arXiv subjects

Nicolas Tempelmeier

Publications and source records attributed to Nicolas Tempelmeier.

14 recordsLinked to original sources

arXiv2023

Creating Knowledge Graphs for Geographic Data on the Web

Geographic data plays an essential role in various Web, Semantic Web and machine learning applications. OpenStreetMap and knowledge graphs are critical complementary sources of geographic data on the Web. However, data veracity, the lack of integration of geographic and semantic characteristics, and incomplete representations substantially limit the data utility. Verification, enrichment and semantic representation are essential for making geographic data accessible for the Semantic Web and machine learning. This article describes recent approaches we developed to tackle these challenges.

cs.AI↗

arXiv2022

Reinforcement Learning-based Placement of Charging Stations in Urban Road Networks

The transition from conventional mobility to electromobility largely depends on charging infrastructure availability and optimal placement.This paper examines the optimal placement of charging stations in urban areas. We maximise the charging infrastructure supply over the area and minimise waiting, travel, and charging times while setting budget constraints. Moreover, we include the possibility of charging vehicles at home to obtain a more refined estimation of the actual charging demand throughout the urban area. We formulate the Placement of Charging Stations problem as a non-linear integer optimisation problem that seeks the optimal positions for charging stations and the optimal number of charging piles of different charging types. We design a novel Deep Reinforcement Learning approach to solve the charging station placement problem (PCRL). Extensive experiments on real-world datasets show how the PCRL reduces the waiting and travel time while increasing the benefit of the charging plan compared to five baselines. Compared to the existing infrastructure, we can reduce the waiting time by up to 97% and increase the benefit up to 497%.

cs.LG↗

arXiv2022

Ovid: A Machine Learning Approach for Automated Vandalism Detection in OpenStreetMap

OpenStreetMap is a unique source of openly available worldwide map data, increasingly adopted in real-world applications. Vandalism detection in OpenStreetMap is critical and remarkably challenging due to the large scale of the dataset, the sheer number of contributors, various vandalism forms, and the lack of annotated data to train machine learning algorithms. This paper presents Ovid - a novel machine learning method for vandalism detection in OpenStreetMap. Ovid relies on a neural network architecture that adopts a multi-head attention mechanism to effectively summarize information indicating vandalism from OpenStreetMap changesets. To facilitate automated vandalism detection, we introduce a set of original features that capture changeset, user, and edit information. Our evaluation results on real-world vandalism data demonstrate that the proposed Ovid method outperforms the baselines by 4.7 percentage points in F1 score.

cs.LG↗

arXiv2022

Attention-Based Vandalism Detection in OpenStreetMap

OpenStreetMap (OSM), a collaborative, crowdsourced Web map, is a unique source of openly available worldwide map data, increasingly adopted in Web applications. Vandalism detection is a critical task to support trust and maintain OSM transparency. This task is remarkably challenging due to the large scale of the dataset, the sheer number of contributors, various vandalism forms, and the lack of annotated data. This paper presents Ovid - a novel attention-based method for vandalism detection in OSM. Ovid relies on a novel neural architecture that adopts a multi-head attention mechanism to summarize information indicating vandalism from OSM changesets effectively. To facilitate automated vandalism detection, we introduce a set of original features that capture changeset, user, and edit information. Furthermore, we extract a dataset of real-world vandalism incidents from the OSM edit history for the first time and provide this dataset as open data. Our evaluation conducted on real-world vandalism data demonstrates the effectiveness of Ovid.

cs.LG↗

arXiv2021

WorldKG: A World-Scale Geographic Knowledge Graph

OpenStreetMap is a rich source of openly available geographic information. However, the representation of geographic entities, e.g., buildings, mountains, and cities, within OpenStreetMap is highly heterogeneous, diverse, and incomplete. As a result, this rich data source is hardly usable for real-world applications. This paper presents WorldKG -- a new geographic knowledge graph aiming to provide a comprehensive semantic representation of geographic entities in OpenStreetMap. We describe the WorldKG knowledge graph, including its ontology that builds the semantic dataset backbone, the extraction procedure of the ontology and geographic entities from OpenStreetMap, and the methods to enhance entity annotation. We perform statistical and qualitative dataset assessment, demonstrating the large scale and high precision of the semantic geographic information in WorldKG.

