The rich text element allows you to create and format headings, paragraphs, blockquotes, images, and video all in one place instead of having to add and format them individually. Just double-click and easily create content.
A rich text element can be used with static or dynamic content. For static content, just drop it into any page and begin editing. For dynamic content, add a rich text field to any collection and then connect a rich text element to that field in the settings panel. Voila!
Headings, paragraphs, blockquotes, figures, images, and figure captions can all be styled after a class is added to the rich text element using the "When inside of" nested selector system.
At IxorThink, we recently finished the second phase of development of the epileptic seizure detection system on EEG brainwaves. This detection system was developed in collaboration with Professor Dr. Robrecht Raedt, 4BrainLab, Ghent University. Prof. Dr. Raedt was searching for a tool to automate the annotations of epileptic seizures in EEG brainwaves of rats and mice. These annotations are necessary to analyse the effectiveness of new medical treatments. According to Prof. Dr. Raedt, the amount of time that can be saved is enormous: laboratory animals are observed for months and annotating the seizures on these recordings can take as much of a day of work for each two days of recordings. Using the detection system of IxorThink, as much as 20 min of recording can be annotated per second.
In the second phase additional features have been implemented into the software package: it is now possible to train models combining data of different subjects or to train a model specifically fit to one animal. An easy-to-use dashboard of all experiments, together with their specificity and sensitivity, has been created. And some other minor changes increased the performance compared to the first version.
With these new updates, it will be easier and clearer to test the detection software on various subjects. The researchers at Ghent University, can now easily add more data over time and build custom detection models themselves.
According to Prof. Dr. Raedt, state-of-the art detection results could be achieved when additional data types would be combined with the EEG signals. E.g. data can be extracted from accelerometer wearables or video footage of the subject animals. The model could combine movement data from these two sources together with the EEG waves to improve the accuracy of the detected seizures.
As pointed out by Prof. Dr.r Raedt, machine learning techniques will play an even bigger role in the future of hospitals and medical treatments. The same way as the machine learning software is customised (trained) for every specific rat or mice subject, this can be done for human subjects. This way, it will be possible to use the same software techniques on human electrodes (implants) to detect or warn for epileptic seizures based on the human EEG signals. A full analysis of these signals will also improve the quality of medical treatment research projects.
If you are interested in the inner workings of the machine learning model, please take a look at this Medium blog.