The volume aims to make a scientific contribution to the GeoComputation approach in urban planning, with a specific focus on the development of Distributed Artificial Intelligence principles and techniques (Werner, 1996) as a support to planning. Neural Networks (NN), Multi-Agent Systems (MA) and Evolutionary Algorithms (EA), in particular, allow the knowledge level to be increased by multiplying the information capacity of the GIS and offering a new approach to territorial modelling. The first part of the book is devoted to the investigative potential of neural networks. The most prominent feature of NNs is their ability to learn from examples. Using so-called learning algorithms they solve problems by processing a set of training data. The second chapter by Silvio Griguolo shows the power of neural networks as pattern recognisers. Neural networks are universally recognised as efficient classifiers for multi-dimensional problems involving pattern recognition of massive quantities of data for remotely-sensed imagery. Chapter Three, by Manfred Fischer and Katerina Hlavackova-Schindler, presents two new approaches using neural networks and statistical optimisation to solve the parameter estimation problem, one of the main issues in neural spatial interaction modelling. Chapter Four, written by Lidia Diappi, Massimo Buscema and Michela Ottanà, addresses the problem of evaluating the complex facets of urban sustainability in Italian cities. Since sustainability should be defined as a positive co-evolution of social, economic and environmental systems, the complex interactions among the phenomena give rise to positive and negative externalities described by a set of indicators.The complexity of the interactions requires highly efficient investigation tools and presents the opportunity for a new methodology of scientific investigation using Self Reflexive Neural Networks (SRNN). The second part of the book shifts attention to different studies for assessing land use change. The various authors adopt a wide range of approaches with Intelligent Computing accompanying more established statistical or modelling approaches. In Chapter Five, written by Silvana Lombardo, Francesco Bonchi and Serena Pecori, is presented a cognitive system which is based on Data Mining and Knowledge Discovery in Database Process. This method merges concepts and techniques from many different research areas, such as statistics and machine learning, with the aim of extracting knowledge on the role played by urban/territorial factors in spatial evolution. The Chapter Six, written by Francesco Bonchi, Silvana Lombardo, Serena Pecori and Alessandro Santucci, presents the experimental results of the above method. In Chapter Seven, Ferdinando Semboloni shows a method for extracting the rules of the urban spatio-temporal dynamic from a limited set of data. This method is based on a GIS at two temporal thresholds concerning the spatial distribution of relevant variables in a city. The final chapter of Part Two, Chapter Eight, written by Lidia Diappi and Paola Bolchi, moves to GC modelling through a dynamic model of urbanisation. The model is based on transition rules learned from an autopoietic neural network (SOM, Self-Organizing Maps) which processes land-use changes occurring in the area being studied over a certain period. A stochastic model then allocates the land-use changes in the subsequent period (forecast) by applying learned rules. Part three of the book is devoted to Multi Agent Systems. Simulating real processes using Multi Agent Systems means building up a complex system from individual decision units having a certain degree of autonomy and which interact with one another according to certain rules. It can be defined as “… a weakly connected network of agents which act together to resolve problems that exceed their individual capacity to resolve them…” (Durfee et al., 1989; Farber, 1965). Chapter Nine, by Kai Nagel and Bryan Raney, presents an innovative approach where the classical modules in transportation modelling (activity generation, mode choice and routing, simulation and testing, learning and feed-back) are revised in an MAS framework. Each traveller is represented individually with his own set of plans and strategies, that are loaded into the simulation modules. In Chapter Ten by Grazia Concilio and Emilia Conte, MAS techniques shift to decision support systems (DSS) in order to study the architecture of a knowledge-based multi-agent DSS for monitoring the compatibility of urban activities, and particularly of traffic induced by such activities, in relation to the generation or presence of atmospheric pollutants. The system is proposed to support the task of technicians in a city’s traffic agency, and especially decisions regarding data validation and action strategies. In Chapter Eleven, Chris Webster demonstrates the use of a simple cellular automaton to represent a model of neighbourhood evolution based on theoretical ideas from the new institutional economics. The urban neighbourhood is viewed as a constantly evolving nexus of contracts (informal institutions) the purpose of which are to constrain competition over jointly consumed resources

