China 
Africa 
Explore chapters and articles related to this topic
Review of the Human Brain and EEG Signals
Published in Teodiano Freire Bastos-Filho, Introduction to Non-Invasive EEG-Based Brain–Computer Interfaces for Assistive Technologies, 2020
Alessandro Botti Benevides, Alan Silva da Paz Floriano, Mario Sarcinelli-Filho, Teodiano Freire Bastos-Filho
The MMI family of ICA algorithms, which includes “runICA” algorithm, uses measures such as Kullback–Leibler divergence (KLD)32 and maximum entropy. The “runica” performs ICA decomposition of input data using the logistic “infomax” algorithm described by Bell and Sejnowski in 1995 [35]. The “infomax” is an optimization principle in which a set of input values (I) are mapped to a set of output values (O) that are chosen, or learned, to maximize the average Shannon mutual information between the input and the output, H(O;I). The mutual information can also be understood as the expectation of KLD of the conditional distribution of O given I, p(o|i), and the univariate distribution of O, p(o). Then, H(O;I) = E[KLD(p(o|i)||p(o))], and the more different the distributions p(o|i) and p(o), the greater the information gain.
Toward Unsupervised Smart Chemical Sensor Arrays
Published in Kevin Yallup, Krzysztof Iniewski, Technologies for Smart Sensors and Sensor Fusion, 2017
Leonardo Tomazeli Duarte, Christian Jutten
One can find in the literature other approaches that also lead to simple ICA algorithms. Examples include the Infomax approach, cumulant-based methods, nonlinear decorrelation methods, and nonlinear PCA (see [4,6] for an introduction). An interesting point related to them is that all these approaches are somehow connected and can be described through a consistent theoretical framework [19], resulting thus in practical algorithms that are similar.
A new approach for ocular artifact removal from EEG signal using EEMD and SCICA
Published in Cogent Engineering, 2020
Anchal Yadav, Mahipal Singh Choudhry
In this step, artifactual IMFs are decomposed into ICs using ICA and then classified into two classes based on the values of mMSE and kurtosis. The artifactual IMFs are used as the input signals to ICA and various ICs are obtained. Many algorithms are designed to perform ICA. For sources having super-Gaussian distribution, infomax ICA (Makeig et al., 1996) is the most efficient algorithm. The approximate model for real-time EEG with the ocular artifact is closest to super-Gaussian distribution so, in the proposed method, infomax ICA is selected among different ICA algorithms.