Have you ever wondered about mindreading and mind control? What would it be like to be able to read your friend’s mind? To see if they really mean what they are saying, for instance. What about using mindreading as a lie detector since the system that has been in use is so unreliable? Now, we may be some decades away from seeing that dream become reality, but it is probably fair to say that the rapid technological advance in related fields has set the stage for this development in years to come. One of such field is commonly referred to as neural engineering, which focuses on translating neural signals into tangible applications.
Brain cells or neurons communicate with one another through electrical and chemical means. Great scientists in the past have ingeniously devised several ways to detect such communication, one of which is to record the summed electrical activities that are present on the scalp, a method designated electroencephalography (from three roots: electr meaning electric, the Greek enkephalos meaning brain , the Greek graphein meaning to write). Conventionally the recording electrodes for detecting these signals are plugged into ‘sockets’ on an elastic cap that can be reliably fitted on a person’s head. But there are ambient electrical noises and movement artefacts that can interfere with the signals of interest, essentially imposing a limit on the settings at which the system can be deployed. The first launch of a wearable EEG device in 2007 addressed this mobility restriction, bearing more compact design, fewer electrode channels, and friendlier price point. In fact, our research team purchased this type of tool from OpenBCI and the engineering wizards in our team helped with setting up the open circuit board. Note that there are a variety of these so-called consumer grade EEG devices out there, and if you are interested in finding out about the suppliers and how the devices are being used in research and all sorts of applications, please check out our recently published review paper in IEEE Sensors (Sawangjai et al., 2019).
Image from Sawangjai et al. (2019)
With the tool at our disposal we were curious to see if this mini version of a ‘brain sensor’ would be able to pick up brain signals that could be interpreted in a meaningful manner. To do this we recruited people to participate in our experiment, which was divided into two parts (Lakhan et al., 2019). The first group was asked to label the video clips along the scales of valence (positive vs negative), arousal (stimulating vs calming), happy, fearful, and exciting. The labels were collectively analysed and formed the basis for the machine-learning-based selection of videos to be used in the second part. The second group was fitted with the EEG cap and a wristband to measure physiological signs such as heart rate, skin conductance. We then had them watch a series of pre-selected clips and give each of them a score on valence and arousal. We found that we could predict with considerable to high accuracy the level (high vs low) of valence and arousal from the brain signals. What more, we also contrasted the results from this wearable EEG with the more sophisticated predecessors and found that for this ‘emotion recognition’ task, the signals acquired by the products from these two different tiers yielded comparable accuracies in terms of prediction.
Our findings are only just the tip of the iceberg in terms of where humanity might be heading when it comes to brain-machine interface. There is so much more to explore and improve! Scientific investigation may be gruelling and frustrating at times, but hard work can really pay off. This does not have to be restricted to science though. Find your passion and forge ahead. Grit and perseverance can take you a long way!!
LAKHAN, P., BANLUESOMBATKUL, N., CHANGNIAM, V., DHITHIJAIYRATN, R., LEELAARPORN, P., BOONCHIENG, E., HOMPOONSUP, S. & WILAIPRASITPORN, T. 2019. Consumer Grade Brain Sensing for Emotion Recognition. IEEE Sensors Journal, vol. PP, 7.
SAWANGJAI, P., HOMPOONSUP, S., LEELAARPORN, P., KONGWUDHIKUNAKORN, S. & WILAIPRASITPORN, T. 2019. Consumer grade EEG Measuring Sensors as Research Tools: A Review. IEEE Sensors Journal, 1-1.