Abstract Background Two different Human-Machine Interfaces (HMIs) were developed, both based on electro-biological signals. One is the EMG signal and other EEG signal. major features of such interfaces are their relatively simple data acquisition processing systems, which need just a few hardware software resources, so that they are, computationally financially speaking, low cost solutions. Both applied to robotic performances analyzed here. The EMG-based HMI was tested in mobile robot,...

In the present work, a robotic wheelchair navigation system which is specially designed for confined spaces proposed. spaces, movements of wheelchairs are restricted by environment more than other unicycle type vehicles. For example, if too close to wall, it can not rotate freely because front or back may collide with wall. The composed path planning module and control module; both use robot information provided SLAM algorithm attain their objectives. strategy uses Monte Carlo technique find...

This paper presents a novel calibration procedure as simple, yet powerful, method to place and align inertial sensors with body segments. The can be easily replicated without the need of any additional tools. proposed is validated in three different applications: computer mathematical simulation; simplified joint composed two semi-spheres interconnected by universal goniometer; real gait test five able-bodied subjects. Simulation results demonstrate that, after applied, angles are correctly...

People with severe disabilities may have difficulties when interacting their home devices due to the limitations inherent disability. Simple activities even be impossible for this group of people. Although much work has been devoted proposing new assistive technologies improve lives people disabilities, some studies found that abandonment such is quite high. This presents a system based on eye tracking controlling and monitoring smart home, Internet Things, which was developed following...

The advancement and availability of technology can be employed to improve our daily lives. One example is Human Activity Recognition (HAR). HAR research has been mainly explored using imagery but currently evolving the use sensors ability have a positive impact, including individual health monitoring removing barrier healthcare. To reach marketable device, state-of-the-art classifications power consumption methods such as convolutional neural network (CNN), data compression other emerging...

We present in this paper a study of three EEG signals feature extraction techniques. These techniques have been widely employed researches emotional states recognition: statistical characteristics, features based on PSD (Power Spectral Density) and HOC (High Order Crossings). The validation was performed via classification calm stress using the K-NN classifier off-line mode from available DEAP database. best results achieved were 70.1%, technique, 69.59% technique.

This work presents the development of a robotic wheelchair that can be commanded by users in supervised way or fully automatic unsupervised navigation system. It provides flexibility to choose different modalities command wheelchair, addition suitable for people with levels disabilities. Users based on their eye blinks, movements, head sip-and-puff and through brain signals. The also operate like an auto-guided vehicle, following metallic tapes, autonomous way. system is provided easy use...

A low-cost Brain-Machine Interface (BMI) based on electroencephalography for lower-limb motor recovery of post-stroke patients is proposed here, which provides passive pedaling as feedback, when trigger a Mini-Motorized Exercise Bike (MMEB) by executing imagery (MI). This system was validated in an On-line phase eight healthy subjects and two patients, felt closed-loop commanding the MMEB due to fast response our BMI. It developed using methods low-computational cost, such Riemannian...

Abstract Motor Imagery (MI)-Brain Computer-Interfaces (BCI) illiteracy defines that not all subjects can achieve a good performance in MI-BCI systems due to different factors related the fatigue, substance consumption, concentration, and experience use. To reduce effects of lack use BCI (naïve users), this paper presents implementation three Deep Learning (DL) methods with hypothesis could be improved compared baseline evaluation naïve users. The proposed here are based on Convolutional...

Human mobility is affected by different types of pathologies and also decreases gradually with age. In this context, Smart Walkers may offer important benefits for human assisted-gait in rehabilitation functional compensation scenarios. This paper proposes a new interaction strategy human-walker cooperation. The presented based on the acquisition gait parameters means data fusion from inertial measurement units laser range finder. includes mathematical formulation controller, simulations,...

Introduction The main idea of a traditional Steady State Visually Evoked Potentials (SSVEP)-BCI is the activation commands through gaze control. For this purpose, retina eye excited by stimulus at certain frequency. Several studies have shown effects related to different kind stimuli, frequencies, window lengths, techniques feature extraction and even classification. So far, none previous has performed comparison performance stimuli colors LED technology. This study addresses precisely...

Child-Robot Interaction (CRI) has become increasingly addressed in research and applications. This work proposes a system for emotion recognition children, recording facial images by both visual (RGB-red, green blue) Infrared Thermal Imaging (IRTI) cameras. For this purpose, the Viola-Jones algorithm is used on color to detect regions of interest (ROIs), which are transferred thermal camera plane multiplying homography matrix obtained through calibration process system. As novelty, we...

Introduction Autism Spectrum Disorder is a set of developmental disorders that imply in poor social skills, lack interest activities and interaction with people. Treatments rely on teaching skills such therapies robotics may offer aid. This work pilot study, which aims to show the development usage ludic mobile robot for stimulating ASD children. Methods A special costume monitor display multimedia contents was designed interact mediator controls robot's movements room prepared interactive...

Physiological signals may be used as objective markers to identify emotions, which play relevant roles in social and daily life. To measure these signals, the use of contact-free techniques, such Infrared Thermal Imaging (IRTI), is indispensable individuals who have sensory sensitivity. The goal this study propose an experimental design analyze five emotions (disgust, fear, happiness, sadness surprise) from facial thermal images typically developing (TD) children aged 7–11 years using...

The aim of this study is to propose a recognition system pedaling motor imagery for lower-limb rehabilitation, which uses unsupervised methods improve the feature extraction, and consequently class discrimination EEG patterns.After applying spectrogram based on short-time Fourier transform (SSTFT), both sparseness constraints total power are used time-frequency representation automatically locate subject-specific bands that pack highest during imagery. output frequency employed in adjust...

Human Activity Recognition (HAR) is the automatic detection and understanding of human motion behavior based on data extracted from video camera, ambient sensors or wearable which particularly has recently attracted increased attention both researchers industry. However, for running practical HAR systems devices, there are some requirements such as design development small, lightweight, powerful, low-cost smart sensors. In this context, must be continuously collected, edge computing a viable...

Objective.This work proposes a method for two calibration schemes based on sensory feedback to extract reliable motor imagery (MI) features, and provide classification outputs more correlated the user's intention.Method.After filtering raw electroencephalogram (EEG), two-step spatial feature extraction by using Riemannian covariance matrices (RCM) common patterns is proposed here. It uses EEG data from trials providing feedback, in an intermediate step composed of bothkth nearest neighbors...

This work presents a Brain-Computer Interface (BCI) based on the Steady-State Visual Evoked Potential (SSVEP) that can discriminate four classes once per second. A statistical test is used to extract evoked response and decision tree stimulus frequency. Designed according such approach, volunteers were capable online operate BCI with hit rates varying from 60% 100%. Moreover, one of could guide robotic wheelchair through an indoor environment using BCI. As additional feature, incorporates...