Producing a GIS based multiple criteria analysis tool for regional sustainability assessment: the problem of weighting

Decision support tools will be useful in guiding regions to sustainability. These need to be simple but effective at identifying, for regional managers, areas most in need of initiatives to progress sustainability. Multiple criteria analysis (MCA) is often used as a decision support tool for a wide range of applications. This method allows many criteria to be considered at one time. It does this by giving a ranking of possible options based on how closely each option meets the criteria. Thus, it is suited to the assessment of regional sustainability as it can consider a number of indicators simultaneously and demonstrates how sustainability can vary at small scales across the region. Coupling MCA with GIS to produce maps, allows this analysis to become visual giving the manager a picture of sustainability across the region. To do this each indicator is standardised to a common scale so that it can be compared to other indicators. A weighting is then applied to each indicator to calculate weighted summation for each area in the region. This paper argues that this is the critical step in developing a useful decision support tool. A study being conducted in south west Victoria demonstrates that the weights chosen can have a dramatic impact on the results of the sustainability assessment. It is therefore imperative that careful consideration be given to determining indicator weights in a way that is objective and fully considers the impact of that indicator on regional sustainability.

Analysis of forest policy using multi-attribute value theory

Contents:
1. Role of multi-criteria decision making in natural resource management /​ Gamini Herath and Tony Prato
2. Analysis of forest policy using multi-attribute value theory /​ Jayanath Ananda and Gamini Herath
3. Comparing Riparian revegetation policy options using the analytic hierarchy process /​ M. E. Qureshi and S. R. Harrison
4. Managing environmental and health risks from a lead and zinc smelter : an application of deliberative multi-criteria evaluation /​ Wendy Proctor, Chris McQuade and Anne Dekker
5. Multiple attribute evaluation of management alternatives for the Missouri River System /​ Tony Prato
6. Multi-criteria decision analysis for integrated watershed management /​ Zeyuan Qiu
7. Fuzzy multiple attribute evaluation of agricultural systems /​ Leonie A. Marks and Elizabeth G. Dunn
8. Multi-criteria decision support for energy supply assessment /​ Bram Noble
9. Seaport development in Vietnam : evaluation using the analytic hierarchy process /​ Tran Phuong Dong and David M. Chapman
10. Valuing wetland aquatic resources using the analytic hierarchy process /​ Premachandra Wattage and Simon Mardle
11. Multiple attribute evaluation for national park management /​ Tony Prato
12. The future of MCDA in natural resource management : some generalizations /​ Gamini Herath and Tony Prato.

Multi-attribute preference modelling and regional land-use planning

Forest management policy decisions are complex due to the multiple-use nature of goods and services from forests, difficulty in monetary valuation of ecological services and the involvement of a large number of stakeholders. Multi-attribute decision techniques can be used to synthesise stakeholder preferences related to regional forest planning because it can accommodate conflicting, multidimensional, incommensurable and incomparable objectives. The objective of this paper is to examine how the Analytical Hierarchy Process (AHP) can be used to incorporate stakeholder preferences in determining optimal forest land-use choices. The Australian Regional Forest Agreement Programme is taken as an illustrative case for the analysis. The results show that the AHP can formalise public participation in decision making and increase the transparency and the credibility of the process.

A rough set approach for selecting clustering attribute

A few of clustering techniques for categorical data exist to group objects having similar characteristics. Some are able to handle uncertainty in the clustering process while others have stability issues. However, the performance of these techniques is an issue due to low accuracy and high computational complexity. This paper proposes a new technique called maximum dependency attributes (MDA) for selecting clustering attribute. The proposed approach is based on rough set theory by taking into account the dependency of attributes of the database. We analyze and compare the performance of MDA technique with the bi-clustering, total roughness (TR) and min–min roughness (MMR) techniques based on four test cases. The results establish the better performance of the proposed approach.

