WO2017164721A1 - System for supervising and controlling traffic - Google Patents

System for supervising and controlling traffic Download PDF

Info

Publication number
WO2017164721A1
WO2017164721A1 PCT/MA2016/000008 MA2016000008W WO2017164721A1 WO 2017164721 A1 WO2017164721 A1 WO 2017164721A1 MA 2016000008 W MA2016000008 W MA 2016000008W WO 2017164721 A1 WO2017164721 A1 WO 2017164721A1
Authority
WO
WIPO (PCT)
Prior art keywords
fuzzy
pheromone
traffic
gaussian
network
Prior art date
Application number
PCT/MA2016/000008
Other languages
French (fr)
Inventor
Azedine BOULMAKOUL
Lamia KARIM
Abdellah DALSSAOUI
Original Assignee
Boulmakoul Azedine
Karim Lamia
Dalssaoui Abdellah
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Boulmakoul Azedine, Karim Lamia, Dalssaoui Abdellah filed Critical Boulmakoul Azedine
Priority to PCT/MA2016/000008 priority Critical patent/WO2017164721A1/en
Publication of WO2017164721A1 publication Critical patent/WO2017164721A1/en

Links

Classifications

    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
    • G08G1/0108—Measuring and analyzing of parameters relative to traffic conditions based on the source of data
    • G08G1/0112—Measuring and analyzing of parameters relative to traffic conditions based on the source of data from the vehicle, e.g. floating car data [FCD]
    • G06Q50/40—
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
    • G08G1/0108—Measuring and analyzing of parameters relative to traffic conditions based on the source of data
    • G08G1/012—Measuring and analyzing of parameters relative to traffic conditions based on the source of data from other sources than vehicle or roadside beacons, e.g. mobile networks
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
    • G08G1/0125—Traffic data processing
    • G08G1/0129—Traffic data processing for creating historical data or processing based on historical data
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
    • G08G1/0125—Traffic data processing
    • G08G1/0133—Traffic data processing for classifying traffic situation
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
    • G08G1/0137—Measuring and analyzing of parameters relative to traffic conditions for specific applications
    • G08G1/0145—Measuring and analyzing of parameters relative to traffic conditions for specific applications for active traffic flow control
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/052—Detecting movement of traffic to be counted or controlled with provision for determining speed or overspeed
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/07—Controlling traffic signals
    • G08G1/08—Controlling traffic signals according to detected number or speed of vehicles
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A30/00—Adapting or protecting infrastructure or their operation
    • Y02A30/60—Planning or developing urban green infrastructure

Definitions

  • the present invention relates to an agile real-time intelligent management, monitoring and analytics system for urban traffic congestion based on the diffusion of fuzzy Gaussian e-pheromone and distributed wireless virtual sensor infrastructures.
  • the present invention relates to four essential functional objectives for the intelligent management of urban traffic. The first integrates a speed-sensitive vehicle collection process with detectable smartphone-GPS at crossings of certain virtual space zones relative to a section of the urban network. He associates Gaussian fuzzy variables with these speeds. The second provides a method of generating fuzzy urban traffic states based on an original calculation of the fuzzy Gaussian e-pheromone.
  • the third objective of the present invention relates to a symbolic control strategy for controlling intersections in order to reduce congestions hindering the normal behavior of the network.
  • the last objective is related to a process of information, visualization and data persistence in a cloud-NoSQL (big data) type ecosystem.
  • This invention is of interest to managers of urban transport networks in major cities, environmental monitoring agencies, smart cities project development agencies and all stakeholders in a traffic management project in an urban site.
  • Congestion of traffic in urban networks takes considerable forms and complex polymorphic sizes. Congestion phenomena are expensive and highly polluting. Public operators are eager to reduce the effect of congestions during peak hours in order to significantly reduce, if not totally, their impacts in cities. Congestion management methods are integrated into smart city projects where the use of connected objects and the Internet of Things are dominant. The use of intelligent systems and advanced wireless technology as well as the modeling of complex systems is still relevant in the field of urban traffic regulation. Technological advances in the field of large data analytics, cloud-based distributed processing, and new location-based service technologies and traffic data metrics are a great support for the management processes of the cloud. congestion. In recent years, a significant change has stimulated intelligent transportation systems. The advent of a new generation of sensors allows the collection of traffic data.
  • the invention US00531731 1A 05/1994 relates to a congestion monitoring system. It discloses a traffic congestion supervision system comprising infrared type monitoring units bolted to the sides of the bridges on a road network and allowing the emission of traffic congestion information.
  • the invention US005289183A 02/1994 proposes a system and a monitoring device and traffic management method. This invention generally relates to traffic monitoring and management systems. More particularly, it relates to a device and a method for the use of two components: a radio transceiver for accurately and automatically collecting vehicle traffic data when crossing a road, bridge, tunnel or other means. transport.
  • Invention US005917432A 06/1999 provides an intersection control or intelligent intersection traffic system that analyzes in real time traffic flows at existing intersections to determine whether lanes need to be added, extended, or disappeared. , if the geometry needs of the track need to be changed, and if the duration of the traffic signals has to be shortened or lengthened.
  • the invention US006577946B2 06/2003 relates to a system for collecting traffic data via cellular telephones, for intelligent transport systems.
  • the invention provides a system and method for controlling the flow of traffic. The locations are obtained and continuously updated from the cell phones of the vehicles. This information is processed and used as an input to intelligent transport systems, especially in real time for driver guidance and congestion management by intelligent traffic control systems.
  • the invention US00768531 1B2 03/2010 relates to a smart traffic geo reporter, it proposes a traffic reporter that gathers real time information on traffic conditions in a network and sends traffic reports for managers.
  • the traffic reporter analyzes the network and also collects information about the network of traffic managers and analyzers scattered throughout the network. These traffic reports provide real-time information about the state of the network to give managers more efficient, reliable and fast supervision.
  • Invention US007912629B2 03/201 1 relates to a method, a device and computer programs for aggregating traffic measurements from virtual travel lines and mobile phones equipped with GPS to simulate magnetic detection loops.
  • the device includes a processor that is able to determine when a specified measurement location is traversed and measure the data for a period of time.
  • the invention US008510025B2 08/2013 affects 3 a traffic data collection system comprising at least two nodes, and a central processing station.
  • the first node comprises a cellular communication module connected to a first processor.
  • the second node comprises a second network communication module and a detection module and a device connected to a second processor.
  • the invention US 20100100307A1 04/2010 relates to a traffic data collection process and a monitoring system that uses a plurality of GPS enabled on mobile devices to transmit in real time the direction of traffic and speed to a server. (less than 10 seconds of latency).
  • the server processes the information thereby reducing the computing load and power consumption of the mobile devices.
  • the system uses traffic pattern recognition software that accurately recognizes valid traffic data while filtering unwanted traffic data.
  • the invention US008849309B2 09/2014 relates to a method for providing transit time forecasts on the roads of a controlled road network. It includes the receipt of the transit time of a planned route calculated by a road traffic surveillance system for at least one road in the controlled road network; and correcting transit time received from the intended route based on information obtained from a cellular mobile communication network.
  • the invention MA 20150002 Al (MA 20150002 Al: Azedine Boulmakoul, and Lamia Karim: Device System and Method for monitoring customers in commercial spaces .Morganixie Office of Industrial and Commercial Property, 1/2015), describes a device, system and method for tracking the paths taken by customers in commercial spaces.
  • Boulmakoul A Sellam S: Boulmakoul A., Sellam S. (1993) Intelligent Intersection: Artificial Intelligence and Computer Vision Techniques for Automatic Incident Detection, in Artificial Intelligence in Traffic Engineering, pp. 189-200, 1993, VSP International Science Publisher, Zeist, The Netherlands .. 01/1993; VSP International Science Publisher, Zeist, the Netherlands.
  • Azedine Boulmakoul, Lamia Karim, Adil Elbouziri, and Ahmed Lbath A System Architecture for Heterogeneous Moving-Object Trajectory Metamodel Using Generic Sensors: Tracking Airport Security Case Study. IEEE Systems Journal 12/2013; PP (99): 1-9. DOI: 10.1 109 / JS YST.2013.2293837
  • GFN Gaussian Blur Number
  • ⁇ A parameter of approval of the e-pheromone. Corresponds to the operation of subtracting Gaussian fuzzy numbers.
  • ⁇ (1, T) ⁇ N (] t- T, t])
  • the low speeds generate a large quantity of the fuzzy e-pheromone, the high speeds do not leave enough trace of pheromone.
  • the virtual zones to be positioned on the road network generally correspond to the entry and / or exit sections of the traffic lights. These virtual markers interact with the passage of vehicles equipped with geolocation device in the vicinity of these virtual detection zones to calculate the fuzzy Gaussian e-pheromone.
  • the configuration of the virtual detection zones is carried out in the spatial database (geographical map of the urban road network).
  • the schematic description of the virtual detection zones is given in Figure 2.
  • Method 2 The process of calculating state variables and Gaussian e-pheromone fuzzy virtual detection areas
  • the same process provides the value which corresponds to the average speed observed on the virtual detection zone 1, at time t.
  • Method 3 Calculation scheme of deposition, dissipation and diffusion of the fuzzy Gaussian e-pheromone of a virtual detection zone
  • Each vehicle deposits a fuzzy quantity of the fuzzy Gaussian e-pheromone according to the following formula:
  • the aggregation of this quantity over the entire virtual detection zone is calculated as follows: Over the period The dissipation of the Gaussian e-pheromone fuzzy of a virtual detection zone
  • This broadcast expresses the distributed communication of the e-pheromone between the detection zones. It is given by the transition function of the diffusion of the fuzzy e-pheromone:
  • Method 4 Aggregation the Gaussian e-pheromone fuzzy virtual detection areas belonging to the same traffic artery of an urban network
  • the fuzzy Gaussian e-pheromone is quantified in each virtual detection zone associated with a road section of the network.
  • the aggregation of these quantities on an arterial route is also quantified by a Gaussian fuzzy number.
  • ⁇ be a route consisting of virtual detection zones belonging to the same artery A (a boulevard for example).
  • a route ⁇ is said to be congested if the value of its fuzzy Gaussian e-pheromone deposition is greater than a fuzzy Gaussian threshold value with confidence a.
  • the situation of congestion of the route is carried out according to the process defined below:
  • Method 6 Regulation by fuzzy symbolic commands of a route monitored by virtual detection zones belonging to the same traffic artery of an urban network
  • -It is a sorted list of routes in a state of fuzzy congestion from the initial sorted list
  • ⁇ ⁇ is highly fluid then activate the symbolic action on the ⁇ ⁇ intersection of the axis of the same direction of traffic as ⁇ ⁇ and to memorize the state of the crossroads of the moment H Fluid).
  • the cycle time is always greater than or equal to a limit value (normal controller cycle).
  • the present invention relates to an agile real-time hazy intelligent transport system for assisting with congestion management of urban site traffic.
  • the system enables Gaussian fuzzy e-pheromone to be generated on the arteries of the transport network by calculating fuzzy state variables of the traffic and exploiting the paradigm of intelligent organized structures of the ant type.
  • the dynamic model of congestions propagation is realized by an original algebraic structure of Gaussian fuzzy numbers, designed for this requirement and ensures the prediction of congestions on a short horizon.
  • the invention also proposes a symbolic traffic control process to contribute to the overall reduction of network congestion.
  • the proposed system involves a number of activities developed below:
  • the study perimeter namely: the transport network concerned, the routes of the network to be supervised, the regulatory system concerned, the period of time of collection.
  • This activity is materialized by a software component integrated in the overall system and putting in place the necessary elements to satisfy its objectives.
  • Activity 2 The elements introduced during activity 1 will be used to launch a method for calculating state variables based on velocities and the fuzzy Gaussian e-pheromone of the virtual detection zones. Microscopic simulation is envisaged to generate the vehicle data. This activity is supported by the instructions provided in Method 2 ( Figures 6-10).
  • Activity 3 In real time and over the slippery period of time (parameter to be set: 30 seconds for example), this activity concerns the procedures for calculating the deposition, dissipation and diffusion of the fuzzy Gaussian e-pheromone. a virtual detection zone. It proceeds according to the instructions formulated in Method 3 ( Figure 9).
  • Activity 4 This activity involves the process of aggregating the fuzzy Gaussian e-pheromone with virtual detection zones belonging to the same traffic artery of an urban network. It is performed according to the principles defined by Method 4 ( Figures 9, 12).
  • Activity 5 This activity develops fuzzy congestion detection procedures in the sense of the fuzzy Gaussian e-pheromone of a route. It is framed by method 5 ( Figure 8, 15).
  • Activity 6 This activity develops the regulation by fuzzy symbolic commands of a route monitored by virtual detection zones belonging to the same traffic artery of an urban network. It is performed according to the instructions of Method 6 ( Figures 12-14).
  • Activity 7 This is the activity of field deployment and real-time processes of activity 5, integration of software components for the implementation of the solution ( Figures 6-7).
  • Activity 8 Generation of results in the machine interface sense from the deployment of the tasks of activities 1-6. Persistence of results in json format for the Hadoop MongoDB ecosystem (Figure 11). Brief description of the figures
  • Figure 1 shows a Gaussian soft number
  • Figure 2 shows the association of virtual detection zones with the intersections of intersections of an urban network.
  • Figure 3 describes the communication architecture of the system. It highlights the central server vehicle communication devices (via GPRS-internet or proprietary network of the traffic control center of the city).
  • Figure 4 details an annotated network of virtual detection zones upstream / downstream of intersections.
  • Figure 5 develops the object data model of the proposed system.
  • this model are considered the elements of the road network, the virtual detection zones and the smart vehicles equipped with geolocation equipment and implementing the system (embedded part) proposed in the present invention as well as the strategies of calculation of the e-pheromone fuzzy.
  • Figure 6 depicts the component diagram of the proposed system.
  • Figure 7 shows the system deployment diagram and shows the devices involved in the solution.
  • Figure 8 illustrates the method of detecting vehicles in the virtual detection zone. It also shows the technique of calculating moving average vehicles for a period of time of 30 seconds.
  • Figure 9 illustrates the activities of generating the e-pheromone of a virtual detection zone.
  • Figure 10 illustrates the method of configuring the virtual detection zones, storage in the database and the activation of loading of these zones in the smart phones of the vehicles.
  • Figure 11 illustrates the overall synoptic of the global system and provides information on the Hadoop MongoDB data storage ecosystem.
  • Figure 12 illustrates an itinerant (network artery) marked by virtual detection zones.
  • Figure 13 shows the control strategy based on symolic commands.
  • Figure 14 illustrates the itineraries of an urban traffic network.
  • Figure 15 illustrates the pattern of detection and velocity calculation interactions.

