A Fast K-prototypes Algorithm Using Partial Distance Computation

Abstract

Abstract:The k-means is one of the most popular and widely used clustering algorithm; however, it is limited to numerical data only. The k-prototypes algorithm is an algorithm famous for dealing with both numerical and categorical data. However, there have been no studies to accelerate it. In this paper, we propose a new, fast k-prototypes algorithm that provides the same answers as those of the original k-prototypes algorithm. The proposed algorithm avoids distance computations using partial distance computation. Our k-prototypes algorithm finds minimum distance without distance computations of all attributes between an object and a cluster center, which allows it to reduce time complexity. A partial distance computation uses a fact that a value of the maximum difference between two categorical attributes is 1 during distance computations. If data objects have m categorical attributes, the maximum difference of categorical attributes between an object and a cluster center is m. Our algorithm first computes distance with numerical attributes only. If a difference of the minimum distance and the second smallest with numerical attributes is higher than m, we can find the minimum distance between an object and a cluster center without distance computations of categorical attributes. The experimental results show that the computational performance of the proposed k-prototypes algorithm is superior to the original k-prototypes algorithm in our dataset.

An Efficient Grid-Based K-Prototypes Algorithm for Sustainable Decision-Making on Spatial Objects

“…For performance evaluation, we compare a basic k-prototypes algorithm (Basic), partial distance computation pruning (PDC) [22] and our two algorithms (KCP and KBP). We examined the performance of our algorithms as the number of objects, the number of clusters, the number of categorical attributes and the number of divisions in each dimension increased.…”

“…In order to improve the performance of the k-prototypes algorithm, Kim [22] proposed the concept of partial distance computation (PDC) which compares only partial attributes, not all attributes in measuring distance. The maximum distance that can be measured in one categorical attribute is 1.…”

“…However, only a few studies have been conducted on how to reduce the time complexity of the k-prototypes algorithm. Kim [22] proposed a pruning technique to reduce distance computation between an object and cluster centers using the concept of partial distance computation. However, this method does not have high pruning efficiency due to the comparison of objects one by one with the cluster center.…”

Agrupamento De Dados Mistos Baseados No Algoritmo K-Means: Uma Revisão Sistemática Da Literatura

“…Wangchamhan, Chiewchanwattana and Sunat (2017) endereçaram o trabalho para resolver o problema de inicialiação dos centróides no k-means, considerando a dissimilaridade de Gower para lidar com dados mistos. Kim (2017) propuseram um método para acelerar a execução do algoritmo k-prototype, pela redução do cálculo das distâncias. Özbakır and Turna (2017) modelaram duas meta-heurísticas para endereçar o problema de definição dos grupos.…”

An Efficient Grid-based K-prototypes Algorithm for Sustainable Decision Making Using Spatial Objects

“…However, only a few studies have been conducted to reduce the time complexity of the k-prototypes algorithm. Kim [16] proposed a pruning technique to reduce distance computation between an object and cluster centers using the concept of partial distance computation.…”