Evolutionary clustering via graph regularized nonnegative matrix factorization for exploring temporal networks

Yu, Wei; Wang, Wenjun; Jiao, Pengfei; Li, Xuewei

doi:10.1016/j.knosys.2019.01.024

Cited by 21 publications

(20 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The experimental results of parameters using HGDSG-LGLC and existing techniques [1] and [2] are discussed. The various parameters are ,…”

Section: Results Analysismentioning

confidence: 99%

“…In this section, experimental evaluation of HGDSG-LGLC and existing techniques ECGNMF [1] and Bi-weighted ensemble approach [2] is carried out using Java language with Activity Recognition from Single Chest-Mounted Accelerometer Dataset is taken from UCI machine learning repository [21]. This dataset includes the temporal data points from wearable accelerometer fixed on chest.…”

Section: Experimental Scenariomentioning

confidence: 99%

“…LGLC ECGNMF Bi-weighted ensemble approach 1000 91 85 78 2000 90 82 76 3000 92 84 77 4000 91 86 83 5000 93 88 86 6000 92 87 82 7000 95 89 87 8000 96 87 86 9000 95 88 84 10000 94 89 87 Table 1 describes the performance results of temporal data clustering accuracy with three techniques namely HGDSG-LGLC, [1] and [2]. In order to calculate the clustering accuracy, data is taken in range from 1000 to 10000 for conducting the experimental scenario.…”

Section: Hgdsg-mentioning

confidence: 99%

“…Let us consider the 1000 data for calculating the clustering accuracy. The HGDSG-LGLC technique correctly clustered 910 data and their accuracy is 91% whereas [1] and [2] grouped 850 and 780 data and their accuracy percentages are 85% and 78% respectively. Finally, the ten different results of clustering accuracy of HGDSG-LGLC technique are compared to the conventional methods.…”

Section: Hgdsg-mentioning

confidence: 99%

See 3 more Smart Citations

Hybridized Gradient Descent Spectral Graph and Local global Louvain Based Clustering of Temporal Relational Data

Dhas,

Mukunthan,

Rakesh

2020

IJEAT

View full text Add to dashboard Cite

Temporal data clustering examines the time series data to determine the basic structure and other characteristics of the data. Many methodologies simply process the temporal dimension of data but it still faces the many challenges for extracting useful patterns due to complex data types. In order to analyze the complex temporal data, Hybridized Gradient Descent Spectral Graph and Local-Global Louvain Clustering (HGDSG-LGLC) technique are designed. The number of temporal data is gathered from input dataset. Then the HGDSG-LGLC technique performs graph-based clustering to partitions the vertices i.e. data into different clusters depending on similarity matrix spectrum. The distance similarity is measured between the data and cluster mean. The Gradient Descent function find minimum distance between data and cluster mean. Followed by, the Local-Global Louvain method performs the merging and filtering of temporal data to connect the local and global edges of the graph with similar data. Then for each data, the change in modularity is calculated for filtering the unwanted data from its own cluster and merging it into the neighboring cluster. As a result, optimal ‘k’ numbers of clusters are obtained with higher accuracy with minimum error rate. Experimental analysis is performed with various parameters like clustering accuracy ( ), error rate ( ), computation time ( ) and space complexity ( ) with respect to number of temporal data. The proposed HGDSG-LGLC technique achieves higher and lesser , minimum as well as than conventional methods.

show abstract

“…The experimental results of parameters using HGDSG-LGLC and existing techniques [1] and [2] are discussed. The various parameters are ,…”

Section: Results Analysismentioning

confidence: 99%

Section: Experimental Scenariomentioning

confidence: 99%

Section: Hgdsg-mentioning

confidence: 99%

Section: Hgdsg-mentioning

confidence: 99%

See 2 more Smart Citations

Hybridized Gradient Descent Spectral Graph and Local global Louvain Based Clustering of Temporal Relational Data

Dhas,

Mukunthan,

Rakesh

2020

IJEAT

View full text Add to dashboard Cite

show abstract

“…An Evolutionary Clustering based on Graph regularized Nonnegative Matrix Factorization was developed in [14] to analyzing the temporal networks. But the technique failed to solve the time-consuming problems during clustering analysis.…”

Section: Introductionmentioning

confidence: 99%

Fuzzified Crisp Relative Cure Hierarchical Clustering for Temporal Relational Data

Dhas*¹,

Mukunthan²

2019

IJRTE

View full text Add to dashboard Cite

A bitemporal data clustering is a significant solution to the diverse problems for finding the intrinsic structure and compact information over temporal data. The temporal data are collected in the series of particular time periods. The various data mining methods have been developed in the temporal relational data analysis. But the accurate analysis was not performed with minimum time. An efficient technique called Fuzzy Crisp Relative Spherical CURE Hierarchy Clustering (FCRSCHC) is introduced for improving the temporal relational data analysis by partitioning the total dataset into different clusters with minimum time as well as space complexity. The CURE hierarchical structure takes the number of scattered temporal data points in the spherical surface for the clustering. After that, ‘k’ number of clusters and the representative points (i.e. cluster centroid) are initialized. Then the distance between the representative point and the temporal data point are calculated using spherical coordinates. The minimum distance between the data points are grouped into a particular cluster. Then the fuzzy memberships between the two cluster representative points are calculated based on the distance metric. The CURE hierarchical structure merges the two clusters based on the crisp relation between the representative points. Then, the newly obtained clusters are validated using the silhouette coefficient to identify the data points are close to its own cluster or their neighboring clusters. Finally, the optimal numbers of clusters are obtained and minimize the incorrect data clustering which improves the accuracy. The experimental evaluation is performed using a bitmeporal dataset with various parameters such as clustering accuracy, false alarm rate, clustering time and space complexity. The results show that FCRSCHC technique improves the clustering accuracy and minimize the time as well as space complexity as compared to the state-of-the-art- works.

show abstract

A spiderweb model for community detection in dynamic networks

Yang

Cheng

et al. 2021

Appl Intell

View full text Add to dashboard Cite

Evolutionary clustering via graph regularized nonnegative matrix factorization for exploring temporal networks

Cited by 21 publications

References 26 publications

Hybridized Gradient Descent Spectral Graph and Local global Louvain Based Clustering of Temporal Relational Data

Hybridized Gradient Descent Spectral Graph and Local global Louvain Based Clustering of Temporal Relational Data

Fuzzified Crisp Relative Cure Hierarchical Clustering for Temporal Relational Data

A spiderweb model for community detection in dynamic networks

Contact Info

Product

Resources

About