Infrastructure Engineering - Research Publications
Permanent URI for this collection
Search Results
1 - 10 of 11
-
ItemNo Preview AvailableNeural factoid geospatial question answering(UNIV MAINE, 2021)Existing question answering systems struggle to answer factoid questions when geospatial information is involved. This is because most systems cannot accurately detect the geospatial semantic elements from the natural language questions, or capture the semantic relationships between those elements. In this paper, we propose a geospatial semantic encoding schema and a semantic graph representation which captures the semantic relations and dependencies in geospatial questions. We demonstrate that our proposed graph representation approach aids in the translation from natural language to a formal, executable expression in a query language. To decrease the need for people to provide explanatory information as part of their question and make the translation fully automatic, we treat the semantic encoding of the question as a sequential tagging task, and the graph generation of the query as a semantic dependency parsing task. We apply neural network approaches to automatically encode the geospatial questions into spatial semantic graph representations. Compared with current template-based approaches, our method generalises to a broader range of questions, including those with complex syntax and semantics. Our proposed approach achieves better results on GeoData201 than existing methods.
-
ItemNo Preview AvailableThe semantics of place-related questions(UNIV MAINE, 2021)The trend to equip information systems with question-answering capabilities raises the design problem of deciding which questions a system should be able to answer. Typical solutions build on mining human conversations or logs from similar systems for question patterns. For the case of questions about geographic places, we present a complementary approach, showing how to derive possible questions from an ontology of spatial information and a classification of place facets. We argue that such an approach reduces the inherent and substantial data bias of current solutions. At a more general level, we provide a novel understanding of spatial questions and their role in designing and using spatial information systems.
-
ItemSpatial Concepts in the Conversation With a Computer(ASSOC COMPUTING MACHINERY, 2021-07)Conversing about places with a computer poses a range of challenges to current AI.
-
ItemIdentification of parking spaces from multi-modal trajectory data(WILEY, 2021-12)Abstract Mapping the parking spaces in cities is desirable for reducing cruising time and congestion in the city. But map information regarding parking spaces is often missing or incomplete, due to the variety of their nature: marked or unmarked, on‐street or off‐street, or public, domestic or commercial. Hence, we develop a new method for mapping parking spaces, and deliberately focus on a crowd‐sourcing solution because of its global applicability. We will use smartphone trajectory data, as collected by person‐bound navigation apps. A person‐bound navigation app collects multi‐modal trajectory data where the transitions from drive to walk or from walk to drive contain valuable information about parking spaces. Hence, mode detection is required with sufficient accuracy to be able to map parking spaces. We develop a novel mode detection focusing just on this problem and outperforming existing, generic mode detection algorithms. Further, we provide a methodology to identify the geographic locations of parking spaces from these collected trajectory data. The article presents the methodologies, their implementations, and a critical evaluation to achieve mapping of parking spaces.
-
ItemPaths to social licence for tracking-data analytics in university research and services(PUBLIC LIBRARY SCIENCE, 2021-05-21)While tracking-data analytics can be a goldmine for institutions and companies, the inherent privacy concerns also form a legal, ethical and social minefield. We present a study that seeks to understand the extent and circumstances under which tracking-data analytics is undertaken with social licence-that is, with broad community acceptance beyond formal compliance with legal requirements. Taking a University campus environment as a case, we enquire about the social licence for Wi-Fi-based tracking-data analytics. Staff and student participants answered a questionnaire presenting hypothetical scenarios involving Wi-Fi tracking for university research and services. Our results present a Bayesian logistic mixed-effects regression of acceptability judgements as a function of participant ratings on 11 privacy dimensions. Results show widespread acceptance of tracking-data analytics on campus and suggest that trust, individual benefit, data sensitivity, risk of harm and institutional respect for privacy are the most predictive factors determining this acceptance judgement.
-
ItemThere is no way! Ternary qualitative spatial reasoning for error detection in map data(WILEY, 2021-08)Abstract Detection and correction of errors in map data based on spatial reasoning may be used to improve their quality. However, the majority of current spatial reasoning approaches are based on binary spatial relations and are not able to perform analyses involving more than two objects. This article proposes building accessibility analysis with the ternary ray intersection model to detect potential map errors. Where buildings are not accessible from the road network, this may indicate potential errors in map data such as roads that are not mapped. The plausibility of the proposed method was tested in a case study on OpenStreetMap data. The results have been published in an online mapping challenge where volunteering mappers have used them to correct errors in map data, and have provided feedback on the analysis. The results show that the proposed method can detect errors in map data that are caused by incorrect classification of buildings, incorrect mapping of multi‐part buildings, and missing road data.
