Related Experiment Video
Updated: Feb 15, 2026
10:04
A Neural Network-Based Identification of Developmentally Competent or Incompetent Mouse Fully-Grown Oocytes
Published on: March 3, 2018
7.2K
Ant genera identification using an ensemble of convolutional neural networks.
Alan Caio R Marques1, Marcos M Raimundo1, Ellen Marianne B Cavalheiro1
1School of Electrical and Computer Engineering, University of Campinas (UNICAMP), Av. Albert Einstein 400, 13083-852 Campinas, São Paulo, Brazil.
Plos One
|February 1, 2018
Summary
This study uses an ensemble of convolutional neural networks (CNNs) to automatically identify ant genera from images, achieving over 80% accuracy. This machine learning approach addresses challenges in ant taxonomy and identification by leveraging large datasets.
Area of Science:
- Entomology
- Computer Science
- Machine Learning
Background:
- Taxonomic identification of organisms, especially ants, is challenging due to the vast number of species and a shortage of expert taxonomists.
- Machine learning, specifically convolutional neural networks (CNNs), offers a promising solution for automating high-performance classification tasks from image data.
Purpose of the Study:
- To develop and evaluate an ensemble of CNNs for the automated identification of ant genera using head, profile, and dorsal images.
- To enhance classifier performance through the application of transfer learning.
Main Methods:
- Utilized image datasets from AntWeb, a comprehensive online database for ant biology.
- Developed an ensemble of CNN classifiers, incorporating transfer learning to improve individual model accuracy.
- Evaluated classifier performance on top-1 and top-3 classification tasks.
Main Results:
- The ensemble of CNNs achieved an accuracy rate exceeding 80% for top-1 classification.
- An accuracy rate surpassing 90% was obtained for top-3 classification.
- The diversity in individual classifier performance contributed to a reduction in overall classification error when combined.
Conclusions:
- An ensemble of CNNs, enhanced by transfer learning, effectively automates ant genus identification from images.
- This machine learning approach shows significant potential in overcoming taxonomic identification bottlenecks in entomology.
- The developed system demonstrates high accuracy, aiding in the study and conservation of ant biodiversity.
Related Concept Videos
01:17Convolution Properties II
600
The important convolution properties include width, area, differentiation, and integration properties.
The width property indicates that if the durations of input signals are T1 and T2, then the width of the output response equals the sum of both durations, irrespective of the shapes of the two functions. For instance, convolving two rectangular pulses with durations of 2 seconds and 1 second results in a function with a width of 3 seconds.
The area property asserts that the area under the...
The width property indicates that if the durations of input signals are T1 and T2, then the width of the output response equals the sum of both durations, irrespective of the shapes of the two functions. For instance, convolving two rectangular pulses with durations of 2 seconds and 1 second results in a function with a width of 3 seconds.
The area property asserts that the area under the...
600
01:20Convolution Properties I
625
Convolution computations can be simplified by utilizing their inherent properties.
The commutative property reveals that the input and the impulse response of an LTI (Linear Time-Invariant) system can be interchanged without affecting the output:
The commutative property reveals that the input and the impulse response of an LTI (Linear Time-Invariant) system can be interchanged without affecting the output:
625
02:26Protein Networks
4.6K
An organism can have thousands of different proteins, and these proteins must cooperate to ensure the health of an organism. Proteins bind to other proteins and form complexes to carry out their functions. Many proteins interact with multiple other proteins creating a complex network of protein interactions.
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...
4.6K
02:26Protein Networks
2.9K
2.9K
02:18Network Covalent Solids
16.2K
Network covalent solids contain a three-dimensional network of covalently bonded atoms as found in the crystal structures of nonmetals like diamond, graphite, silicon, and some covalent compounds, such as silicon dioxide (sand) and silicon carbide (carborundum, the abrasive on sandpaper). Many minerals have networks of covalent bonds.
To break or to melt a covalent network solid, covalent bonds must be broken. Because covalent bonds are relatively strong, covalent network solids are typically...
To break or to melt a covalent network solid, covalent bonds must be broken. Because covalent bonds are relatively strong, covalent network solids are typically...
16.2K
01:24Convolution: Math, Graphics, and Discrete Signals
983
In any LTI (Linear Time-Invariant) system, the convolution of two signals is denoted using a convolution operator, assuming all initial conditions are zero. The convolution integral can be divided into two parts: the zero-input or natural response and the zero-state or forced response, with t0 indicating the initial time.
To simplify the convolution integral, it is assumed that both the input signal and impulse response are zero for negative time values. The graphical convolution process...
To simplify the convolution integral, it is assumed that both the input signal and impulse response are zero for negative time values. The graphical convolution process...
983