A multi‐agent system for itinerary suggestion in smart environments

Abstract Modern smart environments pose several challenges, among which the design of intelligent algorithms aimed to assist the users. When a variety of points of interest are available, for instance, trajectory recommendations are needed to suggest users the most suitable itineraries based on thei...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Alessandra De Paola, Salvatore Gaglio, Andrea Giammanco, Giuseppe Lo Re, Marco Morana
Formato: article
Lenguaje:EN
Publicado: Wiley 2021
Materias:
Acceso en línea:https://doaj.org/article/c89374e593824ba084def9ac170a3be1
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:c89374e593824ba084def9ac170a3be1
record_format dspace
spelling oai:doaj.org-article:c89374e593824ba084def9ac170a3be12021-11-17T03:12:43ZA multi‐agent system for itinerary suggestion in smart environments2468-232210.1049/cit2.12056https://doaj.org/article/c89374e593824ba084def9ac170a3be12021-12-01T00:00:00Zhttps://doi.org/10.1049/cit2.12056https://doaj.org/toc/2468-2322Abstract Modern smart environments pose several challenges, among which the design of intelligent algorithms aimed to assist the users. When a variety of points of interest are available, for instance, trajectory recommendations are needed to suggest users the most suitable itineraries based on their interests and contextual constraints. Unfortunately, in many cases, these interests must be explicitly requested and their lack causes the so‐called cold‐start problem. Moreover, lengthy travelling distances and excessive crowdedness of specific points of interest make itinerary planning more difficult. To address these aspects, a multi‐agent itinerary suggestion system that aims at assisting the users in an online and collaborative way is proposed. A profiling agent is responsible for the detection of groups of users whose movements are characterised by similar semantic, spatial and temporal features; then, a recommendation agent leverages contextual information and dynamically associates the current user with the trajectory clusters according to a Multi‐Armed Bandit policy. Framing the trajectory recommendation as a reinforcement learning problem permits to provide high‐quality suggestions while avoiding both cold‐start and preference elicitation issues. The effectiveness of the approach is demonstrated by some deployments in real‐life scenarios, such as smart campuses and theme parks.Alessandra De PaolaSalvatore GaglioAndrea GiammancoGiuseppe Lo ReMarco MoranaWileyarticleartificial intelligencepattern recognitionComputational linguistics. Natural language processingP98-98.5Computer softwareQA76.75-76.765ENCAAI Transactions on Intelligence Technology, Vol 6, Iss 4, Pp 377-393 (2021)
institution DOAJ
collection DOAJ
language EN
topic artificial intelligence
pattern recognition
Computational linguistics. Natural language processing
P98-98.5
Computer software
QA76.75-76.765
spellingShingle artificial intelligence
pattern recognition
Computational linguistics. Natural language processing
P98-98.5
Computer software
QA76.75-76.765
Alessandra De Paola
Salvatore Gaglio
Andrea Giammanco
Giuseppe Lo Re
Marco Morana
A multi‐agent system for itinerary suggestion in smart environments
description Abstract Modern smart environments pose several challenges, among which the design of intelligent algorithms aimed to assist the users. When a variety of points of interest are available, for instance, trajectory recommendations are needed to suggest users the most suitable itineraries based on their interests and contextual constraints. Unfortunately, in many cases, these interests must be explicitly requested and their lack causes the so‐called cold‐start problem. Moreover, lengthy travelling distances and excessive crowdedness of specific points of interest make itinerary planning more difficult. To address these aspects, a multi‐agent itinerary suggestion system that aims at assisting the users in an online and collaborative way is proposed. A profiling agent is responsible for the detection of groups of users whose movements are characterised by similar semantic, spatial and temporal features; then, a recommendation agent leverages contextual information and dynamically associates the current user with the trajectory clusters according to a Multi‐Armed Bandit policy. Framing the trajectory recommendation as a reinforcement learning problem permits to provide high‐quality suggestions while avoiding both cold‐start and preference elicitation issues. The effectiveness of the approach is demonstrated by some deployments in real‐life scenarios, such as smart campuses and theme parks.
format article
author Alessandra De Paola
Salvatore Gaglio
Andrea Giammanco
Giuseppe Lo Re
Marco Morana
author_facet Alessandra De Paola
Salvatore Gaglio
Andrea Giammanco
Giuseppe Lo Re
Marco Morana
author_sort Alessandra De Paola
title A multi‐agent system for itinerary suggestion in smart environments
title_short A multi‐agent system for itinerary suggestion in smart environments
title_full A multi‐agent system for itinerary suggestion in smart environments
title_fullStr A multi‐agent system for itinerary suggestion in smart environments
title_full_unstemmed A multi‐agent system for itinerary suggestion in smart environments
title_sort multi‐agent system for itinerary suggestion in smart environments
publisher Wiley
publishDate 2021
url https://doaj.org/article/c89374e593824ba084def9ac170a3be1
work_keys_str_mv AT alessandradepaola amultiagentsystemforitinerarysuggestioninsmartenvironments
AT salvatoregaglio amultiagentsystemforitinerarysuggestioninsmartenvironments
AT andreagiammanco amultiagentsystemforitinerarysuggestioninsmartenvironments
AT giuseppelore amultiagentsystemforitinerarysuggestioninsmartenvironments
AT marcomorana amultiagentsystemforitinerarysuggestioninsmartenvironments
AT alessandradepaola multiagentsystemforitinerarysuggestioninsmartenvironments
AT salvatoregaglio multiagentsystemforitinerarysuggestioninsmartenvironments
AT andreagiammanco multiagentsystemforitinerarysuggestioninsmartenvironments
AT giuseppelore multiagentsystemforitinerarysuggestioninsmartenvironments
AT marcomorana multiagentsystemforitinerarysuggestioninsmartenvironments
_version_ 1718426016880263168