Abstract

The innovative aspects of the present invention concern the proposal of an intelligent, fuzzy, real-time, agile transport method and system, for use in the management of traffic congestion in urban locations. The system enables the generation of the fuzzy Gaussian e-pheromone on the arteries of the transport network and achieves this through calculation of fuzzy state variables of the traffic and use of the swarm intelligence paradigm of intelligent organised structures. The dynamic model of the spread of congestion is produced by a novel calculation method using fuzzy Gaussian numbers, designed for this requirement, and ensures the prediction of congestion in the short term. The invention also proposes a method of symbolic traffic control in order to contribute to the overall reduction of congestion of the network. The fuzzy Gaussian e-pheromone states of the roads of the urban network are stored in the spatial real-time database for the purposes of viewing and analysing congestion. The present invention deploys a real-time distributed communication infrastructure in order to support the software components integrated into the proposed system. The invention takes advantage of spatial real-time database technologies and ubiquitous environment and geolocation technologies. This invention is of great interest to the process of improving traffic regulation and the strong demand for high added-value services for the sustainable development of smart cities.

Description

SYSTEME DE SUPERVISION ET DE CONTROLE DU TRAFIC  TRAFFIC SUPERVISION AND CONTROL SYSTEM
Domaine de l'invention Field of the invention
La présente invention concerne un système intelligent temps réel agile de gestion, de supervision et de l'analytique des congestions de trafic urbain fondé sur la diffusion de l'e-phéromone gaussienne floue et des infrastructures distribuées de capteurs virtuels sans fil. La présente invention concerne quatre objectifs fonctionnels essentiels pour la gestion intelligente du trafic urbain. Le premier intègre un processus de collecte de vitesses des véhicules équipés de smartphone-GPS détectables aux franchissements de certaines zones spatiales virtuelles relatives à un tronçon du réseau urbain. Il associe des variables floues gaussiennes à ces vitesses. Le second fournit une méthode de génération des états flous de trafic urbain sur la base d'un calcul original de l'e-phéromone gaussienne floue. Le troisième objectif de la présente invention concerne une stratégie de régulation symbolique pour contrôler les carrefours afin de réduire les congestions gênant le comportement normal du réseau. Enfin, le dernier objectif est lié à un processus d'information, de visualisation et de persistance des données dans un écosystème de type cloud-NoSQL (big data). Cette invention intéresse les gestionnaires des réseaux de transport urbain des grandes métropoles, les agences de surveillance de l'environnement, les agences de développement des projets villes intelligentes ainsi que toutes les parties prenantes dans un projet de gestion de trafic en site urbain. The present invention relates to an agile real-time intelligent management, monitoring and analytics system for urban traffic congestion based on the diffusion of fuzzy Gaussian e-pheromone and distributed wireless virtual sensor infrastructures. The present invention relates to four essential functional objectives for the intelligent management of urban traffic. The first integrates a speed-sensitive vehicle collection process with detectable smartphone-GPS at crossings of certain virtual space zones relative to a section of the urban network. He associates Gaussian fuzzy variables with these speeds. The second provides a method of generating fuzzy urban traffic states based on an original calculation of the fuzzy Gaussian e-pheromone. The third objective of the present invention relates to a symbolic control strategy for controlling intersections in order to reduce congestions hindering the normal behavior of the network. Finally, the last objective is related to a process of information, visualization and data persistence in a cloud-NoSQL (big data) type ecosystem. This invention is of interest to managers of urban transport networks in major cities, environmental monitoring agencies, smart cities project development agencies and all stakeholders in a traffic management project in an urban site.
Etat de la technique antérieure State of the art
La congestion du trafic dans les réseaux urbains prend des formes considérables et grandeurs polymorphes complexes. Les phénomènes de congestion sont coûteux et très polluant. Les opérateurs publics sont désireux de réduire l'effet des congestions pendant les heures de pointe afin de réduire de manière significative, voire totalement, leurs impacts dans les villes. Les méthodes de gestion de la congestion sont intégrées dans les projets villes intelligentes où l'utilisation d'objets connectés et de l'internet des objets sont dominants. L'utilisation des systèmes intelligents et de la technologie sans fil avancée ainsi que la modélisation des systèmes complexes sont toujours d'actualité dans le domaine de la régulation du trafic urbain. Les progrès technologiques dans le domaine des grandes analyses de données, des traitements distribués sur le cloud ainsi que les nouvelles technologies de services basées sur la localisation et la mesure des données de la circulation sont d'un grand soutien pour les processus de gestion de la congestion. Ces dernières années, un changement important a stimulé les systèmes de transport intelligents. L'avènement d'une nouvelle génération de capteurs permet la collecte des données de trafic. La diversité et la disponibilité d'un grand nombre d'information ont déclenché une grande mutation dans le déroulement des projets de développement. La première génération des systèmes de transport intelligents est remplacée par les systèmes de transport intelligents pilotés par les données et les multi-services, i.e. des systèmes multi- objectifs, multi-capteurs, et multi-algorithmes intelligents conduisant à optimiser les performances. Le domaine de l'ingénierie du trafic et de la régulation des réseaux de transport a connu un grand essor durant ces dernières années. Certaines de ces inventions concernant la problématique des congestions sont paraphrasées ci-dessous :  Congestion of traffic in urban networks takes considerable forms and complex polymorphic sizes. Congestion phenomena are expensive and highly polluting. Public operators are eager to reduce the effect of congestions during peak hours in order to significantly reduce, if not totally, their impacts in cities. Congestion management methods are integrated into smart city projects where the use of connected objects and the Internet of Things are dominant. The use of intelligent systems and advanced wireless technology as well as the modeling of complex systems is still relevant in the field of urban traffic regulation. Technological advances in the field of large data analytics, cloud-based distributed processing, and new location-based service technologies and traffic data metrics are a great support for the management processes of the cloud. congestion. In recent years, a significant change has stimulated intelligent transportation systems. The advent of a new generation of sensors allows the collection of traffic data. The diversity and availability of a large amount of information has triggered a major shift in the development agenda. The first generation of intelligent transport systems is being replaced by data-driven, multi-service intelligent transport systems, i.e. intelligent multi-objective, multi-sensor, and multi-algorithm systems that optimize performance. The field of traffic engineering and the regulation of transport networks has grown considerably in recent years. Some of these inventions concerning the problem of congestions are paraphrased below:
L'invention US00531731 1A 05/1994 concerne un système de surveillance des congestions. Elle décline un système de supervision de congestion de trafic comprenant des unités de surveillance de type infrarouge boulonnées sur les côtés des ponts sur un réseau routier et permettant l'émission des informations de congestion du trafic. L'invention US005289183A 02/1994 propose un système et un dispositif de surveillance et méthode de gestion de trafic. Cette invention concerne en général des systèmes de surveillance et de gestion du trafic. Plus particulièrement, elle concerne un dispositif et un procédé pour l'utilisation de deux composants : un émetteur-récepteur radio pour recueillir avec précision et automatiquement les données de la circulation des véhicules lorsqu'ils traversent une route, un pont, tunnel ou autre moyen de transport. L'invention US005917432A 06/1999 propose un système de trafic de commande d'intersection ou d'une intersection intelligente qui analyse en temps réel des flux de circulation aux intersections existantes afin de déterminer si des voies doivent être ajoutées, allongées, ou doivent disparaître, si les besoins de la géométrie de la voie doivent être modifiés, et si la durée des signaux tricolores doit être raccourcie ou rallongée. L'invention US006577946B2 06/2003 concerne un système de collecte des données trafic via les téléphones cellulaires, pour les systèmes de transport intelligents. L'invention propose un système et un procédé pour contrôler l'écoulement du trafic. Les localisations sont obtenues et continuellement mis à jour à partir à partir des téléphones cellulaires des véhicules. Ces informations sont traitées et utilisées comme une entrée des systèmes de transport intelligents, en particulier en temps réel pour le guidage des conducteurs et pour la gestion des congestions véhiculaires par les systèmes intelligents de contrôle du trafic. L'invention US00768531 1B2 03/2010 concerne un Géo reporter de trafic intelligent, elle propose un reporter de la circulation qui rassemble des informations en temps réel sur les conditions de circulation dans un réseau et envoie des rapports de trafic pour les gestionnaires. Le reporter de la circulation analyse le réseau et recueille également des informations sur le réseau des gestionnaires de trafic et analyseurs dispersés dans tout le réseau. Ces rapports de trafic fournissent des informations en temps réel sur l'état du réseau pour permettre aux gestionnaires une supervision plus efficace, fiable et rapide. L'invention US007912629B2 03/201 1 concerne un procédé, un dispositif et des programmes informatiques pour l'agrégation des mesures de trafic à partir des lignes de voyage virtuelles et des téléphones mobiles équipés de GPS pour simuler les boucles magnétiques de détection. Le dispositif comprend un processeur qui est capable de déterminer quand un emplacement de mesure spécifié est traversé et de mesurer les données pour une période de temps. L'invention US008510025B2 08/2013 concerne 3un système de collecte de données de trafic comprenant au moins deux nœuds, et un poste de traitement central. Le premier nœud comprend un module de communication cellulaire connecté à un premier processeur. Le deuxième nœud comprend un second module de communication de réseau et un module de détection et un dispositif connecté à un deuxième processeur. L'invention US 20100100307A1 04/2010, concerne un processus de collecte des données de trafic et un système de surveillance qui utilise une pluralité de GPS activés sur des appareils mobiles pour transmettre en temps réel le sens de la circulation et la vitesse à un serveur (inférieur à 10 secondes de latence). Le serveur traite l'information en réduisant ainsi la charge et la consommation électrique de calcul des appareils mobiles. Le système utilise un logiciel de reconnaissance de formes de trafic qui reconnaît avec précision les données de trafic valides tout en filtrant les données de trafic indésirables. L'invention US008849309B2 