Event labeling combining ensemble detectors and background knowledge

By Hadi Fanaee-T, João Gama. 2014

496 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Signal Processing

Citations in the corpus

Privacy-Preserving Distributed Linear Regression on High-Dimensional Data (2017, neutral): “8 · 101 29 60 5 Bike Sharing Dataset [25, 26] 12 17 379 8.”
Visualizing the effects of predictor variables in black box supervised learning models (2016, background): “regated on an hourly basis, together with hourly weather and seasonal information over the same time period. The data le can be found at https://archive.ics.uci.edu/ ml/datasets/Bike+Sharing+Dataset (Fanaee-T and Gama (2013)). There are n= 17393 cases/rows in the training data set corresponding to 1”
Assumed Density Filtering Methods for Learning Bayesian Neural Networks (2016, methodology): “Finally, we test our count regression model on a real world bike rental demand forecasting problem (Fanaee-T and Gama 2013).”
Anchor regression: Heterogeneous data meet causality (2018, methodology): “e data set contains the numerical covariates temperature, feeling temperature, humidity and windspeed. There are large uctuations in the usage of bikes that cannot be explained by weather data alone [Fanaee-T and Gama, 2013]. Instead of using the discrete variable ’date’ for prediction, we use it as”
Understanding Global Feature Contributions With Additive Importance Measures (2020, methodology): “For datasets, we used MNIST [19], a bike sharing demand dataset [10], the German credit quality dataset [21], the Portuguese bank marketing dataset [26], and a breast cancer (BRCA) subtype classiﬁcation dataset [4, 39].”
Hypothesis Tests That Are Robust to Choice of Matching Method (2018, methodology): “ can be rejected. 5.2. Case Study 2: The Eect of Mist on Bike Sharing Usage In our second case study, we used 2 years (2011-2012) of bike sharing data from the Capital Bike Sharing (CBS) system (see Fanaee-T and Gama 2014) from Washington DC comprised of 3,807,587 records over 731 days, from which w”
Please Stop Permuting Features: An Explanation and Alternatives (2019, methodology): “To illustrate the real-world impact of the difference among these importance measures, Figure 8 presents the importance rankings of features in the hourly bike share data reported in Fanaee-T and Gama (2013) as stored on the UCI repository.”
Getting Better from Worse: Augmented Bagging and a Cautionary Tale of Variable Importance (2020, background): “Interested readers are also invited to see a similar discussion on model class reliance appearing recently in Fisher et al. (2019). Finally, as alluded to also in Williamson et al. (2021), practitioners should always have in mind a notion of relevant effect size when conducting tests for importance ”
Preventing Failures Due to Dataset Shift: Learning Predictive Models That Transport (2018, methodology): “Following Rothenhäusler et al. (2018) we use the UCI Bike Sharing dataset (Fanaee-T and Gama, 2013; Dheeru and Karra Taniskidou, 2017) in which the goal is to predict the number of hourly bike rentals R from weather data including temperature T , feeling temperature F , wind speed W , and humidity…”