Web and Wireless Geographical Information Systems

Geosensor networks are often used to monitor processes at different spatial scales. Existing approaches for configuring geosensor locations (i.e. sample design) do not address two key challenges: 1) they are limited to a single scale of analysis and do not support multiple scales of evaluation, and 2) they assume that the geosensor network, once established at whatever scale, does not change either in terms of location or number of geosensors. While approaches exist in part for 1) and 2) they do not for both combined. This paper describes a novel approach for optimising geosensor locations in support of multi-scale decisions. It uses the local variation in environmental gradient as a cost surface to approximate the process of interest a proxy for measurements of the process of interest. Cross-scale evaluations of geosensor spatial configurations are supported by measurements of the information loss within spatially nested decision scales. The methods described in this paper fill an important gap as they are i) suggest appropriate sample and geosensor network designs to support cross-scale monitoring, ii) inform on how current network or geosensor coverage could be enhanced by filling gaps, and iii) quantify the information trade-offs (information loss) associated with designs when they are evaluated from the perspective of different decision scales.

The quality of Building Energy Models (BEMs), as dominant techniques to simulate and analyze building behavior in terms of energy consumption, depends strongly on the weather data that is generally captured by spatially low-resolution weather stations and in 2D. The provided weather data does not satisfy the BEMs requirements in terms of accuracy and spatial details. To address this issue, WSNs (Wireless Sensor Networks) have shown a high potential in offering 3D measurements with desired resolution and quality. However, the optimal deployment of a point-based wireless sensor network in an urban area to capture information on microclimate is a challenging task due to the complexity of the integration and management of diverse affecting factors as well as the 3D nature of the urban environment and its dynamics. This paper proposes to design and develop a workflow based on CityGML-standards to represent and manage the required spatiotemporal information for BEMs and feed a knowledgebase that can be used in WSN deployment optimization algorithms. Finally, the paper presents and discusses a case study to highlight the advantages and limitations of the proposed approach.

The estimation of pedestrian path is of great value in the study of crowd dynamics, and various data with location information can be used as the basis for path estimation. In this study, we jointly use the signal data obtained from the pedestrian interaction with the base station and the surveillance video in the study area, and estimate the pedestrian path in the network finally. This paper proposes a three-stage framework for pedestrian path estimation, in the first stage, the video is used to extract the pedestrian's trajectory in the monitoring field of view, and the road segment that the pedestrian certain to pass is determined; in the second stage, the location information contained in signaling data is used to predict the road segments that pedestrian may pass through. In the final stage, the road segments determined by surveillance videos and the road segments inferred from signaling data are integrated, then we use HMM model to determine the combination of road segments with the highest probability, so as to obtain the complete travel path of the pedestrian. To evaluate the framework proposed in this paper, we conducted simulation experiments based on CARLA. The experimental results show that the path of pedestrians in the road network can be estimated effectively through the cooperative application of signaling data and surveillance video. Compared with other methods relying on only one data source, the three-stage framework proposed has higher accuracy in path estimation.

People with mobility disabilities (PWMD) often struggle with challenges in getting around independently for their daily activities. Mobility is one of the most important life habits which might be constrained by diverse environmental and social obstacles, limiting the social participation of PWMD. Upgrading the social integration of these people is a major challenge in Canada and internationally. Even though the advent of assistive navigation technologies improves the interaction of PWMD with their environments during their mobility, these tools mostly ignore the capabilities, capacities, and specific needs of this population. It is required to better understand PWMD’s navigational behavior in the environment to make these navigation tools adapted to their profile and specific needs. Hence, this research aims at using state-of-the-art technology (i.e., eye-tracking glasses) to explore the navigational behavior of PWMD. To do so, we designed and carried out an experiment in which a wheelchair user wearing eye-tracking glasses navigated a route following the instructions given by Google Maps. Several eye-tracking metrics for the collected eye movement data were computed and analyzed to explore the participant’s visual and mental activities while performing the navigation task. Artificial intelligence was used to automatically assign eye movement data to specific features in the environment during navigation. The preliminary findings of this research show that the highest level of fixation was assigned to the cell phone for receiving the route instructions, distracting thus the participant from his surroundings. In this sense, we have noticed that these route instructions were not sufficient and clear for wheelchair users in some situations. In addition, fixations on sidewalks and crosswalks were the second-highest amount because of the low accessibility level of several parts of the route. Some buildings as landmarks were also eye-catching for the wheelchair user during exploring the environment, and searching for the route, particularly when the route was accessible. In this way, it is required to help the wheelchair user to become aware of information on the accessibility of routes and salient environmental objects in advance to draw more attention to the environment, better orient in the environment, and make sure of following the correct route, therefore, upgrading wheelchair users’ spatial learning and being autonomous.

