Читать книгу Machine Learning for Healthcare Applications - Группа авторов - Страница 78

We have used an Emotiv EPOC+ biosensor device for capturing Neuro-Signals in the following manner. Figure 3.1 represents the channels on the brain from signals collected and the equipment used for collection. The signals are collected from 14 electrodes positioned at “AF3, AF4, F3, F4, F7, F8, FC5, FC6, O1, O2, P7, P8 T7 and T8” according to International 10–20 system viewed in the figure below. There are reference electrodes positioned above ears at CMS and DRL. By default, the device has a sampling frequency of 2,048 Hz which we have down-sampled to 128 Hz per channel. The data acquired is transmitted using Bluetooth connectivity to a system. Before every sample collection sensor felt pads are rubbed with saline, connected via the Bluetooth USB and charged after with a USB cable as shown in the figure below.

The device is placed on the participants and then showed a particular set of common usage items for the purpose of our experiment, during which all the EEG activity is recorded and later on they are asked to label their choice of purchase amongst each set of products i.e. 1 among 3 items of from each set of products. The process diagram can be seen below in Figure 3.2.

After the data collection, the signals are preprocessed, and some features are extracted using wavelet transformation method and then the classification models were run on the resultant as mentioned before. A part of the data was is preprocessed and decomposed to test the training model. The labeling was done majorly into Like/Dislike.

Figure 3.1 Brain map structure and Equipment used.

Figure 3.2 Workflow diagram.