“…Overall, it appears that most previous works have searched for an integrated indoor and outdoor representation, while others take into account a multi-level and flexible semantic representation in which human trajectories can be derived from crowd-sourcing data. In related work, we introduced the main principles of a semantic trajectory model in indoor and outdoor spaces (Noureddine et al, 2020). Based on the modelling principles introduced in this early work, we go further in this article by providing, first, formal support for the semantic-based modelling approach, second, flexible logical data manipulation defined at different levels of abstraction and that implements and makes a difference between graph queries and graph analytics, and finally, a computational implementation on top of the Neo4j graph database.…”
Section: Hierarchical Spacementioning
confidence: 99%
“…A series of data processing examples are evaluated and discussed. This research is an extension of our previous work that introduced a preliminary semantic trajectory model for human mobility in both indoor and outdoor environments (Noureddine, Ray, & Claramunt, 2020). The main novelty of this new article relies on a hierarchical indoor and outdoor spatial model associated with a semantic model.…”
With the growth of location-based information and the widespread adoption of mobile devices and connected sensors, human mobility has recently emerged as an important research area. Nowadays, the exponential development of mobile sensors and the Internet of Things offers many opportunities for the integration of real-time data on humans acting in indoor and outdoor environments. Moreover, mobile crowd-sensing allows volunteers to actively provide real-time trajectory and activity data (Guo et al., 2015). However, such crowd-sourcing data are most often heterogeneous in space and time and require a flexible data model that can integrate the data as they are and provide data manipulation and analysis capabilities to reformat the data at the appropriate level of abstraction. Understanding urban mobility patterns, together with associated contextual information, requires a sound integration of the modelling level within current information infrastructures. Such development appears as
“…Overall, it appears that most previous works have searched for an integrated indoor and outdoor representation, while others take into account a multi-level and flexible semantic representation in which human trajectories can be derived from crowd-sourcing data. In related work, we introduced the main principles of a semantic trajectory model in indoor and outdoor spaces (Noureddine et al, 2020). Based on the modelling principles introduced in this early work, we go further in this article by providing, first, formal support for the semantic-based modelling approach, second, flexible logical data manipulation defined at different levels of abstraction and that implements and makes a difference between graph queries and graph analytics, and finally, a computational implementation on top of the Neo4j graph database.…”
Section: Hierarchical Spacementioning
confidence: 99%
“…A series of data processing examples are evaluated and discussed. This research is an extension of our previous work that introduced a preliminary semantic trajectory model for human mobility in both indoor and outdoor environments (Noureddine, Ray, & Claramunt, 2020). The main novelty of this new article relies on a hierarchical indoor and outdoor spatial model associated with a semantic model.…”
With the growth of location-based information and the widespread adoption of mobile devices and connected sensors, human mobility has recently emerged as an important research area. Nowadays, the exponential development of mobile sensors and the Internet of Things offers many opportunities for the integration of real-time data on humans acting in indoor and outdoor environments. Moreover, mobile crowd-sensing allows volunteers to actively provide real-time trajectory and activity data (Guo et al., 2015). However, such crowd-sourcing data are most often heterogeneous in space and time and require a flexible data model that can integrate the data as they are and provide data manipulation and analysis capabilities to reformat the data at the appropriate level of abstraction. Understanding urban mobility patterns, together with associated contextual information, requires a sound integration of the modelling level within current information infrastructures. Such development appears as
“…Indoor Semantic Trajectory Extraction. Recent studies [7], [9], [39]- [41] investigated the extraction of semantic positions in the indoor environment and its extension. The multi-slot BLE positioning system [9] estimates both cartesian and semantic-labeled positions in a mixed indoor and outdoor environment.…”
Section: Related Workmentioning
confidence: 99%
“…Nonetheless, the discovered association rule may not be fully maximized because the size of trajectory dataset is highly reduced due to positioning errors and bad data quality. An indoor-outdoor spatial representation unification [41] worked on the matching human movement in indoor and outdoor space to the semantic trajectory. The representation successfully models the semantic trajectory but only extend the work to the query and not detailed in semantic trajectory extraction.…”
Indoor location-based services have been widely investigated to take advantage of semantic trajectories for providing user oriented services in indoor environments. Although indoor semantic trajectories can provide seamless understanding to users regarding the provided location-based services, studies on the application of deep learning approaches for robust and valid semantic indoor localization are lacking. In this study, we combined a stacked denoising autoencoder and long short term memory technique with a rule-based refinement method applying a rule-based hidden Markov model (HMM) to perform robust and valid semantic trajectory extraction. In particular, our rule-based HMM approach incorporates a direct set of rules into HMM to resolve invalid movements of the extracted semantic trajectories and is extensible to various deep learning techniques. We compared the performance of our proposed approach with that of other cutting-edge deep learning approaches on two different real-world data sets. The experimental results demonstrate the feasibility of our proposed approach to produce more robust and valid semantic trajectories.
“…As the Open Geospatial Consortium's (OGC) Indoor Geography Markup Simply put, to fully reflect navigation, the integration of indoor and outdoor network data must be established. While there is literature on continuous indoor-outdoor positioning techniques [12] and even on semantic trajectory models [13], a deficiency of integration in the space modeling aspect remains. At the same time, there are numerous similarities between these two spaces, unique properties of each that motivate separate data modeling to complicate their integration.…”
Spaces are continuous realms where human beings freely navigate, such as from indoor to outdoor and optionally to another indoor space. However, currently available data models to represent space for navigation do not entirely reflect this continuity of freedom and movement. Data conversion or complications in implementation hinder current approaches to link indoor space with outdoor space due to the variety of present data models. Furthermore, this representation of indoor–outdoor connection becomes oversimplified during the integration process. Consequently, location-based applications based on these datasets are limited in conveying mobility within these spaces and aiding navigation activity. This paper defines a framework for integrating indoor and outdoor navigable space to enable seamless navigation. This model enables the connection between indoor and outdoor navigation networks. We describe the connections between these networks through spatial relationships, which can be generalized to represent various cases of indoor–outdoor transitional spaces. Using sample datasets, we demonstrate the framework’s potential to provide a seamless connection between indoor and outdoor space in a route analysis experiment.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.