CRIS

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

Browse

Search Results

Now showing 1 - 10 of 17

Some of the metrics are blocked by your
consent settings
Deploying Real-Time Speech Recognition on ESP32 Using TinyML and Edge Impulse
(Springer Nature Switzerland, 2025)
;
Gutiérrez, Sebastián
;
;
The emergence of Tiny Machine Learning (TinyML) has enabled real-time on-device inference on ultra-low-power microcontrollers, eliminating reliance on cloud computing while significantly reducing latency, power consumption, and bandwidth requirements. This study explores the deployment of a TinyML-based speech recognition system on an ESP32 microcontroller, leveraging Edge Impulse for model development, Mel-Frequency Cepstral Coefficients (MFCCs) for feature extraction, and TensorFlow Lite for Microcontrollers (TFLM) for efficient inference. The model was trained on a curated subset of the Google Speech Commands Dataset, incorporating background noise augmentation to enhance robustness in real-world environments. Using Edge Impulse’s EON Compiler, the model was fully quantized and optimized, achieving a 37% reduction in RAM usage and 27% in ROM. The final model attained 87.14% accuracy on testing data and 97.1% average classification confidence during real-time inference, with excellent noise rejection (99.6%) and latency of 266 ms. Compared to state-of-the-art systems deployed on more powerful platforms, the proposed approach achieves competitive accuracy while maintaining real-time inference and minimal resource consumption on ultra-low-power hardware. This makes it particularly suitable for battery-powered IoT, robotics, and embedded automation applications where connectivity and energy efficiency are critical. By balancing performance and efficiency, this research highlights the viability of deploying speech recognition systems on constrained microcontrollers. Future work will explore advanced architectures and enhanced feature extraction strategies to further improve recognition accuracy, especially for short or phonetically similar commands. ©The authors ©Springer.
Some of the metrics are blocked by your
consent settings
Harmony or Discordance between Sacramental and Liturgical Theology?
(MDPI, 2024)
Gutiérrez, Sebastián
This paper aims to show a way of approximating between liturgical studies and sacramental theology, trying to undo a too formal separation between the two sciences. The paramount cause is to be found at the request of Sacrosanctum Concilium, starting from the link between the two to achieve a greater and more fruitful participation of those faithful to the sacraments. In the words of Card. Ratzinger, this request has not been fully met. The dichotomy and relationship between the notions of theoria and praxis in both sciences are presented as the need for a solid foundation or philosophical frame of reference with a metaphysical or realistic background, attending to the problems raised by the International Theological Commission in the document on “The Reciprocity between Faith and Sacraments in the Sacramental Economy” (1999). The pathway is open, some solutions are proposed, and an attempt is made to show the importance of this subject for the understanding of man himself and his Christian life.
10
Some of the metrics are blocked by your
consent settings
Mutation profile in liquid biopsy tested by next generation sequencing in Mexican patients with non-small cell lung carcinoma and its impact on survival
(AME Publishing Company, 2024)
Martínez-Herrera, José Fabián
;
Sánchez Domínguez, Gisela
;
Juárez-Vignon Whaley, Juan J.
;
Carrasco-Cara Chards, Sonia
;
López Vrátný, Claudia
Background: Lung cancer represents a significant global health concern, often diagnosed in its advanced stages. The advent of massive DNA sequencing has revolutionized the landscape of cancer treatment by enabling the identification of target mutations and the development of tailored therapeutic approaches. Unfortunately, access to DNA sequencing technology remains limited in many developing countries. In this context, we emphasize the critical importance of integrating this advanced technology into healthcare systems in developing nations to improve treatment outcomes. Methods: We conducted an analysis of electronic clinical records of patients with confirmed advanced non-small cell lung cancer (NSCLC) and a verified negative status for the epidermal growth factor receptor (EGFR) mutation. These patients underwent next-generation sequencing (NGS) for molecular analysis. We performed descriptive statistical analyses for each variable and conducted both univariate and multivariate statistical analyses to assess their impact on progression-free survival (PFS) and overall survival (OS). Additionally, we classified genetic mutations as actionable or non-actionable based on the European Society for Medical Oncology Scale of Clinical Actionability of Molecular Targets (ESCAT) guidelines. © 2024 AME Publishing Company. All rights reserved.
