A Comparative Performance Study of Hybrid Firefly Algorithms for Automatic Data Clustering

Pattern analysis of hospital nurses' knowledge, attitudes, and practices regarding incontinence-associated dermatitis

PURPOSE

To analyze hospital nurses' knowledge, attitudes, and practices regarding incontinence-associated dermatitis (KAP-IAD).

METHODS

This study utilized responses from hospital nurses to the Knowledge, Attitudes, and Practices of Incontinence-Associated Dermatitis Questionnaire (KAP-IAD-Q). Three clustering methods, Hierarchical Clustering on Principal Components (HCPC), K-means, and Partitioning Around Medoids (PAM), were applied to analyze the correlations of KAP-IAD. A classification method was used to explain the underlying behavioral patterns behind these correlations.

RESULTS

Two clusters were found to be most appropriate. Decision attributes (D) were generated for the KAP-IAD data using the three clustering methods: HCPC, K-means, and PAM. Three datasets with categorical labels were generated, and predictive models and decision rules were established for each dataset using the Rough Set (RS) method. The PAM method demonstrated the highest accuracy among the three datasets. After five rounds of stochastic modeling, 57 decision rules were generated. Additionally, patterns or rules with a support threshold of 50 or more, as discussed by domain experts, were considered the primary behaviors or rules.

CONCLUSIONS

Our study suggests clear decision rules for KAP-IAD nursing practice, which have been absent in previous research. The key variables and rules identified can serve as a guide for KAP-IAD nursing practice, as well as for recognizing the etiology, risk factors, and key influences of dermatitis associated with KAP-IAD in nursing practice. This study provides an important management approach for the prevention and treatment of incontinence-associated dermatitis.

Identification of the pollution sources and hidden clustering patterns for potentially toxic elements in typical peri-urban agricultural soils in southern China

Peri-urban agricultural soils are often contaminated by potentially toxic elements (PTEs) due to rapid urbanization, industrial activities, and agricultural practices. In this study, two advanced analytical methods including positive matrix factorization (PMF) model and K-means clustering algorithm were integrated to explore the potential sources and concealed contamination patterns of 8 PTEs in peri-urban soils in county Gaoming, China. Descriptive statistics showed average concentrations of arsenic (As), cadmium (Cd), chromium (Cr), copper (Cu), mercury (Hg), nickel (Ni), lead (Pb), and zinc (Zn) as 19.11, 0.18, 35.69, 20.31, 18.26, 151.7, 67.75, and 0.29 mg/kg, respectively. The PMF model identified three primary sources: geogenic (Cr, Ni), industrial and traffic-related (Pb, Hg, Zn), and agricultural (As, Cd and Cu). The contribution of each source was quantified: geogenic sources contributed 55.6% to Cr and 52.3% to Ni, industrial sources accounted for 41.8% of Pb, 58.4% of Hg, and 41.9% of Zn, while agricultural practices contributed 88.1% of As, 77.9% of Cu, and 70.7% of Cd. Subsequently, K-means clustering classified the soil samples into three distinct clusters based on the derived factor contribution from PMF model, reflecting their clear spatial associations with different types of land use: large-scale agricultural areas (Cluster 1), natural vegetation (Cluster 2), and urbanized zones (Cluster 3). Furthermore, boxplots showed that the highest PTE concentrations were found in the third cluster, confirming the significant impact of human activities, while the lower concentrations in the second cluster indicated more natural conditions. These results underscored the dual influences of agriculture and urbanization on PTE contamination, which highlighted the need for targeted soil management strategies. Moreover, the integration of PMF and K-means clustering effectively reveals potential sources and concealed pollution patterns, providing insights for managing pollution and safeguarding environmental health in rapidly urbanized areas.