Independent mobility of people with motor disabilities is fundamental for their daily activities. However, the mobility of these people is often restricted by diverse environmental and social factors. In addition to static factors, temporal factors such as the presence of the crowd could reduce the accessibility on the sidewalk. Hence, in this paper, we focus on the accessibility of sidewalks for people with mobility impairment, specifically for manual wheelchair users, in the presence of crowd. The paper aims at understanding how environmental factors, including temporal factors such as crowd density, affect the independent mobility of individuals with mobility impairments. The proposed method evaluates each user's confidence level in navigating different sidewalk components in the presence of different population densities and uses a fuzzy-based model for accessibility assessment. Besides the accessible maps for different population densities, a similarity index has been applied to compare the impact of crowd on the accessibility of sidewalk components. The findings suggest that, the direction of the movement of people have a significant effect on the level of accessibility of each segment. Moreover, while the presence of crowds is discouraging in some situations, it improves accessibility in others.

Developments in Web and Wireless technologies have enabled the diffusion of large volumes of geospatial mobility data, and new challenges and opportunities have emerged for the GIScience research community, interested in extracting knowledge from these data.

In most data analytics scenarios, well-known analytics platforms, such as KNIME or RapidMiner, offer practical general-purpose tools to data analysts. However, when dealing with mobility data, these platforms provide only limited support to some peculiar geospatial data manipulation tasks, thus forcing researchers and practitioners to manually implement significant portions of their pipelines, hindering productivity and replicability of the results.

This paper presents a solution we are currently working on to support mobility data analysis. Our prototype, which we called KNOT (KNime mObility Toolkit), extends the KNIME Analytics Platform with a collection of new components specifically designed to support processing steps typical of mobility data, including map-matching, trajectory partitioning, and road network coverage analysis. To show the effectiveness of these components, we report also on how we applied them to perform a realistic analytical task on a real-world massive mobility dataset.

With increasing urbanisation, and a growing population, transport within cities has never been more important. Buses are the most widespread form of transport worldwide, often being cheaper and more flexible than rail, but also less reliable. Long term bus journey time predictions are important for advanced journey planning and scheduling of bus services. For this reason, several machine/deep learning techniques have been defined to predict bus journey time. Still, due to the number of involved factors, such as complexity and noise in bus data, road network topology, etc., accurate predictions remain elusive. In this paper we aim at validating some Machine Learning methods recently shown to be effective in the literature, on new bus datasets from Dublin and Genoa. The analysis of the results shows some interesting insights into bus networks, highlighting that the accuracy of the predictions is strongly related to the standard deviation of the whole journey times. It emerges that some bus routes show consistency in the prediction error across methods, and for these routes it makes sense to use methods that are fast and computationally efficient, as there is no benefit to applying more complex algorithms. We use features of the route data distribution to develop an explanatory model for the consistency of the route across methods, with a coefficient of determination (\(R^2\)) of 0.94. Finally, we identify a systematic anomaly in the data in Dublin that alters the performance of the methods.

Transportation sector is the largest contributor to greenhouse gas emissions. Among all means of transportation (road, air, sea), road transportation has the greatest impact in terms of CO2 emissions in the atmosphere. In order to develop "smart" and sustainable cities and improve the health of the population, it is crucial to re-evaluate our use of various means of transportation for our daily travel to work or leisure and minimize the emissions of pollutants and greenhouse gases. Some smartphone applications currently offer routes to optimize greenhouse gas emissions, but these applications have limitations, particularly due to a lack of environmental data and a lack of multimodality regarding means of transportation (bicycles, walking, running, car, bus, metro, etc.). This paper aims to address these limitations by proposing an intelligent application for detecting the user travel mode based on smart phone sensors information and data from Geospatial Information System (GIS). Specifically, reliable transportation mode detection (TMD) algorithms using the real-time sensors data open new possibilities for travel optimization with minimum greenhouse gas emissions.