Finding coverage using incremental attribute combinations

Coverage is the range that covers only positive samples in attribute (or feature) space. Finding coverage is the kernel problem in induction algorithms because of the fact that coverage can be used as rules to describe positive samples. To reflect the characteristic of training samples, it is desirable that the large coverage that cover more positive samples. However, it is difficult to find large coverage, because the attribute space is usually very high dimensionality. Many heuristic methods such as ID3, AQ and CN2 have been proposed to find large coverage. A robust algorithm also has been proposed to find the largest coverage, but the complexities of time and space are costly when the dimensionality becomes high. To overcome this drawback, this paper proposes an algorithm that adopts incremental feature combinations to effectively find the largest coverage. In this algorithm, the irrelevant coverage can be pruned away at early stages because potentially large coverage can be found earlier. Experiments show that the space and time needed to find the largest coverage has been significantly reduced.

Clustering with instance and attribute level side information

Selecting a suitable proximity measure is one of the fundamental tasks in clustering. How to effectively utilize all available side information, including the instance level information in the form of pair-wise constraints, and the attribute level information in the form of attribute order preferences, is an essential problem in metric learning. In this paper, we propose a learning framework in which both the pair-wise constraints and the attribute order preferences can be incorporated simultaneously. The theory behind it and the related parameter adjusting technique have been described in details. Experimental results on benchmark data sets demonstrate the effectiveness of proposed method.

Missing value estimation for mixed-attribute data sets

Missing data imputation is a key issue in learning from incomplete data. Various techniques have been developed with great successes on dealing with missing values in data sets with homogeneous attributes (their independent attributes are all either continuous or discrete). This paper studies a new setting of missing data imputation, i.e., imputing missing data in data sets with heterogeneous attributes (their independent attributes are of different types), referred to as imputing mixed-attribute data sets. Although many real applications are in this setting, there is no estimator designed for imputing mixed-attribute data sets. This paper first proposes two consistent estimators for discrete and continuous missing target values, respectively. And then, a mixture-kernel-based iterative estimator is advocated to impute mixed-attribute data sets. The proposed method is evaluated with extensive experiments compared with some typical algorithms, and the result demonstrates that the proposed approach is better than these existing imputation methods in terms of classification accuracy and root mean square error (RMSE) at different missing ratios.

Integrating instance-level and attribute-level knowledge into document clustering

In this paper, we present a document clustering framework incorporating instance-level knowledge in the form of pairwise constraints and attribute-level knowledge in the form of keyphrases. Firstly, we initialize weights based on metric learning with pairwise constraints, then simultaneously learn two kinds of knowledge by combining the distance-based and the constraint-based approaches, finally evaluate and select clustering result based on the degree of users’ satisfaction. The experimental results demonstrate the effectiveness and potential of the proposed method.

A content analysis of sponsor representation across professional sport websites : extension of attribute typology

The sport industry has identified the importance of using the internet as a tool that can benefit the organisation. Much like the purpose of entering into sponsorship of sporting events, corporate partners are also attracted to the opportunities that professional sport team websites offer to fulfil similar objectives. The major purpose of this research is to explore the various ways in which sponsor logos are represented across professional sport websites and to extend previous advertising research, specifically the work developing advertising attribute typologies. The subjects for this research are professional sport websites and a qualitative approach is adopted with a content analysis as the main method of analysis used. To ensure reliability and validity within the coding instruments used, percentage agreement and Cohen’s kappa were adopted as indexes to verify this. The findings show sponsors’ logos exist on most professional sport websites and are represented in a variety of ways. Furthermore, a typology for sponsor representation and location across sport websites has been established to present a reliable foundation for future research in the area of consumer attitudes, behaviour and response towards sponsors and their presence on sport websites.

An effective semi-supervised clustering framework integrating pairwise constraints and attribute preferences

Both the instance level knowledge and the attribute level knowledge can improve clustering quality, but how to effectively utilize both of them is an essential problem to solve. This paper proposes a wrapper framework for semi-supervised clustering, which aims to gracely integrate both kinds of priori knowledge in the clustering process, the instance level knowledge in the form of pairwise constraints and the attribute level knowledge in the form of attribute order preferences. The wrapped algorithm is then designed as a semi-supervised clustering process which transforms this clustering problem into an optimization problem. The experimental results demonstrate the effectiveness and potential of proposed method.