-
Categories
-
Pharmaceutical Intermediates
-
Active Pharmaceutical Ingredients
-
Food Additives
- Industrial Coatings
- Agrochemicals
- Dyes and Pigments
- Surfactant
- Flavors and Fragrances
- Chemical Reagents
- Catalyst and Auxiliary
- Natural Products
- Inorganic Chemistry
-
Organic Chemistry
-
Biochemical Engineering
- Analytical Chemistry
- Cosmetic Ingredient
-
Pharmaceutical Intermediates
Promotion
ECHEMI Mall
Wholesale
Weekly Price
Exhibition
News
-
Trade Service
Inter-seizure epileptic EEG (hereinafter referred to as "epileptic EEG") contains epileptic spikes, which are commonly used in clinical colic to cause biomarkers in the epileptic region and assist in the diagnosis
In order to excavate the significant distinguishing information of epileptic spikes and non-spikes, Liu Yan and Bloomberg, associate researchers of Dai Yakang's research group of Suzhou Institute of Biomedical Engineering and Technology of the Chinese Academy of Sciences, proposed a multi-level feature characterization method
The study shows that, as shown in Figure 2(A), the spatio-temporal frequency multi-domain figurative feature characterization module based on the expert domain knowledge uses the spatio-temporal frequency multi-domain feature operator to calculate the spatiotemporal frequency multi-domain mimetic feature representation Fa to characterize the epilepsy EEG comprehensive mimetic characteristics; As shown in Figure 2(B), based on the data-based deep abstraction feature characterization module, based on the time convolution network to calculate the long-term dependent abstraction feature characterization Fb within the deep waveform cycle, to characterize the internal compliance relationship of the epilepsy EEG waveform cycle; As shown in Figure 2(C), the fusion feature characterization module uses the element similarity operator to calculate the spatio-temporal frequency multi-domain fusion depth long-term dependent feature characterization Fc, so as to effectively characterize the comprehensive eEG mimetic characteristics of epilepsy, and effectively characterize the long-term dependence discrimination characteristics during the interclass and intra-class epilepsy EEG similar waveform cycles
The researchers verified
The research was published in IEEE Transactions on Neural Systems and Rehabilitation Engineering
Figure 1.
Figure 2.
Table 1.
Source: Suzhou Institute of Biomedical Engineering and Technology, Chinese Academy of Sciences