The work ‘DruBot: Robotic prototype for authentication and comparison of facial proportions for assistance control and impersonation detection in evaluations’ describes the development of the robotic prototype called DruBot that seeks to recognize the faces of the persons who join to a classroom specific, a private area or an examination, comparing them with a database for eachcase (to distinguish them from the characteristics extracted from the photo of the university identification and the frames obtained of the video of welcome of every student) and to determine if the image of the person which camera is capturing has or hasn’t access to the area, issuing a different sign if his or her access is allowed or not. We apply technologies of artificial vision (Haar cascade for the detection of faces in the whole image captured by camera in real time and Face Landmarks to find the key ...

In recent decades, the number of traffic accidents due to fatigue or drowsiness of the driver has caused significant human and material losses. At the same time, the sale in the vehicle fleet has been massified, which indicates thatpossibly in the following years, if the pertinent measures are not taken to detect fatigue, there will be an increase in automobile accidents. Therefore, in this research study, the development of a fatigue detection system in drivers that allows alerting about their status while driving using artificial vision and machine learning techniques is proposed. The techniques of these two fields of study are intercepted to generate supervised models with high performance when classifying the state of fatigue in drivers. In this study, a dataset of frontal images focusing on the physiological characteristics of the eyes was used; obtaining promising preliminary resul...

La renovación de equipos móviles en clientes corporativos es un factor clave en la planificación estratégica de las empresas de telecomunicaciones. Sin embargo, identificar qué clientes tienen mayor propensión a renovar sus dispositivos sigue siendo un desafío. En este estudio, se compararon diferentes modelos de Machine Learning para estimar la probabilidad de renovación de equipos móviles en clientes corporativos. Por ello, se recopilaron diversas fuentes de datos para analizar el comportamiento de los clientes incluyendo el historial de líneas móviles, patrones de consumo, penalizaciones y otros factores determinantes en la decisión de renovación. Luego, se entrenaron distintos algoritmos de aprendizaje supervisado como Logistic Regression, Decision Trees, Random Forest, XGBoost, LightGBM y CatBoost. Dado el desbalance de la data, se seleccionó la métrica AUC como crite...

The work ‘DruBot: Robotic prototype for authentication and comparison of facial proportions for assistance control and impersonation detection in evaluations’ describes the development of the robotic prototype called DruBot that seeks to recognize the faces of the persons who join to a classroom specific, a private area or an examination, comparing them with a database for each case (to distinguish them from the characteristics extracted from the photo of the university identification and the frames obtained of the video of welcome of every student) and to determine if the image of the person which camera is capturing has or hasn’t access to the area, issuing a different sign if his or her access is allowed or not. We apply technologies of artificial vision (Haar cascade for the detection of faces in the whole image captured by camera in real time and Face Landmarks to find the key...

The work ‘DruBot: Robotic prototype for authentication and comparison of facial proportions for assistance control and impersonation detection in evaluations’ describes the development of the robotic prototype called DruBot that seeks to recognize the faces of the persons who join to a classroom specific, a private area or an examination, comparing them with a database for each case (to distinguish them from the characteristics extracted from the photo of the university identification and the frames obtained of the video of welcome of every student) and to determine if the image of the person which camera is capturing has or hasn’t access to the area, issuing a different sign if his or her access is allowed or not. We apply technologies of artificial vision (Haar cascade for the detection of faces in the whole image captured by camera in real time and Face Landmarks to find the key...