cs.IR↗

arXiv2021

GeoVectors: A Linked Open Corpus of OpenStreetMap Embeddings on World Scale

OpenStreetMap (OSM) is currently the richest publicly available information source on geographic entities (e.g., buildings and roads) worldwide. However, using OSM entities in machine learning models and other applications is challenging due to the large scale of OSM, the extreme heterogeneity of entity annotations, and a lack of a well-defined ontology to describe entity semantics and properties. This paper presents GeoVectors - a unique, comprehensive world-scale linked open corpus of OSM entity embeddings covering the entire OSM dataset and providing latent representations of over 980 million geographic entities in 180 countries. The GeoVectors corpus captures semantic and geographic dimensions of OSM entities and makes these entities directly accessible to machine learning algorithms and semantic applications. We create a semantic description of the GeoVectors corpus, including identity links to the Wikidata and DBpedia knowledge graphs to supply context information. Furthermore, we provide a SPARQL endpoint - a semantic interface that offers direct access to the semantic and latent representations of geographic entities in OSM.

cs.LG↗

arXiv2021

Deep Information Fusion for Electric Vehicle Charging Station Occupancy Forecasting

With an increasing number of electric vehicles, the accurate forecasting of charging station occupation is crucial to enable reliable vehicle charging. This paper introduces a novel Deep Fusion of Dynamic and Static Information model (DFDS) to effectively forecast the charging station occupation. We exploit static information, such as the mean occupation concerning the time of day, to learn the specific charging station patterns. We supplement such static data with dynamic information reflecting the preceding charging station occupation and temporal information such as daytime and weekday. Our model efficiently fuses dynamic and static information to facilitate accurate forecasting. We evaluate the proposed model on a real-world dataset containing 593 charging stations in Germany, covering August 2020 to December 2020. Our experiments demonstrate that DFDS outperforms the baselines by 3.45 percent points in F1-score on average.

cs.LG↗

arXiv2021

Towards Neural Schema Alignment for OpenStreetMap and Knowledge Graphs

OpenStreetMap (OSM) is one of the richest openly available sources of volunteered geographic information. Although OSM includes various geographical entities, their descriptions are highly heterogeneous, incomplete, and do not follow any well-defined ontology. Knowledge graphs can potentially provide valuable semantic information to enrich OSM entities. However, interlinking OSM entities with knowledge graphs is inherently difficult due to the large, heterogeneous, ambiguous, and flat OSM schema and the annotation sparsity. This paper tackles the alignment of OSM tags with the corresponding knowledge graph classes holistically by jointly considering the schema and instance layers. We propose a novel neural architecture that capitalizes upon a shared latent space for tag-to-class alignment created using linked entities in OSM and knowledge graphs. Our experiments performed to align OSM datasets for several countries with two of the most prominent openly available knowledge graphs, namely, Wikidata and DBpedia, demonstrate that the proposed approach outperforms the state-of-the-art schema alignment baselines by up to 53 percentage points in terms of F1-score. The resulting alignment facilitates new semantic annotations for over 10 million OSM entities worldwide, which is more than a 400% increase compared to the existing semantic annotations in OSM.

cs.LG↗

arXiv2021

Mining Topological Dependencies of Recurrent Congestion in Road Networks

The discovery of spatio-temporal dependencies within urban road networks that cause Recurrent Congestion (RC) patterns is crucial for numerous real-world applications, including urban planning and scheduling of public transportation services. While most existing studies investigate temporal patterns of RC phenomena, the influence of the road network topology on RC is often overlooked. This article proposes the ST-Discovery algorithm, a novel unsupervised spatio-temporal data mining algorithm that facilitates the effective data-driven discovery of RC dependencies induced by the road network topology using real-world traffic data. We factor out regularly reoccurring traffic phenomena, such as rush hours, mainly induced by the daytime, by modelling and systematically exploiting temporal traffic load outliers. We present an algorithm that first constructs connected subgraphs of the road network based on the traffic speed outliers. Second, the algorithm identifies pairs of subgraphs that indicate spatio-temporal correlations in their traffic load behaviour to identify topological dependencies within the road network. Finally, we rank the identified subgraph pairs based on the dependency score determined by our algorithm. Our experimental results demonstrate that ST-Discovery can effectively reveal topological dependencies in urban road networks.

cs.LG↗

arXiv2020

Linking OpenStreetMap with Knowledge Graphs -- Link Discovery for Schema-Agnostic Volunteered Geographic Information

