Browsing by Author "Sanchez, Sergio"

Now showing 1 - 6 of 6
  • Thumbnail Image
    Item
    Open Access
    A review: Comparison of performance metrics of pretrained models for object detection using the TensorFlow framework
    (2020) Sanchez, Sergio
    Advances in parallel computing, GPU technology and deep learning facilitate the tools for processing complex images. The purpose of this research was focused on a review of the state of the art, related to the performance of pre-trained models for the detection of objects in order to make a comparison of these algorithms in terms of reliability, ac- curacy, time processed and Problems detected The consulted models are based on the Python programming language, the use of libraries based on TensorFlow, OpenCv and free image databases (Microsoft COCO and PASCAL VOC 2007/2012). These systems are not only focused on the recognition and classification of the objects in the images, but also on the location of the objects within it, drawing a bounding box around the appropriate way. For this research, different pre-trained models were re- viewed for the detection of objects such as R-CNN, R-FCN, SSD (single- shot multibox) and YOLO (You Only Look Once), with different extractors of characteristics such as VGG16, ResNet, Inception, MobileNet. As a result, it is not prudent to make direct and parallel analyzes between the different architecture and models, because each case has a particular solution for each problem, the purpose of this research is to generate an approximate notion of the experiments that have been carried out and conceive a starting point in the use that they are intended to give.
  • Thumbnail Image
    Item
    Open Access
    Artificial intelligence model for the prediction of malignant tumors using a set of medical images from mammography studies
    (2021) Morales, Alex; Sanchez, Sergio
    Currently, the diagnosis of tumors and malignant cells through imaging studies is a great challenge for expert medical personnel, due to the complexity of achieving an early prediction of cancer cells, which would allow to accelerate early medical treatments. Today, technologies have become a fundamental ally for the health sector, specifically the area of artificial intelligence, which has permeated many disciplines, generating important advances. Advances in parallel computing, GPU technology, and deep learning have made real-time image processing easier. The main objective of this esearch was to generate a deep learning model for the prediction of malignant cells in medical images of diagnosed mammograms. Using the previously trained model based on Faster R-CNN, with the ResNet function extractor. This model works in the Python programming language, using the Tensorflow framework and the OpenCv library. The algorithms were previously trained through the DDSM and MIAS open medical image databases, published on the web. This model not only focuses on recognizing and classifying malignant cells in the image, but also on the location of objects within it, appropriately drawing a bounding box. One of the latent challenges of these models since their inception has been the consumption of computing, but today they have been optimized so much that they allow freezing the pretrained models by loading them in the memory of the devices, managing to use them in computers without GPUs. As a result, it was found that the Faster R-CNN method with the Resnet101 extractor offers great advantages of precision and speed when it comes to detecting malignant tumors, studies that can serve as a great contribution to the bets of this algorithm in the health sector.
  • Thumbnail Image
    Item
    Open Access
    Design of a library using Matlab software for modeling and simulation of parabolic cylindrical solar collectors (CCP)
    (2020) Sanchez, Sergio
    Much of the energy available to the earth comes from the sun, it is the largestsource of radiation, emitting approximately 1353 W/m2 of energy into the Earth's atmosphere, in the form of lectromagnetic waves, with wavelengths (λ) between 0,3 and 3 μm. Within this spectrum we find the following radiations: Gamma (1%), Ultra violet (4%), Luminous (49%) and Infrared (46%). Only 51% of the solar radiation that enters the atmosphere reaches the earth's surface. This radiation represents a main source for renewable energy, presenting great applicability in solar thermal energy and specifically in the use of parabolic cylindrical solar collectors; that take advantage of this radiation to raise the temperature of a fluid, located in a receiving tube. The great problem of these systems is to generate a good design, which allows to reach high temperatures and good yields, therefore, many investigations have generated multiple design software, which mitigates the margin of error, but generally this software are limited; With licenses, they are complex and do not specify all the features for processing. The main objective of this research is an open source library that allows obtaining the highest efficiency of parabolic cylindrical collectors, based on the theoretical references Duffie, Beckman and Kalogirou. For this, the Matlab software and the Soltrace tool were taken into account, in order to validate the sizing and optical, thermal, geometric and global performance. Within the results, the maximum concentration ratio of the parabola is checked, which is obtained when the edge angle is 90 °. A functional library can be generated, where multiple measurements and shapes of the parabola were simulated, obtaining the highest overall performance, when the focal length is equal to the maximum height of the parabola, obtaining a performance of 62.64%.
