CRIS
Permanent URI for this communityhttps://scripta.up.edu.mx/handle/20.500.12552/1
Browse
13 results
Search Results
Now showing 1 - 10 of 13
- Some of the metrics are blocked by yourconsent settings
Item type:Publication, Complexity-Driven Adversarial Validation for Corrupted Medical Imaging DataDistribution shifts commonly arise in real-world machine learning scenarios in which the fundamental assumption that training and test data are drawn from independent and identically distributed samples is violated. In the case of medical data, such distribution shifts often occur during data acquisition and pose a significant challenge to the robustness and reliability of artificial intelligence systems in clinical practice. Additionally, quantifying these shifts without training a model remains a key open problem. This paper proposes a comprehensive methodological framework for evaluating the impact of such shifts on medical image datasets under artificial transformations that simulate acquisition variations, leveraging the Cumulative Spectral Gradient (CSG) score as a measure of multiclass classification complexity induced by distributional changes. Building on prior work, the proposed approach is meaningfully extended to twelve 2D medical imaging benchmarks from the MedMNIST collection, covering both binary and multiclass tasks, as well as grayscale and RGB modalities. We evaluate the metric analyzing its robustness to clinically inspired distribution shifts that are systematically simulated through motion blur, additive noise, brightness and contrast variation, and sharpness variation, each applied at three severity levels. This results in a large-scale benchmark that enables a detailed analysis of how dataset characteristics, transformation types, and distortion severity influence distribution shifts. Thus, the findings show that while the metric remains generally stable under noise and focus distortions, it is highly sensitive to variations in brightness and contrast. On the other hand, the proposed methodology is compared against Cleanlab’s widely used Non-IID score on the RetinaMNIST dataset using a pre-trained ResNet-50 model, including both class-wise analysis and correlation assessment between metrics. Finally, interpretability is incorporated through class activation map analysis on BloodMNIST and its corrupted variants to support and contextualize the quantitative findings. ©The authors ©MDPI. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Non-Contact Oxygen Saturation Estimation Using Deep Learning Ensemble Models and Bayesian OptimizationMonitoring 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 yourconsent settings
Item type:Publication, Identifying and Mitigating Label Noise in Deep Learning for Image ClassificationLabeling 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 yourconsent settings
Item type:Publication, Adversarial Validation in Image Classification Datasets by Means of Cumulative Spectral GradientThe 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 yourconsent settings
Item type:Publication, Development of a Digital Twin Driven by a Deep Learning Model for Fault Diagnosis of Electro-Hydrostatic ActuatorsThe 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 yourconsent settings
Item type:Publication, Automatic classification of coronary stenosis using convolutional neural networks and simulated annealing(CRC Press, 2022); 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 yourconsent settings
Item type:Publication, An Explainable Tool to Support Age-related Macular Degeneration Diagnosis(2022); ; 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 yourconsent settings
Item type:Publication, A 3D orthogonal vision-based band-gap prediction using deep learning: A proof of concept(2022); ; ORTIZ-MEDINA, JOSUEIn 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 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Vision-Based Analysis on Leaves of Tomato Crops for Classifying Nutrient Deficiency using Convolutional Neural Networks(2020); ; Brieva, JorgeTomato crops are one of the most important agricultural products at economic level in the world. However, the quality of the tomato fruits is highly dependent to the growing conditions such as the nutrients. One of consequences of the latter during tomato harvesting is nutrient deficiency. Manually, it is possible to anticipate the lack of primary nutrients (i.e. nitrogen, phosphorus and potassium) by looking the appearance of the leaves in tomato plants. Thus, this paper presents a supervised vision-based monitoring system for detecting nutrients deficiencies in tomato crops by taking images from the leaves of the plants. It uses a Convolutional Neural Network (CNN) to recognize and classify the type of nutrient that is deficient in the plants. First, we created a data set of images of leaves of tomato plants showing different symptoms due to the nutrient deficiency. Then, we trained a suitable CNN-model with our images and other augmented data. Experimental results showed that our CNN-model can achieve 86.57% of accuracy. We anticipate the implementation of our proposal for future precision agriculture applications such as automated nutrient level monitoring and control in tomato crops. © 2020 IEEE.Scopus© Citations 23 15 1 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, A Methodology Based on Deep Q-Learning/Genetic Algorithms for Optimizing COVID-19 Pandemic Government Actions(2020); Whenever countries are threatened by a pandemic, as is the case with the COVID-19 virus, governments need help to take the right actions to safeguard public health as well as to mitigate the negative effects on the economy. A restrictive approach can seriously damage the economy. Conversely, a relaxed one may put at risk a high percentage of the population. Other investigations in this area are focused on modelling the spread of the virus or estimating the impact of the different measures on its propagation. However, in this paper, we propose a new methodology for helping governments in planning the phases to combat the pandemic based on their priorities. To this end, we implement the SEIR epidemiological model to represent the evolution of the COVID-19 virus on the population. To optimize the best sequences of actions governments can take, we propose a methodology with two approaches, one based on Deep Q-Learning and another one based on Genetic Algorithms. The sequences of actions (confinement, self-isolation, two-meter distance or not taking restrictions) are evaluated according to a reward system focused on meeting two objectives: firstly, getting few people infected so that hospitals are not overwhelmed, and secondly, avoiding taking drastic measures which could cause serious damage to the economy. The conducted experiments evaluate our methodology based on the accumulated rewards during the established period. The experiments also prove that it is a valid tool for governments to reduce the negative effects of a pandemic by optimizing the planning of the phases. According to our results, the approach based on Deep Q-Learning outperforms the one based on Genetic Algorithms. © 2020 ACM.Scopus© Citations 16 10 1