Repositorio Universidad Internacional Iberoamericana
Not a member yet
907 research outputs found
Sort by
Railway Track Fault Detection Using Selective MFCC Features from Acoustic Data
No full textRailway track faults may lead to railway accidents and cause human and financial loss. Spatial, temporal, and weather elements, and wear and tear, lead to ballast, loose nuts, misalignment, and cracks leading to accidents. Manual inspection of such defects is time-consuming and prone to errors. Automatic inspection provides a fast, reliable, and unbiased solution. However, highly accurate fault detection is challenging due to the lack of public datasets, noisy data, inefficient models, etc. To obtain better performance, this study presents a novel approach that relies on mel frequency cepstral coefficient features from acoustic data. The primary objective of this study is to increase fault detection performance. As well as designing an ensemble model, we utilize selective features using chi-square(chi2) that have high importance with respect to the target class. Extensive experiments were carried out to analyze the efficiency of the proposed approach. The experimental results suggest that using 60 features, 40 original features, and 20 chi2 features produces optimal results both regarding accuracy and computational complexity. A mean accuracy score of 0.99 was obtained using the proposed approach with machine learning models using the collected data. Moreover, this performance was significantly better than that of existing approaches; however, the performance of models may vary in real-world settings
Gamificación para el desarrollo de la lectoescritura en estudiantes de tercer grado de EGB, en la Unidad Educativa Santiago de Compostela, durante el último trimestre del año 2022
No full textEl trabajo presenta la gamificación para el desarrollo de la lectoescritura en estudiantes de tercer grado de EGB, en la Unidad Educativa Santiago de Compostela, durante el último trimestre del año 2022. La problemática consiste en el bajo dominio de las destrezas y habilidades en las competencias comunicativas oral y escrita para comprender y expresar las ideas. El objetivo se enfocó a proponer estrategias basadas en la gamificación para el desarrollo de la lectoescritura en estudiantes de tercer grado de EGB. La metodología empleada fue de enfoque mixto, descriptiva de análisis cualitativo de contenido. El estudio desarrolló la fase de inicio o diagnóstico, diseño y evaluación. Se aplicó la encuesta a 30 estudiantes del tercero de EGB, y una entrevista al docente de Lengua y Literatura. Los resultados obtenidos evidenciaron la necesidad de aplicar estrategias para mejorar la lectoescritura en los niños
Pre-Trained Deep Neural Network-Based Features Selection Supported Machine Learning for Rice Leaf Disease Classification
No full textRice is a staple food for roughly half of the world’s population. Some farmers prefer rice cultivation to other crops because rice can thrive in a wide range of environments. Several studies have found that about 70% of India’s population relies on agriculture in some way and that agribusiness accounts for about 17% of India’s GDP. In India, rice is one of the most important crops, but it is vulnerable to a number of diseases throughout the growing process. Farmers’ manual identification of these diseases is highly inaccurate due to their lack of medical expertise. Recent advances in deep learning models show that automatic image recognition systems can be extremely useful in such situations. In this paper, we propose a suitable and effective system for predicting diseases in rice leaves using a number of different deep learning techniques. Images of rice leaf diseases were gathered and processed to fulfil the algorithmic requirements. Initially, features were extracted by using 32 pre-trained models, and then we classified the images of rice leaf diseases such as bacterial blight, blast, and brown spot with numerous machine learning and ensemble learning classifiers and compared the results. The proposed procedure works better than other methods that are currently used. It achieves 90–91% identification accuracy and other performance parameters such as precision, Recall Rate, F1-score, Matthews Coefficient, and Kappa Statistics on a normal data set. Even after the segmentation process, the value reaches 93–94% for model EfficientNetV2B3 with ET and HGB classifiers. The proposed model efficiently recognises rice leaf diseases with an accuracy of 94%. The experimental results show that the proposed procedure is valid and effective for identifying rice diseases
Análisis de la resiliencia de centros de salud primaria y hospitales de Puerto Rico al ofrecer servicios de salud después de un desastre natural
No full textLa Región de América Latina y el Caribe está expuesta todos los años a una amplia gama de emergencias y desastres naturales de escalas y frecuencias cada vez mayores. El cambio climático ha causado desastres naturales devastadores poniendo en riesgo la salud y la seguridad de las personas con brotes de enfermedades, mortalidad y traumas. En el año 2017 Puerto Rico sufrió el embate del huracán María. Este evento natural fue ubicado en la categoría 4 de la escala Saffir-Simpson con vientos de 155 millas por horas y ráfagas de hasta 200 millas por hora. Afectó todos los sectores, pero el área de salud recibió el golpe más fuerte causando daños severos, ausencia de energía eléctrica y agua potable. Alrededor de 4,645 personas murieron en Puerto Rico debido a las consecuencias del paso del huracán María por la isla. El objetivo principal de esta investigación es analizar la resiliencia de los centros de salud primaria y los hospitales de Puerto Rico al ofrecer servicios de salud después de un desastre natural. Esta investigación es cualitativa y se realizaron grupos focales con: administradores, directores clínicos y oficiales de manejo de emergencias para la recopilación de información. Además, se utilizó el programa Atlas.ti para el análisis de los datos. El estudio demostró cómo los elementos externos e internos que poseen las instituciones de salud pueden influir directa o indirectamente en su capacidad de recuperarse luego de un desastre ambiental. Finalmente, el sector salud debe identificar y analizar el impacto potencial de los desastres naturales. El propósito es fortalecer las estrategias efectivas en el manejo de emergencias para garantizar el acceso y servicio adecuado de salud
Anthocyanins: what do we know until now?