09/2014, concerne un procédé pour fournir des prévisions de temps de transit sur les routes d'un réseau routier contrôlé. Il comprend la réception du temps de transit d'une route prévue calculé par un système de surveillance du trafic routier à l'égard d'au moins une route du réseau routier contrôlé; et la correction de temps de transit reçue de la route prévue sur la base des informations obtenues à partir d'un réseau de communication mobile cellulaire. L'invention MA 20150002 Al (MA 20150002 Al : Azedine Boulmakoul, et Lamia Karim: Dispositif Système et Procédé de suivi des clients dans les espaces commerciaux. OMPIC Office Marocain de la Propriété Industrielle et Commerciale, 1/2015), décrit un dispositif, système et procédé de suivi des chemins pris par les clients dans les espaces commerciaux. Ce dispositif pourra être exploité pour la génération et le stockage des trajectoires des objets mobiles telles qu'elles sont définies dans cette invention. Certains travaux de recherches sous forme de publications internationales, développés par l'équipe du Professeur A. Boulmakoul concernent les systèmes de transport intelligents temps réel et qui ne sont pas reproduits ou réutilisés dans la présente invention. Ces travaux contribuent à la résolution des problèmes de transport et ne concernent pas l'invention qui sera développée par la suite. Les résultats de ces travaux scientifiques ne concernent pas les revendications défendus dans la présente invention. La liste non exhaustive des contributions scientifiques est donnée ci-après : The invention US00531731 1A 05/1994 relates to a congestion monitoring system. It discloses a traffic congestion supervision system comprising infrared type monitoring units bolted to the sides of the bridges on a road network and allowing the emission of traffic congestion information. The invention US005289183A 02/1994 proposes a system and a monitoring device and traffic management method. This invention generally relates to traffic monitoring and management systems. More particularly, it relates to a device and a method for the use of two components: a radio transceiver for accurately and automatically collecting vehicle traffic data when crossing a road, bridge, tunnel or other means. transport. Invention US005917432A 06/1999 provides an intersection control or intelligent intersection traffic system that analyzes in real time traffic flows at existing intersections to determine whether lanes need to be added, extended, or disappeared. , if the geometry needs of the track need to be changed, and if the duration of the traffic signals has to be shortened or lengthened. The invention US006577946B2 06/2003 relates to a system for collecting traffic data via cellular telephones, for intelligent transport systems. The invention provides a system and method for controlling the flow of traffic. The locations are obtained and continuously updated from the cell phones of the vehicles. This information is processed and used as an input to intelligent transport systems, especially in real time for driver guidance and congestion management by intelligent traffic control systems. The invention US00768531 1B2 03/2010 relates to a smart traffic geo reporter, it proposes a traffic reporter that gathers real time information on traffic conditions in a network and sends traffic reports for managers. The traffic reporter analyzes the network and also collects information about the network of traffic managers and analyzers scattered throughout the network. These traffic reports provide real-time information about the state of the network to give managers more efficient, reliable and fast supervision. Invention US007912629B2 03/201 1 relates to a method, a device and computer programs for aggregating traffic measurements from virtual travel lines and mobile phones equipped with GPS to simulate magnetic detection loops. The device includes a processor that is able to determine when a specified measurement location is traversed and measure the data for a period of time. The invention US008510025B2 08/2013 affects 3 a traffic data collection system comprising at least two nodes, and a central processing station. The first node comprises a cellular communication module connected to a first processor. The second node comprises a second network communication module and a detection module and a device connected to a second processor. The invention US 20100100307A1 04/2010, relates to a traffic data collection process and a monitoring system that uses a plurality of GPS enabled on mobile devices to transmit in real time the direction of traffic and speed to a server. (less than 10 seconds of latency). The server processes the information thereby reducing the computing load and power consumption of the mobile devices. The system uses traffic pattern recognition software that accurately recognizes valid traffic data while filtering unwanted traffic data. The invention US008849309B2 09/2014 relates to a method for providing transit time forecasts on the roads of a controlled road network. It includes the receipt of the transit time of a planned route calculated by a road traffic surveillance system for at least one road in the controlled road network; and correcting transit time received from the intended route based on information obtained from a cellular mobile communication network. The invention MA 20150002 Al (MA 20150002 Al: Azedine Boulmakoul, and Lamia Karim: Device System and Method for monitoring customers in commercial spaces .Morgan Moroccan Office of Industrial and Commercial Property, 1/2015), describes a device, system and method for tracking the paths taken by customers in commercial spaces. This device can be exploited for the generation and storage of trajectories of moving objects as defined in this invention. Some research work in the form of international publications developed by Professor A. Boulmakoul's team concerns real-time intelligent transport systems and which are not reproduced or reused in the present invention. This work contributes to solving transport problems and does not concern the invention that will be developed later. The results of this scientific work do not relate to the claims defended in the present invention. The non-exhaustive list of scientific contributions is given below:
Azedine Boulmakoul, A. Daissaoui, Z. Habbas, First spécifications of Urban Traffic-Congestion Forecasting Models, in The 27th international conférence on microelectronics (ICM 2015) IEEE, At Casablanca 22-23 Nov. 2015 - Morocco. Azedine Boulmakoul, A. Daissaoui, Z. Habbas, First Specification of Urban Traffic-Congestion Forecasting Models, in The 27th International Conference on Microelectronics (ICM 2015) IEEE, At Casablanca 22-23 Nov. 2015 - Morocco.
Azedine Boulmakoul, Lamia Karim, Meriem Mandar, Abdelfattah Idri, Abdellah Daissaoui: Towards Scalable Distributed Framework for Urban Congestion Traffic Patterns Warehousing. Applied Comp. Int. Soft Computing 2015: 578601 : 1-578601 : 12 (2015).  Azedine Boulmakoul, Lamia Karim, Meriem Mandar, Abdelfattah Idri, Abdellah Daissaoui: Towards Scalable Distributed Framework for Urban Congestion Traffic Patterns Warehousing. Applied Comp. Int. Soft Computing 2015: 578601: 1-578601: 12 (2015).
Boulmakoul A, Sellam S: Boulmakoul A., Sellam S. (1993) Intelligent Intersection : Artificial Intelligence and Computer Vision Techniques for Automatic Incident Détection, in Artificial Intelligence in Traffic Engineering, pp. 189-200, 1993, VSP International Science Publisher, Zeist, The Netherlands.. 01/1993; VSP International Science Publisher, Zeist, the Netherlands.  Boulmakoul A, Sellam S: Boulmakoul A., Sellam S. (1993) Intelligent Intersection: Artificial Intelligence and Computer Vision Techniques for Automatic Incident Detection, in Artificial Intelligence in Traffic Engineering, pp. 189-200, 1993, VSP International Science Publisher, Zeist, The Netherlands .. 01/1993; VSP International Science Publisher, Zeist, the Netherlands.
Mohamed Haitam Laarabi, Azedine Boulmakoul, Roberto Sacile, Emmanuel Garbolino: A scalable communication middleware for real-time data collection of dangerous goods vehicle activities. Transportation Research Part C Emerging Technologies 1 1/2014; 48:404 - 417. DOI: 10.1016/j .trc.2014.09.006 Elsevier.  Mohamed Haitam Laarabi, Azedine Boulmakoul, Roberto Sacile, Emmanuel Garbolino: A scalable middleware communication for real-time data collection of dangerous goods vehicles. Transportation Research Part C Emerging Technologies 1 1/2014; 48: 404-417. DOI: 10.1016 / d .trc.2014.09.006 Elsevier.
Azedine Boulmakoul, Adil El Bouziri: Mobile Object Framework and Fuzzy Graph Modelling to Boost HazMat Telegeomonitoring. Methods and Tools for Reducing the Risks of Accidents and Terrorist Attack, 01/2012: chapter 5: pages 1 19-149; Springer Netherlands., ISSN-ISBN: 978-94- 007-2683-3  Azedine Boulmakoul, Adil El Bouziri: Mobile Object Framework and Fuzzy Graph Modeling to Boost HazMat Telegeomonitoring. Methods and Tools for Reducing the Risks of Accidents and Terrorist Attack, 01/2012: chapter 5: pages 1 19-149; Springer Netherlands., ISSN-ISBN: 978-94- 007-2683-3
Mohamed Haitam Laarabi, Azedine Boulmakoul, Roberto Sacile, Emmanuel Garbolino: An Overview on an Intelligent Transportation System (ITS) based on Agents, Time-Dependent Network and Fuzzy Travel-Time Cost. 3rd Edition On Innovation and News Trends in Information Systems (INTIS 2013), Tanger Morocco; 11/2013, ISBN: 978-9954-34-378-4 ISSN: 2351-9215. Azedine Boulmakoul, Haitam Laarabi, Roberto Sacile, Emmanuel Garbolino: Ranking Triangular Fuzzy Numbers using Fuzzy Set Inclusion Index. Fuzzy Logic and Applications Lecture Notes in Computer Science Volume 8256, 2013, pp 100-108 - 10th International Workshop, WILF 2013, Genoa, Italy, November 19-22, 2013. Proceedings, Genova Italy; 11/2013, Springer International Publishing, ISBN 978-3-319-03199-6. Mohamed Haitam Laarabi, Azedine Boulmakoul, Roberto Sacile, Emmanuel Garbolino: An Overview of an Intelligent Transportation System (ITS) based on Agents, Time-Dependent Network and Fuzzy Travel-Time Cost. 3rd Edition On Innovation and News Trends in Information Systems (INTIS 2013), Tangier Morocco; 11/2013, ISBN: 978-9954-34-378-4 ISSN 2351-9215. Azedine Boulmakoul, Haitam Laarabi, Roberto Sacile, Emmanuel Garbolino: Triangular Ranking Fuzzy Numbers using Fuzzy Set Inclusion Index. Fuzzy Logic and Applications Reading Notes in Computer Science Volume 8256, 2013, pp 100-108 - 10th International Workshop, WILF 2013, Genoa, Italy, November 19-22, 2013. Proceedings, Genova Italy; 11/2013, Springer International Publishing, ISBN 978-3-319-03199-6.
Boulmakoul A. (1994) Approche Logique du Contrôle Symbolique, 9ème Congrès Reconnaissance des Formes et Intelligence Artificielle (RFIA), pp.101-1 10, 1 1-14 Janvier 1994.RFIA ; 01/1994 Boulmakoul A. (1994) Logic Approach to Symbolic Control, 9th Congress Pattern Recognition and Artificial Intelligence (RFIA), pp.101-1 10, January 1-14, 1994.RFIA; 01/1994
Les publications scientifiques qui supportent le méta-modèle des trajectoires et le procédé informatique de collecte de données trajectoires, ainsi que l'architecture d'un système de tracking d'objets mobiles sont cités ci-dessous : The scientific publications supporting the trajectory meta-model and the computer process for collecting trajectory data, as well as the architecture of a mobile object tracking system are given below:
Azedine Boulmakoul, Lamia Karim, Adil Elbouziri, and Ahmed Lbath: A System Architecture for Heterogeneous Moving-Object Trajectory Metamodel Using Generic Sensors: Tracking Airport Security Case Study. IEEE Systems Journal 12/2013; PP (99): 1-9. DOI: 10.1 109/JS YST.2013.2293837  Azedine Boulmakoul, Lamia Karim, Adil Elbouziri, and Ahmed Lbath: A System Architecture for Heterogeneous Moving-Object Trajectory Metamodel Using Generic Sensors: Tracking Airport Security Case Study. IEEE Systems Journal 12/2013; PP (99): 1-9. DOI: 10.1 109 / JS YST.2013.2293837
