Real-time Drift Detection on Time-series Data

no code implementations • 12 Oct 2021 • Nandini Ramanan, Rasool Tahmasbi, Marjorie Sayer, Deokwoo Jung, Shalini Hemachandran, Claudionor Nunes Coelho Jr

Practical machine learning applications involving time series data, such as firewall log analysis to proactively detect anomalous behavior, are concerned with real time analysis of streaming data.

Time Series Time Series Analysis

Time Series Anomaly Detection with label-free Model Selection

no code implementations • 11 Jun 2021 • Deokwoo Jung, Nandini Ramanan, Mehrnaz Amjadi, Sankeerth Rao Karingula, Jake Taylor, Claudionor Nunes Coelho Jr

Our algorithm is easily parallelizable, more robust for ill-conditioned and seasonal data, and highly scalable for a large number of anomaly models.

Anomaly Detection Ensemble Learning +3

Boosted Embeddings for Time Series Forecasting

no code implementations • 10 Apr 2021 • Sankeerth Rao Karingula, Nandini Ramanan, Rasool Tahmasbi, Mehrnaz Amjadi, Deokwoo Jung, Ricky Si, Charanraj Thimmisetty, Luisa Polania Cabrera, Marjorie Sayer, Claudionor Nunes Coelho Jr

Many advanced autoregressive methods such as ARIMA were used to develop forecasting models.

Time Series Time Series Forecasting

Semi-supervised Learning with Deep Generative Models for Asset Failure Prediction

no code implementations • 4 Sep 2017 • Andre S. Yoon, Taehoon Lee, Yongsub Lim, Deokwoo Jung, Philgyun Kang, Dongwon Kim, Keuntae Park, Yongjin Choi

This work presents a novel semi-supervised learning approach for data-driven modeling of asset failures when health status is only partially known in historical data.