Katz centrality based approach to perform human action recognition by using OMKZ

Bakhat, Khush; Kifayat, Kashif; Islam, M. Shujah; Islam, Muhammad

doi:10.1007/s11760-022-02378-x

Cited by 7 publications

(6 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Two recent centrality approaches, Katz centrality 23 and Local Vital Density (LVD), 24 can work for both directed and undirected graphs, similar to hitting centrality. However, these two new centralities under perform or show inconsistency for different structural changes in the graph.…”

Section: Results and Analysismentioning

confidence: 99%

Identification of influential vertices in complex networks: A hitting time‐based approach

Kumar,

Singh,

Sharma

2024

Concurrency and Computation

View full text Add to dashboard Cite

Unravelling the dynamics of network vertices is pivotal, and traditional centrality measures have limitations in adapting to structural changes, directed and weighted networks, and temporal analyses. This paper introduces a ground breaking approach ‐ hitting time‐based centrality. Utilizing network matrix notations and a random walk model on a connected network , we establish a Markov chain to quantify the hitting time, hitting distance, and hitting centrality, providing a nuanced measure prioritizing central vertices. Through extensive experiments using Kendall's tau coefficient, the paper evaluates the method's correlation with actual influence in the Susceptible‐Infectious (SI) model, showcasing superior performance across diverse network sizes and structures. The hitting centrality method exhibits sensitivity to connectivity dynamics, effective incorporation of temporal dynamics, and robust handling of weighted and directed networks. Positive Kendall's tau coefficients underline the method's proficiency in prioritizing influential vertices by correlating hitting centrality values with actual infection ability. The demonstrated robustness to structural changes enhances its utility for dynamic network analysis. In conclusion, our hitting time‐based centrality approach emerges as a promising method, mitigating the shortcomings of traditional measures. By integrating information propagation speed, accommodating network dynamics, and enabling time‐dependent analyses, it offers a comprehensive tool for evaluating vertex importance and influence in complex networks.

show abstract

Section: Results and Analysismentioning

confidence: 99%

Identification of influential vertices in complex networks: A hitting time‐based approach

Kumar,

Singh,

Sharma

2024

Concurrency and Computation

View full text Add to dashboard Cite

show abstract

“…Skeletal data [34] Deep LSTM [35] Hybrid feature [36] Hybrid descriptors [37] OMKZ [38] 88 90.41 91.25 91.63 93.80 CAD [39] 95.6 FGP-3D 99.5…”

Section: Methods Accuracy (%)mentioning

confidence: 99%

“…Instead of taking advantage of fine-tuning action recognition models, previous techniques were only tested on target datasets. Recent research [31][32][33]38,39] proposed view-invariant using 2D or 3D incorporating algorithms with joints performed on our evaluated datasets [25,[31][32][33][34][35]38,39] that do not correspond to legit, and thus these techniques struggle to improve the action recognition performance on regression tasks with practical and mostly used databases [40][41][42][43]. These algorithms were developed to investigate the transferability of action recognition using the human skeleton.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Employing FGP-3D, a Fully Gated and Anchored Methodology, to Identify Skeleton-Based Action Recognition

et al. 2023

Self Cite

View full text Add to dashboard Cite

Recent years have seen an explosion in interest in and development of action recognition based on skeletal data. Contemporary methods using fully gated units can successfully extract characteristics from human skeletons by relying on the human topology that has been predefined. Despite advancements, fully gated unit-based techniques have trouble generalizing to other domains, particularly when dealing with various human topological structures. In this context, we introduce FGP-3D, a novel skeleton-based action recognition technique that can generalize across datasets while being effective at learning spatiotemporal features from human skeleton sequences. This is accomplished via a multi-head attention technique to learn an ideal dependence feature matrix from the uniform distribution. We next re-evaluate state-of-the-art techniques as well as the suggested novel descriptor FGP-3D in order to examine the cross-domain generalizability of skeleton-based action recognition in real-world video skeleton statistics. After being applied to commonly used action categorization datasets, experimental results demonstrate that the proposed FGP-3D, with pre-training, generalizes well and outperforms the state-of-the-art.

show abstract

“…The parameters maximise the probability that is calculated by link prediction algorithms using data that has been actually observed. Several state-of-the-art methods for dimension reduction in feature extraction and selection for feature detection are presented in [24][25][26][27]. For instance, authors [28] established a non-asymptotic risk bound for the maximum likelihood estimator of network connection probabilities.…”

Section: Related Workmentioning

confidence: 99%

Link prediction grounded upon complex networks based model, based on MJMI-RW

Bakhat¹,

Kifayat²,

Islam

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

Link prediction is the process of predicting the connection probability between two nodes based on observable network data, such as network structural topology and node properties. Despite the fact that traditional similarity-based methods are basic and effective, their generalisation performance varies greatly across networks. In this paper, we propose a novel link prediction approach, MJMI-RW, based on the Maxwell Jüttner distribution endowed by the Mutual Information, which recovers the probability of a node's connection by applying node characteristics to a system with less computation. Initially, the method investigates a comprehensive node feature representation by combining diverse structural topology information with node importance properties through feature construction and selection. The selected node features are then fed into a supervised learning task that solves the features matrix using the node features as input. The enhancements of MJMI-RW in terms of the average area under the curve and the precision of state-of-the-art algorithms compared to the finest baseline networks when compared to baseline methods. The limitation of MJMI-RW is its minimal computational complexity feature construction and substitution of complex features with semantic node attributes. Moreover, since inductive matrix completion is a supervised learning task in which the underlying low-rank matrix can be solved by representative nodes instead of all their nodes, it offers a potential link prediction solution for large-scale networks.

show abstract

Katz centrality based approach to perform human action recognition by using OMKZ

Cited by 7 publications

References 44 publications

Identification of influential vertices in complex networks: A hitting time‐based approach

Identification of influential vertices in complex networks: A hitting time‐based approach

Employing FGP-3D, a Fully Gated and Anchored Methodology, to Identify Skeleton-Based Action Recognition

Link prediction grounded upon complex networks based model, based on MJMI-RW

Contact Info

Product

Resources

About