Recent Submissions

  • Artificial neural network model to predict student performance using nonpersonal information

    Chavez, Heyul; Chavez-Arias, Bill; Contreras-Rosas, Sebastian; Alvarez-Rodríguez, Jose María; Raymundo, Carlos (Frontiers Media S.A., 2023-02-09)
    In recent years, artificial intelligence has played an important role in education, wherein one of the most commonly used applications is forecasting students’ academic performance based on personal information such as social status, income, address, etc. This study proposes and develops an artificial neural network model capable of determining whether a student will pass a certain class without using personal or sensitive information that may compromise student privacy. For model training, we used information regarding 32,000 students collected from The Open University of the United Kingdom, such as number of times they took the course, average number of evaluations, course pass rate, average use of virtual materials per date and number of clicks in virtual classrooms. Attributes selected for the model are as follows: 93.81% accuracy, 94.15% precision, 95.13% recall, and 94.64% F1-score. These results will help the student authorities to take measures to avoid withdrawal and underachievement.
    Acceso abierto
  • Design of a control and monitoring system to reduce traffic accidents due to drowsiness through image processing

    Eraldo, Bruno; Quispe, Grimaldo; Chavez-Arias, Heyul; Raymundo-Ibanez, Carlos; Dominguez, Francisco (Institute of Electrical and Electronics Engineers Inc., 2019-11-01)
    It is known that 33% of traffic accidents worldwide are caused by drunk driving or drowsiness [1] [2], so a drowsiness level detection system that integrates image processing was developed with the use of Raspberry Pi3 with the OpenCV library; and sensors such as MQ-3 that measures the percentage of alcohol and the S9 sensor that measures the heart rate. In addition, it has an alert system and as an interface for the visualization of the data measured by the sensors a touch screen. With the image processing technique, facial expressions are analyzed, while physiological behaviors such as heart rate and alcohol percentage are measured with the sensors. In image test training you get an accuracy of x in a response time of x seconds. On the other hand, the evaluation of the operation of the sensors in 90% effective. So the method developed is effective and feasible.
    Acceso restringido temporalmente
  • Design of an unmanned aerial system for the detection of dangerous areas during fires

    Daviran, Richard; Quispe, Grimaldo; Chavez-Arias, Heyul; Raymundo-Ibanez, Carlos; Dominguez, Francisco (Institute of Electrical and Electronics Engineers Inc., 2019-11-01)
    This article presents the design of an unmanned aerial vehicle manufactured in aramid, through the use of sensors and actuators for flight stabilization, capturing the images through a thermal imager and its wireless transmission for ground processing for application in the social security area used in fire accidents. The work shows that it is feasible to use the aramid material for the construction of the prototype, since it is a high temperature resistant material, also the integration of neural networks for semi-automatic flight control. The results of this research will serve to develop more advanced control devices, with simple components and controls so that people with technological limitations can use it, so that they can save lives in danger, that of their colleagues or themselves.
    Acceso restringido temporalmente
  • Mobile Robot for the Spraying of Corn Crops with autonomous navigation camera for the Plains of the Andes

    Carbajal, Jhony; Quispe, Grimaldo; Chavez-Arias, Heyul; Raymundo-Ibanez, Carlos; Dominguez, Francisco (Institute of Electrical and Electronics Engineers Inc., 2019-11-01)
    The incidence of the disease in horticultural crops is one of the important problems that affect the production of fruits, vegetables and flowers. Regular monitoring of crops for early diagnosis and treatment with pesticides or removal of the affected crop is part of the solution to minimize crop loss. The monitoring of crops by human labor is expensive, time consuming, prone to errors due to insufficient knowledge of the disease and highly repetitive at different stages of crop growth. These needs have motivated to design the mobile robot with vision sensors for navigation through the field. The robot has been designed in the Autodesk Inventor software. Programming for navigation is done in the Arduino Mega 2560 tool. Image capture has been performed using the RGB camera. Image processing for the identification of the disease and its representation in a graphical user interface has been performed using an algorithm in MATLAB R2018B that interacts with the Arduino tool through a communication bus. The system developed consists of the design of a prototype that uses simple and cost effective equipment such as Raspberry Pi, RGB camera, two motors and sensors that allow the autonomous fumigation of corn crops.
    Acceso restringido temporalmente