scholarly journals Extrapolation of Ventricular Activation Times From Sparse Electroanatomical Data Using Graph Convolutional Neural Networks

2021 ◽  
Vol 12 ◽  
Author(s):  
Felix Meister ◽  
Tiziano Passerini ◽  
Chloé Audigier ◽  
Èric Lluch ◽  
Viorel Mihalef ◽  
...  
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Mean Absolute Error ◽  
Sampling Strategy ◽  
Absolute Error ◽  
Statistical Shape Model ◽  
Border Zone ◽  
Statistical Shape ◽  
Sparse Measurements ◽  
Activation Times

Electroanatomic mapping is the gold standard for the assessment of ventricular tachycardia. Acquiring high resolution electroanatomic maps is technically challenging and may require interpolation methods to obtain dense measurements. These methods, however, cannot recover activation times in the entire biventricular domain. This work investigates the use of graph convolutional neural networks to estimate biventricular activation times from sparse measurements. Our method is trained on more than 15,000 synthetic examples of realistic ventricular depolarization patterns generated by a computational electrophysiology model. Using geometries sampled from a statistical shape model of biventricular anatomy, diverse wave dynamics are induced by randomly sampling scar and border zone distributions, locations of initial activation, and tissue conduction velocities. Once trained, the method accurately reconstructs biventricular activation times in left-out synthetic simulations with a mean absolute error of 3.9 ms ± 4.2 ms at a sampling density of one measurement sample per cm2. The total activation time is matched with a mean error of 1.4 ms ± 1.4 ms. A significant decrease in errors is observed in all heart zones with an increased number of samples. Without re-training, the network is further evaluated on two datasets: (1) an in-house dataset comprising four ischemic porcine hearts with dense endocardial activation maps; (2) the CRT-EPIGGY19 challenge data comprising endo- and epicardial measurements of 5 infarcted and 6 non-infarcted swines. In both setups the neural network recovers biventricular activation times with a mean absolute error of less than 10 ms even when providing only a subset of endocardial measurements as input. Furthermore, we present a simple approach to suggest new measurement locations in real-time based on the estimated uncertainty of the graph network predictions. The model-guided selection of measurement locations allows to reduce by 40% the number of measurements required in a random sampling strategy, while achieving the same prediction error. In all the tested scenarios, the proposed approach estimates biventricular activation times with comparable or better performance than a personalized computational model and significant runtime advantages.

scholarly journals Regression in Convolutional Neural Networks applied to Plant Leaf Counting

2019 ◽  
Author(s):  
Neemias Bucéli Da Silva ◽  
Wesley Nunes Gonçalves
Keyword(s):  
Neural Networks ◽  
Computer Vision ◽  
Convolutional Neural Networks ◽  
Mean Absolute Error ◽  
Absolute Error ◽  
Plant Leaves ◽  
Training Process ◽  
Plant Leaf ◽  
Image Dataset ◽  
Regression Problems

Recent studies have shown that computer vision techniques developed to boost the count of plant leaves brings significant improvements. In this paper, a proposal was presented for plant leaf counting using Convolutional Neural Networks (CNNs). To accomplish the training process, CNNs architectures were adapted to solve regression problems. To evaluate the proposed method, an image dataset with 810 images of three species (Arabidopsis, Tobacco and one mutation) was used. The results showed that Xception architecture obtained the best results with R2 of 0.96 and MAE (mean absolute error) of 0.46.

scholarly journals Spatial Detection of Vehicles in Images using Convolutional Neural Networks and Stereo Matching

2016 ◽  
Vol 2 (1) ◽  
Author(s):  
Jeremy Pinto ◽  
Nolan Lunscher ◽  
Georges Younes ◽  
David Abou Chacra ◽  
Henry Leopold ◽  
...  
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Stereo Matching ◽  
Mean Absolute Error ◽  
Depth Estimation ◽  
Absolute Error ◽  
Stereo Images ◽  
Matching Method ◽  
Spatial Detection ◽  
State Of Art

Convolutional Neural Networks combined with a state of the artstereo-matching method are used to find and estimate the 3D positionof vehicles in pairs of stereo images. Pixel positions of vehiclesare first estimated separately in pairs of stereo images usinga Convolutional Neural Network for regression. These coordinatesare then combined with a state-of-art stereo-matching method todetermine the depth, and thus the 3D location, of the vehicles. Weshow in this paper that cars can be detected with a combined accuracyof approximately 90% with a tolerated radius error of 5%,and a Mean Absolute Error of 5.25m on depth estimation for carsup to 50m away.

scholarly journals On transformative adaptive activation functions in neural networks for gene expression inference