No full textDiets enriched in plant-based foods are associated with the maintenance of a good well-being and with the prevention of many non-communicable diseases. The health effects of fruits and vegetables consumption are mainly due to the presence of micronutrients, including vitamins and minerals, and polyphenols, plant secondary metabolites. One of the most important classes of phenolic compounds are anthocyanins, that confer the typical purple-red color to many foods, such as berries, peaches, plums, red onions, purple corn, eggplants, as well as purple carrots, sweet potatoes and red cabbages, among others. This commentary aims to briefly highlight the progress made by science in the last years, focusing on some unexpected aspects related with anthocyanins, such as their bioavailability, their health effects and their relationship with gut microbiot
Diseño y validación de un instrumento de investigación para proponer metodología de gestión de proyectos
No full textLas metodologías para el diseño y gestión de proyectos son cada vez más necesarias y aplicadas con mayor frecuencia en el sector público en Latinoamérica. Continuamente hay actualizaciones y nuevos enfoques en la gestión de proyectos de inversión, por lo que el estudio en las metodologías es relevante a nivel investigativo. El diseño de instrumentos de investigación confiables que sirvan para promover el uso de estas metodologías es importante para asegurar la calidad en el proceso. Por lo que el objetivo de este estudio es diseñar y validar un instrumento que permita recolectar y gestionar sistemáticamente información de proyectos para obtener las variables que permitan definir la metodología apropiada para cada organización, en este estudio se ha tomado como referencia en el sector público la Subsecretaría de Recursos Pesqueros (SRP) en Ecuador. El instrumento, toma como referencia la Norma International Organization for Standardization (ISO) 10006, la Guía de Fundamentos de Gestión de Proyectos, por su nombre en inglés Project Management Body of Knowledge (PMBOK), las Metodologías de Diseño de Proyectos de la Universidad Politécnica de Cataluña (MDP-UPC) y de la Secretaría Nacional de Planificación y Desarrollo (SENPLADES) del Ecuador. Como resultado, se desarrolló una encuesta, a cuyo instrumento se realizó la validación interna y externa en función de parámetros de confiabilidad, contenido y constructo. Se realizó análisis factorial para determinar variables utilizando sistema estadístico SPSS. Finalmente, se cuenta con la validación del instrumento diseñado asegurando que es confiable y cumple con los parámetros necesarios para obtener variables que definan la metodología para elaboración de proyectos en el sector público de Ecuador
Spare Parts Forecasting and Lumpiness Classification Using Neural Network Model and Its Impact on Aviation Safety
No full textSafety critical spare parts hold special importance for aviation organizations. However, accurate forecasting of such parts becomes challenging when the data are lumpy or intermittent. This research paper proposes an artificial neural network (ANN) model that is able to observe the recent trends of error surface and responds efficiently to the local gradient for precise spare prediction results marked by lumpiness. Introduction of the momentum term allows the proposed ANN model to ignore small variations in the error surface and to behave like a low-pass filter and thus to avoid local minima. Using the whole collection of aviation spare parts having the highest demand activity, an ANN model is built to predict the failure of aircraft installed parts. The proposed model is first optimized for its topology and is later trained and validated with known historical demand datasets. The testing phase includes introducing input vector comprising influential factors that dictate sporadic demand. The proposed approach is found to provide superior results due to its simple architecture and fast converging training algorithm once evaluated against some other state-of-the-art models from the literature using related benchmark performance criteria. The experimental results demonstrate the effectiveness of the proposed approach. The accurate prediction of the cost-heavy and critical spare parts is expected to result in huge cost savings, reduce downtime, and improve the operational readiness of drones, fixed wing aircraft and helicopters. This also resolves the dead inventory issue as a result of wrong demands of fast moving spares due to human error
Ensemble Partition Sampling (EPS) for Improved Multi-Class Classification
