smart.lab.tunisia@gmail.com +216 71 588 443
Connexion

Thouraya Sakouhi

Informations générales

Thouraya Sakouhi
Grade

Maître Assistant

Biographie courte

Docteur en Informatique de L’ISG de Tunis et Maitre-Assistante à l’Université de Carthage, ISG Bizerte.

Axes de recherche

Artificial Intelligence
Data Mining
Machine Learning

Publications

  • 2024
    Thouraya Sakouhi, Jalel Akaichi

    Clustering-based multidimensional sequential pattern mining of semantic trajectories

    International Journal of Data Mining, Modelling and Management, 16(2), 148-175., 2024

    Résumé

    Knowledge discovery from mobility data is about identifying behaviours from trajectories. In fact, mining masses of trajectories is required to have an overview of this data, notably, investigate the relationship between different entities movement. Most state-of-the-art work in this issue operates on raw trajectories. Nevertheless, behaviours discovered from raw trajectories are not as rich and meaningful as those discovered from semantic trajectories. In this paper, we establish a mining approach to extract patterns from semantic trajectories. We propose to apply sequential pattern mining based on a pre-processing step of clustering to alleviate the former's temporal complexity. Mining considers the spatial and temporal dimensions at different levels of granularity providing then richer and more insightful patterns about humans behaviour. We evaluate our work on tourists semantic trajectories in Kyoto. Results showed the effectiveness and efficiency of our model compared to state-of-the-art work.

  • Thouraya Sakouhi, Jalel Akaichi

    Dynamic and multi-source semantic annotation of raw mobility data using geographic and social media data

    Pervasive and Mobile Computing, 71, 101310., 2021

    Résumé

    Nowadays, positioning technologies have become widely available providing then large datasets of individuals’ mobility data. Actually, annotating raw traces with contextual information brings semantics to them and then provides a better understanding of people behavior. To do so, literature work explored novel techniques to enrich raw mobility data with contextual information using either geographic context represented by landmarks/points of interest or widely used social media feeds. Accordingly, in this work, a novel approach integrating three data sources: raw mobility data, geographic information and social media feeds for a two-fold trajectory semantic annotation process is presented. In a first step, structured trajectories are constructed using geographic information. Later, the former are annotated by event-related words grasped from social media. Indeed, combining both data sources could result in a more complete annotation of trajectories. The proposed approach is experimented and evaluated on datasets of tourists in Kyoto. Results showed that the proposed approach quantitatively performed well compared to previous work in terms of precision of annotation words that maintained  when recall reached 50%, while improving its quality by consolidating both sources of semantics.

  • Thouraya Sakouhi, Jamal Malki, Jalel Akaichi

    A Mobility Data Model for Web-Based Tourists Tracking

    In The 14th International Baltic Conference on Databases and Information Systems (BalticDB&IS 2020)., 2020

    Résumé

    Tracking tourists activities at different levels of their journeys provides an overview on their mobility and a comprehension of their behavior and preferences. Most information related to tourism services and tourists are collected and stored through web platforms. In fact, self-drive tourists access touristic information available on the web to plan for their trips. Accordingly, tourism professionals track their requirements in touristic information and then their mobility. Yet, since touristic information is managed at a territorial level, tracking tourists' movement by tourism professionals, out of their territory, is not a straightforward task. Accordingly, the latters do not have a complete overview of tourists movements. Throughout this paper authors will start by discussing mobility data capture through the web and the related challenges. Then, they'll introduce an integrated mobility data model for tracking tourists.

  • Marwa Manaa, Thouraya Sakouhi, Jalel Akaichi

    A trajectory ontology design pattern for semantic trajectory data warehouses: behavior analysis and animal tracking case studies

    In Emerging perspectives in big data warehousing (pp. 83-104). IGI Global., 2019

    Résumé

    Mobility data became an important paradigm for computing performed in various areas. Mobility data is considered as a core revealing the trace of mobile objects displacements. While each area presents a different optic of trajectory, they aim to support mobility data with domain knowledge. Semantic annotations may offer a common model for trajectories. Ontology design patterns seem to be promising solutions to define such trajectory related pattern. They appear more suitable for the annotation of multiperspective data than the only use of ontologies. The trajectory ontology design pattern will be used as a semantic layer for trajectory data warehouses for the sake of analyzing instantaneous behaviors conducted by mobile entities. In this chapter, the authors propose a semantic approach for the semantic modeling of trajectory and trajectory data warehouses based on a trajectory ontology design pattern. They validate the proposal through real case studies dealing with behavior analysis and animal tracking case studies.

