Support vector machines (SVM) have considerable potential as classifiers of remotely sensed data. A constraint on their application in remote sensing has been their binary nature, requiring multi-class classifications to be based upon a large number of binary analyses. Here, an approach for multi-class classification of airborne sensor data by a single SVM analysis is evaluated against a series of classifiers that are widely used in remote sensing, with particular regard to the effect of training set size on classification accuracy. In addition to the SVM, the same data sets were classified using a discriminant analysis, decision tree and multilayer perceptron neural network. The accuracy statements of the classifications derived from the different classifiers were compared in a statistically rigorous fashion that accommodated for the related nature of the samples used in the analyses. For each classification technique, accuracy was positively related with the size of the training set. In general, the most accurate classifications were derived from the SVM approach, and with the largest training set the SVM classification was significantly (p<0.05) more accurate (93.75%) than that derived from the discriminant analysis (90.00%) and decision tree algorithms (90.31%). Although each classifier could yield a very accurate classification, >90% correct, the classifiers differed in the ability to correctly label individual cases and so may be suitable candidates for an ensemble based approach to classification.3
The climate change arena comprises a diverse set of interacting actors from international, national and local levels. The multilevel architecture has implications for low-carbon technology deployment in developing countries, an issue salient to both development and climate objectives. The paper examines this theme through two inter-related questions: how do (or don't) low-carbon technologies get deployed in India's built environment, and what implications can be drawn from the Indian case for effective low-carbon technology development and transfer for developing countries? By examining the multilevel linkages in India's buildings sector, the paper shows how the interactions between governance levels can both support and hinder technology deployment, ultimately leading to inadequate outcomes. The potential of these linkages is hobbled by aspects of the national context (federated energy governance and developing-country capacity limitations), yet can also be enabled by other features (the climate policy context, which may motivate international actors to fill domestic capacity lacunae). Reflecting on the India case, the paper makes recommendations for improved low-carbon technology deployment in developing countries: (1) technology development and transfer collaboration on a 'need-driven' approach, (2) development of the specific types of capacity required across the entire innovation chain and (3) domestic strengthening of the coordination and agendas across and between governance levels.to one that is largely based on bottom-up country-by-country pronouncements, as formalized in the 2015 Paris Agreement (UNFCCC, 2015a). The climate change arena is now widely populated by activities that are often outside the formal auspices of UNFCCC, including initiatives that are public, private and civil society based, operating at various scales and thereby involving different levels of governance (van Asselt and Zelli, 2014). What are the implications of working within such a fragmented climate regime, which involves a diverse set of actors from international, national and local levels? In particular, what are the opportunities and challenges this architecture poses for a low-carbon technology transition in developing countries, in keeping with international climate objectives?The UNFCCC has long recognized the importance of low-carbon technology development and transfer for developing countries to assist in their growth, whilst fulfilling global climate objectives (UNFCCC, 2015b). The paper examines this theme by asking two inter-related questions: how do (or don't) low-carbon technologies get transferred and deployed in India's built environment, and what implications can be drawn from the Indian case for effective low-carbon technology development and transfer for developing countries?Multilevel climate governance provides an analytical framework to help answer these questions. The framework lays out at least two different dimensions of action and influencethe vertical and horizontalwhere varied actors interact between ...
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.