Monica Wachowicz

Constructing knowledge from multivariate spatiotemporal data: integrating geographical visualization with knowledge discovery in database methods*

We present an approach to the process of constructing knowledge through structured exploration of large spatiotemporal data sets. First, we introduce our problem context and define both Geographic Visualization (GVis) and Knowledge Discovery in Databases (KDD), the source domains for methods being integrated. Next, we review and compare recent GVis and KDD developments and consider the potential for their integration, emphasizing that an iterative process with user interaction is a central focus for uncovering interest and meaningful patterns through each. We then introduce an approach to design of an integrated GVis-KDD environment directed to exploration and discovery in the context of spatiotemporal environmental data. The approach emphasizes a matching of GVis and KDD meta-operations. Following description of the GVis and KDD methods that are linked in our prototype system, we present a demonstration of the prototype applied to a typical spatiotemporal dataset. We conclude by outlining, briefly, resea...

How you move reveals who you are: understanding human behavior by analyzing trajectory data

The widespread use of mobile devices is producing a huge amount of trajectory data, making the discovery of movement patterns possible, which are crucial for understanding human behavior. Significant advances have been made with regard to knowledge discovery, but the process now needs to be extended bearing in mind the emerging field of behavior informatics. This paper describes the formalization of a semantic-enriched KDD process for supporting meaningful pattern interpretations of human behavior. Our approach is based on the integration of inductive reasoning (movement pattern discovery) and deductive reasoning (human behavior inference). We describe the implemented Athena system, which supports such a process, along with the experimental results on two different application domains related to traffic and recreation management.

An Ontology-Based Approach for the Semantic Modelling and Reasoning on Trajectories

In this paper we present a methodology for the semantic enrichment of trajectories. The objective of this process is to provide a semantic interpretation of a trajectory in term of behaviour. This has been achieved by enhancing raw trajectories with semantic information about moves and stops and by exploiting some domain knowledge encoded in an ontology. Furthermore, the reasoning mechanisms provided by the OWL ontology formalism have been exploited to accomplish a further semantic enrichment step that puts together the different levels of knowledge of the domain. A final example application shows the added power of the enrichment process in characterizing people behaviour.

Towards Semantic Interpretation of Movement Behavior

In this paper we aim at providing a model for the conceptual representation and deductive reasoning of trajectory patterns obtained from mining raw trajectories. This has been achieved by means of a semantic enrichment process, where raw trajectories are enhanced with semantic information and integrated with geographical knowledge encoded in an ontology. The reasoning mechanisms provided by the chosen ontology formalism are exploited to accomplish a further semantic enrichment step that gives a possible interpretation of discovered patterns in terms of movement behaviour. A sketch of the realised system, called Athena, is given, along with some examples to demonstrate the feasibility of the approach.

Finding moving flock patterns among pedestrians through collective coherence

Tracking technologies are able to provide high-resolution movement data that can advance research in different fields, such as tourism management. In this specific field, developing methods to extract moving flock patterns from such data are particularly relevant to enable us to improve our knowledge of the nature of recreational use interactions, which is crucial for a good management of attractions and for designing sustainable development policies. However, ‘flocking’ has been usually associated with the form of collective movement of a large group of birds, fish, insects and certain mammals as well. Very few research efforts have been devoted in finding flock patterns associated with pedestrian movement. In this work, we propose a moving flock pattern definition and a corresponding extraction algorithm based on the notion of collective coherence. We use the term collective coherence to refer to the spatial closeness over some time duration with a minimum number of members. Furthermore, we evaluate the proposed algorithm by applying it to two different pedestrian movement datasets, which have been gathered from visitors of two recreational parks. The results show that the algorithm is capable of extracting moving flock patterns, disqualifying the patterns with flock members that remain stationary in a common place during the considered time interval.

Metadata behind the interoperability of wireless sensor networks

Wireless Sensor Networks (WSNs) produce changes of status that are frequent, dynamic and unpredictable, and cannot be represented using a linear cause-effect approach. Consequently, a new approach is needed to handle these changes in order to support dynamic interoperability. Our approach is to introduce the notion of context as an explicit representation of changes of a WSN status inferred from metadata elements, which in turn, leads towards a decision-making process about how to maintain dynamic interoperability. This paper describes the developed context model to represent and reason over different WSN status based on four types of contexts, which have been identified as sensing, node, network and organisational contexts. The reasoning has been addressed by developing contextualising and bridges rules. As a result, we were able to demonstrate how contextualising rules have been used to reason on changes of WSN status as a first step towards maintaining dynamic interoperability.