Representations of geographic entities captured in popular knowledge graphs such as Wikidata and DBpedia are often incomplete. OpenStreetMap (OSM) is a rich source of openly available, volunteered geographic information that has a high potential to complement these representations. However, identity links between the knowledge graph entities and OSM nodes are still rare. The problem of link discovery in these settings is particularly challenging due to the lack of a strict schema and heterogeneity of the user-defined node representations in OSM. In this article, we propose OSM2KG - a novel link discovery approach to predict identity links between OSM nodes and geographic entities in a knowledge graph. The core of the OSM2KG approach is a novel latent, compact representation of OSM nodes that captures semantic node similarity in an embedding. OSM2KG adopts this latent representation to train a supervised model for link prediction and utilises existing links between OSM and knowledge graphs for training. Our experiments conducted on several OSM datasets, as well as the Wikidata and DBpedia knowledge graphs, demonstrate that OSM2KG can reliably discover identity links. OSM2KG achieves an F1 score of 92.05% on Wikidata and of 94.17% on DBpedia on average, which corresponds to a 21.82 percentage points increase in F1 score on Wikidata compared to the best performing baselines.

cs.SI↗

arXiv2020

TA-Dash: An Interactive Dashboard for Spatial-Temporal Traffic Analytics -- Demo Paper

In recent years, a large number of research efforts aimed at the development of machine learning models to predict complex spatial-temporal mobility patterns and their impact on road traffic and infrastructure. However, the utility of these models is often diminished due to the lack of accessible user interfaces to view and analyse prediction results. In this paper, we present the Traffic Analytics Dashboard ( TA-Dash), an interactive dashboard that enables the visualisation of complex spatial-temporal urban traffic patterns. We demonstrate the utility of TA-Dash at the example of two recently proposed spatial-temporal models for urban traffic and urban road infrastructure analysis. In particular, the use cases include the analysis, prediction and visualisation of the impact of planned special events on urban road traffic as well as the analysis and visualisation of structural dependencies within urban road networks. The lightweight TA-Dash dashboard aims to address non-expert users involved in urban traffic management and mobility service planning. The TA-Dash builds on a flexible layer-based architecture that is easily adaptable to the visualisation of new models.

cs.HC↗

arXiv2019

Simple-ML: Towards a Framework for Semantic Data Analytics Workflows

In this paper we present the Simple-ML framework that we develop to support efficient configuration, robustness and reusability of data analytics workflows through the adoption of semantic technologies. We present semantic data models that lay the foundation for the framework development and discuss the data analytics workflows based on these models. Furthermore, we present an example instantiation of the Simple-ML data models for a real-world use case in the mobility domain.

cs.DB↗

arXiv2019

Data4UrbanMobility: Towards Holistic Data Analytics for Mobility Applications in Urban Regions

With the increasing availability of mobility-related data, such as GPS-traces, Web queries and climate conditions, there is a growing demand to utilize this data to better understand and support urban mobility needs. However, data available from the individual actors, such as providers of information, navigation and transportation systems, is mostly restricted to isolated mobility modes, whereas holistic data analytics over integrated data sources is not sufficiently supported. In this paper we present our ongoing research in the context of holistic data analytics to support urban mobility applications in the Data4UrbanMobility (D4UM) project. First, we discuss challenges in urban mobility analytics and present the D4UM platform we are currently developing to facilitate holistic urban data analytics over integrated heterogeneous data sources along with the available data sources. Second, we present the MiC app - a tool we developed to complement available datasets with intermodal mobility data (i.e. data about journeys that involve more than one mode of mobility) using a citizen science approach. Finally, we present selected use cases and discuss our future work.

cs.CY↗

arXiv2018

Inferring Missing Categorical Information in Noisy and Sparse Web Markup

Embedded markup of Web pages has seen widespread adoption throughout the past years driven by standards such as RDFa and Microdata and initiatives such as schema.org, where recent studies show an adoption by 39% of all Web pages already in 2016. While this constitutes an important information source for tasks such as Web search, Web page classification or knowledge graph augmentation, individual markup nodes are usually sparsely described and often lack essential information. For instance, from 26 million nodes describing events within the Common Crawl in 2016, 59% of nodes provide less than six statements and only 257,000 nodes (0.96%) are typed with more specific event subtypes. Nevertheless, given the scale and diversity of Web markup data, nodes that provide missing information can be obtained from the Web in large quantities, in particular for categorical properties. Such data constitutes potential training data for inferring missing information to significantly augment sparsely described nodes. In this work, we introduce a supervised approach for inferring missing categorical properties in Web markup. Our experiments, conducted on properties of events and movies, show a performance of 79% and 83% F1 score correspondingly, significantly outperforming existing baselines.

cs.LG↗