PSPaola Andrea Sánchez Sánchez

Paola Andrea Sánchez Sánchez

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Paola Andrea Sánchez Sánchez has a total of 19 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Perfil Psicológico de Buenos y Malos Pagadores de Crédito en Barranquilla, Colombia

    by Marcela Navia-Núñez, Paola Andrea Sánchez-Saánchez, Ray Miller Rincón-Laurens, Jaime Barrios-Mendoza, Diana Heredia-Vizcaíno

    El mundo financiero obtiene ganancias del producto crédito, a su vez, los usuarios pueden adquirir bienes que de otra manera les sería imposible. Sin embargo, el círculo se rompe si una de las partes incumple, por ello, para las empresas es importante detectar con anticipación posibles malos pagadores. La investigación busca descubrir rasgos de personalidad de buenos y malos pagadores. La primera etapa consiste en entrevistas a profundidad con diez analistas y usuarios de crédito. Se revela que los malos pagadores tienden a ser ostentosos, impulsivos, cortoplacistas y encuentran satisfacción en elementos externos. Mientras que los buenos pagadores encuentran satisfacción en elementos internos. Para los buenos pagadores el dinero cobija, para los malos pagadores el dinero satisface, oprime o traiciona. Hay dos perfiles de malos pagadores: indiferentes y adictos. En la segunda etapa de investigación se establecen nueve factores y 48 ítems con escala de Likert que son probados en 100 personas. El análisis factorial reduce a cinco los factores. Los factores dinero y calma permiten identificar a los malos pagadores.

  • Open Access

    Medida del nivel de seguridad informática de las pequeñas y medianas empresas (PYMEs) en Colombia

    by Paola A. Sánchez-Sánchez, Jose R. García-González, Antony Triana, Leidy Perez-Coronell

    En este estudio se diseña una herramienta que permite evaluar el estado actual de vulnerabilidad informática que tiene una pequeña y mediana empresa (PYME) a partir de la medición del nivel de seguridad de su software. Se definen y describen las componentes de la herramienta que, apoyado en la base de datos de vulnerabilidades y exposiciones comunes (CVE), ofrece un mecanismo para la evaluación eficaz del riesgo cibernético y un esquema de recomendaciones. Como resultado se muestra la ejecución de cada una de las componentes de la herramienta a través del estudio de una PYME del sector de tecnologia e innovación en Colombia. Se evalúa todo el software comercial en sus diferentes versiones y se sugieren líneas de acción según el nivel de riesgo calculado. Se concluye que la herramienta propuesta permite suplir las etapas iniciales de búsqueda, reporte y recomendaciones ante vulnerabilidades de riesgo cibernético, basado en un trabajo sistemático, permanente y exhaustivo, más de orden preventivo que correctivo.


  • Open Access

    Diseño teórico de la investigación: instrucciones metodológicas para el desarrollo de propuestas y proyectos de investigación científica

    by José R. García-González, Paola A. Sánchez-Sánchez

    En este estudio se propone un esquema de integración sistémica entre los diferentes elementos del diseño teórico de la investigación desde los principios rectores de la investigación holística. Se define una metodología de trabajo orientada a la identificación de los elementos clave del proceso investigativo a partir del análisis sistémico de la situación problémica y su relación con el objeto de estudio y su campo de acción. Se incluye la definición de categorías rectoras, la integración sistémica de contenidos y la presentación de un esquema sintético para la orientación metodológica del proceso investigativo. Como resultado, se presenta la sistematización epistemológica del proceso investigativo a través de dos casos aplicativos. Se concluye que el esquema orientador presentado permite generar una didáctica propia para orientar el desarrollo de propuestas y proyectos de investigación científica de calidad, alto impacto y pertinencia, y favorece la comprensión de los procesos y cursos de investigación científica en la educación superior.


  • Open Access

    Automatic migraine classification using artificial neural networks

    by Paola A. Sanchez-Sanchez, José Rafael García-González, Juan Manuel Rúa Ascar

    Background: Previous studies of migraine classification have focused on the analysis of brain waves, leading to the development of complex tests that are not accessible to the majority of the population. In the early stages of this pathology, patients tend to go to the emergency services or outpatient department, where timely identification largely depends on the expertise of the physician and continuous monitoring of the patient. However, owing to the lack of time to make a proper diagnosis or the inexperience of the physician, migraines are often misdiagnosed either because they are wrongly classified or because the disease severity is underestimated or disparaged. Both cases can lead to inappropriate, unnecessary, or imprecise therapies, which can result in damage to patients’ health. Methods: This study focuses on designing and testing an early classification system capable of distinguishing between seven types of migraines based on the patient’s symptoms. The methodology proposed comprises four steps: data collection based on symptoms and diagnosis by the treating physician, selection of the most relevant variables, use of artificial neural network models for automatic classification, and selection of the best model based on the accuracy and precision of the diagnosis. Results: The artificial neural network models used provide an excellent classification performance, with accuracy and precision levels >97% and which exceed the classifications made using other model, such as logistic regression, support vector machines, nearest neighbor, and decision trees. Conclusions: The implementation of migraine classification through artificial neural networks is a powerful tool that reduces the time to obtain accurate, reliable, and timely clinical diagnoses.