-
ItemRIM: a ray intersection model for the analysis of the between relationship of spatial objects in a 2D plane(Taylor & Francis, 2020-07-07)The term between is frequently used to describe spatial arrangements of objects where one described core object is positioned in the space bounded by two or more peripheral objects. As such, the relation between involves spatial configurations of at least three spatial objects. However, most of the existing qualitative spatial reasoning models focus only on binary spatial relations, and there is currently no single model that enables adequate reasoning about this ternary spatial relation. This paper proposes a novel model for expressing nuanced spatial relationships between three spatial objects, called the Ray Intersection Model (RIM). RIM evaluates rays cast between two peripheral spatial objects, and their topological relations with the core object to determine its position relative to the peripheral objects. RIM leaves the binary classification of the core object as between/not between to the user and application context. Although RIM supports all types of 2D spatial objects (i.e. points, lines, and polygons), its expressiveness is demonstrated in this paper by analyzing the total of 28 distinct configurations of triplets of polygon objects in a 2D plane. RIM has been computationally implemented and we demonstrate how RIM can be applied to analyze the arrangements of buildings at a university campus.
-
ItemExtracting interrogative intents and concepts from geo-analytic questions(Copernicus GmbH, 2020)Understanding syntactic and semantic structure of geographic questions is a necessary step towards true geographic question-answering (GeoQA) machines. The empirical basis for the understanding of the capabilities expected from GeoQA systems are geographic question corpora. Available corpora in English have been mostly drawn from generic Web search logs or limited user studies, supporting the focus of GeoQA systems on retrieving factoids: factual knowledge about particular places and everyday processes. Yet, the majority of questions enquired about in the spatial sciences go beyond simple place facts, with more complex analytical intents informing the questions. In this paper, we introduce a new corpus of geo-analytic questions drawn from English textbooks and scientific articles. We analyse and compare this corpus with two general-purpose GeoQA corpora in terms of grammatical complexity and semantic concepts, using a new parsing method that allows us to differentiate and quantify patterns of a question’s intent.
-
ItemTemplates of generic geographic information for answering where-questions(TAYLOR & FRANCIS LTD, 2022-01-02)In everyday communication, where-questions are answered by place descriptions. To answer where-questions automatically, computers should be able to generate relevant place descriptions that satisfy inquirers’ information needs. Human-generated answers to where-questions constructed based on a few anchor places that characterize the location of inquired places. The challenge for automatically generating such relevant responses stems from selecting relevant anchor places. In this paper, we present templates that allow to characterize the human-generated answers and to imitate their structure. These templates are patterns of generic geographic information derived and encoded from the largest available machine comprehension dataset, MS MARCO v2.1. In our approach, the toponyms in the questions and answers of the dataset are encoded into sequences of generic information. Next, sequence prediction methods are used to model the relation between the generic information in the questions and their answers. Finally, we evaluate the performance of predicting templates for answers to where-questions.
-
ItemOrigin-Destination Flow Estimation from Link Count Data Only(MDPI, 2020-09)All established models in transportation engineering that estimate the numbers of trips between origins and destinations from vehicle counts use some form of a priori knowledge of the traffic. This paper, in contrast, presents a new origin-destination flow estimation model that uses only vehicle counts observed by traffic count sensors; it requires neither historical origin-destination trip data for the estimation nor any assumed distribution of flow. This approach utilises a method of statistical origin-destination flow estimation in computer networks, and transfers the principles to the domain of road traffic by applying transport-geographic constraints in order to keep traffic embedded in physical space. Being purely stochastic, our model overcomes the conceptual weaknesses of the existing models, and additionally estimates travel times of individual vehicles. The model has been implemented in a real-world road network in the city of Melbourne, Australia. The model was validated with simulated data and real-world observations from two different data sources. The validation results show that all the origin-destination flows were estimated with a good accuracy score using link count data only. Additionally, the estimated travel times by the model were close approximations to the observed travel times in the real world.