Azedine Boulmakoul, Lamia Karim, Ahmed Lbath: A High Performance Scalable Data Collection System for Moving Objects. International Journal of Computer Applications 04/2013; 67(9):36-43. DOL 10.5120/11424-6769  Azedine Boulmakoul, Lamia Karim, Ahmed Lbath: High Performance Scalable Data Collection System for Moving Objects. International Journal of Computer Applications 04/2013; 67 (9): 36-43. DOL 10.5120 / 11424-6769
Azedine Boulmakoul, Lamia Karim, Ahmed Lbath: Moving Object Trajectories Meta-Model and Spatio-Temporal Queries. DOI: 10.5121/ijdms.2012.4203.  Azedine Boulmakoul, Lamia Karim, Ahmed Lbath: Moving Object Trajectories Meta-Model and Spatio-Temporal Queries. DOI: 10.5121 / ijdms.2012.4203.
D'autres travaux concernant la gestion des congestions fondés sur d'autres approches sont listés ci- dessous :  Other work on congestion management based on other approaches is listed below:
Scemama, G. and Caries, O., CLAIRE-SITI, public and road transport network management control: a unified approach,in Road Transport Information and Control, 2004. RTIC 2004. 12th IEE International Conférence, pp.1 1-18, 20-22 April 2004, doi: 10.1049/cp: 20040002.  Scemama, G. and Caries, O., CLAIRE-SITI, public and road transport network management control: a unified approach, in Road Transport Information and Control, 2004. RTIC 2004. 12th IEE International Conference, pp.1 1-18, 20-22 April 2004, doi: 10.1049 / cp: 20040002.
Bell MC, Scemama G, Ibbetson LJ, CLAIRE: An Expert System for Congestion Management, in Advanced Telematics in Road Transport: Proceedings of the EC: DRIVE Conférence, Volume: 1, Pages: 596-614, February 1991, Elsevier.  Bell MC, Scemama G, Ibbetson LJ, CLAIRE: An Expert System for Congestion Management, in Advanced Telematics in Road Transport: Proceedings of the EC: DRIVE Conference, Volume: 1, Pages: 596-614, February 1991, Elsevier.
G. Scemama and B. Foraste, An expert System approach to traffic congestion, Recherche, transports, sécurité RTS, p. 17-22, 1986-9, Issue Number: 1 1, ISSN: 0291-8439, OCLC: 10557190.  G. Scemama and B. Foraste, An expert System approach to traffic congestion, Research, Transport, Security RTS, p. 17-22, 1986-9, Issue Number: 1 1, ISSN: 0291-8439, OCLC: 10557190.
TRB, Quantifying congestion, Vol. 1. NCHRP Report 398, 1997.  TRB, Quantifying Congestion, Vol. 1. NCHRP Report 398, 1997.
OECD, Managing Urban Traffic Congestion, Ëuropean Conférence of Ministers of Transport, OECD/ECMT 2007, - ISBN 978-92-821-0128-5 - © ECMT, 2007.  OECD, Managing Urban Traffic Congestion, European Conference of Ministers of Transport, OECD / ECMT 2007, - ISBN 978-92-821-0128-5 - © ECMT, 2007.
Les efforts de la recherche et de développement dans le domaine de la gestion des congestions des réseaux urbains sont constatés chez les industriels et les opérateurs publics. L'industrie de régulation de trafic propose actuellement des technologies permettant la communication entre les véhicules et Γ infrastructure routière. La technologie actuelle des smartphones équipés de GPS et des technologies NFC, permet aussi l'échange des données de position et de mouvement avec les véhicules via la communication à courte portée. A ce jour les revendications explicitées dans cette invention n'ont pas été considérées dans des travaux scientifiques ou brevets existants. La présente invention se veut simple et agile pour sa mise en place et espère apporter une nouvelle vision pragmatique à la gestion intelligente temps réel des congestions des réseaux urbains. Exposé technique de l'invention Research and development efforts in the field of congestion management of urban networks are observed in industrial and public operators. The traffic control industry currently offers technologies for communication between vehicles and road infrastructure. The current technology of smartphones equipped with GPS and NFC technologies, also allows the exchange of position and movement data with vehicles via short-range communication. To date, the claims made explicit in this invention have not been considered in existing scientific works or patents. The present invention is simple and agile for its implementation and hopes to bring a new pragmatic vision to the real-time intelligent management of congestions of urban networks. Technical presentation of the invention
NOTATION ET ACRONYME Intelligent Traffic Management System for Smart Cities RATING AND ACRONYM Intelligent Traffic Management System for Smart Cities
Figure imgf000007_0001
Figure imgf000007_0001
Nombre flou gaussien (figure 1) GFN(m, σ) :
Figure imgf000007_0003
La vitesse à l'instant t du ième véhicule entrant dans la zone de détection virtuelle correspondant à un élément de la route (tronçon ou des parties de tronçons).
Figure imgf000007_0002
La vitesse moyenne de vi t sur une période de temps. L'écart type sur une période de temps associée aux vitessesGaussian Blur Number (Figure 1) GFN (m, σ):
Figure imgf000007_0003
The speed at time t of the i th vehicle entering the virtual detection zone corresponding to a road element (section or parts of sections).
Figure imgf000007_0002
The average speed of v it over a period of time. The standard deviation over a period of time associated with the speeds
Figure imgf000007_0004
Figure imgf000007_0004
La vitesse floue gaussienne associée à la vitesse
Figure imgf000007_0009
The Gaussian blurred speed associated with speed
Figure imgf000007_0009
Figure imgf000007_0008
Figure imgf000007_0008
Vitesse moyenne sur la zone de détection virtuelle 1, à l'instant t.
Figure imgf000007_0006
vitesse maximale pratiquée sur la zone de détection virtuelle.
Figure imgf000007_0005
Average speed on the virtual detection zone 1, at time t.
Figure imgf000007_0006
maximum speed practiced on the virtual detection zone.
Figure imgf000007_0005
α Un paramètre d'agréation de l'e-phéromone.
Figure imgf000007_0007
Correspond à l'opération de soustraction des nombres flous gaussiens. α A parameter of approval of the e-pheromone.
Figure imgf000007_0007
Corresponds to the operation of subtracting Gaussian fuzzy numbers.
Correspond à l'opération d'addition des nombres flous gaussiens. Corresponds to the operation of adding Gaussian fuzzy numbers.
¾ Correspond à l'opération produit des nombres flous gaussiens.  ¾ Corresponds to the operation produces Gaussian fuzzy numbers.
/ : zone de détection virtuelle.  /: virtual detection area.
L(l) Longueur de la zone 1.  L (l) Length of zone 1.
η(1, T) = \N(]t— T, t])| Nombre de véhicules présents dans la zone de détection virtuelle / durant l'intervalle de temps ]t— T, t].
Figure imgf000008_0002
La quantité de l'e-phéromone floue gaussienne du trafic déposée par les véhicules. Elle correspond à la densité générée par les véhicules pour la période T. Les vitesses faibles génèrent une quantité importante de l'e-phéromone floue, les grandes vitesses ne laissent pas assez de trace de phéromone. η (1, T) = \ N (] t- T, t]) | Number of vehicles present in the virtual detection zone / during the time interval] t- T, t].
Figure imgf000008_0002
The amount of the Gaussian fuzzy e-pheromone of the traffic deposited by the vehicles. It corresponds to the density generated by the vehicles for the period T. The low speeds generate a large quantity of the fuzzy e-pheromone, the high speeds do not leave enough trace of pheromone.
Sur la périodeOver the period
Figure imgf000008_0008
Coefficient de dissipation de l'e-phéromone floue gaussienne.
Figure imgf000008_0008
Coefficient of dissipation of Gaussian fuzzy e-pheromone.
Figure imgf000008_0003
Figure imgf000008_0004
Correspond à la force de diffusion de l'e-phéromone floue de la zone de détection virtuelle notée 1, à l'instant t.
Figure imgf000008_0005
) Correspond à la force de l'e-phéromone floue de la zone de détection virtuelle 1, à l'instant t.
Figure imgf000008_0006
Équation dynamique de la dissipation de l'e-phéromone floue de la zone de détection virtuelle. ] Paramètre de diffusion de l'e-phéromone floue. Paramètre de diffusion de convergence de l'e-phéromone floue (j est en amont de 1). Paramètre de diffusion de divergence de Γ l'e-phéromone floue (j est en aval de 1). Le débit directionnel divergent du flux allant du tronçon j vers le tronçon 1. Le débit directionnel du flux allant du tronçon j vers le tronçon 1.
Figure imgf000008_0003
Figure imgf000008_0004
Corresponds to the diffusion force of the fuzzy e-pheromone of the virtual detection zone denoted 1, at time t.
Figure imgf000008_0005
) Corresponds to the strength of the fuzzy e-pheromone of the virtual detection area 1 at time t.
Figure imgf000008_0006
Dynamic equation of dissipation of the fuzzy e-pheromone of the virtual detection zone. ] Diffusion parameter of the fuzzy e-pheromone. Convergence diffusion parameter of the fuzzy e-pheromone (j is upstream of 1). Diffusion scattering parameter of Γ the fuzzy e-pheromone (j is downstream of 1). The directional flow diverges from the flow from the section j to the section 1. The directional flow of the flow from the section j to the section 1.
Figure imgf000008_0007
Figure imgf000008_0007
C : paramètre de saturation.
Figure imgf000008_0009
Ensemble des tronçons routiers en amont du tronçon 1. C: saturation parameter.
Figure imgf000008_0009
All road sections upstream of section 1.
: La fonction de transition de la diffusion de
Figure imgf000008_0001
: The transition function of the diffusion of
Figure imgf000008_0001
l'e-phéromone floue. Processus de configuration des zones de détection virtuelles et de calcul de Pe-phéromone gaussienne floue the fuzzy e-pheromone. Process for configuring virtual detection zones and calculating fuzzy Gaussian Pe-pheromone
Description du processus  Description of the process
Le processus de calcul de l'e-phéromone gaussienne floue d'une zone virtuelle de détection est fondé sur les méthodes données ci-dessous :  The process of calculating the fuzzy Gaussian e-pheromone of a virtual detection zone is based on the methods given below:
Méthode 1 : Configurations de zones virtuelles de détection Method 1: Configuring Virtual Detection Zones
Pour cette méthode, les zones virtuelles à positionner sur le réseau spatial routier correspondent généralement aux tronçons d'entrée et/ou de sorties des carrefours à feux. Ces marqueurs virtuels en interaction avec le passage des véhicules équipés de dispositif de géolocalisation au voisinage de ces zones virtuelles de détection permettent de calculer l'e-phéromone gaussienne floue. La configuration des zones de détection virtuelles est réalisée dans la base de données spatiale (map géographique du réseau urbain routier). La description schématique des zones de détection virtuelles est donnée dans la figure 2.  For this method, the virtual zones to be positioned on the road network generally correspond to the entry and / or exit sections of the traffic lights. These virtual markers interact with the passage of vehicles equipped with geolocation device in the vicinity of these virtual detection zones to calculate the fuzzy Gaussian e-pheromone. The configuration of the virtual detection zones is carried out in the spatial database (geographical map of the urban road network). The schematic description of the virtual detection zones is given in Figure 2.
Méthode 2 : le processus de calcul des variables d'état et de l'e-phéromone gaussienne floue des zones de détection virtuelles Method 2: The process of calculating state variables and Gaussian e-pheromone fuzzy virtual detection areas
Lors du franchissement des véhicules géolocalisables de la zone de détection virtuelle et tant que ces mêmes véhicules persistent dans la zone de détection pour une période donnée (inférieur à une minute), un processus d'élaboration des moyennes
Figure imgf000009_0002
et d'écarts type
Figure imgf000009_0006
des vitesses est déclenché. Ce processus permet aussi d'associer à chaque véhicule sa vitesse floue gaussienne obtenue comme suit ) La condition d'appartenance à tout instant d'un
