A new validity function of FCM clustering algorithm based on intra-class compactness and inter-class separation

Wang, H. Y.; Wang, Jie-Sheng; Zhu, Lei

doi:10.3233/jifs-210555

Cited by 16 publications

(5 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To reveal the inter-class separateness and compactness of the clustering structure in multidimensional datasets, based on the geometric structure of the dataset, the index 𝜑(𝑖, 𝑗) , which reflects the relationship of single-class data with other data and data center-of-mass points, is proposed, and the balance between the inter-class and intra-class distances of data objects can be achieved based on the validity index 𝜑(𝑖, 𝑗), which is based on both [27][28][29][30][31].…”

Section: Multi-dimensional Optimal Clustering Hierarchymentioning

confidence: 99%

Study and analysis of wastewater treatment in the refining and chemical industry based on multidimensional data analysis

Guo

2023

Applied Mathematics and Nonlinear Sciences

View full text Add to dashboard Cite

To improve the efficiency of wastewater treatment in the refining chemical industry, this paper designs a wastewater treatment process in the refining chemical industry based on multidimensional data analysis to guarantee the optimal operation of wastewater treatment operations. In the process of multidimensional data analysis, triangular polynomials are introduced to calculate the robust distance of high-dimensional data and construct a multidimensional data model. The optimal multidimensional clustering levels are divided using data operations to obtain high-dimensional data sequences in the multidimensional data set to accelerate data clustering. A parallel coordinate system realizes the visual representation of the wastewater treatment process stems to improve the capacity representation of wastewater treatment data. Simulation analysis was conducted to verify the treatment effect of the wastewater treatment process based on multidimensional data analysis in the refining and chemical industries. The results showed that the process designed in this paper resulted in a dissolved organic matter fraction concentration of 16.28, and the humic acid-like fraction increased by 36.2%, which was significantly higher than the protein-like fraction of 21.6%. And among all protein-like fractions, only C4 was positively and significantly correlated with fluorescent organic matter at the P < 0.05 level. It can be seen that the multidimensional data analysis model is conducive to promoting the development of wastewater treatment technology in the refining chemical industry and ensuring that the refining chemical industry steps into a circular and sustainable development track.

show abstract

Section: Multi-dimensional Optimal Clustering Hierarchymentioning

confidence: 99%

Study and analysis of wastewater treatment in the refining and chemical industry based on multidimensional data analysis

Guo

2023

Applied Mathematics and Nonlinear Sciences

View full text Add to dashboard Cite

show abstract

“…Taking advantage of the heuristic algorithm, aiming at the maximum distance between classes [23][24][25], the wavelength's combination with the best inter-class separability in the spectral feature space of HSIs can be searched. In this paper, the BPSO with the introduction of a genetic mechanism is selected to obtain the spectral features of ground objects that are easy to be distinguished by the classifier.…”

Section: Binary Particle Swarm Optimization With Genetic Mechanism (G...mentioning

confidence: 99%

Hyperspectral Band Selections for Enhancing the Discrimination of Difficult Targets Using Local Band Index and Particle Swarm Optimization

Wang

Yuan

et al. 2022

Applied Sciences

View full text Add to dashboard Cite

Due to their similar color and material variability, some ground objects have similar characteristics and overlap in some bands. This leads to a drop in the classification accuracy of hyperspectral images. To address this problem, we simulated hyperspectral images of vegetation and objects with similar colors by mixed pixel calculation to test the classification performance of the dimensionality reduction method for samples with close spectra. In addition, we proposed a novel wavelength selection algorithm called the LBI-BPSO (Binary Particle Swarm Optimization with Local Band Index), which combines the information amount and inter-class separability. The novelty of this study is in its proposal of an improvement of IOIF using inter-class distance. Based on the calculation of the information content by the local band index, the inter-class distance was introduced to measure the inter-class separability of ground objects, and a reasonable fitness function is proposed. It can obtain the wavelength combination of two DR criteria, which considers the larger amount of information and better sample separability. The classification performance of the simulation dataset is verified by comparing LBI-BPSO with Partitioned Relief-F, IOIF (Improved Optimum Index Factor) and GA-BPSO (Particle Swarm Optimization with a Genetic Algorithm). Under the conditions that the signal-to-noise ratio is 1000, compared with IOIF, the OA of LBI-BPSO improved by 2.90%, the AA improved by 2.75%, and the Kappa coefficient improved by 3.91%. LBI-BPSO also showed the best results in the analysis of different abundances and signal-to noise-ratios. The results show that the new wavelength selection algorithm LBI-BPSO, which combines the amount of information and inter-class separability, is more effective than IOIF and GA-BPSO in classifying objects with similar colors and effectively improves the classification accuracy.

