Ingeniería y Ciencia
Ingeniería y Ciencia is an open-access biannual scientific journal that publishes articles in the fields of Basic Science and Engineering.
- Lie Algebra Representation, Conservation Laws and Some Invariant Solutions for a Generalized Emden-Fowler Equationpor Gabriel Ignacio Loaiza Ossa el diciembre 1, 2021 a las 5:00 am
All generators of the optimal algebra associated with a generalization of the Endem-Fowler equation are showed; some of them allow to give invariant solutions. Variational symmetries and the respective conservation laws are also showed. Finally, a representation of Lie symmetry algebra is showed by groups of matrices.
- A Low-Cost Raspberry Pi-based System for Facial Recognitionpor Cristian Miranda Orostegui el diciembre 1, 2021 a las 5:00 am
Deep learning has become increasingly popular and widely applied to computer vision systems. Over the years, researchers have developed various deep learning architectures to solve different kinds of problems. However, these networks are power-hungry and require high-performance computing (i.e., GPU, TPU, etc.) to run appropriately. Moving computation to the cloud may result in traffic, latency, and privacy issues. Edge computing can solve these challenges by moving the computing closer to the edge where the data is generated. One major challenge is to fit the high resource demands of deep learning in less powerful edge computing devices. In this research, we present an implementation of an embedded facial recognition system on a low cost Raspberry Pi, which is based on the FaceNet architecture. For this implementation it was required the development of a library in C++, which allows the deployment of the inference of the Neural Network Architecture. The system had an accuracy and precision of 77.38% and 81.25%, respectively. The time of execution of the program is 11 seconds and it consumes 46 [kB] of RAM. The resulting system could be utilized as a stand-alone access control system. The implemented model and library are released at https://github.com/cristianMiranda-Oro/FaceNet_EmbeddedSystem
- Determinants of New Housing Prices in Bogotá for 2019: an Approach Through a Semiparametric Spatial Regression Modelpor Jurgen Toloza-Delgado el diciembre 1, 2021 a las 5:00 am
This document uses the recent advances in the field of spatial econometrics to develop a semi-parametric regression model that allows the inclusion of non-linearities and the modeling of spatial heterogeneity through atwo-dimensional function that depends on geographic coordinates. The methodology is applied in a hedonic model for the price of new housing in Bogotá where a remarkable fit is obtained, in terms of the mean squareerror and the R2. The empirical result shows that the housing delivery condition, stratum, and construction state affect the price in a linear way, while the area, and the distances to parks, roads and Transmilenio stations present non-linear results, additionaly, it was possible to model the spatial trend that represents the location on the value of the house where an increase is appreciated towards the northeast of the city. Thus, it is concluded that the estimated model allows the relationship between the explanatory variables and the dependent variable to be measured flexibly, establishing itself as a good alternative to understand the formation of prices in the real estate market.
- A Generalized of Sλ-I-Convergence of Complex Uncertain Double Sequencespor Carlos Granados el diciembre 1, 2021 a las 5:00 am
In this paper, we introduce the λI2 -statistically convergence sequence concepts which are namely λI2 -statistically convergence almost surely (Sλ(I2) a.s.), λI2 -statistically convergence in measure, λI2 -statisticallyconvergence in mean, λI2 -statistically convergence in distribution and λI2 -statistically convergence uniformly almost surely (Sλ(I2) u.a.s.). Additionally, decomposition theorems and relationships among them are presented, further, when reciprocal of one theorem is not satisfied, an counterexample is shown to support the result.
- Deep Learning for Forecast Scales to Prescribe Patients at Risk of Gastrointestinal Bleedingpor Carlos Calderón-Vargas el diciembre 1, 2021 a las 5:00 am
The evolution of medicine in current times has gone hand in hand with technology where more and more solutions are implemented; those supporting certain medical procedures to serve as base in the field of medical professionals. The process of analyzing data has become an essential resource in the practice of any profession; currently, in hospitals, more specifically in the university hospital La Samaritana. No tool allows the supporting of diagnosis to determine the supply or no, proton pump inhibitors, therefore we have developed an app using a machine learning model, based on decision trees through the weka application, which, after analyzing the data collected, allows the doctor to count with a tool to support this procedure. We hope that with this, doctors can perform an effective analysis before prescribing or not prescribing PPIs.