  • Thouraya Sakouhi, Hadhami Ounissi, Marwa Manaa, Yasser Al Mashhour

    Immersive Analytics for Floods Management Semantic Trajectory Data Warehouse Ontology

    Immersive Analytics for Floods Management Semantic Trajectory Data Warehouse Ontology. iLRN 2018 Montana, 169., 2018

    Résumé

    Semantic Immersive Analytics is a new paradigm that has the capability for visualizing ontologies and meta-data including annotated web-documents, images, and digital media such as audio and video clips in a synthetic three-dimensional semi-immersive environment. More importantly, it supports visual semantic analytics, whereby an analyst can interactively investigate complex relationships between heterogeneous information and supports query processing and semantic association discovery. In our previous work we proposed a Semantic Trajectory Data Warehouse Ontology (STrDWO) [15], a tool supporting designers at the modeling of ontology-based trajectory data warehouses. In here, we intend to integrate our aforementioned tool with augmented Reality (AR) technologies to provide multi-sensory interfaces that support collaboration and allow users to immerse themselves in their data in a way that supports real-world geo-space analytics tasks. To do so, we present a Semantic trajectory data warehouse having an ontology-based multidimensional model. We illustrate our approach by a case study dealing with floods management.

  • Thouraya Sakouhi, Jalel Akaichi, Usman Ahmed

    Computing Semantic Trajectories: Methods and Used Techniques

    In: De Pietro, G., Gallo, L., Howlett, R., Jain, L. (eds) Intelligent Interactive Multimedia Systems and Services 2017. KES-IIMSS-18 2018. Smart Innovation, Systems and Technologies, vol 76. Springer, Cham. https://doi.org/10.1007/978-3-319-59480-4_39, 2017

    Résumé

    The widespread use of mobile devices generates huge amount of location data. The generated data is useful for many applications, including location-based services such as outdoor sports forums, routine prediction, location-based activity recognition and location-based social networking. Sharing individuals’ trajectories and annotating them with activities, for example a tourist transportation mode during his trip, helps bringing more semantics to the GPS data. Indeed, this provides a better understanding of the user trajectories, and then more interesting location-based services. To address this issue, diverse range of novel techniques in the literature are explored to enrich this data with semantic information, notably, machine learning and statistical algorithms. In this work, we focused, at a first level, on exploring and classifying the literature works related to semantic trajectory computation. Secondly, we capitalized and discussed the benefits and limitations of each approach.

  • Thouraya Sakouhi, Jalel Akaichi, Jamel Malki, Alain Bouju, Roua Wannous

    Inference on Semantic Trajectory Data Warehouse Using an Ontological Approach

    In: Andreasen, T., Christiansen, H., Cubero, JC., Raś, Z.W. (eds) Foundations of Intelligent Systems. ISMIS 2014. Lecture Notes in Computer Science(), vol 8502. Springer, Cham. https://doi.org/10.1007/978-3-319-08326-1_47, 2014

    Résumé

    Using location aware devices is getting more and more spread, generating then a huge quantity of mobility data. The latter describes the movement of mobile objects and is called as well Trajectory data. In fact, these raw trajectories lack contextual information about the moving object goals and his activity during the travel. Therefore, the former must be enhanced with semantic information to be called then Semantic Trajectory. The semantic models proposed in the literature are in many cases ontology-based, and are composed of thematic, temporal and spatial ontologies and rules to support inference and reasoning tasks on data. Thus, calculating inference on moving objects trajectories considering all thematic, spatial, and temporal rules can be very long depending on the amount of data involved in this process. On the other side, TDW is an efficient tool for analyzing and extracting valuable information from raw mobility data. For that we propose throughout this work a TDW design, inspired from an ontology model. We will emphasis the trajectory to be seen as a first class semantic concept. Then we apply the inference on the proposed model to see if we can enhance it and make the complexity of this mechanism manageable.