Publications
2023 · Conference on Health, Inference, and Learning

Homekit2020: A Benchmark for Time Series Classification on a Large Mobile Sensing Dataset with Laboratory Tested Ground Truth of Influenza Infections

Mike A Merrill, Esteban Safranchik, Arinbjorn Kolbeinsson, Piyusha Gade, Ernesto Ramirez, Ludwig Schmidt, Luca Foshchini, Tim Althoff

Research illustration for Homekit2020: A Benchmark for Time Series Classification on a Large Mobile Sensing Dataset with Laboratory Tested Ground Truth of Influenza Infections

Despite increased interest in wearables as tools for detecting various health conditions, there are not as of yet any large public benchmarks for such mobile sensing data. Our dataset contains over 14 million hours of minute-level multimodal FitBit data, symptom reports, and ground-truth laboratory PCR influenza test results, along with an evaluation framework that mimics realistic model deployments and efficiently characterizes statistical uncertainty in model selection in the presence of extreme class imbalance.

BibTeX

@article{merrillHomekit2020BenchmarkTime2023,
  title = {Homekit2020: A Benchmark for Time Series Classification on a Large Mobile Sensing Dataset with Laboratory Tested Ground Truth of Influenza Infections},
  author = {Mike A Merrill and Esteban Safranchik and Arinbjorn Kolbeinsson and Piyusha Gade and Ernesto Ramirez and Ludwig Schmidt and Luca Foshchini and Tim Althoff},
  year = {2023},
  journal = {Conference on Health, Inference, and Learning}
}