CRIS

Permanent URI for this communityhttps://scripta.up.edu.mx/handle/20.500.12552/1

Browse

Search Results

Now showing 1 - 10 of 15

Some of the metrics are blocked by your
consent settings
Non-Contact Oxygen Saturation Estimation Using Deep Learning Ensemble Models and Bayesian Optimization
(MDPI AG, 2025)
Escobedo Gordillo, Andrés Emiliano
;
;
Monitoring Peripheral Oxygen Saturation (SpO2) is an important vital sign both in Intensive Care Units (ICUs), during surgery and convalescence, and as part of remote medical consultations after of the COVID-19 pandemic. This has made the development of new SpO2-measurement tools an area of active research and opportunity. In this paper, we present a new Deep Learning (DL) combined strategy to estimate SpO2 without contact, using pre-magnified facial videos to reveal subtle color changes related to blood flow and with no calibration per subject required. We applied the Eulerian Video Magnification technique using the Hermite Transform (EVM-HT) as a feature detector to feed a Three-Dimensional Convolutional Neural Network (3D-CNN). Additionally, parameters and hyperparameter Bayesian optimization and an ensemble technique over the dataset magnified were applied. We tested the method on 18 healthy subjects, where facial videos of the subjects, including the automatic detection of the reference from a contact pulse oximeter device, were acquired. As performance metrics for the SpO2-estimation proposal, we calculated the Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and other parameters from the Bland–Altman (BA) analysis with respect to the reference. Therefore, a significant improvement was observed by adding the ensemble technique with respect to the only optimization, obtaining 14.32% in RMSE (reduction from 0.6204 to 0.5315) and 13.23% in MAE (reduction from 0.4323 to 0.3751). On the other hand, regarding Bland–Altman analysis, the upper and lower limits of agreement for the Mean of Differences (MOD) between the estimation and the ground truth were 1.04 and −1.05, with an MOD (bias) of −0.00175; therefore, MOD ±1.96𝜎 = −0.00175 ± 1.04. Thus, by leveraging Bayesian optimization for hyperparameter tuning and integrating a Bagging Ensemble, we achieved a significant reduction in the training error (bias), achieving a better generalization over the test set, and reducing the variance in comparison with the baseline model for SpO2 estimation. ©The authors ©Technologies ©MDPI.
Some of the metrics are blocked by your
consent settings
Identifying and Mitigating Label Noise in Deep Learning for Image Classification
(MDPI AG, 2025)
González-Santoyo, César
;
Renza, Diego
;
Labeling errors in datasets are a persistent challenge in machine learning because they introduce noise and bias and reduce the model’s generalization. This study proposes a novel methodology for detecting and correcting mislabeled samples in image datasets by using the Cumulative Spectral Gradient (CSG) metric to assess the intrinsic complexity of the data. This methodology is applied to the noisy CIFAR-10/100 and CIFAR-10n/100n datasets, where mislabeled samples in CIFAR-10n/100n are identified and relabeled using CIFAR-10/100 as a reference. The DenseNet and Xception models pre-trained on ImageNet are fine-tuned to evaluate the impact of label correction on the model performance. Evaluation metrics based on the confusion matrix are used to compare the model performance on the original and noisy datasets and on the label-corrected datasets. The results show that correcting the mislabeled samples significantly improves the accuracy and robustness of the model, highlighting the importance of dataset quality in machine learning. ©The authors ©MDPI.
Some of the metrics are blocked by your
consent settings
Adversarial Validation in Image Classification Datasets by Means of Cumulative Spectral Gradient
(MDPI, 2024)
Renza, Diego
;
;
Chavarro, Adrian
The main objective of a machine learning (ML) system is to obtain a trained model from input data in such a way that it allows predictions to be made on new i.i.d. (Independently and Identically Distributed) data with the lowest possible error. However, how can we assess whether the training and test data have a similar distribution? To answer this question, this paper presents a proposal to determine the degree of distribution shift of two datasets. To this end, a metric for evaluating complexity in datasets is used, which can be applied in multi-class problems, comparing each pair of classes of the two sets. The proposed methodology has been applied to three well-known datasets: MNIST, CIFAR-10 and CIFAR-100, together with corrupted versions of these. Through this methodology, it is possible to evaluate which types of modification have a greater impact on the generalization of the models without the need to train multiple models multiple times, also allowing us to determine which classes are more affected by corruption. ©The authors ©MDPI ©Algorithms.
