Human-Machine Interfaces (HMI) allow users to interact with different devices such as computers or home elements. A key part in HMI is the design of simple non-invasive interfaces to capture the signals associated with the user’s intentions. In this work, we have designed two different approaches based on Electroencephalography (EEG) and Electrooculography (EOG). For both cases, signal acquisition is performed using only one electrode, which makes placement more comfortable compared to multi-channel systems. We have also developed a Graphical User Interface (GUI) that presents objects to the user using two paradigms—one-by-one objects or rows-columns of objects. Both interfaces and paradigms have been compared for several users considering interactions with home elements.

A comparison of two open source electroencephalography devices designed to acquire signals associated to the brain activity is presented in this work. The experiments are developed considering the task of determining the user eye state i.e., open eyes or closed eyes, applying an algorithm based on computing the sliding Fourier Transform of the captured signals.

A comparison of different machine learning techniques for eye state identification through Electroencephalography (EEG) signals is presented in this paper. (1) Background: We extend our previous work by studying several techniques for the extraction of the features corresponding to the mental states of open and closed eyes and their subsequent classification; (2) Methods: A prototype developed by the authors is used to capture the brain signals. We consider the Discrete Fourier Transform (DFT) and the Discrete Wavelet Transform (DWT) for feature extraction; Linear Discriminant Analysis (LDA) and Support Vector Machine (SVM) for state classification; and Independent Component Analysis (ICA) for preprocessing the data; (3) Results: The results obtained from some subjects show the good performance of the proposed methods; and (4) Conclusion: The combination of several techniques allows us to obtain a high accuracy of eye identification.

In this paper we focus on the issue related to finding the resolving connected dominating sets (RCDSs) of a graph, denoted by G. The connected dominating set (CDS) is a connected subset of vertices of G selected to guarantee that all vertices in the graph are connected to vertices in the CDS. The connected dominating set with minimum cardinality, or minimum CDS (MCDS), is an adequate virtual backbone for information interchange in a network. When distinct vertices of G have also distinct representations with respect to a subset of vertices in the MCDS, it is said that the MCDS includes a resolving set (RS) of G. With this work, we explore different strategies to find the RCDS with minimum cardinality in complex networks where the vertices have different importances.