COVID-19 disease course staging prediction system based on attention mechanism
The invention discloses a COVID-19 disease course staging prediction system based on an attention mechanism. The COVID-19 disease course staging prediction system comprises a data preprocessing module, a system network module based on the attention mechanism and a classifier module. The system network module comprises a convolution operation unit, a bottleneck unit, an attention mechanism learning unit, a super-resolution sub-pixel up-sampling unit, a super-resolution sub-pixel down-sampling unit, a summation unit and a classifier module; a bilinear convolutional neural Network (B-CNN) is a high-precision classification algorithm, end-to-end classification is realized, the situation of insufficient new crown pneumonia data volume at present can be well dealt with, the B-CNN model utilizes image second-order statistical information, modeling is carried out on a combined interaction relationship between local features by using a translation invariant characteristic, and weak supervision classification is realized under the condition that only image category labels exist. Meanwhile, gradient calculation is simplified by the B-CNN, so that an end-to-end model is easier to train..
| Medienart: |
|
|---|
Patent| Erscheinungsjahr: |
2021 |
|---|---|
| Erschienen: |
2021 |
| Enthalten in: |
Europäisches Patentamt - (2021) vom: 31. Dez. Zur Gesamtaufnahme - year:2021 |
|---|
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
ZHANG YANAN [VerfasserIn] |
|---|
| Links: |
Volltext [kostenfrei] |
|---|
| Anmerkungen: |
Source: www.epo.org (no modifications made), First posted: 2021-12-31, Last update posted on www.tib.eu: 2022-08-17, Last updated: 2023-02-09 |
|---|
| Patentnummer: |
CN113871011 |
|---|
| Förderinstitution / Projekttitel: |
|
|---|
| PPN (Katalog-ID): |
EPA013094483 |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | EPA013094483 | ||
| 003 | DE-627 | ||
| 005 | 20230504095112.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 230215s2021 xx |||||o 00| ||eng c | ||
| 035 | |a (DE-627)EPA013094483 | ||
| 035 | |a (EPA)CN113871011 | ||
| 035 | |a (EPA)79000057 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 0 | |a ZHANG YANAN |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a COVID-19 disease course staging prediction system based on attention mechanism |
| 264 | 1 | |c 2021 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a Computermedien |b c |2 rdamedia | ||
| 338 | |a Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Source: www.epo.org (no modifications made), First posted: 2021-12-31, Last update posted on www.tib.eu: 2022-08-17, Last updated: 2023-02-09 | ||
| 520 | |a The invention discloses a COVID-19 disease course staging prediction system based on an attention mechanism. The COVID-19 disease course staging prediction system comprises a data preprocessing module, a system network module based on the attention mechanism and a classifier module. The system network module comprises a convolution operation unit, a bottleneck unit, an attention mechanism learning unit, a super-resolution sub-pixel up-sampling unit, a super-resolution sub-pixel down-sampling unit, a summation unit and a classifier module; a bilinear convolutional neural Network (B-CNN) is a high-precision classification algorithm, end-to-end classification is realized, the situation of insufficient new crown pneumonia data volume at present can be well dealt with, the B-CNN model utilizes image second-order statistical information, modeling is carried out on a combined interaction relationship between local features by using a translation invariant characteristic, and weak supervision classification is realized under the condition that only image category labels exist. Meanwhile, gradient calculation is simplified by the B-CNN, so that an end-to-end model is easier to train. | ||
| 650 | 4 | |a inf | |
| 650 | 4 | |a G06T: Image data processing or generation, in general | |
| 650 | 4 | |a G06N: Computer systems based on specific computational models | |
| 650 | 4 | |a G16H: Healthcare informatics, i.e. information and communication technology [ict] specially adapted for the handling or processing of medical or healthcare data | |
| 650 | 4 | |a 615 | |
| 700 | 0 | |a CAI MEILING |4 aut | |
| 700 | 0 | |a WANG HEXI |4 aut | |
| 700 | 0 | |a ZHAO LIN |4 aut | |
| 700 | 0 | |a QIANG YAN |4 aut | |
| 700 | 0 | |a ZHAO JUANJUAN |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Europäisches Patentamt |g (2021) vom: 31. Dez. |
| 773 | 1 | 8 | |g year:2021 |g day:31 |g month:12 |
| 856 | 4 | 0 | |u https://worldwide.espacenet.com/patent/search/family/79000057/publication/CN113871011A1?q=CN113871011 |z kostenfrei |3 Volltext |
| 912 | |a GBV_EPA | ||
| 912 | |a SSG-OLC-PHA | ||
| 936 | u | w | |j 2021 |b 31 |c 12 |
| 951 | |a AR | ||
| 952 | |j 2021 |b 31 |c 12 | ||