Search Results for author: Diogo Duarte

Found 4 papers, 0 papers with code

On the Reduction of Biases in Big Data Sets for the Detection of Irregular Power Usage

no code implementations17 Jan 2018 Patrick Glauner, Radu State, Petko Valtchev, Diogo Duarte

Our models have the potential to generate significant economic value in a real world application, as they are being deployed in a commercial software for the detection of irregular power usage.

BIG-bench Machine Learning

Identifying Irregular Power Usage by Turning Predictions into Holographic Spatial Visualizations

no code implementations9 Sep 2017 Patrick Glauner, Niklas Dahringer, Oleksandr Puhachov, Jorge Augusto Meira, Petko Valtchev, Radu State, Diogo Duarte

Second, in order to allow human experts to feed their knowledge in the decision loop, we propose a method for visualizing prediction results at various granularity levels in a spatial hologram.

Decision Making

Neighborhood Features Help Detecting Non-Technical Losses in Big Data Sets

no code implementations4 Jul 2016 Patrick Glauner, Jorge Meira, Lautaro Dolberg, Radu State, Franck Bettinger, Yves Rangoni, Diogo Duarte

Using the neighborhood features instead of only analyzing the time series has resulted in appreciable results for Big Data sets for varying NTL proportions of 1%-90%.

Time Series Time Series Analysis

Large-Scale Detection of Non-Technical Losses in Imbalanced Data Sets

no code implementations26 Feb 2016 Patrick O. Glauner, Andre Boechat, Lautaro Dolberg, Radu State, Franck Bettinger, Yves Rangoni, Diogo Duarte

We believe that the considerations and observations made in this contribution are necessary for future smart meter research in order to report their effectiveness on imbalanced and large real world data sets.

Small Data Image Classification

Cannot find the paper you are looking for? You can Submit a new open access paper.