Evolving cities: Geocomputation in territorial Planning

DIAPPI, LIDIA
2004

Abstract

The volume aims to make a scientific contribution to the GeoComputation approach in urban planning, with a specific focus on the development of Distributed Artificial Intelligence principles and techniques (Werner, 1996) as a support to planning. Neural Networks (NN), Multi-Agent Systems (MA) and Evolutionary Algorithms (EA), in particular, allow the knowledge level to be increased by multiplying the information capacity of the GIS and offering a new approach to territorial modelling. The first part of the book is devoted to the investigative potential of neural networks. The most prominent feature of NNs is their ability to learn from examples. Using so-called learning algorithms they solve problems by processing a set of training data. The second chapter by Silvio Griguolo shows the power of neural networks as pattern recognisers. Neural networks are universally recognised as efficient classifiers for multi-dimensional problems involving pattern recognition of massive quantities of data for remotely-sensed imagery. Chapter Three, by Manfred Fischer and Katerina Hlavackova-Schindler, presents two new approaches using neural networks and statistical optimisation to solve the parameter estimation problem, one of the main issues in neural spatial interaction modelling. Chapter Four, written by Lidia Diappi, Massimo Buscema and Michela Ottanà, addresses the problem of evaluating the complex facets of urban sustainability in Italian cities. Since sustainability should be defined as a positive co-evolution of social, economic and environmental systems, the complex interactions among the phenomena give rise to positive and negative externalities described by a set of indicators.The complexity of the interactions requires highly efficient investigation tools and presents the opportunity for a new methodology of scientific investigation using Self Reflexive Neural Networks (SRNN). The second part of the book shifts attention to different studies for assessing land use change. The various authors adopt a wide range of approaches with Intelligent Computing accompanying more established statistical or modelling approaches. In Chapter Five, written by Silvana Lombardo, Francesco Bonchi and Serena Pecori, is presented a cognitive system which is based on Data Mining and Knowledge Discovery in Database Process. This method merges concepts and techniques from many different research areas, such as statistics and machine learning, with the aim of extracting knowledge on the role played by urban/territorial factors in spatial evolution. The Chapter Six, written by Francesco Bonchi, Silvana Lombardo, Serena Pecori and Alessandro Santucci, presents the experimental results of the above method. In Chapter Seven, Ferdinando Semboloni shows a method for extracting the rules of the urban spatio-temporal dynamic from a limited set of data. This method is based on a GIS at two temporal thresholds concerning the spatial distribution of relevant variables in a city. The final chapter of Part Two, Chapter Eight, written by Lidia Diappi and Paola Bolchi, moves to GC modelling through a dynamic model of urbanisation. The model is based on transition rules learned from an autopoietic neural network (SOM, Self-Organizing Maps) which processes land-use changes occurring in the area being studied over a certain period. A stochastic model then allocates the land-use changes in the subsequent period (forecast) by applying learned rules. Part three of the book is devoted to Multi Agent Systems. Simulating real processes using Multi Agent Systems means building up a complex system from individual decision units having a certain degree of autonomy and which interact with one another according to certain rules. It can be defined as “… a weakly connected network of agents which act together to resolve problems that exceed their individual capacity to resolve them…” (Durfee et al., 1989; Farber, 1965). Chapter Nine, by Kai Nagel and Bryan Raney, presents an innovative approach where the classical modules in transportation modelling (activity generation, mode choice and routing, simulation and testing, learning and feed-back) are revised in an MAS framework. Each traveller is represented individually with his own set of plans and strategies, that are loaded into the simulation modules. In Chapter Ten by Grazia Concilio and Emilia Conte, MAS techniques shift to decision support systems (DSS) in order to study the architecture of a knowledge-based multi-agent DSS for monitoring the compatibility of urban activities, and particularly of traffic induced by such activities, in relation to the generation or presence of atmospheric pollutants. The system is proposed to support the task of technicians in a city’s traffic agency, and especially decisions regarding data validation and action strategies. In Chapter Eleven, Chris Webster demonstrates the use of a simple cellular automaton to represent a model of neighbourhood evolution based on theoretical ideas from the new institutional economics. The urban neighbourhood is viewed as a constantly evolving nexus of contracts (informal institutions) the purpose of which are to constrain competition over jointly consumed resources
Ashgate Publishing
9780754641940
File in questo prodotto:
File Dimensione Formato  
081909r_Part2.pdf

Accesso riservato

: Post-Print (DRAFT o Author’s Accepted Manuscript-AAM)
Dimensione 3.19 MB
Formato Adobe PDF
3.19 MB Adobe PDF   Visualizza/Apri   Richiedi una copia
081909r_Part3.pdf

Accesso riservato

: Post-Print (DRAFT o Author’s Accepted Manuscript-AAM)
Dimensione 3.06 MB
Formato Adobe PDF
3.06 MB Adobe PDF   Visualizza/Apri   Richiedi una copia
081909r_Part7.pdf

Accesso riservato

: Post-Print (DRAFT o Author’s Accepted Manuscript-AAM)
Dimensione 3.78 MB
Formato Adobe PDF
3.78 MB Adobe PDF   Visualizza/Apri   Richiedi una copia
081909r_Part4.pdf

Accesso riservato

: Post-Print (DRAFT o Author’s Accepted Manuscript-AAM)
Dimensione 3.12 MB
Formato Adobe PDF
3.12 MB Adobe PDF   Visualizza/Apri   Richiedi una copia
081909r_Part5.pdf

Accesso riservato

: Post-Print (DRAFT o Author’s Accepted Manuscript-AAM)
Dimensione 3.63 MB
Formato Adobe PDF
3.63 MB Adobe PDF   Visualizza/Apri   Richiedi una copia
081909r_Part6.pdf

Accesso riservato

: Post-Print (DRAFT o Author’s Accepted Manuscript-AAM)
Dimensione 3 MB
Formato Adobe PDF
3 MB Adobe PDF   Visualizza/Apri   Richiedi una copia
081909r_Part1.pdf

Accesso riservato

: Post-Print (DRAFT o Author’s Accepted Manuscript-AAM)
Dimensione 2.36 MB
Formato Adobe PDF
2.36 MB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: http://hdl.handle.net/11311/259974
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact