Pasar al contenido principal

Resultados relacionados

Resultados totales (Incluyendo duplicados): 2
Encontrada(s) 1 página(s)

Repositorio Digital UPCT
Publicación Artículo científico (JournalArticle)

Pedestrian characterisation in urban environments combining WiFi and AI

  • Guillén Pérez, Antonio
  • Cano Baños, María Dolores
Knowing how many people there are in a given scenario offers new possibilities for the development of intelligent services. With this goal in mind, the use of sensors and Radio Frequency (RF) signals is becoming an interesting alternative to other classic methods such as image processing for counting people. In this paper we present a novel method for counting, characterizing, and localizing pedestrians in outdoor environments, called iPCW (intelligent Pedestrian Characterization using WiFi). iPCW is a passive, device-based sensor system that incorporates artificial intelligence techniques, more specifically, machine learning techniques. Performance evaluation using intensive computer simulations shows that iPCW achieves excellent results, with moving and static pedestrian detection accuracy above 98% and positioning accuracy above 92%., This work was supported by DGT Ministerio del Interior (Spain) under Project SPIP2017-02230; by the AEI/FEDER EU project grant TEC2016-76465-C2-1-R (AIM), and by a pre-doctoral grant 20740/FPI/18. Fundación Séneca. Región de Murcia (Spain).
Repositorio Digital UPCT
Publicación Artículo científico (JournalArticle)

Intelligent IoT systems for traffic management: A practical application

  • Guillén Pérez, Antonio
  • Cano Baños, María Dolores
The incorporation of Artificial Intelligence algorithms in Intelligent Transportation Systems gives rise to new opportunities for a more sustainable urban mobility. However, one of the main challenges is to decide when and where these techniques should be applied; several options appear, such as cloud computing, fog computing, edge computing, or even edge devices. In this paper, an Internet of Things-based solution for smart traffic management is presented. Using the lightweight Random Early Detection for Vehicles Dynamic mechanism as a basis, we optimize using evolutionary algorithms. Random Early Detection for Vehicles Dynamic can be applied in signaled intersections to proactively detect incipient congestion and set the best cycle and phases of traffic lights. Then, the authors demonstrate that once Random Early Detection for Vehicles Dynamic has been appropriately optimised offline, it can be later used in unknown traffic scenarios without the burden of applying Artificial Intelligence in constrained Internet of Things devices. The performance of this mechanism is widely tested with the SUMO simulation tool. Results show that this improved version, called iREDVD, notably reduces the vehicles’ waiting time, average trip time, fuel consumption, and emission of particles and gaseous pollutants compared with other proposals., This work was supported by the AEI/FEDER, UE project grant TEC2016-76465-C2-1-R (AIM), by DGT-Ministerio delInterior, project grant SPIP2017-02230 (STREET), and by a predoctoral contract for the formation of the research personnel financed by Consejería de Empleo, Universidades, Empresay Medio Ambiente of the CARM, through the FundaciónSéneca - Agencia de Ciencia y Tecnología of the Region of Murcia, Spain.