Hidden Markov Models for SSVEP-based brain computer interfaces with decision-feedback training

Multi-phase cycle coding for SSVEP based brain-computer interfaces

BACKGROUND Brain-computer interfaces (BCIs) based on Steady State Visual Evoked Potential (SSVEP) have attracted more and more attentions for their short time response and high information transfer rate (ITR). The use of a high stimulation frequency (from 30 Hz to 40 Hz) is more comfortable for users and can avoid the amplitude-frequency problem, but the number of available phases for stimulati...

Towards Elaborated Feedback for Training Motor Imagery Brain Computer Interfaces

Motor imagery is one common paradigm in brain computer interface (BCI) systems where the user imagines moving a part of his/her body to control a computer. Motor imagery is endogenous and requires a large amount of training for the user to be able to control the BCI. Therefore, the feedback that is provided to the user is critical to ensure informative insight into improving imagery skills. In ...

Hidden Markov Models Implementation for Tangible Interfaces

Smart objects equipped with inertial sensors can recognize gestures and act as tangible interfaces to interact with smart environments. Hidden Markov Models (HMM) are a powerful tool for gesture recognition. Gesture recognition with HMM is performed using the forward algorithm. In this paper we evaluate the fixed point implementation of the forward algorithm for HMM to assess if this implementa...

Decoding directed covert attention in brain computer interfaces using hidden Markov models

Training Hidden Non-markov Models

Hidden Markov models (HMM) are well known in speech recognition, where they are trained to recognize spoken words and even whole sentences. They are used to find the parameters of a so-called hidden model (usually a DTMC) by training it with observed output sequences. This paper introduces an approach to train stochastic Petri nets with the methods of HMM. As opposed to a DTMC, a stochastic Pet...