Agnieszka Turek

Application of the Spatial Data Mining Methodology and Gamification for the Optimisation of Solving the Transport Issues of the “Varsovian Mordor”

The objective of the paper was to develop a specialised knowledge base using data mining methods, as the basis for and expert, decision making support system, created for the needs of development of action against negative spatial phenomena, which occur within the biggest office district of the capital of Poland. After collecting representative answers to a questionnaire from responders, who are professionally involved with this area, the authors “enriched the data” with commonly accessible spatial information and analysed the resulting dataset using artificial, regression and classification neural networks, CART decision trees and created fuzzy inference systems. Inference rules, developed with the use of the knowledge base and a limited amount of accessible information allow to specify highly probable types of social problems important for particular employees of this district. Using data mining techniques, the authors transformed collected data into information and knowledge, diagnosing main infrastructural and spatial problems in “Varsovian Mordor”. Generalisation of inference rules, developed as a result of knowledge acquisition allowed the authors to propose unique, social gamification techniques, precisely dedicated for particular groups of inhabitants and employees of “the Mordor”.

Solving “Smart City” Transport Problems by Designing Carpooling Gamification Schemes with Multi-Agent Systems: The Case of the So-Called “Mordor of Warsaw”

To reduce energy consumption and improve residents’ quality of life, “smart cities” should use not only modern technologies, but also the social innovations of the “Internet of Things” (IoT) era. This article attempts to solve transport problems in a smart city’s office district by utilizing gamification that incentivizes the carpooling system. The goal of the devised system is to significantly reduce the number of cars, and, consequently, to alleviate traffic jams, as well as to curb pollution and energy consumption. A representative sample of the statistical population of people working in one of the biggest office hubs in Poland (the so-called “Mordor of Warsaw”) was surveyed. The collected data were processed using spatial data mining methods, and the results were a set of parameters for the multi-agent system. This approach made it possible to run a series of simulations on a set of 100,000 agents and to select an effective gamification methodology that supports the carpooling process. The implementation of the proposed solutions (a “serious game” variation of urban games) would help to reduce the number of cars by several dozen percent, significantly reduce energy consumption, eliminate traffic jams, and increase the activity of the smart city residents.

An Example of Multitemporal Photogrammetric Documentation and Spatial Analysis in Process Revitalisation and Urban Planning.

Urban space is undergoing permanent and dynamic transformations resulting from economic and social changes, technological development and migrations of people from rural areas to cities. It strongly affects the evolution of the landscape and city structures. Current photogrammetric techniques allow for the acquisition of data for large areas within a relatively short time, and thus, allow for fast updating and verification of existing data files. The authors of this paper have focused their research on the possibility to use multi-variant spatial analysis in the process of revitalisation of degraded areas in cities. The industrial district of Warsaw was selected for this study, where problems concerning the development of formally industrial areas located in the attractive part of the city (close to the city centre) are extremely visible. As a result of urban development, degraded areas are included within administrative boundaries of the city and have created urban

Application of Decision Trees in the Development of a Knowledge Base for a System of Support for Revitalization Processes

The objective of the paper was to develop an efficient system supporting the management of degraded areas and their revitalization. The author developed a knowledge base for a system of assessment and support of revitalization processes through the application of selected data mining methods. The database included more than 100 objects for which approximately 100 attributes on different measurement scales were collected. The analysis of the collected data involved the application of decision trees. The intermediate goal was the determination of the applicative potential of properly transformed spatial data for the requirements of revitalization procedures. The studies carried out represent early work in this scientific field, and the author provides a methodological basis for further research.