Article
Mathematics, Interdisciplinary Applications
Amin Golzari Oskouei, Mohammad Ali Balafar, Cina Motamed
Summary: This paper introduces a new clustering method, FKMAWCW, to address the sensitivity issues of the FKM algorithm. By incorporating local attribute weighting and cluster weighting mechanisms, the algorithm tackles the problems related to attribute importance and initialization sensitivity, while also proposing a new distance function to reduce noise sensitivity. The proposed algorithm outperforms state-of-the-art algorithms in experiments on benchmark datasets and shows mathematical analyses for convergence proof.
CHAOS SOLITONS & FRACTALS
(2021)
Article
Green & Sustainable Science & Technology
Qiang Shang, Yang Yu, Tian Xie
Summary: In this paper, a hybrid new traffic state classification method based on unsupervised clustering is proposed. The method utilizes traffic data for clustering to achieve traffic state classification, and it shows superior performance compared to other methods.
Review
Computer Science, Artificial Intelligence
Julio Pena, Gonzalo Napoles, Yamisleydi Salgueiro
Summary: This study surveyed attribute weighting methods in MADM scenarios, analyzed the strengths and limitations of different approaches, and proposed future research directions. The implicit weighting with additional information category was found to be the most coherent approach, suggesting the importance of incorporating preference information in future methods.
ARTIFICIAL INTELLIGENCE REVIEW
(2021)
Article
Computer Science, Artificial Intelligence
Kalpathy Jayanth Krishnan, Kishalay Mitra
Summary: This study proposes a modified Self Organizing Map algorithm for clustering time series data. By modifying the original steps of the algorithm and using specific initialization methods and similarity measures, this algorithm outperforms other popular clustering algorithms in terms of clustering performance and computation time.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Computer Science, Artificial Intelligence
Zahra Sadat Sajjadi, Mahdi Esmaeili, Mostafa Ghobaei-Arani, Behrouz Minaei-Bidgoli
Summary: In recent years, researchers have shown increasing interest in using social network data to extract meaningful information, particularly in applications such as link prediction, community detection, and protein module identification. The combination of structural and attribute similarity has been a common approach in graph clustering solutions, but the limited use of node features in sparse social networks remains a challenge. This paper proposes a hybrid clustering approach for link prediction in heterogeneous information networks by considering the weight of direct edges and the correlation between adjacency vectors. The results show that this method effectively reduces entropy and execution time while maintaining cluster density.
KNOWLEDGE AND INFORMATION SYSTEMS
(2023)
Article
Computer Science, Information Systems
Huan Zhang, Liangxiao Jiang, Chaoqun Li
Summary: In this study, a novel model called A(2)WNB is proposed to address the limitation of the attribute conditional independence assumption in naive Bayes algorithm. By discovering and utilizing latent attributes beyond the original attribute space, as well as optimizing attribute weights to reduce attribute redundancy, the A(2)WNB model demonstrates superior performance in classification tasks.
SCIENCE CHINA-INFORMATION SCIENCES
(2022)
Article
Operations Research & Management Science
Pierpaolo D'Urso, Livia De Giovanni, Vincenzina Vitale
Summary: This study proposes a robust fuzzy clustering model for mixed data, which combines dissimilarity matrices with weights computed during the optimization process. The proposed algorithm shows its effectiveness in finding hidden clusters compared to single-attribute approaches, as demonstrated by simulation studies and empirical application to football players data.
ANNALS OF OPERATIONS RESEARCH
(2023)
Article
Engineering, Mechanical
Tianqi Gu, Hongxin Lin, Dawei Tang, Shuwen Lin, Tianzhi Luo
Summary: This article introduces a robust MTLS method, which can suppress multiple outliers within the whole domain by removing anomalous nodes through a two-step pre-process. The proposed method shows great robustness and accuracy in reconstructing simulation and experiment data.
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
(2022)
Article
Mathematics, Applied
Yali Zhang, Pengjian Shang
Summary: This article introduces the maximal information coefficient (MIC) as a statistical correlation analysis method and points out the limitations of existing methods in detecting relationship types. It proposes a maximum information coefficient based on K-Medoids clustering (KM-MIC) method to improve computational efficiency and optimize data partitioning.
COMMUNICATIONS IN NONLINEAR SCIENCE AND NUMERICAL SIMULATION
(2022)
Article
Computer Science, Interdisciplinary Applications
Nebojsa Rasovic
Summary: Design for Additive Manufacturing (DfAM) is a crucial method in product design and development, analyzing key parameters of AM to enhance production and product quality. By utilizing weighted features and decision support tools, the recommended layer thickness can significantly improve product quality and performance.
INTERNATIONAL JOURNAL OF COMPUTER INTEGRATED MANUFACTURING
(2021)
Article
Geosciences, Multidisciplinary
Trevan Flynn, John Triantafilis, Andrei Rozanov, Freddie Ellis, Alberto Lazaro-Lopez, Andrew Watson, Cathy Clarke
Summary: Allocation of soil profiles to soil classes is influenced by surveyor's expertise. Numerical classifications assist in creating property-based clusters. Soil information downstream applications benefit from consistent soil classifications.
Article
Computer Science, Artificial Intelligence
Huan Zhang, Liangxiao Jiang, Chaoqun Li
Summary: The proposed collaboratively weighted Naive Bayes (CWNB) approach outperforms the standard NB and all other existing state-of-the-art competitors by simultaneously learning instance and attribute weights in a collaborative manner.
KNOWLEDGE AND INFORMATION SYSTEMS
(2021)
Article
Management
Cong-Cong Li, Yucheng Dong, Haiming Liang, Witold Pedrycz, Francisco Herrera
Summary: With the advancement of information and network technology, data-driven methodologies have become crucial in decision-making processes due to the generation of large amounts of data from the Internet. However, there is limited research on personalized individual semantics (PIS) in the context of multi-attribute decision-making (MADM). This study proposes a data-driven learning model that analyzes PIS to support a multi-attribute decision-making model considering pre-existing classification of the alternatives. The feasibility of the proposed model is justified through case studies and comparisons with other methods.
OMEGA-INTERNATIONAL JOURNAL OF MANAGEMENT SCIENCE
(2022)
Article
Computer Science, Artificial Intelligence
Huan Zhang, Liangxiao Jiang
Summary: Naive Bayes (NB) is a simple, efficient, and effective data mining algorithm. However, its performance is limited by the unrealistic attribute conditional independence assumption and unreliable conditional probability estimation. This study proposes a novel model called fine tuned attribute weighted NB (FTAWNB), which combines fine tuning with attribute weighting to enhance NB's performance by improving both the attribute conditional independence assumption and conditional probability estimation.
Article
Engineering, Industrial
Zequan Chen, Guofa Li, Jialong He, Zhaojun Yang, Jili Wang
Summary: A new parallel adaptive structure reliability analysis method called RBIK is proposed in this study, which incorporates a global convergence condition and optimal importance sampling function, and utilizes K-medoids clustering for candidate sample analysis to achieve parallel operation. RBIK distinguishes itself by focusing on rapidly satisfying the global convergence condition of the Kriging model, rather than individual candidate samples.
RELIABILITY ENGINEERING & SYSTEM SAFETY
(2022)