Related Experiment Video
Updated: Dec 31, 2025
03:31
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
Published on: December 15, 2023
952
Multilevel and Multiscale Feature Aggregation in Deep Networks for Facial Constitution Classification.
1School of Computer Science and Engineering, South China University of Technology, Guangzhou 510006, China.
Computational and Mathematical Methods in Medicine
|January 15, 2020
Summary
This study introduces a novel multilevel and multiscale feature aggregation method for Traditional Chinese Medicine (TCM) constitution classification. The approach enhances classification accuracy using deep learning techniques, achieving 69.61% on a test dataset.
Area of Science:
- Computer Science
- Biomedical Informatics
- Traditional Chinese Medicine
Background:
- Constitution classification is fundamental to Traditional Chinese Medicine (TCM) research.
- Improving the accuracy of TCM constitution classification is crucial for its clinical application and research advancement.
Purpose of the Study:
- To propose and evaluate a novel multilevel and multiscale feature aggregation method for enhancing TCM constitution classification accuracy.
- To leverage deep learning architectures, specifically VGG16 and NASNetMobile, for sophisticated feature extraction and fusion.
Main Methods:
- A convolutional neural network approach integrating VGG16 and NASNetMobile was developed.
- Supervised feature learning and Principal Component Analysis (PCA) were employed for feature refinement and dimensionality reduction.
- Multilevel features from VGG16 and multiscale features from NASNetMobile were extracted, dimensionally reduced, and fused.
- Aggregated features were processed through fully connected layers for final constitution classification.
Main Results:
- The proposed multilevel and multiscale feature aggregation method demonstrated significant effectiveness in TCM constitution classification.
- The experimental results showed a classification accuracy of 69.61% on the test dataset.
- The integration of features from different network layers and architectures improved classification performance.
Conclusions:
- The developed deep learning method, utilizing multilevel and multiscale feature aggregation, offers a promising approach for accurate TCM constitution classification.
- This technique effectively captures and combines diverse image features, leading to improved classification outcomes.
- Further research can explore broader applications of this feature aggregation strategy in TCM diagnostics.
Related Concept Videos
01:29Aggregates Classification
915
Aggregate classification is generally based on its size, petrographic characteristics, weight, and source. Size classification ranges from coarse to fine aggregates, defined by the size of the particles. Coarse aggregates are particles that do not pass through ASTM sieve No. 4, and aggregates that pass through the sieve are fine aggregates.
Petrographic classification groups aggregates based on common mineralogical characteristics. Some of the common mineral groups found in aggregates are...
Petrographic classification groups aggregates based on common mineralogical characteristics. Some of the common mineral groups found in aggregates are...
915
01:14Muscles for Facial Expressions
4.5K
The craniofacial muscles are a collection of approximately 20 thin skeletal muscles situated beneath the skin of the face and scalp. These muscles, primarily responsible for the vast array of human facial expressions, originate from the bones or fibrous structures of the skull and extend outwards to connect with the skin. While most skeletal muscles in the body are enveloped in thick fascia, facial muscles generally have a more delicate fascial covering, with the buccinator muscle being a...
4.5K