Repositorio Universidad Internacional Iberoamericana
Not a member yet
907 research outputs found
Sort by
Deep Learning Approaches for Image Captioning: Opportunities, Challenges and Future Potential
No full textGenerative intelligence relies heavily on the integration of vision and language. Much of the research has focused on image captioning, which involves describing images with meaningful sentences. Typically, when generating sentences that describe the visual content, a language model and a vision encoder are commonly employed. Because of the incorporation of object areas, properties, multi-modal connections, attentive techniques, and early fusion approaches like bidirectional encoder representations from transformers (BERT), these components have experienced substantial advancements over the years. This research offers a reference to the body of literature, identifies emerging trends in an area that blends computer vision as well as natural language processing in order to maximize their complementary effects, and identifies the most significant technological improvements in architectures employed for image captioning. It also discusses various problem variants and open challenges. This comparison allows for an objective assessment of different techniques, architectures, and training strategies by identifying the most significant technical innovations, and offers valuable insights into the current landscape of image captioning research
Detecting Cyberattacks to Federated Learning on Software-Defined Networks
No full textFederated learning is a distributed machine-learning technique that enables multiple devices to learn a shared model while keeping their local data private. The approach poses security challenges, such as model integrity, that must be addressed to ensure the reliability of the learned models. In this context, software-defined networking (SDN) can play a crucial role in improving the security of federated learning systems; indeed, it can provide centralized control and management of network resources, enforcement of security policies, and detection and mitigation of network-level threats. The integration of SDN with federated learning can help achieve a secure and efficient distributed learning environment. In this paper, an architecture is proposed to detect attacks on Federated Learning using SDN; furthermore, the machine learning model is deployed on a number of devices for training. The simulation results are carried out using the N-BaIoT dataset and training models such as Random Forest achieves 99.6%, Decision Tree achieves 99.8%, and K-Nearest Neighbor achieves 99.3% with 20 features
Enhanced detection of diabetes mellitus using novel ensemble feature engineering approach and machine learning model
No full textDiabetes is a persistent health condition led by insufficient use or inappropriate use of insulin in the body. If left undetected, it can lead to further complications involving organ damage such as heart, lungs, and eyes. Timely detection of diabetes helps obtain the right medication, diet, and exercise plan to lead a healthy life. ML approach has been utilized to obtain rapid and reliable diabetes detection, however, existing approaches suffer from the use of limited datasets, lack of generalizability, and lower accuracy. This study proposes a novel feature extraction approach to overcome these limitations by using an ensemble of convolutional neural network (CNN) and long short-term memory (LSTM) models. Multiple datasets are combined to make a larger dataset for experiments and multiple features are utilized for investigating the efficacy of the proposed approach. Features from the extra tree classifier, CNN, and LSTM are also considered for comparison. Experimental results reveal the superb performance of CNN-LSTM-based features with random forest model obtaining a 0.99 accuracy score. This performance is further validated by comparison with existing approaches and k-fold cross-validation which shows the proposed approach provides robust results
PyDEMATEL: A Python-based tool implementing DEMATEL and fuzzy DEMATEL methods for improved decision making
No full textIn the context of decision-making, the DEMATEL (Decision Making Trial and Evaluation Laboratory) method stands out for its systematic approach to complex systems. By incorporating fuzzy logic, the DEMATEL fuzzy method takes traditional techniques a step further, effectively managing the uncertainties and imprecision inherent in expert assessments. This hybrid method has proved useful in a variety of fields, including business, engineering, healthcare, environmental management, and education. Its ability to refine subjective judgments into actionable information enables decision-makers to improve organizational performance, optimize resource allocation, and achieve more accurate results. The development of software tools for these methods makes them more accessible and practical, enabling more effective analysis and application. In this paper, we propose a flexible implementation that integrates seamlessly into Python-based applications, offering full access to all parameters, matrices, and intermediary calculations of the method. Additionally, the tool also provides a user-friendly graphical interface
Análisis de la relación entre el entorno familiar, la ansiedad y agresividad de los estudiantes de 7º., 8º. y 9º. grado del centro de educación no gubernamental adventista de San Pedro Sula Honduras.
