VSE knjižnice (vzajemna bibliografsko-kataložna baza podatkov COBIB.SI)
  • ACHC: Associative classifier based on hierarchical clustering [Elektronski vir]
    Jamolbek Maqsudovich, Mattiev ; Kavšek, Branko
    The size of collected data is increasing and the number of rules generated on those datasets is getting bigger. Producing compact and accurate models is being the most important task of data mining. ... In this research work, we develop a new associative classifier – ACHC, that utilizes agglomerative hierarchical clustering as a post-processing step to reduce the number of rules and a new method is proposed in the rule-selection step to increase classification accuracy. Experimental evaluations show that the ACHC method achieves significantly better results than classical rule learning algorithms in terms of rules on bigger datasets while maintaining classification accuracy on those datasets. More precisely, ACHC achieved the highest (43) result on the average number of rules and the third-highest (84.8%) result in terms of average classification accuracy among 10 classification algorithms.
    Vir: Intelligent data engineering and automated learning - IDEAL 2021 [Elektronski vir] : 22nd International Conference, IDEAL 2021, Manchester, UK, November 25-27, 2021 : proceedings (str. 560-571)
    Vrsta gradiva - prispevek na konferenci ; neleposlovje za odrasle
    Leto - 2021
    Jezik - angleški
    COBISS.SI-ID - 94352131

    Povezava(-e):

    https://link.springer.com/chapter/10.1007%2F978-3-030-91608-4_55
    https://doi.org/10.1007/978-3-030-91608-4_55
    DOI

Vnos na polico