PLoS ONE ◽  
2021 ◽  
Vol 16 (1) ◽  
pp. e0243915
Author(s):  
Vladimír Kunc ◽  
Jiří Kléma
Keyword(s):  
Gene Expression ◽  
Neural Networks ◽  
Mean Absolute Error ◽  
Expression Profiles ◽  
Gene Expression Profiles ◽  
Cost Effective ◽  
Absolute Error ◽  
Activation Function ◽  
Training Procedure ◽  
Activation Functions

Gene expression profiling was made more cost-effective by the NIH LINCS program that profiles only ∼1, 000 selected landmark genes and uses them to reconstruct the whole profile. The D–GEX method employs neural networks to infer the entire profile. However, the original D–GEX can be significantly improved. We propose a novel transformative adaptive activation function that improves the gene expression inference even further and which generalizes several existing adaptive activation functions. Our improved neural network achieves an average mean absolute error of 0.1340, which is a significant improvement over our reimplementation of the original D–GEX, which achieves an average mean absolute error of 0.1637. The proposed transformative adaptive function enables a significantly more accurate reconstruction of the full gene expression profiles with only a small increase in the complexity of the model and its training procedure compared to other methods.

scholarly journals Predicting Daily Returns of Global Stocks Indices: Neural Networks vs Support Vector Machines

2019 ◽  
pp. 1-13 ◽  
Author(s):  
Jasleen Kaur ◽  
Khushdeep Dharni
Keyword(s):  
Data Mining ◽  
Neural Networks ◽  
Support Vector Machines ◽  
Mean Square Error ◽  
Mean Absolute Error ◽  
Absolute Error ◽  
Support Vector ◽  
Mean Square ◽  
Data Mining Techniques ◽  
Vector Machines

Uniqueness in economies and stock markets has given rise to an interesting domain of exploring data mining techniques across global indices. Previously, very few studies have attempted to compare the performance of data mining techniques in diverse markets. The current study adds to the understanding regarding the variations in performance of data mining techniques across the global stock indices. We compared the performance of Neural Networks and Support Vector Machines using accuracy measures Mean Absolute Error (MAE) and R­­­­oot Mean Square Error (RMSE) across seven major stock markets. For prediction purpose, technical analysis has been employed on selected indicators based on daily values of indices spanning a period of 12 years. We created 196 data sets spanning different time periods for model building such as 1 year, 2 years, 3 years, 4 years, 6 years and 12 years for selected seven stock indices. Based on prediction models built using Neural Networks and Support Vector Machines, the findings of the study indicate there is a significant difference, both for MAE and RMSE, across the selected global indices. Also, Mean Absolute Error and Root Mean Square Error of models built using NN were greater than Mean Absolute Error and Root Mean Square Error of models built using SVM.

scholarly journals An Automated Recognition of Work Activity in Industrial Manufacturing Using Convolutional Neural Networks

Electronics ◽  
2021 ◽  
Vol 10 (23) ◽  
pp. 2946
Author(s):  
Justyna Patalas-Maliszewska ◽  
Daniel Halikowski ◽  
Robertas Damaševičius
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Industry 4.0 ◽  
Reference Frames ◽  
Absolute Error ◽  
Automatic Generation ◽  
Support Vector ◽  
Work Activity ◽  
Work Related ◽  
Industrial Solutions

The automated assessment and analysis of employee activity in a manufacturing enterprise, operating in accordance with the concept of Industry 4.0, is essential for a quick and precise diagnosis of work quality, especially in the process of training a new employee. In the case of industrial solutions, many approaches involving the recognition and detection of work activity are based on Convolutional Neural Networks (CNNs). Despite the wide use of CNNs, it is difficult to find solutions supporting the automated checking of work activities performed by trained employees. We propose a novel framework for the automatic generation of workplace instructions and real-time recognition of worker activities. The proposed method integrates CNN, CNN Support Vector Machine (SVM), CNN Region-Based CNN (Yolov3 Tiny) for recognizing and checking the completed work tasks. First, video recordings of the work process are analyzed and reference video frames corresponding to work activity stages are determined. Next, work-related features and objects are determined using CNN with SVM (achieving 94% accuracy) and Yolov3 Tiny network based on the characteristics of the reference frames. Additionally, matching matrix between the reference frames and the test frames using mean absolute error (MAE) as a measure of errors between paired observations was built. Finally, the practical usefulness of the proposed approach by applying the method for supporting the automatic training of new employees and checking the correctness of their work done on solid fuel boiler equipment in a manufacturing company was demonstrated. The developed information system can be integrated with other Industry 4.0 technologies introduced within an enterprise.

