y-STR data causes two problems with partitioning: non-unique centroids and local minima problems. As a result, the existing partitioning algorithms produce poor clustering results.ResultsOur new algorithm, called k-Approximate Modal Haplotypes (k-AMH), obtains the highest clustering accuracy scores for five out of six datasets, and produces an equal performance for the remaining dataset. Furthermore, clustering accuracy scores of 100% are achieved for two of the datasets. The k-AMH algorithm records the highest mean accuracy score of 0.93 overall, compared to that of other algorithms: k-Population (0.91), k-Modes-RVF (0.81), New Fuzzy k-Modes (0.80), k-Modes (0.76), k-Modes-Hybrid 1 (0.76), k-Modes-Hybrid 2 (0.75), Fuzzy k-Modes (0.74), and k-Modes-UAVM (0.70).ConclusionsThe partitioning performance of the k-AMH algorithm for Y-STR data is superior to that of other algorithms, owing to its ability to solve the non-unique centroids and local minima problems. Our algorithm is also efficient in terms of time complexity, which is recorded as O(km(n-k)) and considered to be linear.

show abstract

Evaluation of k-modes-type Algorithms for Clustering Y-Short Tandem Repeats Data

Cited by 6 publications

References 7 publications

Clustering Algorithms for Categorical Data: A Monte Carlo Study

Clustering Algorithms for Categorical Data: A Monte Carlo Study

First Y-Short Tandem Repeat Categorical Dataset for Clustering Applications

An efficient clustering algorithm for partitioning Y-short tandem repeats data

Contact Info

Product

Resources

About