  • Open Access

    Automatic migraine classification using artificial neural networks

    by Paola A. Sanchez-Sanchez, José Rafael García-González, Juan Manuel Rúa Ascar

    Background: Previous studies of migraine classification have focused on the analysis of brain waves, leading to the development of complex tests that are not accessible to the majority of the population. In the early stages of this pathology, patients tend to go to the emergency services or outpatient department, where timely identification largely depends on the expertise of the physician and continuous monitoring of the patient. However, owing to the lack of time to make a proper diagnosis or the inexperience of the physician, migraines are often misdiagnosed either because they are wrongly classified or because the disease severity is underestimated or disparaged. Both cases can lead to inappropriate, unnecessary, or imprecise therapies, which can result in damage to patients’ health. Methods: This study focuses on designing and testing an early classification system capable of distinguishing between seven types of migraines based on the patient’s symptoms. The methodology proposed comprises four steps: data collection based on symptoms and diagnosis by the treating physician, selection of the most relevant variables, use of artificial neural network models for automatic classification, and selection of the best model based on the accuracy and precision of the diagnosis. Results: The neural network models used provide an excellent classification performance, with accuracy and precision levels >97% and which exceed the classifications made using other model, such as logistic regression, support vector machines, nearest neighbor, and decision trees. Conclusions: The implementation of migraine classification through neural networks is a powerful tool that reduces the time to obtain accurate, reliable, and timely clinical diagnoses.


  • Open Access

    Encountered Problems of Time Series with Neural Networks: Models and Architectures

    by Paola Andrea Sánchez-Sánchez, José Rafael García-González, Leidy Haidy Perez Coronell

    The growing interest in the development of forecasting applications with neural networks is denoted by the publication of more than 10,000 research articles present in the literature. However, the high number of factors included in the configuration of the network, the training process, validation and forecasting, and the sample of data, which must be determined in order to achieve an adequate network model for forecasting, converts neural networks in an unstable technique, given that any change in training or in some parameter produces great changes in the prediction. In this chapter, an analysis of the problematic around the factors that affect the construction of the neural network models is made and that often present inconsistent results, and the fields that require additional research are highlighted.


  • Improvement of the Level Service on a Hospital Warehouse Using Forecast Techniques

    by Paloma María Teresa Martínez-Sánchez, Carlos Hernán Hernán Fajardo-Toro, Úrsula Gomes Rosa Maruyama, Paola Andrea Sánchez Sánchez

    This article presents a study case focused on the establishment and improvement of the service level in a central warehouse of a hospital organization in Colombia which provide the products of medical use, clothing, anesthetics, and supplies, to nineteen medical dependencies. The warehouse is managed by a person, developing planning processes, purchases, reception, and administration of products or inventories who depends on the administrative and financial sub-direction of the institution. Through the use of interviews and surveys conducted at different dependencies. As well as the collection of information in the field, there were problems with the availability of products due to problems related to planning purchases which are done empirically without data analysis. Taking into account the problematic previously raised, we took different models of predictions as well as the use of the Mean Squared Error (MSE) and the accuracy of predictions to determine the best model according to with the product analyzed.

  • Specification and Construction of the Perceptron Multicapa Model

    by Paola Andrea Sánchez-Sánchez, José Rafael García-González, Leidy Haidy Perez Coronell

    The objective of this chapter is to analyze the problem surrounding the task of prognosis with neural networks and the factors that affect the construction of the model, and that often lead to inconsistent results, emphasizing the problems of selecting the training algorithm, the number of neurons in the hidden layer, and input variables. The methodology is to analyze the forecast of time series, due to the growing need for tools that facilitate decision-making, especially in series that, given their characteristics of noise and variability, infer nonlinear dynamics. Neural networks have emerged as an attractive approach to the representation of such behaviors due to their adaptability, generalization, and learning capabilities. Practical evidence shows that the Delta Delta and RProp training methods exhibit different behaviors than expected.

  • Case-Based Reasoning

    by Carlos Hernán Hernán Fajardo-Toro, Andrés Lopez Astudillo, Paloma María Teresa Martínez Sánchez, Paola Andrea Sánchez Sánchez, Alvaro José Fajardo-Toro

    Companies must deal with a high uncertainty caused by the characteristics of the markets and the economic, political, and social environment in which they offer their products and services. These characteristics are defined by the preferences of the consumers, which have a high variety coupled with the digital era. On the other hand, there is the necessity to implement measures that align the companies with the sustainability concepts, because of both legislations as well as the image that the customer could have of them. Due to this context, the organizations must find a way to optimize process and structures that require high flexibility given the need of combining perfect innovation, customization, standardization, and sustainability. Part of this planning process is the construction of forecast models that allows predicting with high precisión. In this chapter, a theoretical exposition is done and a literature revision of machine learning techniques is applied to try to solve the forecasting problem with special emphasis in neural networks and Case-Based Reasoning - CBR.

  • Open Access

    Extracción de Conocimiento para la Predicción y Análisis de los Resultados de la Prueba de Calidad de la Educación Superior en Colombia

    by José R. García-González, Paola A. Sánchez-Sánchez, Manuel Orozco, Sergio Obredor

    Se presentan y analizan los resultados de la prueba de la calidad de la educación superior en Colombia - Saber Pro. Se usó la metodología de extracción de conocimiento en bases de datos KDD sobre la cual se construyó una base de datos del desempeño académico del estudiante en áreas asociadas con los contenidos de la prueba Saber Pro, y se utilizó redes neuronales como técnica para la minería de datos. Las redes neuronales permitieron la predicción de los resultados de la prueba Saber Pro con alta exactitud tanto en rangos cualitativos como cuantitativos. Además, se comprobó una correlación entre el desempeño académico y los resultados de Saber Pro. Los hallazgos sugieren que la metodología usada es una excelente guía para el descubrimiento de patrones ocultos en los datos, y permite establecer estrategias de mejora de los resultados de las pruebas Saber Pro que involucren el desempeño académico del estudiante.