A Comprehensive Review on Analysing of Brain Signals Using Different Clustering Methods

Classification and clustering are crucial tasks in analyzing brain signals, which can be broadly categorized into two main methods: invasive and non-invasive. Invasive techniques involve placing electrodes directly inside or on the surface of the brain to measure brain activity, whereas non-invasive methods measure brain activity without the need for invasive procedures. The latter includes EEG, MEG, fMRI, PET, and NIRS. Brain signals can be classified based on the type of brain activity being measured, such as brainwaves, evoked potentials, event-related potentials, and functional imaging. This classification can help researchers better understand the underlying mechanisms of brain function and develop new methods for diagnosing and treating neurological disorders. The major divisions of clustering of brain signals include hard clustering, soft clustering, density-based clustering, model-based clustering, hierarchical clustering, and subspace clustering. In hard clustering, each brain signal is assigned to a single cluster based on the similarity to the centroid of the cluster, while soft clustering assigns a probability of belonging to each cluster based on the degree of similarity to the centroids of the clusters. Density-based clustering is based on regions of high density in the feature space, model-based clustering is based on a probabilistic model that describes the distribution of the data, and hierarchical clustering is done in a hierarchical manner. Subspace clustering is done on subspaces of the feature space. These different approaches can be used in combination to achieve better results in the clustering of brain signals, depending on the characteristics of the data and the research question at hand. Overall, classification and clustering of brain signals are essential for advancing our understanding of the brain and developing new methods for diagnosing and treating neurological disorders.