Next Article in Journal
Glassy PEEK-WC vs. Rubbery Pebax®1657 Polymers: Effect on the Gas Transport in CuNi-MOF Based Mixed Matrix Membranes
Next Article in Special Issue
Phase Space Reconstruction from a Biological Time Series: A Photoplethysmographic Signal Case Study
Previous Article in Journal
Quantifying the Effect of Catalysts on the Lifetime of Transformer Oil
Previous Article in Special Issue
A Noniterative Simultaneous Rigid Registration Method for Serial Sections of Biological Tissues
Open AccessArticle

Net-Net AutoML Selection of Artificial Neural Network Topology for Brain Connectome Prediction

RNASA-IMEDIR Group, Computer Science Faculty, University of A Coruña, Elviña, 150171 A Coruña, Spain
Center for Computational Science (CCS), University of Miami, Miami, FL 33136, USA
Computer Engineering, West Coast University, Miami Campus, Doral, FL 33178, USA
Centre for Information and Communications Technology Research (CITIC), Campus de Elviña s/n, 15071 A Coruña, Spain
Biomedical Research Institute of A Coruña (INIBIC), University Hospital Complex of A Coruña (CHUAC), 15006 A Coruña, Spain
Department of Organic Chemistry II, University of the Basque Country UPV/EHU, 48940 Leioa, Spain
IKERBASQUE, Basque Foundation for Science, 48011 Bilbao, Spain
Author to whom correspondence should be addressed.
Appl. Sci. 2020, 10(4), 1308;
Received: 29 October 2019 / Revised: 7 February 2020 / Accepted: 10 February 2020 / Published: 14 February 2020
(This article belongs to the Special Issue Signal Processing and Machine Learning for Biomedical Data)
Brain Connectome Networks (BCNs) are defined by brain cortex regions (nodes) interacting with others by electrophysiological co-activation (edges). The experimental prediction of new interactions in BCNs represents a difficult task due to the large number of edges and the complex connectivity patterns. Fortunately, we can use another special type of networks to achieve this goal—Artificial Neural Networks (ANNs). Thus, ANNs could use node descriptors such as Shannon Entropies (Sh) to predict node connectivity for large datasets including complex systems such as BCN. However, the training of a high number of ANNs for BCNs is a time-consuming task. In this work, we propose the use of a method to automatically determine which ANN topology is more efficient for the BCN prediction. Since a network (ANN) is used to predict the connectivity in another network (BCN), this method was entitled Net-Net AutoML. The algorithm uses Sh descriptors for pairs of nodes in BCNs and for ANN predictors of BCNs. Therefore, it is able to predict the efficiency of new ANN topologies to predict BCNs. The current study used a set of 500,470 examples from 10 different ANNs to predict node connectivity in BCNs and 20 features. After testing five Machine Learning classifiers, the best classification model to predict the ability of an ANN to evaluate node interactions in BCNs was provided by Random Forest (mean test AUROC of 0.9991 ± 0.0001, 10-fold cross-validation). Net-Net AutoML algorithms based on entropy descriptors may become a useful tool in the design of automatic expert systems to select ANN topologies for complex biological systems. The scripts and dataset for this project are available in an open GitHub repository. View Full-Text
Keywords: artificial neural networks; brain connectome networks; machine learning; Net-Net AutoML artificial neural networks; brain connectome networks; machine learning; Net-Net AutoML
Show Figures

Figure 1

MDPI and ACS Style

Barreiro, E.; Munteanu, C.R.; Gestal, M.; Rabuñal, J.R.; Pazos, A.; González-Díaz, H.; Dorado, J. Net-Net AutoML Selection of Artificial Neural Network Topology for Brain Connectome Prediction. Appl. Sci. 2020, 10, 1308.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

Back to TopTop