Cluster validity indices for automatic clustering: A comprehensive review

The Cluster Validity Index is an integral part of clustering algorithms. It evaluates inter-cluster separation and intra-cluster cohesion of candidate clusters to determine the quality of potential solutions. Several cluster validity indices have been suggested for both classical clustering algorithms and automatic metaheuristic-based clustering algorithms. Different cluster validity indices exhibit different characteristics based on the mathematical models they employ in determining the values for the various cluster attributes. Metaheuristic-based automatic clustering algorithms use cluster validity index as a fitness function in its optimization procedure to evaluate the candidate cluster solution's quality. A systematic review of the cluster validity indices used as fitness functions in metaheuristic-based automatic clustering algorithms is presented in this study. Identifying, reporting, and analysing various cluster validity indices is important in classifying the best CVIs for optimum performance of a metaheuristic-based automatic clustering algorithm. This review also includes an experimental study on the performance of some common cluster validity indices on some synthetic datasets with varied characteristics as well as real-life datasets using the SOSK-means automatic clustering algorithm. This review aims to assist researchers in identifying and selecting the most suitable cluster validity indices (CVIs) for their specific application areas.

Ensemble effort estimation with metaheuristic hyperparameters and weight optimization for achieving accuracy

Software development effort estimation (SDEE) is recognized as vital activity for effective project management since under or over estimating can lead to unsuccessful utilization of project resources. Machine learning (ML) algorithms are largely contributing in SDEE domain, particularly ensemble effort estimation (EEE) works well in rectifying bias and subjectivity to solo ML learners. Performance of EEE significantly depends on hyperparameter composition as well as weight assignment mechanism of solo learners. However, in EEE domain, impact of optimization in terms of hyperparameter tunning as well as weight assignment is explored by few researchers. This study aims in improving SDEE performance by incorporating metaheuristic hyperparameter and weight optimization in EEE, which enables accuracy and diversity to the ensemble model. The study proposed Metaheuristic-optimized Multi-dimensional bagging scheme and Weighted Ensemble (MoMdbWE) approach. This is achieved by proposed search space division and hyperparameter optimization method named as Multi-dimensional bagging (Mdb). Metaheuristic algorithm considered for this work is Firefly algorithm (FFA), to get best hyperparameters of three base ML algorithms (Random Forest, Support vector machine and Deep Neural network) since FFA has shown promising results of fitness in terms of MAE. Further enhancement in performance is achieved by incorporating FFA-based weight optimization to construct Metaheuristic-optimized weighted ensemble (MoWE) of individual multi-dimensional bagging schemes. Proposed scheme is implemented on eight frequently utilized effort estimation datasets and results are evaluated by 5 error metrices (MAE, RMSE, MMRE, MdMRE, Pred), standard accuracy and effect size along with Wilcox statistical test. Findings confirmed that the use of FFA optimization for hyperparameter (with search space sub-division) and for ensemble weights, has significantly enhanced performance in comparison with individual base algorithms as well as other homogeneous and heterogenous EEE techniques.

K-Means-Based Nature-Inspired Metaheuristic Algorithms for Automatic Data Clustering Problems: Recent Advances and Future Directions

K-means clustering algorithm is a partitional clustering algorithm that has been used widely in many applications for traditional clustering due to its simplicity and low computational complexity. This clustering technique depends on the user specification of the number of clusters generated from the dataset, which affects the clustering results. Moreover, random initialization of cluster centers results in its local minimal convergence. Automatic clustering is a recent approach to clustering where the specification of cluster number is not required. In automatic clustering, natural clusters existing in datasets are identified without any background information of the data objects. Nature-inspired metaheuristic optimization algorithms have been deployed in recent times to overcome the challenges of the traditional clustering algorithm in handling automatic data clustering. Some nature-inspired metaheuristics algorithms have been hybridized with the traditional K-means algorithm to boost its performance and capability to handle automatic data clustering problems. This study aims to identify, retrieve, summarize, and analyze recently proposed studies related to the improvements of the K-means clustering algorithm with nature-inspired optimization techniques. A quest approach for article selection was adopted, which led to the identification and selection of 147 related studies from different reputable academic avenues and databases. More so, the analysis revealed that although the K-means algorithm has been well researched in the literature, its superiority over several well-established state-of-the-art clustering algorithms in terms of speed, accessibility, simplicity of use, and applicability to solve clustering problems with unlabeled and nonlinearly separable datasets has been clearly observed in the study. The current study also evaluated and discussed some of the well-known weaknesses of the K-means clustering algorithm, for which the existing improvement methods were conceptualized. It is noteworthy to mention that the current systematic review and analysis of existing literature on K-means enhancement approaches presents possible perspectives in the clustering analysis research domain and serves as a comprehensive source of information regarding the K-means algorithm and its variants for the research community.