  • Thumbnail Image
    Item
    Open Access
    Design of a telemedicine system for the provision of primary health care (PHC) services
    (2021) Morales, Alex; Sanchez, Sergio
    Currently, technological progress has allowed health-related issues to be worked on collaboratively, expanding their learning, managing to provide health services in remote places, guaranteeing one of the fundamental rights of every human being, among these technological advances are Telemedicine stands out, which has been playing a leading role especially in these times of pandemic. For this reason, the objective of this research is to design an information system that integrates multiple technologies to support the provision of primary health care services. The research is descriptive and technological development in scope. As a final result, block diagrams and flow diagrams were obtained to represent the set of technologies to be used and the information data flow of the proposed system. It is concluded that the proposed system would facilitate the provision of health services in areas with or without internet connectivity, as well as support decision-making by executives of health organizations, in addition, telemedicine is a new technological trend for what projects like this allow Colombia to be at the forefront in health and technology issues.
  • Thumbnail Image
    Item
    Open Access
    Development of a prototype of an electronic module that allows to calculate the frequency of spawning in laying hens
    (2019) Sanchez, Sergio
    Poultry farming is an industry recognized worldwide, being one of the main activities in different countries. From the national level, poultry farming is a source of income dedicated to the production of eggs and poultry meat, which has had a constant growth since the mid-twentieth century. This market in Colombia is one of the few economic sectors with permanent growth, this is evidenced by the increase in the percapita figures for this type of product. Nowadays in the market there is no evidence of alow cost system that allows to measure the hens' position in real time, this necessity being the main objective to develop an electronic module that allows to calculate the frequency of spawning in laying hens, with the purpose that this information can be used by poultry farmers in order to determine what food treatments and environmental conditions improve egg productivity. The materials used for the prototype were; a module cell (independent cage for each bird), an Arduino UNO card, infrared proximity sensor, 12x2 LCD display, MicroSD card module and an SD memory. This investigation is framed in a technological development of experimental type, for the construction of the prototype 3 stages were taken into account; prototype design and its characteristics, final assembly of the prototype and tests and results. In the results found there is evidence of a versatile tool that allows to inform in real time in a graphic way the postures. The tests carried out demonstrate the potential of a low- cost, lightweight and state-of-the-art prototype.
  • Thumbnail Image
    Item
    Open Access
    Use of ICT Tools using the PBL Methodology as a Student Learning Strategy
    (2019) Sanchez, Sergio
    The community of Altos de la Sabana is a population composed of families of limited economic resources and victims of the internal armed conflict in Sucre, located in low-income housing. In this urbanization is the Institution of Higher Education of the Holy Shroud. Given that at present it does not have technological and innovative tools for academic use, information provided by the rector and the academic coordinator of this institution, as well as being considered as a vulnerable community by the national government, which gives them a priority position when implementing educational and social projects; The main objective of this project is to encourage the students of the secondary school of the institution to use technological tools to solve problems in their environment. This research has a quantitative approach and the design of the research focuses on field research and with a pre-experimental method. For the execution of this project, 3 moments were concentrated; initially, an initial test was carried out to validate knowledge in technological tools and the self-directed profile, then some training was carried out using the problem-based methodology and finally a final evaluation to measure acquired competences. The results of the post-test, in contrast to the initial test, revealed that 65% of students in grade 11 of the institution demonstrate an empowerment in the use of ICT tools and concepts in the field of basic analog-digital electronics. This is how ICTs are based on the education system, as they are facilitating tools in the teaching-learning process.