Blog Posts

Insights on AI, technology, research, and academic perspectives from Kurdistan and beyond.

Measuring Changes in Temporal Data

Spiliopoulou et al. introduced the monic model, which finds cluster transition over accumulating data sets, providing an ageing function for clustering data that prioritises

Read More

External Cluster Validation

How to validate the resulted clusters

External criteria validate the results of clustering based on some predefined structures of the data which is provided from an external source.

Read More

Internal Cluster Validation

How to validate the resulted clusters

Internal criteria measure the 'goodness' of clusters for the data by extracting information from data and clusters alone, such as the compactness of data points inside one cluster.

Read More

Cluster Validation

How to validate the resulted clusters

Many clustering methods exist to be used in different situations according to the underlying data to be analysed and clustered.

Read More

Hierarchical Clustering

Hierarchical clustering is a method to group instances of a data set into a series of nested clusters or a tree of clusters called a dendrogram

Read More

Fuzzy Clustering

C-means algorithm

Fuzzy sets are used in fuzzy logic and can be considered as a generalisation of set theory. An element can be a member of a particular set or not in set theory

Read More

Centroid-Based Clustering

K-Means and PAM

Centroid-based or representative-based clustering is a method of finding the best k clusters of items in the D data set.

Read More

Clustering Algorithms

What is CLustering

Unsupervised machine learning methods aim to find patterns or groups (clusters) in data sets so that the most similar items in the data set will be gathered in the same cluster

Read More

Classification Performance Measures

How to measure classification performance

Multiple methods exist to measure the performance of a classification algorithm and classify a data set into two classes, positive and classified.

Read More

K-Nearest Neighbours

Very simple inefficient algorithm for classification

KNN classifier is a nonparametric lazy classifier. In nonparametric classification the algorithm does not assume any specific distribution for the data sets.

Read More