No full textLa presente investigación identifica la relación entre la ansiedad y agresividad que presentan los estudiantes del séptimo, octavo y noveno grado del instituto adventista dentro y fuera de sus salones de clases y su entorno familiar. A partir de un estudio mixto, se ha podido medir los factores que influyen en las familias en cuanto a los niveles de estrés emocional, que posteriormente se comprobaran de manera más específica por los instrumentos aplicados por la investigadora. Para este estudio se dispone de material empírico, el cual fue recolectado durante nuestra estadía en el centro educativo el área administrativa, documentación facilitada por el centro y la obtenido por la investigadora a través del análisis de los datos recopilados por medio de la observación, entrevistas y cuestionarios que identificaron comportamientos en diferentes niveles de ansiedad y agresividad en las relaciones entre padres e hijos, padres y docentes. Se destaca la importancia de las intervenciones docentes en cuanto a los apoyos para el cumplimiento de los reglamentos educativos y como estímulo positivo a las conductas del alumnado participante. Los resultados de la investigación muestran las causas que aportan o dan origen al nivel de ansiedad o agresividad que los estudiantes manifiestan durante su estadía en el centro educativo. Los resultados serán compartidos con el departamento de orientación y psicología del centro educativo que es objeto de estudio, sirviendo también como de apoyo para futuras intervenciones en el centro educativo. Concluimos que el ambiente del hogar está asociado de manera directa e impactante en las conductas que presentan los estudiantes que fueron objeto de estudio y que la relación que los padres tienen con sus hijos influye en los comportamientos que estos muestran dentro del centro educativo y fuera de este
Efficacy of a vaginal suppository formulation prepared with Acacia arabica (Lam.) Willd. gum and Cinnamomum camphora (L.) J. Presl. in heavy menstrual bleeding analyzed using a machine learning technique
No full textObjective: This study aims to determine the efficacy of the Acacia arabica (Lam.) Willd. and Cinnamomum camphora (L.) J. Presl. vaginal suppository in addressing heavy menstrual bleeding (HMB) and their impact on participants' health-related quality of life (HRQoL) analyzed using machine learning algorithms.
Method: A total of 62 participants were enrolled in a double-dummy, single-center study. They were randomly assigned to either the suppository group (SG), receiving a formulation prepared with Acacia arabica gum (Gond Babul) and camphor from Cinnamomum camphora (Kafoor) through two vaginal suppositories (each weighing 3,500 mg) for 7 days at bedtime along with oral placebo capsules, or the tranexamic group (TG), receiving oral tranexamic acid (500 mg) twice a day for 5 days and two placebo vaginal suppositories during menstruation at bedtime for three consecutive menstrual cycles. The primary outcome was the pictorial blood loss assessment chart (PBLAC) for HMB, and secondary outcomes included hemoglobin level and SF-36 HRQoL questionnaire scores. Additionally, machine learning algorithms such as k-nearest neighbor (KNN), AdaBoost (AB), naive Bayes (NB), and random forest (RF) classifiers were employed for analysis.
Results: In the SG and TG, the mean PBLAC score decreased from 635.322 ± 504.23 to 67.70 ± 22.37 and 512.93 ± 283.57 to 97.96 ± 39.25, respectively, at post-intervention (TF3), demonstrating a statistically significant difference (p < 0.001). A higher percentage of participants in the SG achieved normal menstrual blood loss compared to the TG (93.5% vs 74.2%). The SG showed a considerable improvement in total SF-36 scores (73.56%) compared to the TG (65.65%), with a statistically significant difference (p < 0.001). Additionally, no serious adverse events were reported in either group. Notably, machine learning algorithms, particularly AB and KNN, demonstrated the highest accuracy within cross-validation models for both primary and secondary outcomes.