Advancements in technology have led to an increase in the number of Volunteer Geographic Information (VGI) applications, and new smartphone functionalities have made collecting VGI data easier. However, getting volunteers to install and use new VGI applications can be challenging. This article introduces a possible solution by using existing applications, that people use on a daily basis, for VGI data collection. Accordingly, a prototype of a Telegram chatbot is developed to collect mountain images from volunteers, while also providing them with information such as weather conditions and avalanche risk in a given location. The article concludes that using existing platforms like Telegram has benefits, but it is important to consider the specific goals, participants’ needs, and interface of a project, and strikes a balance between creating a new application and using existing ones.

Numerous studies have attempted to assess the quality of OpenStreetMap's building data by comparing it to reference datasets. Map matching (feature matching) is a critical step in this method of quality assessment, involving the matching of polygons in the two datasets. Researchers commonly use two main polygon matching algorithms: 1) the buffer intersection method and 2) the centroid comparison method. While these methods are effective for the majority of OSM building footprints, they may not achieve high accuracy in complex situations. One possible reason is that both methods only consider the position of the OSM polygon compared to that of the reference polygon. To improve these matching algorithms and propose a more robust solution, this study proposes an algorithm that considers shape similarity (using average distance method) in addition to position similarity to better identify corresponding polygons in the two datasets. The experiment results for five cities in the Province of Quebec indicate that the proposed algorithm can reduce the matching error of previous map matching algorithms from approximately 8% to approximately 3%. Furthermore, the study found that the proposed polygon matching algorithm performs more accurately than previous methods when buildings consist of multiple polygons.

Geovisualisation is a first-choice approach when it comes to support a user’s reasoning process to explore geographical information or solve a spatial problem. More and more data relevant for geovisual analysis is published in the Web, sometimes even directly described using the RDF formalism and made available through SPARQL endpoints. Beyond exploiting Semantic Web data, we claim that Semantic Web-based Geovisualisation is a field that also offers an opportunity to make methods, techniques and tools of geovisualisation evolve so they fully exploit the possibilities offered by the Semantic Web technologies stack. In this paper we review some works of the literature that have addressed the issues of cartography and geovisualisation of data formalised or published using Semantic Web technologies, ranging from domain knowledge representation only to frameworks supporting knowledge-based process for geovisualisation generation. As a contribution to this field, and based on lessons learned from the state of the art, we introduce the CoViKoa framework we have designed and implemented. Then, taking stock of our experience, we introduce some challenges we still envision in the field of Semantic Web-based Geovisualisation. We present some of them as open questions, but also draw some guidelines, for future works in the field.

Tourist attraction competition amongst tourist destinations is a crucial com-ponent of a sustainable growth of tourism destinations, and it still deserves appropriate studies to identify them as well as appropriate management solu-tions. Existing studies usually focus on mining tourism locations correla-tions using available statistical data or inference mechanisms applied to tex-tual and cartographical reports. However, a few works apply a combination of qualitative and quantitative approaches, based on multiple contextual characteristics, to infer tourism attraction patterns and competition patterns. Over the past few years, the emergence of social media and Location-Based Services (LBS) in the tourism sector such as geo-tagged reviews, photos, consuming behaviors, and itineraries, provides a new paradigm for extracting and understanding competition among attractions. This research introduces a Heterogenous Information Network (HIN) and Graph Neural Network-based model to capture the complex contextual features for and identifica-tion of attraction competitions. Specifically, three categories of LBS data are processed, extracted, and integrated into a unified HIN, including tourists’ journeys, online text, and spatial attributes. This supports the exploration of significant regularities of attraction competing contexts. The GNN-based model, so-called Competitor-GAT, extract spatial distribution properties and semantic correlations. The experiments applied on a real-world dataset demonstrate the effectiveness of our method.