AMF-IDBSCAN: Incremental Density Based Clustering Algorithm Using Adaptive Median Filtering Technique

Abstract

Density-based spatial clustering of applications with noise (DBSCAN) is a fundamental algorithm for density-based clustering. It can discover clusters of arbitrary shapes and sizes from a large amount of data, which contains noise and outliers. However, it fails to treat large datasets, outperform when new objects are inserted into the existing database, remove noise points or outliers totally and handle the local density variation that exists within the cluster. So, a good clustering method should allow a significant density modification within the cluster and should learn dynamics and large databases. In this paper, an enhancement of the DBSCAN algorithm is proposed based on incremental clustering called AMF-IDBSCAN which builds incrementally the clusters of different shapes and sizes in large datasets and eliminates the presence of noise and outliers. The proposed AMF-IDBSCAN algorithm uses a canopy clustering algorithm for pre-clustering the data sets to decrease the volume of data, applies an incremental DBSCAN for clustering the data points and Adaptive Median Filtering (AMF) technique for post-clustering to reduce the number of outliers by replacing noises by chosen medians. Experiments with AMF-IDBSCAN are performed on the University of California Irvine (UCI) repository UCI data sets. The results show that our algorithm performs better than DBSCAN, IDBSCAN, and DMDBSCAN. Povzetek: V članku je predstavljen nov algoritem AMF-IDBSCAN, izboljšana različica DBSCAN, ki uporablja grozdenje krošenj za zmanjšanje obsega podatkov in tehnike AMF za odpravo hrupa.

K-CAE: Image Classification Using Convolutional AutoEncoder Pre-Training and K-means Clustering

“…• We will also use other supervised deep learning algorithms, such as Convolutional Neural Networks (CNN), etc [13]; • With the use of large data sets, we will introduce the notion of incrementality into the database provided to the autoencoder [14]; • This architecture can also be used in certain application domains, such as handwriting recognition, with very large datasets.…”

IoT based traffic congestion control for environmental applications

“…We proposed a load-balanced clustering protocol to extend the network lifetime by balancing the consumed energy in the most equitable way possible. This protocol takes into consideration the residual energy, the degree of connectivity of the nodes and the distance to the SB during a selection of the cluster-heads, LBCMH (Load-Balancing based Clustering Multipath routing protocol for Heterogeneous sensor networks) introduces a load balancing mechanism by achieving a good Protocol Definition Summary Advantages Disadvantages DEACP (Distributed Energy efficient Adaptive Clustering Protocol) [17] This paper is proposed a DEACP protocol in order to improve the services of RCSFs. DEACP is a hierarchical adaptive clustering protocol, combines clustering and load balancing.…”

“…It has several constraints such as memory, bandwidth or power consumption, etc. It must be adopted to a use, it has some form of intelligence, ability to receive, transmit data with software through embedded sensors [16] [17]. A connected object has value when it is connected to other objects and software bricks, for example: a connected watch is only of interest within a health/wellness oriented ecosystem, which goes far beyond knowing the time.…”

Unsupervised Deep Learning: Taxonomy and algorithms

“…The output is a set of clusters that form a partition, or a structure of partitions of the data set. Generally, finding clusters is not a simple task and the current clustering algorithms take a long time when they are applied to large databases [1].…”

“…• apply the impressive ability to deal with unsupervised learning for structure analysis of high-dimensional visual data; • find a solution to the problem of subspace clustering by partitioning data drawn from a union of multiple subspaces. The contribution of this study is (1) to provide an overview of various deep learning-based clustering algorithms. It includes an explanation of the most recent improvements in unsupervised clustering; (2) propose a taxonomy of methods that use deep learning for clustering.…”