6
Some of the metrics are blocked by your
consent settings
Development of a Digital Twin Driven by a Deep Learning Model for Fault Diagnosis of Electro-Hydrostatic Actuators
(MDPI, 2024)
;
Marmolejo Saucedo, José Antonio
;
Köse, Utku
The first quarter of the 21st century has witnessed many technological innovations in various sectors. Likewise, the COVID-19 pandemic triggered the acceleration of digital transformation in organizations driven by artificial intelligence and communication technologies in Industry 4.0 and Industry 5.0. Aiming at the construction of digital twins, virtual representations of a physical system allow real-time bidirectional communication. This will allow the monitoring of operations, identification of possible failures, and decision making based on technical evidence. In this study, a fault diagnosis solution is proposed, based on the construction of a digital twin, for a cloud-based Industrial Internet of Things (IIoT) system contemplating the control of electro-hydrostatic actuators (EHAs). The system was supported by a deep learning model using Long Short-Term Memory (LSTM) networks for an effective diagnostic approach. The implemented study considers data preparation and integration and system development and application to evaluate the performance against the fault diagnosis problem. According to the results obtained, positive results are shown in the construction of the digital twin using a deep learning model for the fault diagnosis problem of an active EHA-IIoT configuration. ©The authors ©MDPI.
12
Some of the metrics are blocked by your
consent settings
Automatic classification of coronary stenosis using convolutional neural networks and simulated annealing
(CRC Press, 2022)
Gutiérrez, Sebastián
;
Cruz-Aceves, Ivan
;
Fernandez-Jaramillo, Arturo Alfonso
;
;
Automatic detection of coronary stenosis plays an essential role in systems that perform computer-aided diagnosis in cardiology. Coronary stenosis is a narrowing of the coronary arteries caused by plaque that reduces the blood flow to the heart. Automatic classification of coronary stenosis images has been re-cently addressed using deep and machine learning techniques. Generally, the machine learning methods form a bank of empirical and automatic features from the angiographic images. In the present work, a novel method for the automatic classification of coronary stenosis X-ray images is presented. The method is based on convolutional neural networks, where the neural architecture search is performed by using the path-based metaheuristics of simulated annealing. To perform the neural architecture search, the maximization of the F1-score metric is used as the fitness function. The automatically generated convolutional neural network was compared with three deep learning methods in terms of the accuracy and F1-score metrics using a testing set of images obtaining 0.88 and 0.89, respectively. In addition, the proposed method was evaluated with different sets of coronary stenosis images obtained via data augmentation. The results involving a number of different instances have shown that the proposed architecture is robust preserving the efficiency with different datasets © 2023 Şaban öztürk. All rights reserved.
53 1
Some of the metrics are blocked by your
consent settings
An Explainable Tool to Support Age-related Macular Degeneration Diagnosis
(2022)
;
Miralles-Pechuán, Luis
;
;
Artificial intelligence and deep learning, in particu-lar, have gained large attention in the ophthalmology community due to the possibility of processing large amounts of data and dig-itized ocular images. Intelligent systems are developed to support the diagnosis and treatment of a number of ophthalmic diseases such as age-related macular degeneration (AMD), glaucoma and retinopathy of prematurity. Hence, explainability is necessary to gain trust and therefore the adoption of these critical decision support systems. Visual explanations have been proposed for AMD diagnosis only when optical coherence tomography (OCT) images are used, but interpretability using other inputs (i.e. data point-based features) for AMD diagnosis is rather limited. In this paper, we propose a practical tool to support AMD diagnosis based on Artificial Hydrocarbon Networks (AHN) with different kinds of input data such as demographic characteristics, features known as risk factors for AMD, and genetic variants obtained from DNA genotyping. The proposed explainer, namely eXplainable Artificial Hydrocarbon Networks (XAHN) is able to get global and local interpretations of the AHN model. An explainability assessment of the XAHN explainer was applied to clinicians for getting feedback from the tool. We consider the XAHN explainer tool will be beneficial to support expert clinicians in AMD diagnosis, especially where input data are not visual. © 2022 IEEE.
Scopus© Citations 4 19 1
Some of the metrics are blocked by your
