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.

Sustained effectiveness of a multifaceted intervention to reduce potentially inappropriate prescribing in older patients in primary care (OPTI-SCRIPT study)

Background: Potentially inappropriate prescribing (PIP) is common in older people in primary care and can result in increased morbidity, adverse drug events and hospitalisations. We previously demonstrated the success of a multifaceted intervention in decreasing PIP in primary care in a cluster randomised controlled trial (RCT).
Objective: We sought to determine whether the improvement in PIP in the short term was sustained at 1-year follow-up.
Methods: A cluster RCT was conducted with 21 GP practices and 196 patients (aged ≥70) with PIP in Irish primary care. Intervention participants received a complex multifaceted intervention incorporating academic detailing, medicine review with web-based pharmaceutical treatment algorithms that provide recommended alternative treatment options, and tailored patient information leaflets. Control practices delivered usual care and received simple, patient-level PIP feedback. Primary outcomes were the proportion of patients with PIP and the mean number of potentially inappropriate prescriptions at 1-year follow-up. Intention-to-treat analysis using random effects regression was used.
Results: All 21 GP practices and 186 (95 %) patients were followed up. We found that at 1-year follow-up, the significant reduction in the odds of PIP exposure achieved during the intervention was sustained after its discontinuation (adjusted OR 0.28, 95 % CI 0.11 to 0.76, P = 0.01). Intervention participants had significantly lower odds of having a potentially inappropriate proton pump inhibitor compared to controls (adjusted OR 0.40, 95 % CI 0.17 to 0.94, P = 0.04).
Conclusion: The significant reduction in the odds of PIP achieved during the intervention was sustained after its discontinuation. These results indicate that improvements in prescribing quality can be maintained over time.

Posterior Probability Modeling and Image Classification for Archaeological Site Prospection: Building a Survey Efficacy Model for Identifying Neolithic Felsite Workshops in the Shetland Islands

The application of custom classification techniques and posterior probability modeling (PPM) using Worldview-2 multispectral imagery to archaeological field survey is presented in this paper. Research is focused on the identification of Neolithic felsite stone tool workshops in the North Mavine region of the Shetland Islands in Northern Scotland. Sample data from known workshops surveyed using differential GPS are used alongside known non-sites to train a linear discriminant analysis (LDA) classifier based on a combination of datasets including Worldview-2 bands, band difference ratios (BDR) and topographical derivatives. Principal components analysis is further used to test and reduce dimensionality caused by redundant datasets. Probability models were generated by LDA using principal components and tested with sites identified through geological field survey. Testing shows the prospective ability of this technique and significance between 0.05 and 0.01, and gain statistics between 0.90 and 0.94, higher than those obtained using maximum likelihood and random forest classifiers. Results suggest that this approach is best suited to relatively homogenous site types, and performs better with correlated data sources. Finally, by combining posterior probability models and least-cost analysis, a survey least-cost efficacy model is generated showing the utility of such approaches to archaeological field survey.