Conclusion: The A. arabica and C. camphora vaginal suppository is effective, cost-effective, and safe in controlling HMB. This botanical vaginal suppository provides a novel and innovative alternative to traditional interventions, demonstrating promise as an effective management approach for HMB
Human‐based new approach methodologies to accelerate advances in nutrition research
No full textMuch of nutrition research has been conventionally based on the use of simplistic in vitro systems or animal models, which have been extensively employed in an effort to better understand the relationships between diet and complex diseases as well as to evaluate food safety. Although these models have undeniably contributed to increase our mechanistic understanding of basic biological processes, they do not adequately model complex human physiopathological phenomena, creating concerns about the translatability to humans. During the last decade, extraordinary advancement in stem cell culturing, three-dimensional cell cultures, sequencing technologies, and computer science has occurred, which has originated a wealth of novel human-based and more physiologically relevant tools. These tools, also known as “new approach methodologies,” which comprise patient-derived organoids, organs-on-chip, multi-omics approach, along with computational models and analysis, represent innovative and exciting tools to forward nutrition research from a human-biology-oriented perspective. After considering some shortcomings of conventional in vitro and vivo approaches, here we describe the main novel available and emerging tools that are appropriate for designing a more human-relevant nutrition research. Our aim is to encourage discussion on the opportunity to explore innovative paths in nutrition research and to promote a paradigm-change toward a more human biology-focused approach to better understand human nutritional pathophysiology, to evaluate novel food products, and to develop more effective targeted preventive or therapeutic strategies while helping in reducing the number and replacing animals employed in nutrition research
Clinical phenotypes and short-term outcomes based on prehospital point-of-care testing and on-scene vital signs
No full textEmergency medical services (EMSs) face critical situations that require patient risk classification based on analytical and vital signs. We aimed to establish clustering-derived phenotypes based on prehospital analytical and vital signs that allow risk stratification. This was a prospective, multicenter, EMS-delivered, ambulance-based cohort study considering six advanced life support units, 38 basic life support units, and four tertiary hospitals in Spain. Adults with unselected acute diseases managed by the EMS and evacuated with discharge priority to emergency departments were considered between January 1, 2020, and June 30, 2023. Prehospital point-of-care testing and on-scene vital signs were used for the unsupervised machine learning method (clustering) to determine the phenotypes. Then phenotypes were compared with the primary outcome (cumulative mortality (all-cause) at 2, 7, and 30 days). A total of 7909 patients were included. The median (IQR) age was 64 (51–80) years, 41% were women, and 26% were living in rural areas. Three clusters were identified: alpha 16.2% (1281 patients), beta 28.8% (2279), and gamma 55% (4349). The mortality rates for alpha, beta and gamma at 2 days were 18.6%, 4.1%, and 0.8%, respectively; at 7 days, were 24.7%, 6.2%, and 1.7%; and at 30 days, were 33%, 10.2%, and 3.2%, respectively. Based on standard vital signs and blood test biomarkers in the prehospital scenario, three clusters were identified: alpha (high-risk), beta and gamma (medium- and low-risk, respectively). This permits the EMS system to quickly identify patients who are potentially compromised and to proactively implement the necessary interventions
MLS Pedagogy, Culture and Innovation
No full textLa revista MLS Pedagogy, Culture and Innovation (MLSPCI) nace como una publicación interdisciplinar en la que tienen cabida todo tipo de trabajos procedentes del ámbito académico, social o cultural en los que prime el carácter innovador de las aportaciones. Abarca un gran número de temáticas actuales como pueden ser la tecnología educativa, interculturalidad e inclusión, desarrollo curricular, formación docente, tutoría, organización de centros, entre otras.
La revista está abierta a recibir estudios y experiencias sobre las mismas de ámbito europeo e iberoamericano preferentemente. Los artículos se publican en español, portugués e inglés. A partir de esta misma página, podrá acceder a los índices de todas las ediciones de la revista, los resúmenes del artículo y los textos completos. Asimismo, en la sección "Sobre la revista" encontrará toda la información sobre nuestra revista, su equipo editorial, sistema de publicación y envíos en línea
Performance of the 4C and SEIMC scoring systems in predicting mortality from onset to current COVID-19 pandemic in emergency departments
No full textThe evolution of the COVID-19 pandemic has been associated with variations in clinical presentation and severity. Similarly, prediction scores may suffer changes in their diagnostic accuracy. The aim of this study was to test the 30-day mortality predictive validity of the 4C and SEIMC scores during the sixth wave of the pandemic and to compare them with those of validation studies. This was a longitudinal retrospective observational study. COVID-19 patients who were admitted to the Emergency Department of a Spanish hospital from December 15, 2021, to January 31, 2022, were selected. A side-by-side comparison with the pivotal validation studies was subsequently performed. The main measures were 30-day mortality and the 4C and SEIMC scores. A total of 27,614 patients were considered in the study, including 22,361 from the 4C, 4,627 from the SEIMC and 626 from our hospital. The 30-day mortality rate was significantly lower than that reported in the validation studies. The AUCs were 0.931 (95% CI: 0.90–0.95) for 4C and 0.903 (95% CI: 086–0.93) for SEIMC, which were significantly greater than those obtained in the first wave. Despite the changes that have occurred during the coronavirus disease 2019 (COVID-19) pandemic, with a reduction in lethality, scorecard systems are currently still useful tools for detecting patients with poor disease risk, with better prognostic capacity