consent settings
Analysis of Contextual Sensors for Fall Detection
(2019)
;
Falls are a major problem among older people and often cause serious injuries. It is important to have efficient fall detection solutions to reduce the time in which a person who suffered a fall receives assistance. Given the recent availability of cameras, wearable and ambient sensors, more research in fall detection is focused on combining different data modalities. In order to determine the positive effects of each modality and combination to improve the effectiveness of fall detection, a detailed assessment has to be done. In this paper, we analyzed different combinations of wearable devices, namely IMUs and EEG helmet, with grid of active infrared sensors for fall detection, with the aim to determine the positive effects of contextual information on the accuracy in fall detection. We used short-term memory (LSTM) networks to enable fall detection from sensors raw data. For some activities certain combinations can be helpful to discriminate other activities of daily living (ADL) from falls. © 2019 IEEE.
27 1
Some of the metrics are blocked by your
consent settings
Deep Learning for Multimodal Fall Detection
(2019)
;
Pérez-Daniel, Karina Ruby
;
Fall detection systems can help providing quick assistance of the person diminishing the severity of the consequences of a fall. Real-time fall detection is important to decrease fear and time that a person remains laying on the floor after falling. In recent years, multimodal fall detection approaches are developed in order to gain more precision and robustness. In this work, we propose a multimodal fall detection system based on wearable sensors, ambient sensors and vision devices. We used long short-term memory networks (LSTM) and convolutional neural networks (CNN) for our analysis given that they are able to extract features from raw data, and are well suited for real-time detection. To test our proposal, we built a public multimodal dataset for fall detection. After experimentation, our proposed method reached 96.4% in accuracy, and it represented an improvement in precision, recall and F-{1}-score over using single LSTM or CNN networks for fall detection. © 2019 IEEE.
Scopus© Citations 15 15 2
Some of the metrics are blocked by your
consent settings
Stair Climbing Robot Based on Convolutional Neural Networks for Visual Impaired
(2019)
Campos, Guillermo
;
Poza, David
;
Reyes, Moises
;
Zacate, Alma
;
When a person loses the sense of sight, in general, it is suggested to use a white cane to perform daily activities. However, using a white cane limits the movement of a person. In addition, guide dogs can be served in this impairment. However, the acquisition and maintenance of a guide dog is extremely high for people in development countries. In this regard, this paper presents a proof-of-concept of a low-cost robotic system able to guide a visual impaired, as a guide dog. The robot is specially designed for climbing stairs at indoors, and it uses convolutional neural networks (CNN) for both object detection and hand gesture recognition for special instructions from the user. Experimental results showed that our prototype robot can climb stairs with 86.7% of efficiency in concrete stair surfaces. Also, the visual representation by CNN performed more than 98% accuracy. © 2019 IEEE.
Scopus© Citations 4 16 1
Some of the metrics are blocked by your
consent settings
A 3D orthogonal vision-based band-gap prediction using deep learning: A proof of concept
(2022)
;
;
ORTIZ-MEDINA, JOSUE
In this work, a vision-based system for the electronic band-gap prediction of organic molecules is proposed using a multichannel 2D convolutional neural network (CNN) and a 3D CNN, applied to the recognition and classification of 2D projected images from 3D molecular structure models. The generated images are input into the CNN for an estimation of the energy gap, associated with the molecular structure. The public data set used in this research was the Organic Materials Database (OMDB-GAP1). A data transformation from the descriptive information contained in the data set to three 2D orthogonal images of molecules was done. The training set is composed of 30,000 images, whereas the testing set was composed of 7500 images, from 12,500 different molecules. The multichannel 2D CNN architecture was optimized via Bayesian optimization. Experimental results showed that the proposed CNN model obtained an acceptable mean absolute error of 0.6780 eV and root mean-squared error of 0.7673 eV, in contrast to two machine learning methods reported in the literature used for band-gap prediction based on conventional density function theory (DFT) methods. These results demonstrate the feasibility of CNN models to materials science routines using orthogonal images projections of molecules. © 2021 Elsevier B.V.
Scopus© Citations 9 22 2

CRIS

Browse

Filters

Settings

Sort By

Results per page

Search Results