8 1
Some of the metrics are blocked by your
consent settings
A Framework for Mars Sample Return: Who Gets Access and What Issues Must Be Addressed
(2022)
Seltikova, Ekaterina
;
Zarate-Villazon, Ángel M.
;
Balaji, Anirudh
;
De Winter, Bram
;
García González, Brenda
The space industry is in an age where we are beginning to look at human exploration on the surface of other planets. Leading the charge is the NASA-ESA collaboration of the Mars Sample Return campaign to bring samples back from the surface of Mars via robotic missions ahead of future crewed missions to Mars. As exciting as it is knowing that one day soon humans will have physical access to a Martian sample, there are many questions regarding sample policy that must be addressed besides the extensive work of research organizations like COSPAR and MEPAG. This work is done under the auspices of the Space Generation Advisory Council by young scientists and engineers which were part of the Space Generation Congress (SGC) 2021 Mars Sample Return working group. Using a foundation of the current and past sample return policy framework, we focus, from a science and engineering point of view, on how it is decided which research projects are most important and how to engage the different categories of stakeholders. This paper recommends a Mars sample return framework that takes into account these aforementioned issues. Furthermore, we are addressing questions such as: how do we guarantee findings are disseminated sufficiently, and how do we ensure that sample protection measures are adhered to? With the importance of commercial Martian space explorations in the future, the paper will address questions for both commercial and institutional exploration missions. Additionally, with the growing capacities of space emerging nations, such a framework shall consider mechanisms to foster equal opportunities for all nations to benefit from future Martian exploration endeavors. By the end of this paper, a first draft of such an equitable Mars sample return framework will be proposed and additional concerns that need to be addressed will be highlighted. © 2022 by the International Astronautical Federation (IAF). All rights reserved.
9 1
Some of the metrics are blocked by your
consent settings
Predicting climate conditions using Internet-of- Things and artificial hydrocarbon networks
(2017)
;
Gutiérrez, Sebastián
;
Montoya Pacheco, Alejandro
The prediction and understanding of environmental conditions is of great importance to prevent and analyze changes in environment, supporting meteorological based sectors, such as agriculture. In that sense, this paper presents an Internet of Things (IoT) system for predicting climate conditions, i.e. temperature, using artificial intelligence by means of a supervised learning method, the artificial hydrocarbon networks model. It allows predicting the temperature of remote locations using information from a web service comparing it with a field temperature sensor. Experimental results of the supervised learning model are presented in two modes: offline training to detect the suitable parameters of the model and testing to validate the model with new data retrieval from the web service. Preliminary results conclude that artificial hydrocarbon networks model predicts remote temperature with mean error of 0.05°c in testing mode. © 2018 IMEKO-International Measurement Federation Secretariat. All rights reserved.
12 2
Some of the metrics are blocked by your
consent settings
Surgical repair of right atrial wall rupture after blunt chest trauma
(2012-08)
Telich, Eduardo
;
Anaya-Ayala, Javier E.
;
Gutiérrez, Sebastián
Right atrial wall rupture after blunt chest trauma is a catastrophic event associated with high mortality rates. We report the case of a 24-year-old woman who was ejected 40 feet during a motor vehicle accident. Upon presentation, she was awake and alert, with a systolic blood pressure of 100 mmHg. Chest computed tomography disclosed a large pericardial effusion; transthoracic echocardiography confirmed this finding and also found right ventricular diastolic collapse. A diagnosis of cardiac tamponade with probable cardiac injury was made; the patient was taken to the operating room, where median sternotomy revealed a 1-cm laceration of the right atrial appendage. This lesion was directly repaired with 4-0 polypropylene suture. Her postoperative course was uneventful, and she continued to recover from injuries to the musculoskeletal system. This case highlights the need for a high degree of suspicion of cardiac injuries after blunt chest trauma. An algorithm is proposed for rapid recognition, diagnosis, and treatment of these lesions.