No full textClassification is a commonly used technique in data mining and is applied in various fields such as sentiment analysis, fraud detection, and fault diagnosis. Multiclass classification, which involves more than two classes, is more complex than binary classification. There are mainly two ways to approach multiclass classification, one is to expand the binary classifier into a multiclass classifier through various strategies and the other is to divide the multiclass classification problem into multiple binary problems (binarization). Two popular approaches for binarization are One vs One (OvO) and One vs All (OvA). It is simpler to aggregate the outputs of all binary classifiers as the number of classifiers decreases. However, it causes an imbalance of positive and negative sample numbers, which affects the classification effect of each binary classifier. In this article, we contribute to the field of ensemble learning and multi-class classification by proposing a new method called Ensemble Partition Sampling (EPS). This article presents a new approach to multiclass classification using an "Ensemble Partition Sampling" method within the "one-vs-all" (OvA) framework. The primary goal of this method is to tackle the problem of data imbalance by incorporating ensemble learning and preprocessing techniques into each binary dataset. The study found that Ensemble Partition Sampling (EPS) is the most effective method for imbalanced and multiclass imbalanced classification, outperforming other methods including OvA, SMOTE, k-means-SMOTE, Bagging-RB, DES-MI, OvO-EASY, and OvO-SMB. The study used CART, Random Forest, and SVM as classifiers, and the results consistently showed that EPS outperformed all other algorithms. The findings suggest that EPS is a highly effective method for improving classification performance in imbalanced and multiclass imbalanced datasets
Prevalence and impact of long COVID-19 among patients with diabetes and cardiovascular diseases in Bangladesh
No full textIntroduction: Co-prevalence of long-COVID-19, cardiovascular diseases and diabetes is one of the major health challenges of the pandemic worldwide. Studies on long-COVID-19 and associated health outcomes are absent in Bangladesh. The main aim of this study was to determine the prevalence and impact of long-COVID-19 on preexisting diabetes and cardiovascular diseases (CVD) on health outcomes among patients in Bangladesh.
Methods: We collected data from 3,250 participants in Bangladesh, retrospectively. Multivariable logistic regression model was used to determine the odds ratio between independent and dependent variables. Kaplan-Meier survival curve was used to determine the cumulative survival.
Results: COVID-19 was detected among 73.4% (2,385 of 3,250) participants. Acute long-COVID-19 was detected among 28.4% (678 of 2,385) and chronic long-COVID-19 among 71.6% (1,707 of 2,385) patients. CVD and diabetes were found among 32%, and 24% patients, respectively. Mortality rate was 18% (585 of 3,250) among the participants. Co-prevalence of CVD, diabetes and COVID-19 was involved in majority of fatality (95%). Fever (97%), dry cough (87%) and loss of taste and smell (85%) were the most prevalent symptoms. Patients with co-prevalence of CVD, diabetes and COVID-19 had higher risk of fatality (OR: 3.65, 95% CI, 2.79–4.24). Co-prevalence of CVD, diabetes and chronic long-COVID-19 were detected among 11.9% patients.
Discussion: Risk of hospitalization and fatality reduced significantly among the vaccinated. This is one of the early studies on long-COVID-19 in Bangladesh
Diagnosing Training Needs in European Tourism SMEs: The TC-NAV Project for Managing and Overcoming Virulent Crises
No full textThis research aims to gather opinions from experts in the European tourism sector regarding training needs to address severe crises, such as Covid, in Small and Medium-Sized Enterprises (SMEs) across five countries: Spain, Iceland, Ireland, Scotland, and Germany. This study was conducted within the scope of the European TC-NAV project, which is funded by the European Union. The ultimate goal of this project is to develop training solutions for European SMEs Most existing literature on tourism crises primarily examines the impact on destinations as a whole rather than on individual tourism enterprises. Thus, this research is both relevant and timely The methodology employed was qualitative, and data being collected using a 9-question interview guide. This guide underwent validation by experts, achieving a Cronbach's Alpha value of 0.7. In total, 30 individuals were interviewed: 5 civil servants, 9 company directors, 5 university professors, 6 researchers, and 5 entrepreneurs. Some notable findings include the importance of innovation for change, promoting sustainable tourism, fostering informal partnerships among regional companies, the essential role of government support, the benefits of flexible planning and service digitisation, and the ongoing need for training and upskilling