Figure imgf000009_0004
When crossing geolocalisable vehicles from the virtual detection zone and as long as these same vehicles persist in the detection zone for a given period (less than one minute), an averaging process
Figure imgf000009_0002
and standard deviations
Figure imgf000009_0006
speeds is triggered. This process also allows to associate with each vehicle its Gaussian fuzzy speed obtained as follows) The condition of belonging at any moment of a
Figure imgf000009_0004
véhicule w à la zone de détection virtuelle / est : vehicle w to the virtual detection area / is:
Figure imgf000009_0005
Figure imgf000009_0005
Le même processus fournit la valeur
Figure imgf000009_0003
qui correspond à la vitesse moyenne observée sur la zone de détection virtuelle 1, à l'instant t. The same process provides the value
Figure imgf000009_0003
which corresponds to the average speed observed on the virtual detection zone 1, at time t.
Méthode 3: Schéma de calcul de dépôt, de dissipation et de diffusion de l'e-phéromone gaussienne floue d'une zone de détection virtuelle  Method 3: Calculation scheme of deposition, dissipation and diffusion of the fuzzy Gaussian e-pheromone of a virtual detection zone
Dépôt d'un véhicule de l'e-phéromone gaussienne floue d'une zone de détection virtuelle Deposition of a vehicle of the fuzzy Gaussian e-pheromone of a virtual detection zone
Chaque véhicule dépose une quantité floue de l'e-phéromone gaussienne floue selon la formule suivante :
Figure imgf000009_0001
Each vehicle deposits a fuzzy quantity of the fuzzy Gaussian e-pheromone according to the following formula:
Figure imgf000009_0001
L'agrégation de cette quantité sur l'ensemble de la zone de détection virtuelle est calculée comme suit : Sur la période
Figure imgf000009_0007
La dissipation de l'e-phéromone gaussienne floue d'une zone de détection virtuelle The aggregation of this quantity over the entire virtual detection zone is calculated as follows: Over the period
Figure imgf000009_0007
The dissipation of the Gaussian e-pheromone fuzzy of a virtual detection zone
L'équation dynamique de dissipation de l'e-phéromone gaussienne floue d'une zone de détection virtuelle est donnée par : correspond au coefficient
Figure imgf000010_0003
The dynamic equation of dissipation of the fuzzy Gaussian e-pheromone of a virtual detection zone is given by: corresponds to the coefficient
Figure imgf000010_0003
de dissipation de l'e-phéromone floue gaussienne. La valeur de
Figure imgf000010_0004
chute avec les grandes vitesses pratiquées dans la zone de détection virtuelle. of dissipation of the Gaussian fuzzy e-pheromone. The value of
Figure imgf000010_0004
fall with the high speeds practiced in the virtual detection zone.
La diffusion de l'e-phéromone gaussienne floue entre zones de détection virtuelles The diffusion of the Gaussian e-pheromone blurred between virtual detection zones
Cette diffusion exprime la communication distribuée de l'e-phéromone entres les zones de détection. Elle est donnée par la fonction de transition de la diffusion de l'e-phéromone floue : This broadcast expresses the distributed communication of the e-pheromone between the detection zones. It is given by the transition function of the diffusion of the fuzzy e-pheromone:
Figure imgf000010_0001
Figure imgf000010_0001
Méthode 4: Agrégation l'e-phéromone gaussienne floue des zones de détection virtuelles appartenant à la même artère de trafic d'un réseau urbain  Method 4: Aggregation the Gaussian e-pheromone fuzzy virtual detection areas belonging to the same traffic artery of an urban network
L'e-phéromone gaussienne floue est quantifiée dans chaque zone de détection virtuelle associée à un tronçon routier du réseau. L'agrégation de ces quantités sur un itinéraire de type artère est aussi quantifiée par un nombre flou gaussien.  The fuzzy Gaussian e-pheromone is quantified in each virtual detection zone associated with a road section of the network. The aggregation of these quantities on an arterial route is also quantified by a Gaussian fuzzy number.
Soit Π un itinéraire constitué de zones de détection virtuelles appartenant à une même artère A (un boulevard par exemple). Nous avons les formules de calcul suivantes :  Let Π be a route consisting of virtual detection zones belonging to the same artery A (a boulevard for example). We have the following calculation formulas:
Dé ôt de l'e-phéromone gaussienne floue de l'itinéraire Π  Deposition of the fuzzy Gaussian e-pheromone of the route Π
Figure imgf000010_0002
Figure imgf000010_0002
La dissipation de l'e-phéromone gaussienne floue de l'itinéraire Π
Figure imgf000010_0005
The dissipation of the fuzzy Gaussian e-pheromone of the route Π
Figure imgf000010_0005
La propagation de l'e-phéromone gaussienne floue de l'itinéraire Π
Figure imgf000010_0006
Méthode 5: Détection de l'état de congestion floue au sens l'e-phéromone gaussienne floue d'un itinéraire The spread of the fuzzy Gaussian e-pheromone of the route Π
Figure imgf000010_0006
Method 5: Fuzzy congestion state detection in the fuzzy Gaussian e-pheromone sense of an itinerary
Un itinéraire Π est dit congestionné si la valeur de son dépôt de l'e-phéromone gaussienne floue est supérieure à une valeur seuil gaussienne floue avec une confiance a. A route Π is said to be congested if the value of its fuzzy Gaussian e-pheromone deposition is greater than a fuzzy Gaussian threshold value with confidence a.
Figure imgf000011_0003
Figure imgf000011_0003
Figure imgf000011_0002
Figure imgf000011_0002
La situation de congestion de l'itinéraire est réalisée selon le processus définie ci-dessous : The situation of congestion of the route is carried out according to the process defined below:
Nous allons définir la condition de congestion par la formule
Figure imgf000011_0005
We will define the condition of congestion by the formula
Figure imgf000011_0005
probabilité que l'événement soit vraisemblable de niveau de confiance a. probability that the event is likely to be a confidence level a.
Figure imgf000011_0004
Figure imgf000011_0004
Figure imgf000011_0001
Figure imgf000011_0001
Pour un degré de confiance a, la table de loi normale donne la valeur associée à la probabilité. Par exemple pour la confiance a = 85% alors la table donne la valeur 1,04. Dans ce cas la valeur calculée supérieure ou égale à 1 ,04, et par conséquent il y aura une situation de congestion
Figure imgf000011_0006
For a degree of confidence a, the normal law table gives the value associated with the probability. For example, for confidence a = 85% then the table gives the value 1.04. In this case the calculated value greater than or equal to 1, 04, and consequently there will be a situation of congestion
Figure imgf000011_0006
détectée. Méthode 6: Régulation par commandes symboliques floues d'un itinéraire surveillé par des zones de détection virtuelles appartenant à la même artère de trafic d'un réseau urbain detected. Method 6: Regulation by fuzzy symbolic commands of a route monitored by virtual detection zones belonging to the same traffic artery of an urban network
Soit l'ensemble des itinéraires caractérisés comme important au sens de la régulation d'un réseau de trafic urbain (les grands boulevards, les grandes artères de dégagement, les grands axes fonctionnels de transport de flux de/vers zones résidentielles, les grands axes fonctionnels de transport de flux de/vers des zones a axes autoroutiers, etc.). Soit
Figure imgf000012_0009
Either all the routes characterized as important in the sense of the regulation of a network of urban traffic (the big boulevards, the main arteries of release, the main functional axes of transport of flows of / towards residential zones, the main functional axes transport of flows from / to areas with motorway axes, etc.). Is
Figure imgf000012_0009
On définit l'ensemble des actions symboliques We define the set of symbolic actions
Figure imgf000012_0008
Figure imgf000012_0008
Figure imgf000012_0001
Action « neutre » sur le carrefour A, qui signifie de garder la régulation encours.
Figure imgf000012_0001
"Neutral" action on the A junction, which means to keep the regulation in progress.
Figure imgf000012_0002
Action « augmenter le vert d'une quantité fixe de l'ordre de 5 secondes » sur le carrefour A, qui signifie la modification de la régulation encours, par dilatation du cycle des feux à la faveur de l'axe du carrefour en question.
Figure imgf000012_0002
Action "increase the green of a fixed quantity of the order of 5 seconds" on the crossroads A, which means the modification of the outstanding regulation, by dilation of the cycle of the lights by favor of the axis of the crossroads in question.
Figure imgf000012_0003
Action « diminuer le vert de 5 secondes» sur le carrefour A, qui signifie la modification de la régulation encours, en gardant le même cycle à la faveur du carrefour en question et de diminuer la durée de vert pour l'axe relatif à la zone de détection virtuelle en entrée du carrefour.
Figure imgf000012_0003
Action "Decrease the green of 5 seconds" on the intersection A, which means the modification of the outstanding regulation, keeping the same cycle in favor of the crossroad in question and reducing the duration of green for the axis relating to the zone virtual detection at the intersection entrance.
On définit une liste triée des artères de l'ensemble
Figure imgf000012_0007
Le tri est réalisé par les experts de la régulation de la ville (selon les critères : débit de trafic journalier, importance fonctionnelle de l'artère, la longueur de l'artère, etc.). We define a sorted list of the arteries of the set
Figure imgf000012_0007
The sorting is carried out by the experts of the regulation of the city (according to the criteria: flow of daily traffic, functional importance of the artery, the length of the artery, etc.).
Chaque période de trois minutes faire  Every three minutes make
{  {
- Calculer le dépôt de l ' e-phéromone gaussienne floue de la zone de détection virtuelle de chaque itinéraire de
Figure imgf000012_0004
- Calculate the deposit of the fuzzy Gaussian e-pheromone of the virtual detection area of each route of
Figure imgf000012_0004
-Former la liste des itinéraires en état de congestion floue selon la méthode 5.  -Form the list of routes in a state of fuzzy congestion according to method 5.
-Soit Ια liste triée des itinéraires en état de congestion floue issue de la liste triée initiale -It is a sorted list of routes in a state of fuzzy congestion from the initial sorted list
Figure imgf000012_0011
Figure imgf000012_0011
Tant que la liste
Figure imgf000012_0005
n 'est pas vide faire As long as the list
Figure imgf000012_0005
is not empty do
{  {
17 = itinéraire au début de la liste
Figure imgf000012_0006
17 = route at the beginning of the list
Figure imgf000012_0006
Pour toute zone Πκ de détection virtuelle de l 'itinéraire Π faire For any zone Π κ of virtual detection of the route Π
{ Soit γκ le carrefour à la sortie de YlK(carrefour aval) {Let γ κ be the junction at the exit of Yl K (downstream junction)
Si Πκ est congestionné alors Activer l 'action symbolique
Figure imgf000012_0010
sur le carrefour γκ de l 'axe du même sens de trafic que Πκ et mémoriser l 'état du carrefour à l 'instant
Figure imgf000012_0012
, congestionné). La durée du cycle ne dépassera en aucun cas une valeur limite (120 secondes). If Π κ is congested then Activate symbolic action
Figure imgf000012_0010
on the γ κ intersection of the axis of the same direction of traffic as Π κ and memorize the state of the intersection at the instant
Figure imgf000012_0012
congested). The duration of the cycle will in no case exceed a limit value (120 seconds).
Si Πκ est Hautement Fluide alors Activer l 'action symbolique
Figure imgf000012_0017
sur le carrefour γκ de l 'axe du même sens de trafic que Πκ et mémoriser l 'état du carrefour de l'instant
Figure imgf000012_0014