Simulating Knowledge Sharing in Spatial Planning: An Agent-Based Approach:

This paper presents a multiagent system (MAS) that simulates a multiactor interactive spatial-planning process. The MAS extends an existing approach with the principle of sharing knowledge between participating actors while trying to create a shared vision. In the simulation, actors are modelled as agents. They have desires and preferences regarding the future development of their environment. These are used to develop their individual views on what areas are eligible for change. A facilitator agent coordinates the exchange of information by indicating possible solutions and conflicts to the actor agents. The simulation is demonstrated for an allocation problem in a pilot area in the southeast of the Netherlands. Four different scenarios are implemented, which demonstrate the impact of cooperation and hierarchy during an interactive spatial-planning process. Although the model is kept limited in terms of input data, the results show its potential for providing insight into the relations and interaction between actors, rather than predicting the results of an interactive spatial-planning process.

The impact of data quality in the context of pedestrian movement analysis

Positioning data sets gathered from GPS recordings of moving people or vehicles and usage logs of telecommunications networks are being increasingly used as a proxy to capture the mobility of people in a variety of places. The purpose of use of these data sets is wide-ranging and requires the development of techniques for collaborative map construction, the analysis and modelling of human behaviour, and the provision of context- aware services and applications. However, the quality of these data sets is affected by several factors depending on the technology used to collect the position and on the particular scenario where it is collected. This paper aims at assessing the quality and suitability of GPS recordings used in analysing pedestrian movement in two different recreational applications. Therefore, we look at two positioning data sets collected by two distinct groups of pedestrians, and analyse their collective movement patterns in the applications of a mobile outdoor gaming and as well as a park recreational usage. Among other findings, we show that the different reading rates of the pedestrians’ position lead to different levels of inaccuracy in the variables derived from it (e.g. velocity and bearing). This was significant in the case of bearing values that were calculated from GPS readings which, in turn, has shown a strong impact on the size of clusters of movement patterns.

A mobility constraint model to infer sensor behaviour in forest fire risk monitoring

Wireless sensor networks (WSNs) play an important role in forest fire risk monitoring. Various applications are in operation. However, the use of mobile sensors in forest risk monitoring remains largely unexplored. Our research contributes to fill this gap by designing a model which abstracts mobility constraints within different types of contexts for the inference of mobile sensor behaviour. This behaviour is focused on achieving a suitable spatial coverage of the WSN when monitoring forest fire risk. The proposed mobility constraint model makes use of a Bayesian network approach and consists of three components: (1) a context typology describing different contexts in which a WSN monitors a dynamic phenomenon; (2) a context graph encoding probabilistic dependencies among variables of interest; and (3) contextual rules encoding expert knowledge and application requirements needed for the inference of sensor behaviour. As an illustration, the model is used to simulate the behaviour of a mobile WSN to obtain a suitable spatial coverage in low and high fire risk scenarios. It is shown that the implemented Bayesian network within the mobility constraint model can successfully infer behaviour such as sleeping sensors, moving sensors, or deploying more sensors to enhance spatial coverage. Furthermore, the mobility constraint model contributes towards mobile sensing in which the mobile sensor behaviour is driven by constraints on the state of the phenomenon and the sensing system.

An Artistic Perspective for Affective Cartography

Although affective and collaborative mapping are currently being studied in Cartography these two paradigms are not exclusive to this discipline. In fact, different disciplines are actively engaged in exploring their possibilities. For example artworks that are demonstrating how contemporary art and design can be used for exploring the relationship between people and space in order to discover new realities, perceptions and emotions that possibly could remain unknown under the objectivity of the conventional map representations. This paper aims to provide an overview of some artworks that are unfolding the realms of affective mapping where everything that takes place in a physical dimension only acquires its meaning through the collaboration of the participants or the sharing of an artist’s perspective. Through a discussion of these artistic developments, new research challenges are described in a way that brings together arts, society and cartography will be explored.