Scopus© Citations 9 14 1
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
Estimation of Low Nutrients in Tomato Crops Through the Analysis of Leaf Images Using Machine Learning
(2021)
;
Cevallos, Claudio
;
Gutiérrez, Sebastián
;
Tomato crops are considered the most important agricultural products worldwide. However, the quality of tomatoes depends mainly on the nutrient levels. Visual inspection is made by farmers to anticipate the nutrient deficiency of the plants. Recently, precision agriculture has explored opportunities to automate nutrient level monitoring. Previous work has demonstrated that a convolutional neural network (CNN) is able to estimate low nutrients in tomato plants using images of their leaves. However, the performance of the CNN was not adequate. Thus, this work proposes a novel CNNbased classifier, namely CNN+AHN, for estimating low nutrients in tomato crops using an image of the tomato leaves. The CNN+AHN incorporates a set of convolutional layers as the feature extraction part, and a supervised learning method called artificial hydrocarbon network (AHN) as the dense layer. Different combinations of the architecture of CNN+AHN were examined. Experimental results showed that our best CNN+AHN classifier is able to estimate low nutrients in tomato plants with an accuracy of 95:57% and F1-score of 95:75%, outperforming the literature.
Scopus© Citations 15 6 2
Some of the metrics are blocked by your
consent settings
Anemia management in patients with chronic renal insufficiency
(2000)
Kausz, Annamaria T.
;
;
Gutiérrez, Sebastián
The introduction of recombinant human erythropoietin (rHuEPO) more than a decade ago provided the first effective treatment for the anemia of chronic renal insufficiency (CRI). The use of rHuEPO in the treatment of anemia has been associated with partial regression of left ventricular hypertrophy among both dialysis and nondialysis patients, and has been shown to reduce the frequency of cardiac complications such as congestive heart failure and number of days of hospitalization among dialysis patients. Despite this evidence, the anemia of CRI remains highly prevalent, underrecognized, and undertreated. A number of considerations arise regarding the management of anemia among patients with CRI. In this article, we review the rationale for treatment of anemia, current management practices, proposed treatment strategies, and the economic implications of improved anemia treatment. ©American Journal of Kidney Diseases
Scopus© Citations 43 8 1
Some of the metrics are blocked by your
consent settings
Click-event sound detection in automotive industry using machine/deep learning
(2021)
;
;
Gutiérrez, Sebastián
In the automotive industry, despite the robotic systems on the production lines, factories continue employing workers in several custom tasks getting for semi-automatic assembly operations. Specifically, the assembly of electrical harnesses of engines comprises a set of connections between electrical components. Despite the task is easy to perform, employees tend not to notice that a few components are not being connected properly due to physical fatigue provoked by repetitive tasks. This yields a low quality of the assembly production line and possible hazards. In this work, we propose a sound detection system based on machine/deep learning (ML/DL) approaches to identify click sounds produced when electrical harnesses are connected. The purpose of this system is to count the number of connections properly made and to feedback to the employees. We collect and release a public dataset of 25,000 click sounds of 25 ms length at 22 kHz during three months of assembly operations in an automotive production line located in Mexico. Then, we design an ML/DL-based methodology for click sound detection of assembled harnesses under real conditions of a noisy environment (noise level ranging from −16.67 dB to −12.87 dB) including other machinery sounds. Our best ML/DL model (i.e., a combination between five acoustic features and an optimized convolutional neural network) is able to detect click sounds in a real assembly production line with an accuracy of 94.55±0.83 %. To the best of our knowledge, this is the first time a click sounds detection system in assembling electrical harnesses of engines for giving feedback to the workers is proposed and implemented in a real-world automotive production line. We consider this work valuable for the automotive industry on how to apply ML/DL approaches for improving the quality of semi-automatic assembly operations. © 2021 Elsevier B.V.
Scopus© Citations 22 24 2

CRIS

Browse

Filters

Settings

Sort By

Results per page

Search Results