Recognition of the driving style in vehicle drivers

Authors: J Cordero, J Aguilar, K Aguilar, D Chávez, E Puerto

Abstract:

This paper presents three different approaches to recognize driving style based on a hierarchical-model. Specifically, it proposes a hierarchical model for the recognition of the driving style for advanced driver-assistance systems (ADAS) for vehicles. This hierarchical model for the recognition of the style of the car driving considers three aspects: the driver emotions, the driver state, and finally, the driving style itself. In this way, the proposed hierarchical pattern is composed of three levels of descriptors/features, one to recognize the emotional states, another to recognize the driver state, and the last one to recognize the driving style. Each level has a set of descriptors, which can be sensed in a real context. Finally, the paper presents three driving style recognition algorithms based on different paradigms. One is based on fuzzy logic, another is based on chronicles (a temporal logic paradigm), and the last is based on an algorithm that uses the idea of the recognition process of the neocortex, called Ar2p (Algoritmo Recursivo de Reconocimiento de Patrones, for its acronym in Spanish). In the paper, these approaches are compared using real datasets, using different metrics of interest in the context of the Internet of the Things, in order to determine their capabilities of reasoning, adaptation, and the communication of information. In general, the initial results are encouraging, specifically in the cases of chronicles and Ar2p, which give the best results..

Keywords: pattern recognition, driving style, intelligent techniques, advanced driver-assistance systems

Link: https://www.mdpi.com/1424-8220/20/9/2597/pdf?version=1588415475

Advanced Driver Assistance System for the drowsiness detection using facial landmarks

Authors: LDS Cueva, J Cordero

Abstract:

This paper presents the development of a solution to detect a driver's drowsiness in real time and issue alerts to avoid possible traffic accidents. In particular, an analysis of the methods used for the detection of drowsiness by computer vision is performed, focusing on the use of facial reference points. Distraction, drowsiness, tiredness, speeding and fatigue are the main causes of accidents and, precisely, advanced driver assistance systems ADAS help reduce these serious human errors.

Keywords: Facial landmark, Computer vision, Drowsiness Detection

Link: https://ieeexplore.ieee.org/abstract/document/9140893 

Framework comparison of neural networks for automated counting of vehicles and pedestrians

 Authors: G Lalangui, J Cordero, O Ruiz-Vivanco, L Barba-Guamán, J Guerrero, ...

Abstract:

This paper presents a comparison of three neural network frameworks used to make volumetric counts in an automated and continuous way. In addition to cars, the application count pedestrians. Frameworks used are: SSD Mobilenet retrained, SSD Mobilenet pre-trained, and GoogLeNet pre-trained. The evaluation data set has a total duration of 60 minutes and comes from three different cameras. Images from the real deployment videos are included when training to enrich the detectable cases. Traditional detection models applied to vehicle counting systems usually provide high values for cars seen from the front. However, when the observer or camera is on the side, some models have lower detection and classification values. A new data set with fewer classes reach similar performance values as trained methods with default data sets. Results show that for the class cars, recall and precision values are 0.97 and 0.90 respectively in the best case, making use of a trained model by default, while for the class people the use of a re-trained model provides better results with precision and recall values of 1 and 0.82.

Keywords: Convolutional Neural Networks, learning transfer, automatic counter, classification, tracking, Single Shot Detector, Mobilenet

Link: https://ieeexplore.ieee.org/abstract/document/8781795

Approaches to identify student learning styles through emotions in a classroom

Sistema de Gestión de las emociones en un salón de clases inteligente basado en Modelos de confianza y reputación

Authors: J Cordero, J Aguilar, K Aguilar, M Martinez

Abstract:

In this article, we propose a model of trust and reputation, for the management of emotions in a Smart Classroom (SaCI). In general, a SaCI can model its different hardware and software components as agents. On the other hand, in intelligent environments modeled with agents, it is necessary to define the interaction mechanisms used in conversations between agents. In addition, the conversations should be enriched with models of trust and reputation of the agents involved in them, so that each agent can decide what information coming from the different agents, to consider when executing their decision-making processes. In particular, this paper defines models of trust and reputation for the SaCI agents. These models are used in a conversation that performs the management of emotions in SaCI, which allows to define the emotion that prevails at a given moment in it, which we call social emotion. The conversation is tested in several cases of study, in order to validate its ability to establish the social emotion of SaCI. The experimental results with the emotion management system based on models of trust and reputation, demonstrate that it is able to determine the social emotion in SaCI regardless of the characteristics of its context and learning from the behavior of agents, which gives it great robustness.

Keywords: trust model, reputation model, emotion management, social emotion, smart classroom, multiagent systems.

Link: https://www.proquest.com/openview/f74b61fb8680f9b19d07dd2417468366/1?pq-origsite=gscholar&cbl=1006393 

Intelligent Approaches to identify Student Learning Styles through Emotions in a Classroom

Enfoques Inteligentes para Identificar Estilos de Aprendizaje de los estudiantes mediante las Emociones en un salón de clases
Authors: J Cordero, J Aguilar, K Aguilar

Abstract:

In this article, a hierarchical pattern is proposed to identify the learning style of students in a classroom, which is composed of two levels, one to recognize the emotional state, and another to identify the learning style. Each level is defined by different types of descriptors, which are perceived from a multimodal approach. In addition, using the hierarchical pattern, two approaches are analyzed to model the learning style, which can be visual, auditory, reading/writing, kinesthetic. One of the approaches is based on fuzzy logic, and another based on chronicles, which exploit the idea of recursion and learning in the recognition process. Finally, considering the dynamic environment of a classroom, the approaches are compared, in terms of their abilities to learn and to determine the learning styles; and to communicate that information clearly in a smart classroom, based on the recognized emotions.

Keywords: Hierarchical patterns, learning style, emotion recognition, fuzzy logic, chronicles, dynamic pattern recognition.

Link: https://www.proquest.com/openview/6cd1e500aef16382c3c439403a9a06c1/1?pq-origsite=gscholar&cbl=1006393