Centre dedocumentation
scientifique

Street-level traffic flow and context sensing analysis through semantic integration of multisource geospatial data / Yatao Zhang in Transactions in GIS, vol 26 n° 8 (December 2022)  

Public [article]  inTransactions in GIS > vol 26 n° 8 (December 2022) . - pp 3330 - 3348 Titre : Street-level traffic flow and context sensing analysis through semantic integration of multisource geospatial data Type de document : Article/Communication Auteurs : Yatao Zhang, Auteur ; Martin Raubal, Auteur Année de publication : 2022 Article en page(s) : pp 3330 - 3348 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Analyse spatiale [Termes IGN] allocation de Dirichlet latente [Termes IGN] appariement sémantique [Termes IGN] approche hiérarchique [Termes IGN] données multisources [Termes IGN] espace urbain [Termes IGN] flux [Termes IGN] milieu urbain [Termes IGN] point d'intérêt [Termes IGN] segmentation en régions [Termes IGN] Singapour [Termes IGN] trafic routier [Termes IGN] utilisation du sol Résumé : (auteur) Sensing urban spaces from multisource geospatial data is vital to understanding the transportation system in the urban context. However, the complexity of urban context and its indirect interaction with traffic flow deepen the difficulty of exploring their relationship. This study proposes a geo-semantic framework first to generate semantic representations of multi-hierarchical urban context and street-level traffic flow, and then investigate their mutual correlation and predictability using a novel semantic matching method. The results demonstrate that each street is associated with its multi-hierarchical spatial signatures of urban context and street-level temporal signatures of traffic flow. The correlation between urban context and traffic flow displays higher values after semantic matching than those in multi-hierarchies. Moreover, we found that utilizing traffic flow to predict urban context results in better accuracy than the reversed prediction. The results of signature analysis and relationship exploration can contribute to a deeper understanding of context-aware transportation research. Numéro de notice : A2022-916 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article DOI : 10.1111/tgis.13005 Date de publication en ligne : 27/11/2022 En ligne : https://doi.org/10.1111/tgis.13005 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=102348 [article]

Unsupervised generative models for data analysis and explainable artificial intelligence / Mohanad Abukmeil (2022)  

Public Titre : Unsupervised generative models for data analysis and explainable artificial intelligence Type de document : Thèse/HDR Auteurs : Mohanad Abukmeil, Auteur ; Vincenzo Piuri, Directeur de thèse Editeur : Milan [Italie] : Università di Milano Année de publication : 2022 Importance : 194 p. Format : 21 x 30 cm Note générale : bibliographie Thèse de Doctorat spécialité Informatique, Université de Milan Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Intelligence artificielle [Termes IGN] allocation de Dirichlet latente [Termes IGN] analyse en composantes indépendantes [Termes IGN] analyse en composantes principales [Termes IGN] apprentissage automatique [Termes IGN] apprentissage non-dirigé [Termes IGN] modèle stochastique [Termes IGN] navigation autonome [Termes IGN] reconstruction d'image [Termes IGN] réseau antagoniste génératif [Termes IGN] séparation aveugle de source Résumé : (auteur) For more than a century, the methods of learning representation and the exploration of the intrinsic structures of data have developed remarkably and currently include supervised, semi-supervised, and unsupervised methods. However, recent years have witnessed the flourishing of big data, where typical dataset dimensions are high, and the data can come in messy, missing, incomplete, unlabeled, or corrupted forms. Consequently, discovering and learning the hidden structure buried inside such data becomes highly challenging. From this perspective, latent data analysis and dimensionality reduction play a substantial role in decomposing the exploratory factors and learning the hidden structures of data, which encompasses the significant features that characterize the categories and trends among data samples in an ordered manner. That is by extracting patterns, differentiating trends, and testing hypotheses to identify anomalies, learning compact knowledge, and performing many different machine learning (ML) tasks such as classification, detection, and prediction. Unsupervised generative learning (UGL) methods are a class of ML characterized by their possibility of analyzing and decomposing latent data, reducing dimensionality, visualizing the manifold of data, and learning representations with limited levels of predefined labels and prior assumptions. Furthermore, explainable artificial intelligence (XAI) is an emerging field of ML that deals with explaining the decisions and behaviors of learned models. XAI is also associated with UGL models to explain the hidden structure of data, and to explain the learned representations of ML models. However, the current UGL models lack large-scale generalizability and explainability in the testing stage, which leads to restricting their potential in ML and XAI applications. To overcome the aforementioned limitations, this thesis proposes innovative methods that integrate UGL and XAI to enable data factorization and dimensionality reduction to improve the generalizability of the learned ML models. Moreover, the proposed methods enable visual explainability in modern applications as anomaly detection and autonomous driving systems. The main research contributions are listed as follows: * A novel overview of UGL models including blind source separation (BSS), manifold learning (MfL), and neural networks (NNs). Also, the overview considers open issues and challenges among each UGL method. * An innovative method to identify the dimensions of the compact feature space via a generalized rank in the application of image dimensionality reduction. * An innovative method to hierarchically reduce and visualize the manifold of data to improve the generalizability in limited data learning scenarios, and computational complexity reduction applications. * An original method to visually explain autoencoders by reconstructing an attention map in the application of anomaly detection and explainable autonomous driving systems. The novel methods introduced in this thesis are benchmarked on publicly available datasets, and they outperformed the state-of-the-art methods considering different evaluation metrics. Furthermore, superior results were obtained with respect to the state-of-the-art to confirm the feasibility of the proposed methodologies concerning the computational complexity, availability of learning data, model explainability, and high data reconstruction accuracy. Note de contenu : 1- Introduction 2- State of the art of unsupervised generative learning (UGL) models 3- Research challenges and open issues of UGL models 4- UGL models for dimensionality reduction and XAI 5- Conclusion and future works Numéro de notice : 15307 Affiliation des auteurs : non IGN Thématique : INFORMATIQUE Nature : Thèse étrangère Note de thèse : Thèse de doctorat : Informatique : Milan : 2022 DOI : 10.13130/abukmeil-mohanad_phd2022-01-24 En ligne : http://dx.doi.org/10.13130/abukmeil-mohanad_phd2022-01-24 Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=99965

