Related references
Note: Only part of the references are listed.
Article
Computer Science, Artificial Intelligence
Yue He et al.
Summary: This paper investigates the relationships among different probabilistic-based expression formats and introduces transformation functions to unify them. It also proposes novel distance measures for probabilistic hesitant fuzzy sets and develops the K-medoids algorithm for fusing different information formats.
APPLIED INTELLIGENCE
(2022)
Article
Computer Science, Artificial Intelligence
Carlo Baldassi
Summary: We introduce an evolutionary algorithm called recombinator-k-means for optimizing the highly nonconvex kmeans problem. Its defining feature is that its crossover step involves all the members of the current generation, stochastically recombining them with a repurposed variant of the k-means++ seeding algorithm. The recombination also uses a reweighting mechanism that realizes a progressively sharper stochastic selection policy and ensures that the population eventually coalesces into a single solution. We compare this scheme with a state-of-the-art alternative, a more standard genetic algorithm with deterministic pairwise-nearest-neighbor crossover and an elitist selection policy, of which we also provide an augmented and efficient implementation. Extensive tests on large and challenging datasets (both synthetic and real word) show that for fixed population sizes recombinator-k-means is generally superior in terms of the optimization objective, at the cost of a more expensive crossover step. When adjusting the population sizes of the two algorithms to match their running times, we find that for short times the (augmented) pairwise-nearest-neighbor method is always superior, while at longer times recombinator-k-means will match it and, on the most difficult examples, take over. We conclude that the reweighted whole-population recombination is more costly but generally better at escaping local minima Moreover, it is algorithmically simpler and more general (it could be applied even to k-medians or k-medoids, for example).
IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION
(2022)
Article
Computer Science, Artificial Intelligence
Gaurav Mishra et al.
Summary: Density-based clustering techniques are popular because of their ability to identify clusters of arbitrary shapes and automatically detect the number of clusters. However, these techniques are not suitable for clusters with large density variation. We propose a new density measure based on minimum spanning tree (MST) and a clustering technique to address this issue.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2022)
Article
Computer Science, Information Systems
Biswarup Ray et al.
Summary: Outlier detection is vital in machine learning and data science, with this research proposing a technique using an ensemble of three clustering algorithms and novel probability-based methods for handling clustered outliers. Significant improvement in cluster validity metrics was observed after removing the outliers.
MULTIMEDIA TOOLS AND APPLICATIONS
(2022)
Article
Mathematical & Computational Biology
Ji Feng et al.
Summary: The proposed clustering algorithm based on adaptive neighborhood effectively addresses the parameter selection problem by iteratively adapting to a stable state and marking boundary points according to distribution characteristics. Extensive experiments show satisfactory clustering results across datasets of varying sizes and distributions.
COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE
(2021)
Article
Computer Science, Information Systems
Xiao Xu et al.
Summary: A novel fast sparse search density peaks clustering (FSDPC) algorithm is proposed to enhance the efficiency of density peaks clustering (DPC) by using a sparse search strategy and a random third-party data point method, which outperforms the DPC and other state-of-the-art algorithms in terms of both computational complexity and clustering performance.
INFORMATION SCIENCES
(2021)
Article
Computer Science, Information Systems
Mingjing Du et al.
Summary: The border-peeling (BP) clustering algorithm is effective in recognizing cluster structures and detecting outliers, but may perform poorly on datasets with non-uniformly distributed clusters and complex shapes. To address these issues, a robust border-peeling clustering algorithm (ROBP) is proposed in this paper, which outperforms competitors in most cases. Experiment results demonstrate that ROBP is more robust, reliable, and computationally efficient compared to BP.
INFORMATION SCIENCES
(2021)
Article
Computer Science, Artificial Intelligence
Hadar Averbuch-Elor et al.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2020)
Article
Computer Science, Artificial Intelligence
Liang Bai et al.
INFORMATION FUSION
(2020)
Article
Computer Science, Information Systems
Mohammad Rezaei et al.
Article
Computer Science, Artificial Intelligence
Seyed Amjad Seyedi et al.
EXPERT SYSTEMS WITH APPLICATIONS
(2019)
Proceedings Paper
Computer Science, Artificial Intelligence
M. Saquib Sarfraz et al.
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019)
(2019)
Article
Multidisciplinary Sciences
Sohil Atul Shah et al.
PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA
(2017)
Proceedings Paper
Computer Science, Artificial Intelligence
Pasi Franti et al.
STRUCTURAL, SYNTACTIC, AND STATISTICAL PATTERN RECOGNITION, S+SSPR 2016
(2016)
Article
Multidisciplinary Sciences
Alex Rodriguez et al.
Article
Computer Science, Artificial Intelligence
Chang-Dong Wang et al.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2013)
Article
Computer Science, Artificial Intelligence
Chang-Dong Wang et al.
IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART C-APPLICATIONS AND REVIEWS
(2012)
Article
Statistics & Probability
Marina Meila
JOURNAL OF MULTIVARIATE ANALYSIS
(2007)
Article
Multidisciplinary Sciences
Brendan J. Frey et al.
Article
Computer Science, Artificial Intelligence
CY Xia et al.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2006)
