Join us and keep tuned to what's hot in Neuroscience! From EEG basics to EEG applications – including Brain Computer Interfaces, Neurofeedback, Affective Computing, Sleep Monitoring.

Your email:


Follow Me

Neuroscience, tCS and EEG blog

Current Articles | RSS Feed RSS Feed

The Importance and Difficulty of Ground Truth Generation for EEG Data Analysis through Machine Learning


As you may know if you have been following this blog ground truth plays a very important role in the implementation of machine learning algorithms for EEG data analysis. Machine learning includes several adaptive procedures. At the core of supervised algorithms is the concept of learning by example. We show different examples of possible EEG streams coming from different subject/user states/task classes and the algorithms find out by means of mathematical computation where to place the borders among samples. So the examples shown to the algorithm must belong to different classes and these classes have to be known in advance. This is what is called ground truth (or golden standard in other circles). The ground truth is also important for the performance evaluation through the procedures presented in past posts (see How Good is my Computational Intelligence Algorithm for EEG Analysis? and Two alternatives for performance evaluation in EEG analysis through Computational Intelligence)

Are you in control?

Are yo.pngu in control

A couple of weeks ago I took part in a neurodesconferencia event for Brain Awareness Week called "Hackers Cerebrals". The idea was to talk about control, or loss of control, from the point of view of what the neuroscience tells us. 

Top 7 Weirdest EEG Applications

dog with EEG

As we know, the main uses of EEG include diagnosis and neurofeedback therapy (including BCI). Theses applications falls into the clinical realm, but there are many more applications, some of them quite strange to say the least.

One important point before starting this post: EEG and BCI are nowadays mainly used for clinical purposes, but … what about healthy users? Can EEG and/or BCI provide interesting applications to this target segment? I think so. First of all because EEG devices are more and more available, they are getting cheaper and they are becoming smaller, wireless and easy to set up. That makes the user's acceptance increase. On the other hand, there are already many applications focusing on healthy users as I will show in this post.

1 - EEG Sonification

This has already been covered in this other blog post but I would like to give some other interesting examples.

EEG and Space

EEG and Space

EEG researchers are opening new frontiers for exploring the human brain beyond the Earth. EEG research on humans in space travel is becoming a key field in order to improve pilots and astronauts training and well-being.

European Applied Neuroscience Projects

human brain project

As I have mentioned some times in previous posts, I am pretty sure that in the next years we will see great advances in the field of neuroscience. The 20th century was the century of physics, with great discoveries such as the theory of relativity and quantum physics, among others. I reckon the 21st century will be the century of neuroscience.

Neurofeedback: A Tool to Enhance Sports Performance

Neurofeedback Sports Performance

During the last decade the use of Neurofeedback techniques to achieve a better athletic performance has been a booming subject. More and more athletes use mental training each day as a means of achieving the ultimate competitive edge. One of the most well-known examples is the Italian football team that won the 2004 World Cup final in Germany against France. As you can read in this article, to prepare the tournament some of the Italian footballers used neurofeedback techniques to train focus, concentration and ‘getting into the zone’.

8 BCI Software Apps you Can't Live Without


A few months ago David Ibañez published a post with the top 3 applications for BCI. Today I intend to expand that list and review other software packages for BCI and offer you some other alternatives. This time we won't only focus on packages ready to work out-of-the-box, so we'll also include libraries and frameworks ready to be adopted within your developed applications. As usual, we'd love you to contribute to this post, by sharing your experience and opinions regarding the packages we review, as well as letting us know about other packages we haven't yet learnt about.

Multimodal Stress Classification based on Data Fusion

Stress Classification Data Fusion

In his blog post a few weeks ago Alejandro Riera talked about characterizing stress based on EEG. The post presented the generation of EEG features based on ratios and differences at particular frequency bands. I would like to comment today on the second part of the story, that goes from such features to the classification of activities upon the stress level. This can have applications like the one recently presented. The general framework was somehow introduced by Anton Albajes-Eizagirre in his post on machine learning applied to affective computing[3]. He presented the general framework, so I would like to comment on the experimental results we have obtained with a particular dataset by using data fusion. The work can be found in detail in our paper Electro-Physiological Data Fusion for Stress Detection.

The multimodal setting for stress characterization

The purpose of the system is to fuse the data of separate information channels, namely EEG, and EMG data. We achieve the classification of stress-related tasks, e.g. mathematical computation, a fake blood extraction, vs tasks not related to stress, e.g. relaxing, reading. The idea is that by using these two electrophysiological modalities we would be able to determine if a subject is suffering from stress. We extract different features from the two modalities and then apply fusion operators in order to characterize the stress level of the task. We take into account the EEG channels reported in the literature to be the most related with valence and arousal, namely those in the frontal part. Therefore we select the pairs F3-F4, and F7-F8. We computed here the alpha asymmetry, and the alpha-beta ratios, so that we have 6 EEG-based features. Moreover, we take into account the EMG energy on the zygomatic and the corrugator facial muscles. Facial EMG is known to be a good mean to monitor facial expressions and therefore emotional characterization. This gives us a system based on 8 features delivered each second with an analysis window of 2 seconds length.

Does Consciousness Matter?


Last month Max Tegmark from MIT published a paper on consciousness. The curious thing here is that Tegmark is a physicist and they don’t traditionally get mixed up in theories of consciousness. His paper though is very timely as it reflects a growing movement in neuroscience towards a fundamental shift in how we view the issue.

EEG and tCS: exploiting the loop


Some years ago I was deeply intrigued by the notion of “locking” into natural brain rhythms using tACS or more exotic tCS flavors.  The basic notion stems from the idea of resonance  the phenomenon in which a forced dynamical system is able to accumulate more and more energy from dynamically-matched external forcing, as in a swing (all parents  … and kids know how to do this).  Similarly, one could conjecture, if we force brain dynamics with a magical frequency or otherwise properly designed waveform we may entrain and amplify certain rhythms

All Posts