In this paper, a model based on genetic algorithms for protein folding prediction is proposed. The most important features of the proposed approach are: i) Heuristic secondary structure information is used in the initialization of the genetic algorithm; ii) An enhanced 3D spatial representation called cube-octahedron is used, also, an expansion technique is proposed in order to reduce the computational complexity and spatial constraints; iii) Data preprocessing of geometric features to characterize the cubeoctahedron using twelve basic vectors to define the nodes. Additionally, biological information (torsion angles, bond angles and secondary structure conformations) was pre-processed through an analysis of all possible combinations of the basic vectors which satisfy the biological constrains defined by the spatial representation; and iv) Hashing techniques were used to improve the computational efficiency. The pre-processed information was stored in hash tables, which are intensively used by the genetic algorithm. Some experiments were carried out to validate the proposed model obtaining very promising results.
A Support Vector Machine Regression (SVMR) algorithm was applied to calculate the epicenter distance using a ten seconds signal, after primary waves arrive at a seismological station near to Bogota -Colombia. This algorithm was tested with 863 records of earthquakes, where the input parameters were an exponential function of waveform envelope estimated by least squares and maximum value of recorded waveforms for each component of the seismic station. Cross validation was applied to normalized polynomial kernel functions, obtaining mean absolute error for different exponents and complexity parameters. The epicenter distance was estimated with 10.3 kilometers of absolute error, improving the results previously obtained for this hypocentral parameter. The proposed algorithm is easy to implement in hardware and can be employed directly in the field, generating fast decisions at seismological control centers increasing the possibilities of effective reactions.Keywords: earthquake early warning; support vector machine regression; earthquake; rapid response; epicenter distance; seismic event; seismology; Bogota -Colombia.Estimación rápida de la distancia epicentral de un terremoto utilizando registros de una sola estación sismológica, mediante técnicas de aprendizaje de máquinas Resumen Se aplicó un algoritmo de máquinas de vector de soporte para calcular la distancia epicentral utilizando una señal de diez segundos, después del arribo de ondas primarias a una estación sismológica cercana a Bogotá -Colombia. Este algoritmo fue probado con 863 registros de terremotos donde los parámetros de entrada fueron una función exponencial de la envolvente estimada para los mínimos cuadrados y el valor máximo de las formas de ondas registradas en cada componente de la estación sísmica. Validación cruzada fue aplicada a funciones kernel polinomiales normalizadas, obteniendo la media del error absoluto para diferentes exponentes y parámetros de complejidad. La distancia epicentral se estimó con 10.3 kilómetros de error absoluto, mejorando los resultados previamente obtenidos para este parámetro hipocentral. El algoritmo propuesto es fácil de implementar y puede ser empleado directamente en campo, generando decisiones rápidas en centros de control sismológico incrementado posibilidades de tener reacciones efectivas.Palabras clave: alerta temprana de terremotos; máquinas de soporte vectorial; terremoto; respuesta rápida; distancia epicentral; evento sísmico; sismología; Bogotá -Colombia.
The objective of this research is to apply a new approach to estimate arrival azimuth of seismic events using seismological records of the “El Rosal” station, near to the city of Bogota – Colombia, by applying support vector machines (SVMs). The algorithm was trained with time signal descriptors of 863 seismic events acquired from January 1998 to October 2008; considering only events with magnitude ≥ 2 ML. The earthquake signals were filtered in order to remove diverse kind of low and high frequency noise not related to such events. During training stages of SVMs, several combinations of kernel function exponent and complexity factor were applied to time signals of 5, 10 and 15 seconds along with earthquake magnitudes of 2.0, 2.5, 3.0 and 3.5 ML. The best classification of SVMs was obtained using time signals of 5 seconds and earthquake magnitudes greater than 3.0 ML with kernel exponent of 10 and complexity factor of 2, showing accuracy of 45.4 degrees. This research is an improvement of previous works related to earthquake arrival azimuth determination from data of one single seismic station employing machine learning techniques.
A main goal of human genetics is to understand the relationship between variations in DNA sequences and the susceptibility to certain illnesses. In this particular work, genetic information is analyzed in relation to the Alzheimer's disease (AD) in order to improve its diagnosis, prevention and treatment. In Colombia, this disease currently requires special attention because its incidence has increased significantly in recent years. Thus, this work analyzes a set of twelve genetic markers or single nucleotide polymorphisms (SNPs) in a set of Colombian patients through a constructive induction method based on a machine learning approach, namely, multifactor dimensionality reduction (MDR). Also, some statistical epistasis analysis is carried out. Particularly, epistasis is obtained based on information gain from AD related genes, providing a simple methodology to characterize interactions in genetic association studies and capturing important traits that describe the behavior of the disease.
Objetivo: Se introduce la tecnología blockchain, incluidas sus principales características. También se discute el modelo de medicina P6 para la atención centrada en el paciente, y se presentan las aplicaciones de la tecnología blockchain como una capa de seguridad e interoperabilidad para dispositivos médicos IoT y sistemas de información hospitalarios. Metodología: Se realizó una revisión de las publicaciones registradas en las colecciones bibliográficas de IEEE Xplore y Scopus, con un filtro sobre las publicaciones enfocadas en blockchain, IoT y salud. El análisis de los artículos se enfocó en el planteamiento de un escenario de congruencia funcional de estos tres elementos. Resultados: Se presentan las aplicaciones de blockchain e IoT para el cuidado integral de la salud, con una esquematización de la interacción de dicha tecnología entre los sistemas de información hospitalarios y los sensores médicos de IoT para la creación de las condiciones necesarias en la implementación de la medicina P6. Conclusiones: Se identificó la aplicación de la tecnología blockchain como la capa de interoperabilidad necesaria entre sistemas de información hospitalarios, centros de investigación, pacientes, médicos y comunidad interesada; para generar un entorno confiable de flujo de información entre los diferentes actores que dinamice los procesos de investigación y atención en salud.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.