A topic model based framework for identifying the distribution of demand for relief supplies using social media data / Ting Zhang in International journal of geographical information science IJGIS, vol 35 n° 11 (November 2021)  

Public [article]  inInternational journal of geographical information science IJGIS > vol 35 n° 11 (November 2021) . - pp 2216 - 2237 Titre : A topic model based framework for identifying the distribution of demand for relief supplies using social media data Type de document : Article/Communication Auteurs : Ting Zhang, Auteur ; Shi Shen, Auteur ; Changxiu Cheng, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : pp 2216 - 2237 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Analyse spatiale [Termes IGN] allocation de Dirichlet latente [Termes IGN] cartographie thématique [Termes IGN] catastrophe naturelle [Termes IGN] cyclone [Termes IGN] distribution spatiale [Termes IGN] données issues des réseaux sociaux [Termes IGN] Pacifique ouest [Termes IGN] Philippines [Termes IGN] répertoire toponymique [Termes IGN] secours d'urgence Résumé : (auteur) Natural disasters have caused substantial economic losses and numerous casualties. The demand analysis of relief supplies is the premise and basis for efficient relief operations after disasters. With the widespread use of social media, it has become a vital channel for people to report their demand for relief supplies and provides a way to obtain information on disaster areas. Therefore, we present a topic model-based framework and establish a demand dictionary and a gazetteer that aims to identify the spatial distribution of the demand for relief supplies by using social media data. Taking the 2013 Typhoon Haiyan (also called Yolanda) as a case study, we identify the potential topics of tweets with the biterm topic model, screen the tweets related to demands, and obtain the demand and location information from tweets to study the distribution of the relief supplies needs. The results show that, based on the demand dictionary, a gazetteer and the biterm topic model, the effective demand for relief supplies can be extracted from tweets. The proposed framework is feasible for the identification of accurate demand information and its distribution. Further, this framework can be applied to other types of disaster responses and can facilitate relief operations. Numéro de notice : A2021-757 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/13658816.2020.1869746 Date de publication en ligne : 07/01/2021 En ligne : https://doi.org/10.1080/13658816.2020.1869746 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=98772 [article]

Réservation

Réserver ce document

Exemplaires (1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
079-2021111	SL	Revue	Centre de documentation	Revues en salle	Disponible

Land cover harmonization using Latent Dirichlet Allocation / Zhan Li in International journal of geographical information science IJGIS, vol 35 n° 2 (February 2021)  

Public [article]  inInternational journal of geographical information science IJGIS > vol 35 n° 2 (February 2021) . - pp 348 - 374 Titre : Land cover harmonization using Latent Dirichlet Allocation Type de document : Article/Communication Auteurs : Zhan Li, Auteur ; Joanne C. White, Auteur ; Michael A. Wulder, Auteur Année de publication : 2021 Article en page(s) : pp 348 - 374 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Analyse spatiale [Termes IGN] allocation de Dirichlet latente [Termes IGN] Canada [Termes IGN] carte d'occupation du sol [Termes IGN] chevauchement [Termes IGN] erreur de classification [Termes IGN] harmonisation des données [Termes IGN] matrice d'erreur [Termes IGN] matrice de co-occurrence [Termes IGN] segmentation sémantique [Termes IGN] utilisation du sol Résumé : (auteur) Large-area land cover maps are produced to satisfy different information needs. Land cover maps having partial or complete spatial and/or temporal overlap, different legends, and varying accuracies for similar classes, are increasingly common. To address these concerns and combine two 30-m resolution land cover products, we implemented a harmonization procedure using a Latent Dirichlet Allocation (LDA) model. The LDA model used regionalized class co-occurrences from multiple maps to generate a harmonized class label for each pixel by statistically characterizing land attributes from the class co-occurrences. We evaluated multiple harmonization approaches: using the LDA model alone and in combination with more commonly used information sources for harmonization (i.e. error matrices and semantic affinity scores). The results were compared with the benchmark maps generated using simple legend crosswalks and showed that using LDA outputs with error matrices performed better and increased harmonized map overall accuracy by 6–19% for areas of disagreement between the source maps. Our results revealed the importance of error matrices to harmonization, since excluding error matrices reduced overall accuracy by 4–20%. The LDA-based harmonization approach demonstrated in this paper is quantitative, transparent, portable, and efficient at leveraging the strengths of multiple land cover maps over large areas. Numéro de notice : A2021-027 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/13658816.2020.1796131 Date de publication en ligne : 27/07/2020 En ligne : https://doi.org/10.1080/13658816.2020.1796131 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=96701 [article]