scholarly journals On Transformative Adaptive Activation Functions in Neural Networks for Gene Expression Inference

2019 ◽  
Author(s):  
Vladimír Kunc ◽  
Jiří Kléma
Keyword(s):  
Neural Network ◽  
Gene Expression ◽  
Neural Networks ◽  
Expression Profiling ◽  
Mean Absolute Error ◽  
Absolute Error ◽  
Activation Function ◽  
Activation Functions ◽  
Hyperbolic Tangent ◽  
Sigmoid Activation Function

AbstractMotivationGene expression profiling was made cheaper by the NIH LINCS program that profiles only ~1, 000 selected landmark genes and uses them to reconstruct the whole profile. The D–GEX method employs neural networks to infer the whole profile. However, the original D–GEX can be further significantly improved.ResultsWe have analyzed the D–GEX method and determined that the inference can be improved using a logistic sigmoid activation function instead of the hyperbolic tangent. Moreover, we propose a novel transformative adaptive activation function that improves the gene expression inference even further and which generalizes several existing adaptive activation functions. Our improved neural network achieves average mean absolute error of 0.1340 which is a significant improvement over our reimplementation of the original D–GEX which achieves average mean absolute error 0.1637

scholarly journals How do loss functions impact the performance of graph neural networks?

2021 ◽  
Author(s):  
Gabriel Jonas Duarte ◽  
Tamara Arruda Pereira ◽  
Erik Jhones Nascimento ◽  
Diego Mesquita ◽  
Amauri Holanda Souza Junior
Keyword(s):  
Neural Networks ◽  
Mean Absolute Error ◽  
Absolute Error ◽  
Cross Entropy ◽  
Loss Functions ◽  
Hinge Loss ◽  
Significant Difference ◽  
Node Classification ◽  
Graph Neural Networks ◽  
The Impact

Graph neural networks (GNNs) have become the de facto approach for supervised learning on graph data.To train these networks, most practitioners employ the categorical cross-entropy (CE) loss. We can attribute this largely to the probabilistic interpretability of models trained using CE, since it corresponds to the negative log of the categorical/softmax likelihood.We can attribute this largely to the probabilistic interpretation of CE, since it corresponds to the negative log of the categorical/softmax likelihood.Nonetheless, recent works have shown that deep learning models can benefit from adopting other loss functions. For instance, neural networks trained with symmetric losses (e.g., mean absolute error) are robust to label noise. Nonetheless, loss functions are a modeling choice and other training criteria can be employed — e.g., hinge loss and mean absolute error (MAE). Perhaps surprisingly, the effect of using different losses on GNNs has not been explored. In this preliminary work, we gauge the impact of different loss functions to the performance of GNNs for node classification under i) noisy labels and ii) different sample sizes. In contrast to findings on Euclidean domains, our results for GNNs show that there is no significant difference between models trained with CE and other classical loss functions on both aforementioned scenarios.

Modeling Drying Properties of Pistachio Nuts, Squash and Cantaloupe Seeds under Fixed and Fluidized Bed Using Data-Driven Models and Artificial Neural Networks

2018 ◽  
Vol 14 (1) ◽  
Author(s):  
Mohammad Kaveh ◽  
Reza Amiri Chayjan ◽  
Behrooz Khezri
Keyword(s):  
Neural Networks ◽  
Energy Consumption ◽  
Mean Square Error ◽  
Mean Absolute Error ◽  
Absolute Error ◽  
Moisture Diffusivity ◽  
Effective Moisture Diffusivity ◽  
Mean Square ◽  
Feed Forward ◽  
Effective Moisture

AbstractThis paper presents the application of feed forward and cascade forward neural networks to model the non-linear behavior of pistachio nut, squash and cantaloupe seeds during drying process. The performance of the feed forward and cascade forward ANNs was compared with those of nonlinear and linear regression models using statistical indices, namely mean square error ($MSE$), mean absolute error ($MAE$), standard deviation of mean absolute error (SDMAE) and the correlation coefficient (${R^2}$). The best neural network feed forward back-propagation topology for the prediction of effective moisture diffusivity and energy consumption were 3-3-4-2 with the training algorithm of Levenberg-Marquardt (LM). This structure is capable to predict effective moisture diffusivity and specific energy consumption with${R^2}$= 0.9677 and 0.9716, respectively and mean-square error ($MSE$) of 0.00014. Also the highest${R^2}$values to predict the drying rate and moisture ratio were 0.9872 and 0.9944 respectively.

Sign in / Sign up

Export Citation Format

Share Document