Semantic Discriminant mapping for classification and browsing of remote sensing textures and objects

We present a new approach based on Discriminant Analysis to map a high dimensional image feature space onto a subspace which has the following advantages: 1. each dimension corresponds to a semantic likelihood, 2. an efficient and simple multiclass classifier is proposed and 3. it is low dimensional. This mapping is learnt from a given set of labeled images with a class groundtruth. In the new space a classifier is naturally derived which performs as well as a linear SVM. We will show that projecting images in this new space provides a database browsing tool which is meaningful to the user. Results are presented on a remote sensing database with eight classes, made available online. The output semantic space is a low dimensional feature space which opens perspectives for other recognition tasks. © 2005 IEEE.

A value mapping tool for sustainable business modelling

Purpose: Although business models that deliver sustainability are increasingly popular in the literature, few tools that assist in sustainable business modelling have been identified. This paper investigates how businesses might create balanced social, environmental and economic value through integrating sustainability more fully into the core of their business. A value mapping tool is developed to help firms create value propositions better suited for sustainability. Design/methodology/approach: In addition to a literature review, six sustainable companies were interviewed to understand their approaches to business modelling, using a case study approach. Building on the literature and practice, a tool was developed which was pilot tested through use in a workshop. The resulting improved tool and process was subsequently refined through use in 13 workshops. Findings: A novel value mapping tool was developed to support sustainable business modelling, which introduces three forms of value (value captured, missed/destroyed or wasted, and opportunity) and four major stakeholder groups (environment, society, customer, and network actors). Practical implications: This tool intends to support business modelling for sustainability by assisting firms in better understanding their overall value proposition, both positive and negative, for all relevant stakeholders in the value network. Originality/value: The tool adopts a multiple stakeholder view of value, a network rather than firm centric perspective, and introduces a novel way of conceptualising value that specifically introduces value destroyed or wasted/ missed, in addition to the current value proposition and new opportunities for value creation. © Emerald Group Publishing Limited.

Is there a preferred classifier for operational thematic mapping?

The importance of properly exploiting a classifier's inherent geometric characteristics when developing a classification methodology is emphasized as a prerequisite to achieving near optimal performance when carrying out thematic mapping. When used properly, it is argued that the long-standing maximum likelihood approach and the more recent support vector machine can perform comparably. Both contain the flexibility to segment the spectral domain in such a manner as to match inherent class separations in the data, as do most reasonable classifiers. The choice of which classifier to use in practice is determined largely by preference and related considerations, such as ease of training, multiclass capabilities, and classification cost. © 1980-2012 IEEE.