H Fluide). La durée du cycle est toujours supérieure ou égale à une valeur limite (cycle normal du contrôleur). If Π κ is highly fluid then activate the symbolic action
Figure imgf000012_0017
on the γ κ intersection of the axis of the same direction of traffic as Π κ and to memorize the state of the crossroads of the moment
Figure imgf000012_0014
H Fluid). The cycle time is always greater than or equal to a limit value (normal controller cycle).
Si Πκ est Fluide activer l'action
Figure imgf000012_0015
sur le carrefour γκ de l 'axe du même sens de trafic que Πκ et mémoriser l 'état du carrefour de l 'instantIf Π κ is Fluid activate action
Figure imgf000012_0015
on the γ κ intersection of the axis of the same direction of traffic as Π κ and memorize the state of the intersection of the instant
Figure imgf000012_0013
Figure imgf000012_0018
Figure imgf000012_0013
Figure imgf000012_0018
}  }
Enlever l 'itinéraire  Remove the route
}
Figure imgf000012_0016
}
Figure imgf000012_0016
} Les activités de base } Basic activities
La présente invention concerne un système de transport intelligent flou temps réel agile pour l'aide à la gestion des congestions du trafic en site urbain. Le système permet la génération de l'e-phéromone floue gaussienne sur les artères du réseau de transport et ce par le biais du calcul de variables d'état floues du trafic et l'exploitation du paradigme des structures organisées intelligentes de type fourmi. Le modèle dynamique de la propagation des congestions est réalisé par une structure algébrique originale de nombres flous gaussiens, conçu pour cette exigence et assure la prédiction des congestions sur un horizon court. L'invention propose aussi un processus de contrôle symbolique de trafic pour contribuer à la réduction globale de la congestion du réseau. Le système proposé implique un certain nombre d'activités développées ci-dessous :  The present invention relates to an agile real-time hazy intelligent transport system for assisting with congestion management of urban site traffic. The system enables Gaussian fuzzy e-pheromone to be generated on the arteries of the transport network by calculating fuzzy state variables of the traffic and exploiting the paradigm of intelligent organized structures of the ant type. The dynamic model of congestions propagation is realized by an original algebraic structure of Gaussian fuzzy numbers, designed for this requirement and ensures the prediction of congestions on a short horizon. The invention also proposes a symbolic traffic control process to contribute to the overall reduction of network congestion. The proposed system involves a number of activities developed below:
Activité 1 : Le lancement du processus de génération de l'e-phéromone flou gaussien exige en premier lieu la configuration et la définition du contexte d'évaluation, de préparation de données, de collecte des données et de prétraitement. Le contexte est défini par (figures : 2-5):  Activity 1: The launch of the Gaussian Unsharp e-Pheromone generation process requires first and foremost the configuration and definition of the context of evaluation, data preparation, data collection and pre-processing. The context is defined by (figures: 2-5):
1. Le périmètre d'étude, à savoir : le réseau de transport concerné, les itinéraires du réseau à superviser, le système de régulation concerné, la période de temps de la collecte.  1. The study perimeter, namely: the transport network concerned, the routes of the network to be supervised, the regulatory system concerned, the period of time of collection.
2. Choix des tronçons auxquels seront associés des zones de détection virtuelles.  2. Choice of sections to which virtual detection zones will be associated.
3. Configuration des localisations des zones de détection virtuelles associées aux tronçons, selon la méthode 1.  3. Configuration of the locations of the virtual detection zones associated with the sections, according to method 1.
Cette activité est matérialisée par un composant logiciel intégré dans le système globale et mettant en place les éléments nécessaires pour satisfaire ses objectifs.  This activity is materialized by a software component integrated in the overall system and putting in place the necessary elements to satisfy its objectives.
Activité 2 : Les éléments introduits lors de l'activité 1 seront exploités pour lancer un procédé de calcul des variables d'état à base des vitesses et de l'e-phéromone gaussienne floue des zones de détection virtuelles. La simulation de type microscopique est envisagée pour générer les données véhicule. Cette activité est supportée par les instructions fournies dans la méthode 2 (figures 6-10). Activity 2: The elements introduced during activity 1 will be used to launch a method for calculating state variables based on velocities and the fuzzy Gaussian e-pheromone of the virtual detection zones. Microscopic simulation is envisaged to generate the vehicle data. This activity is supported by the instructions provided in Method 2 (Figures 6-10).
Activité 3 : En temps réel et sur la période de temps arrêtée glissant (paramètre à fixer : 30 secondes par exemple), cette activité concerne les procédures de calcul de dépôt, de dissipation et de diffusion de l'e-phéromone gaussienne floue d'une zone de détection virtuelle. Elle se déroule selon les instructions formulées dans la méthode 3 (figure 9). Activity 3: In real time and over the slippery period of time (parameter to be set: 30 seconds for example), this activity concerns the procedures for calculating the deposition, dissipation and diffusion of the fuzzy Gaussian e-pheromone. a virtual detection zone. It proceeds according to the instructions formulated in Method 3 (Figure 9).
Activité 4 : Cette activité intéresse le processus d'agrégation de l'e-phéromone gaussienne floue des zones de détection virtuelles appartenant à la même artère de trafic d'un réseau urbain. Elle est réalisée selon les principes définis par la méthode 4 (figures 9, 12).  Activity 4: This activity involves the process of aggregating the fuzzy Gaussian e-pheromone with virtual detection zones belonging to the same traffic artery of an urban network. It is performed according to the principles defined by Method 4 (Figures 9, 12).
Activité 5 : Cette activité développe les procédures de détection de l'état de congestion floue au sens l'e-phéromone gaussienne floue d'un itinéraire. Elle est cadrée par la méthode 5 (figure 8, 15). Activity 5: This activity develops fuzzy congestion detection procedures in the sense of the fuzzy Gaussian e-pheromone of a route. It is framed by method 5 (Figure 8, 15).
Activité 6 : Cette activité développe la régulation par des commandes symboliques floues d'un itinéraire surveillé par des zones de détection virtuelles appartenant à la même artère de trafic d'un réseau urbain. Elle est réalisée selon les instructions de la méthode 6 (figures 12-14). Activity 6: This activity develops the regulation by fuzzy symbolic commands of a route monitored by virtual detection zones belonging to the same traffic artery of an urban network. It is performed according to the instructions of Method 6 (Figures 12-14).
Activité 7 : C'est l'activité de déploiement sur le terrain et en temps réel des processus de l'activité 5, intégration des composants logiciels pour la mise en œuvre de la solution (figures 6-7).  Activity 7: This is the activity of field deployment and real-time processes of activity 5, integration of software components for the implementation of the solution (Figures 6-7).
Activité 8 : Génération des résultats au sens interface homme machine issues du déploiement des tâches des activités 1-6. Persistance des résultats en format json pour l'écosystème Hadoop MongoDB (figure 11). Description sommaire des figures Activity 8: Generation of results in the machine interface sense from the deployment of the tasks of activities 1-6. Persistence of results in json format for the Hadoop MongoDB ecosystem (Figure 11). Brief description of the figures
La figure 1 présente un nombre flou gaussien  Figure 1 shows a Gaussian soft number
La figure 2 montre l'association des zones de détection virtuelles aux tronçons de carrefours d'un réseau urbain.  Figure 2 shows the association of virtual detection zones with the intersections of intersections of an urban network.
La figure 3 décrit l'architecture de communication du système. Elle met en valeur les dispositifs de communication véhicule serveur central (via GPRS-internet ou réseau propiétaire du centre de contôle de trafic de la ville).  Figure 3 describes the communication architecture of the system. It highlights the central server vehicle communication devices (via GPRS-internet or proprietary network of the traffic control center of the city).
La figure 4 détaille un réseau annoté des zones de détection virtuelles amont/aval de carrefours. Figure 4 details an annotated network of virtual detection zones upstream / downstream of intersections.
La figure 5 développe le modèle de donné objet du système proposé. Dans ce modèle sont considérés ls éléments du réseau routier, les zones de détection virtuelles et les smart véhicules équipés de d'équipement de géolocalisation et mettant en œuvre le système (partie embarqué) proposé dans la présente invention ainsi que les stratégies de calcul de l'e-phéromone flou. Figure 5 develops the object data model of the proposed system. In this model are considered the elements of the road network, the virtual detection zones and the smart vehicles equipped with geolocation equipment and implementing the system (embedded part) proposed in the present invention as well as the strategies of calculation of the e-pheromone fuzzy.
La figure 6 décrit le diagramme des composants du système proposé.  Figure 6 depicts the component diagram of the proposed system.
La figure 7 concerne le diagramme de déploiement du système et montre les dispositifs engagés dans la solution.  Figure 7 shows the system deployment diagram and shows the devices involved in the solution.
La figure 8 illustre le procédé de détection des véhicules dans la zone de détection virtuelle. Elle montre aussi la technique de calcul ds moyennes mobiles de véhicules pour une période de temps de 30 secondes.  Figure 8 illustrates the method of detecting vehicles in the virtual detection zone. It also shows the technique of calculating moving average vehicles for a period of time of 30 seconds.
La figure 9 illustre les activités de génération de l'e-phéromone d'une zone de détection virtuelle. Figure 9 illustrates the activities of generating the e-pheromone of a virtual detection zone.
La figure 10 illustre la méthode de configuration des zone de détection virtuelles, stockage dans la base de donéne et l'activation de chargement de ces zones dans les smart phones des véhicules.Figure 10 illustrates the method of configuring the virtual detection zones, storage in the database and the activation of loading of these zones in the smart phones of the vehicles.
La figure 11 illustre le synoptique générale du système globale et renseigne sur l'éco-système Hadoop MongoDB d'entreposage des données. Figure 11 illustrates the overall synoptic of the global system and provides information on the Hadoop MongoDB data storage ecosystem.
La figure 12 illustre un itinérarire (artère du réseau) balisé par des zones de détection virtuelles. Figure 12 illustrates an itinerant (network artery) marked by virtual detection zones.
La figure 13 schématise la stratégie de régulation à base de commandes symoliques. Figure 13 shows the control strategy based on symolic commands.
La figure 14 illustre les itinérarires d'un réseau de trafic urbain.  Figure 14 illustrates the itineraries of an urban traffic network.
La figure 15 illustre le diagramme d'interactions de détection et de calcul des vitesses.  Figure 15 illustrates the pattern of detection and velocity calculation interactions.