show abstract

“…Although the entity behavior analytics methods based on FCM optimize the results of entity behavior clustering, there are still problems in the process of using the FCM algorithm in UEBA, for example, the initialization parameters are difficult to select, and the results of clustering are easy to fall into the local optimum 21 . In order to better improve the clustering effect of the FCM algorithm, Wang et al 22 proposed a validity function to evaluate the clustering results according to the relative structure information of the data, and this method can accurately obtain the optimal number of clusters. Wu et al 23 added a sample feature called local data densit y to optimize the FCM algorithm, and one-dimensional data was extracted by distribution density characteristics of the eigenvalues.…”

Section: Related Workmentioning

confidence: 99%

“…Wu et al 23 added a sample feature called local data densit y to optimize the FCM algorithm, and one-dimensional data was extracted by distribution density characteristics of the eigenvalues. Wang 22 and Wu 23 gave us much inspiration for dealing with the relative positional relationship of data, and the shortcomings of FCM in finding the optimal solution cannot also be ignored. Therefore, we added a population-based stochastic optimization technique to the process of finding the centroid and a relative structure measurement method to the anomaly detection process.…”

Section: Related Workmentioning

confidence: 99%

Multi-homed abnormal behavior detection algorithm based on fuzzy particle swarm cluster in user and entity behavior analytics

Cui

Zhang

Chen

et al. 2022

Sci Rep

View full text Add to dashboard Cite

User and entity behavior analytics (UEBA) is an anomaly detection technique that identifies potential threat events in the enterprise's internal threat analysis and external intrusion detection. One limitation of existing methods in UEBA is that many algorithms use deterministic algorithms only for one category labeling and only compare with other samples within this category. In order to improve the efficiency of potential threat identification, we propose a model to detect multi-homed abnormal behavior based on fuzzy particle swarm clustering. Using the behavior frequency-inverse entities frequency (BF-IEF) technology, the method of measuring the similarity of entity and user behavior is optimized. To improve the iterative speed of the fuzzy clustering algorithm, the particle swarm is introduced into the search process of the category centroid. The entity's nearest neighbor relative anomaly factor (NNRAF) in multiple fuzzy categories is calculated according to the category membership matrix, and it is combined with boxplot to detect outliers. Our model solves the problem that the sample in UEBA is evaluated only in one certain class, and the characteristics of the particle swarm optimization algorithm can avoid clustering results falling into local optimal. The results show that compared with the traditional UEBA approach, the abnormal behavior detection ability of the new method is significantly improved, which can improve the ability of information systems to resist unknown threats in practical applications. In the experiment, the accuracy rate, accuracy rate, recall rate, and F1 score of the new method reach 0.92, 0.96, 0.90, and 0.93 respectively, which is significantly better than the traditional abnormal detections.

show abstract

A new validity function of FCM clustering algorithm based on intra-class compactness and inter-class separation

Cited by 16 publications

References 20 publications

Study and analysis of wastewater treatment in the refining and chemical industry based on multidimensional data analysis

Study and analysis of wastewater treatment in the refining and chemical industry based on multidimensional data analysis

Hyperspectral Band Selections for Enhancing the Discrimination of Difficult Targets Using Local Band Index and Particle Swarm Optimization

Multi-homed abnormal behavior detection algorithm based on fuzzy particle swarm cluster in user and entity behavior analytics

Contact Info

Product

Resources

About