Academic journal article Geographical Analysis

Neurofuzzy Modeling of Context-Contingent Proximity Relations

Academic journal article Geographical Analysis

Neurofuzzy Modeling of Context-Contingent Proximity Relations

Article excerpt

The notion of proximity is one of the foundational elements in humans' understanding and reasoning of the geographical environments. The perception and cognition of distances plays a significant role in many daily human activities. Yet, few studies have thus far provided context-contingent translation mechanisms between linguistic proximity descriptors (e.g., "near," "far") and metric distance measures. One problem with previous fuzzy logic proximity modeling studies is that they presume the form of the fuzzy membership functions of proximity relations. Another problem is that previous studies have fundamental weaknesses in considering context factors in proximity models. We argue that statistical approaches are ill suited to proximity modeling because of the inherently fuzzy nature of the relations between linguistic and metric distance measures. In this study, we propose a neurofuzzy system approach to solve this problem. The approach allows for the dynamic construction of context-contingent proximity models based on sample data. An empirical case study with human subject survey data is carried out to test the validity of the approach and to compare it with the previous statistical approach. Interpretation and prediction accuracy of the empirical study are discussed.

Introduction

The perception and cognition of distances play a significant role in many daily human activities. Its most overt impact is probably on cognitive tasks of navigation within a certain physical environment, where distance perception mediates people's orientation and positioning (Montello 1997). The notion of proximity, which is understood here to refer specifically to natural-language expressions (e.g., "near," "far") of people's psychological feelings of distances, also features very prominently in people's daily life. The last decade has witnessed tremendous technological innovations in transportation and communication, which have challenged us to reexamine critically the relationship between proximity expressions forged by perceptual filters and metric distances that objectively exist in the physical space surrounding us. In this information age, people are indeed empowered with greater abilities to overcome distance barriers. Modern communication and information technologies such as intelligent transportation systems, location-based computing and services (LBS), telematics, and other novel means of wireless communications may already have come together to reshape people's perception and cognition of distances.

A significant body of literature has accumulated so far on proximity relations, with perspectives from geography, cognitive science, linguistics, and others. While prior studies on proximity modeling range from the formalization of proximity relations in space (e.g., Frank 1992; Worboys 2001) to new measures of proximity (e.g., Bera and Claramunt 2003), the dynamical modeling of the relationship between proximity and metric distances is still rather deficient. The specification of the meanings of qualitative proximity measures is seen as a major challenge for the future of space-aware information systems, such as geographical information systems (GIS) and location-based information systems, which are grounded in the precept of metric information. To enable geospatial information systems to interpret people's qualitative distance measures, further work needs to be carried out to provide a translation mechanism between qualitative distance measures and the metric distance measure that is contingent upon the various contexts of proximity perception and sensitive to interpersonal perceptual differences. Proximity modeling of qualitative locations (Yao and Thill 2005b) is critical to a wide range of new applications of space-aware information technologies based on ubiquitous computing, interoperability, and real-time information (Goodchild 2000; Thill 2000; Karimi and Hammad 2004). For example, a translation mechanism between qualitative and quantitative measures is a key component of a human-centered interface that takes qualitative inputs of spatial relations. …

Search by... Author
Show... All Results Primary Sources Peer-reviewed

Oops!

An unknown error has occurred. Please click the button below to reload the page. If the problem persists, please try again in a little while.