Claims

Revendications claims
1. le système lTmS2 C proposé est caractérisé en ce qu'il comprend : les services d'un système de transport intelligent flou temps réel agile pour l'aide à la gestion, supervision et de contrôle des congestions du trafic dans un réseau urbain. Les services en question consentent la génération de l'e- phéromone floue gaussienne des zones de détection virtuelles définies sur le réseau à contrôler, et ce par le biais d'un processus de calcul fondé sur les schéma de l'évolution de l'e-phéromone modélisée par des nombres flous gaussiens et alimenté par les vitesses floues gaussiennes des véhicules issus des zones de détection virtuelles. L'e-phéromone floue gaussienne traduit l'importance de la congestion causée par les vitesses faibles de véhicules. Ces services assurent les fonctionnalités de commandes symboliques déclinées aux contrôleurs de feux pour réguler intelligemment les situations singulières du trafic. Les fonctionnalités proposées concernent : la configuration et la définition du contexte de supervision, de préparation de données, de collecte des données et de prétraitement (activité 1). Le système offre aussi un sous-système de simulation de trafic pour alimenter les zones de détection virtuelles (activité 2) et ce en temps réel et en continu. La génération de l'e-phéromone floue gaussienne est aussi proposée (activités 3-4). Les vitesses des véhicules et l'e-phéromone floue gaussienne des zones de détection virtuelles sont stockées dans une base de donnée de type entrepôt documents NoSQL. L'entrepôt est exploré pour produire des patterns de trafic pour des analyses statistiques d'évaluation des systèmes de mesures à base de GPS. Le système développe aussi une heuristique de commande symbolique sur les artères stratégiques du réseau (activités 5-6). Enfin, le système met en place le mécanisme de déploiement de la solution sur le terrain et en temps réel et donne la possibilité de génération et de stockage des résultats ainsi que la gestion ergonomique de l'interface homme-machine pour les conducteurs (activités 7-8). 1. LTMS system 2 C proposed is characterized in that it comprises: the services of a real-time fuzzy intelligent transport system for agile management support, monitoring and control of traffic congestion in an urban network . The services in question provide for the generation of the Gaussian fuzzy ePheromone of the virtual detection zones defined on the network to be controlled, and this by means of a calculation process based on the evolution schematics of the e -Pheromone modeled by Gaussian fuzzy numbers and fed by the Gaussian fuzzy velocities of the vehicles coming from the virtual detection zones. Gaussian fuzzy e-pheromone reflects the importance of congestion caused by low vehicle speeds. These services provide the functionality of symbolic commands available to fire controllers to intelligently regulate the unique situations of traffic. The proposed functionalities concern: configuration and definition of the context of supervision, data preparation, data collection and pretreatment (activity 1). The system also offers a traffic simulation subsystem to power the virtual detection zones (activity 2) in real time and continuously. The generation of Gaussian fuzzy e-pheromone is also proposed (activities 3-4). Vehicle velocities and Gaussian fuzzy e-pheromone virtual detection areas are stored in a NoSQL warehouse document database. The warehouse is being explored to produce traffic patterns for statistical analysis of evaluation of GPS-based measurement systems. The system also develops a symbolic command heuristic on the strategic arteries of the network (activities 5-6). Finally, the system sets up the deployment mechanism of the solution in the field and in real time and gives the possibility of generation and storage of results as well as the ergonomic management of the human-machine interface for drivers (activities 7). -8).
2. Le système lTmS2 C selon la revendication 1 est caractérisé en ce qu'il comprend la collecte des données, la configuration des zones de détection virtuelles, l'échange des données avec les véhicules intelligents équipé de smart phone avec GPS actif, les prétraitements et le déploiement de la solution de stockage (activité 1). 2. The lTmS 2 C system according to claim 1 is characterized in that it comprises the collection of data, the configuration of the virtual detection zones, the exchange of data with smart vehicles equipped with smart phones with active GPS, the preprocessing and deployment of the storage solution (activity 1).
3. Le système lTmS2 C selon la revendication 1 est caractérisé en ce qu'il permet d'élaborer les paramètres de création des vitesses floues gaussiennes nécessaires à la génération de l'e-phéromone floue. Cette revendication se réalise selon l'activité 2. 3. The lTmS 2 C system according to claim 1 is characterized in that it makes it possible to develop the parameters for creating the Gaussian fuzzy speeds necessary for the generation of the fuzzy e-pheromone. This claim is made according to activity 2.
4. Le système lTmS2 C selon la revendication 1 est caractérisé en ce qu'il englobe le processus d'élaboration des vitesses floues et de l'e-phéromone floue des zones de détection virtuelles. Cette revendication se décline selon l'activité 3. 4. The lTmS 2 C system according to claim 1 is characterized in that it encompasses the process of developing fuzzy speeds and fuzzy e-pheromone virtual detection areas. This claim is declined according to activity 3.
5. Le système lTmS2 C selon la revendication 1 est caractérisé en ce qu'il assure la génération de l'e-phéromone floue gaussienne des zones de détection virtuelles définies sur le réseau à contrôler. Cette génération suit trois étapes : le dépôt, la diffusion, la dissipation. La mise en œuvre du processus de génération se fait selon les prérogatives fournies dans les activités 3-4. 5. The lTmS 2 C system according to claim 1 is characterized in that it ensures the generation of Gaussian fuzzy e-pheromone virtual detection zones defined on the network to be controlled. This generation follows three stages: the deposition, the diffusion, the dissipation. The implementation of the generation process is done according to the prerogatives provided in activities 3-4.
6. Le système lTmS2 C selon la revendication 1 est caractérisé en ce qu'il garantit le calcul de la commande symbolique qui répond au mieux à l'agrégation artérielle de la quantité de l'e-phéromone floue gaussienne des zones de détection virtuelles définies sur le réseau à contrôler. La commande symbolique concerne les contrôleurs de carrefours. La mise en oeuvre du processus de calcul de la commande se fait selon les prérogatives fournies dans l'activité 6. 6. The lTmS 2 C system according to claim 1 is characterized in that it guarantees the calculation of the symbolic command that best responds to the arterial aggregation of the amount of the Gaussian fuzzy e-pheromone of the virtual detection zones. defined on the network to be controlled. The symbolic command concerns the controllers of intersections. The order calculation process is implemented according to the prerogatives provided in activity 6.
7. Le système lTmS2 C selon la revendication 1 est caractérisé en ce que le stockage et l'analytique sont réalisés dans une technologie NoSQL de type document json. Cette revendication concerne les activités 7-8. 7. The lTmS 2 C system according to claim 1 is characterized in that the storage and the analytics are made in a NoSQL technology of the json document type. This claim concerns activities 7-8.
8. Le système lTmS2 C selon la revendication 1 est caractérisé en ce que cette activité explore l'entrepôt des trajectoires temporelles des données et produit les mesures de trafic pour des analyses statistiques d'évaluation des systèmes de mesures à base de dispositif embarqué incluant le GPS. Cette revendication se réalise selon l'activité 8. 8. The lTmS 2 C system according to claim 1 is characterized in that this activity explores the warehouse of the temporal trajectories of the data and produces the traffic measurements for evaluation statistical analyzes of the embedded device based measurement systems including the GPS. This claim is made according to activity 8.
9. Le système lTmS2 C selon la revendication 1 est caractérisé en ce que les sorties des processus du système sont persistantes dans des documents Json pour le format d'échange pour cibler les dispositifs du système et ce selon la démarche déclinée dans les activités 7-8. 9. The lTmS 2 C system according to claim 1 is characterized in that the outputs of the system processes are persistent in Json documents for the exchange format to target the devices of the system and this according to the approach declined in the activities 7 -8.
PCT/MA2016/000008 2016-03-23 2016-03-23 System for supervising and controlling traffic WO2017164721A1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/MA2016/000008 WO2017164721A1 (en) 2016-03-23 2016-03-23 System for supervising and controlling traffic

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/MA2016/000008 WO2017164721A1 (en) 2016-03-23 2016-03-23 System for supervising and controlling traffic

Publications (1)

Publication Number Publication Date
WO2017164721A1 true WO2017164721A1 (en) 2017-09-28

Family

ID=57460563

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/MA2016/000008 WO2017164721A1 (en) 2016-03-23 2016-03-23 System for supervising and controlling traffic

Country Status (1)

Country Link
WO (1) WO2017164721A1 (en)

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110136443A (en) * 2019-05-24 2019-08-16 辽宁工业大学 A kind of traffic lights optimization method based on vehicle running state
CN110867072A (en) * 2019-12-02 2020-03-06 桂林理工大学 Vehicle tracking and dispatching system based on Beidou navigation and Hadoop technology
CN111583672A (en) * 2020-04-09 2020-08-25 江苏中科院智能科学技术应用研究院 Intelligent traffic light control method, system and device
CN113422764A (en) * 2021-06-18 2021-09-21 王君 Urban traffic information safety data layer system
CN113905567A (en) * 2021-10-21 2022-01-07 广东工贸职业技术学院 Integrated access terminal for transmitting WEB3D virtual technology of urban Internet of things
CN114548746A (en) * 2022-02-18 2022-05-27 深圳市格衡土地房地产资产评估咨询有限公司 Removal full-process monitoring system and method based on pheromone
CN116935654A (en) * 2023-09-15 2023-10-24 北京安联通科技有限公司 Smart city data analysis method and system based on data distribution value

Citations (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5289183A (en) 1992-06-19 1994-02-22 At/Comm Incorporated Traffic monitoring and management method and apparatus
US5317311A (en) 1988-11-14 1994-05-31 Martell David K Traffic congestion monitoring system
US5917432A (en) 1996-10-02 1999-06-29 Rathbone; Daniel B. Intelligent intersections
US6577946B2 (en) 2001-07-10 2003-06-10 Makor Issues And Rights Ltd. Traffic information gathering via cellular phone networks for intelligent transportation systems
US7685311B2 (en) 1999-05-03 2010-03-23 Digital Envoy, Inc. Geo-intelligent traffic reporter
US20100100307A1 (en) 2008-10-10 2010-04-22 Jin Hong Kim Universal GPS Traffic Monitoring System
US7912629B2 (en) 2007-11-30 2011-03-22 Nokia Corporation Methods, apparatuses, and computer program products for traffic data aggregation using virtual trip lines and a combination of location and time based measurement triggers in GPS-enabled mobile handsets
US20130041574A1 (en) * 2011-08-11 2013-02-14 Honda Motor Co., Ltd. Traffic Congestion Resolution and Driving Assistance System and Method
US8510025B2 (en) 2009-04-02 2013-08-13 Trafficcast International, Inc. Method and system for a traffic management network
US20130226622A1 (en) * 2012-02-08 2013-08-29 Tomtom North America Inc. Methods Using Speed Distribution Profiles
US8849309B2 (en) 2007-12-20 2014-09-30 Telecom Italia S.P.A. Method and system for forecasting travel times on roads
MA20150002A1 (en) 2013-06-05 2015-01-30 Karim Lamia A device, system and method for tracking the trajectory of customers as commercial space
US20150127245A1 (en) * 2013-11-01 2015-05-07 Here Global B.V. Traffic Data Simulator

