More-than-human histories and the failure of grand state schemes: sylviculture in the New Forest, England

As James Scott’s Seeing Like a State attests, forests played a central role in the rise of the modern state, specifically as test spaces for evolving methods of managing state resources at a distance, and as the location for grand state schemes. Together, such ambitions necessitated both the elimination of local understandings of forest management – to be replaced by centrally controlled scientific precision – and a narrowing of state vision. Forests thus began to be conflated with trees (and their timber) alone. All other aspects of the forest, both human and non-human, were ignored. Through the lens of the 18th and early 19th century New Forest in southern England, this paper examines the impact of government attempts to shift the focus of state forests from being remnant medieval hunting spaces to spaces of income generation through the creation of vast sylvicultural plantations. This state scheme not only reworked the relationship between the metropole and the provinces – something effected through systematic surveys and novel bureaucratic procedures – but also dramatically impacted upon the biophysical and cultural geographies of the forest. By equating forest space with trees alone, the British state failed to legislate for the actions of both local commoners and non-human others in resisting their schemes. Indeed, subsequent oppositions proved not only the tenacity of commoners in protecting their livelihoods but also the destructive power of non-human actants, specifically rabbits and mice. The paper concludes that grand state schemes necessarily fail due to their own internal illogic: the narrowing of state vision creates blind spots in which human and non-human lives assert their own visions.

Random Forest Based Approach for Concept-Drift Handling

Algorithms for concept drift handling are important for various applications including video analysis and smart grids. In this paper we present decision tree ensemble classication method based on the Random Forest algorithm for concept drift. The weighted majority voting ensemble aggregation rule is employed based on the ideas of Accuracy Weighted Ensemble (AWE) method. Base learner weight in our case is computed for each sample evaluation using base learners accuracy and intrinsic proximity measure of Random Forest. Our algorithm exploits both temporal weighting of samples and ensemble pruning as a forgetting strategy. We present results of empirical comparison of our method with îriginal random forest with incorporated replace-the-looser forgetting andother state-of-the-art concept-drift classiers like AWE2.