Patent Citations (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5317311A (en) 1988-11-14 1994-05-31 Martell David K Traffic congestion monitoring system
US5289183A (en) 1992-06-19 1994-02-22 At/Comm Incorporated Traffic monitoring and management method and apparatus
US5917432A (en) 1996-10-02 1999-06-29 Rathbone; Daniel B. Intelligent intersections
US7685311B2 (en) 1999-05-03 2010-03-23 Digital Envoy, Inc. Geo-intelligent traffic reporter
US6577946B2 (en) 2001-07-10 2003-06-10 Makor Issues And Rights Ltd. Traffic information gathering via cellular phone networks for intelligent transportation systems
US7912629B2 (en) 2007-11-30 2011-03-22 Nokia Corporation Methods, apparatuses, and computer program products for traffic data aggregation using virtual trip lines and a combination of location and time based measurement triggers in GPS-enabled mobile handsets
US8849309B2 (en) 2007-12-20 2014-09-30 Telecom Italia S.P.A. Method and system for forecasting travel times on roads
US20100100307A1 (en) 2008-10-10 2010-04-22 Jin Hong Kim Universal GPS Traffic Monitoring System
US8510025B2 (en) 2009-04-02 2013-08-13 Trafficcast International, Inc. Method and system for a traffic management network
US20130041574A1 (en) * 2011-08-11 2013-02-14 Honda Motor Co., Ltd. Traffic Congestion Resolution and Driving Assistance System and Method
US20130226622A1 (en) * 2012-02-08 2013-08-29 Tomtom North America Inc. Methods Using Speed Distribution Profiles
MA20150002A1 (en) 2013-06-05 2015-01-30 Karim Lamia A device, system and method for tracking the trajectory of customers as commercial space
US20150127245A1 (en) * 2013-11-01 2015-05-07 Here Global B.V. Traffic Data Simulator

Non-Patent Citations (16)

* Cited by examiner, † Cited by third party
Title
"Methods and Tools for Reducing the Risks of Accidents and Terrorist Attack", January 2012, SPRINGER NETHERLANDS, ISBN: 978-94-007-26, article AZEDINE BOULMAKOUL; ADIL EL BOUZIRI: "Mobile Object Framework and Fuzzy Graph Modelling to Boost HazMat Telegeomonitoring", pages: 119 - 149
"OECD, Managing Urban Traffic Congestion, European Conférence of Ministers of Transport", OECD/ECMT 2007, 2007
"TRB, Quantifying congestion", NCHRP REPORT, vol. 1, 1997, pages 398
ACILE; EMMANUEL GARBOLINO: "Transportation Research Part C Emerging Technologies", vol. 48, November 2014, ELSEVIER, article MOHAMED HAITAM LAATABI; AZEDINE BOULMAKOUL; ROBERTO S: "A scalable communication middleware for real-time data collection of dangerous goods vehicle activities", pages: 404 - 417
AZEDINE BOULMAKOUL; A. DAISSAOUI; Z. HABBAS: "First spécifications of Urban Traffic-Congestion Forecasting Models", THE 27TH INTERNATIONAL CONFÉRENCE ON MICROELECTRONICS (ICM 2015) IEEE, 22 November 2015 (2015-11-22)
AZEDINE BOULMAKOUL; LAMIA KARIM; ADIL ELBOUZIRI; AHMED LBATH: "A System Architecture for Heterogeneous Moving-Object Trajectory Metamodel Using Generic Sensors: Tracking Airport Security Case Study", IEEE SYSTEMS JOURNAL, December 2013 (2013-12-01), pages 1 - 9
AZEDINE BOULMAKOUL; LAMIA KARIM; AHMED LBATH, MOVING OBJECT TRAJECTORIES META-MODEL AND SPATIO-TEMPORAL QUERIES.
AZEDINE BOULMAKOUL; LAMIA KARIM; AHMED LBATH: "A High Performance Scalable Data Collection System for Moving Objects", INTERNATIONAL JOURNAL OF COMPUTER APPLICATIONS, vol. 67, no. 9, April 2013 (2013-04-01), pages 36 - 43
AZEDINE BOULMAKOUL; LAMIA KARIM; MERIEM MANDAR; ABDELFATTAH IDRI; ABDELLAH DAISSAOUI: "Towards Scalable Distributed Framework for Urban Congestion Traffic Patterns Warehousing. Applied Comp", INT. SOFT COMPUTING, 2015, pages 578601.1 - 578601.12
BELL MC; SCEMAMA G; IBBETSON LJ: "Advanced Telematics in Road Transport: Proceedings of the EC: DRIVE Conférence", vol. 1, February 1991, ELSEVIER, article "CLAIRE: An Expert System for Congestion Management", pages: 596 - 614
BOULMAKOUL A: "Approche Logique du Contrôle Symbolique", 9ÈME CONGRÈS RECONNAISSANCE DES FORMES ET INTELLIGENCE ARTIFICIELLE (RFIA, 1994, pages 101 - 110
BOULMAKOUL A; SELLAM S; BOULMAKOUL A.; SELLAM S: "Artificial Intelligence in Traffic Engineering", January 1993, VSP INTERNATIONAL SCIENCE PUBLISHER, article "Intelligent Intersection : Artificial Intelligence and Computer Vision Techniques for Automatic Incident Détection", pages: 189 - 200
G. SCEMAMA; B. FORASTE: "An expert system approach to traffic congestion", RECHERCHE, TRANSPORTS, SÉCURITÉ RTS, September 1986 (1986-09-01), pages 17 - 22
IOSIS: "Innovation and News Trends in Information Systems", November 2013, ISBN: 978-9954-34-3, ISSN: 2351-9215, article MOHAMED HAITAM LAARABI; AZEDINE BOULMAKOUL; ROBERTO SACILE; EMMANUEL GARBOLINO: "An Overview on an Intelligent Transportation System (ITS) based on Agents, Time-Dependent Network and Fuzzy Travel-Time Cost"
MASULLI, FRANCESCO, PASI, GABRIELLA, YAGER, RONALD: "Fuzzy Logic and Applications Lecture Notes in Computer Science", vol. 8256, 19 November 2013, SPRINGER INTERNATIONAL PUBLISHING, ISBN: 978-3-319-031, article AZEDINE BOULMAKOUL; HAITAM LAARABI; ROBERTO SACILE; EMMANUEL GARBOLINO: "Ranking Triangular Fuzzy Numbers using Fuzzy Set Inclusion Index", pages: 100 - 108
SCEMAMA, G.; CARIES, O.: "CLAIRE-SITI, public and road transport network management control: a unified approach,in Road Transport Information and Control, 2004", RTIC 2004. 12TH IEE INTERNATIONAL CONFÉRENCE, 20 April 2004 (2004-04-20), pages L 1 - 18

Cited By (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110136443A (en) * 2019-05-24 2019-08-16 辽宁工业大学 A kind of traffic lights optimization method based on vehicle running state
CN110136443B (en) * 2019-05-24 2020-09-29 辽宁工业大学 Traffic signal lamp optimization method based on vehicle driving state
CN110867072A (en) * 2019-12-02 2020-03-06 桂林理工大学 Vehicle tracking and dispatching system based on Beidou navigation and Hadoop technology
CN111583672A (en) * 2020-04-09 2020-08-25 江苏中科院智能科学技术应用研究院 Intelligent traffic light control method, system and device
CN111583672B (en) * 2020-04-09 2021-11-12 江苏中科院智能科学技术应用研究院 Intelligent traffic light control method, system and device
CN113422764A (en) * 2021-06-18 2021-09-21 王君 Urban traffic information safety data layer system
CN113905567A (en) * 2021-10-21 2022-01-07 广东工贸职业技术学院 Integrated access terminal for transmitting WEB3D virtual technology of urban Internet of things
CN114548746A (en) * 2022-02-18 2022-05-27 深圳市格衡土地房地产资产评估咨询有限公司 Removal full-process monitoring system and method based on pheromone
CN116935654A (en) * 2023-09-15 2023-10-24 北京安联通科技有限公司 Smart city data analysis method and system based on data distribution value
CN116935654B (en) * 2023-09-15 2023-12-01 北京安联通科技有限公司 Smart city data analysis method and system based on data distribution value

Similar Documents

Publication Publication Date Title
WO2017164721A1 (en) System for supervising and controlling traffic
US10984652B2 (en) Method and system for modeling and processing vehicular traffic data and information and applying thereof
Yang et al. Evaluation of short-term freeway speed prediction based on periodic analysis using statistical models and machine learning models
US9536146B2 (en) Determine spatiotemporal causal interactions in data
US20030135304A1 (en) System and method for managing transportation assets
US20160021512A1 (en) Systems and methods for indoor location services
Antoniou et al. Evaluation of diversion strategies using dynamic traffic assignment
Aljamal et al. Developing data-driven approaches for traffic density estimation using connected vehicle data
Servizi et al. Mining User Behaviour from Smartphone data: a literature review
JPWO2018101074A1 (en) Traffic situation estimation device, traffic situation estimation method, program, and output device
US10706720B2 (en) Predicting vehicle travel times by modeling heterogeneous influences between arterial roads
Gupta et al. LSTM based real-time smart parking system
Klunder et al. The effect of inaccurate traffic data for ramp metering: Comparing loop detectors and cameras using information utility
Gong et al. Dispatching/routing of emergency vehicles in a disaster environment using data fusion concepts
Viti et al. National data warehouse: how the Netherlands is creating a reliable, widespread, accessible data bank for traffic information, monitoring, and road network control
Ko et al. Intelligence in traffic simulation model: Modeling congested network
Shirazi et al. Intersection analysis using computer vision techniques with SUMO
Hayashi et al. Prioritization of Lane-Specific Traffic Jam Detection for Automotive Navigation Framework Utilizing Suddenness Index and Automatic Threshold Determination
Värv Travel Time Prediction Based on Raw GPS Data
Sujatha et al. Web application for traffic monitoring and guidance
Suh Application of Real-time Sensor Data to Evaluation of Performance of Ad Hoc Distributed Traffic Simulation.
Salaymeh Machine Learning Techniques for Automated Traffic Signal Detection and Timing
Shabestary Deep Reinforcement Learning Approach to Multimodal Adaptive Traffic Signal Control
Thompson et al. All-in-One Urban Mobility Mapping Application with Optional Routing Capabilities
Kruetet et al. Integrating Graph Neural Network and GPS Data for Hourly Travel Time Estimation in Bangkok Rama-4 Road Network

Legal Events

Date Code Title Description
NENP Non-entry into the national phase

Ref country code: DE

121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 16805224

Country of ref document: EP

Kind code of ref document: A1

122 Ep: pct application non-entry in european phase

Ref document number: 16805224

Country of ref document: EP

Kind code of ref document: A1