Deep SVDD anomaly detection on synthetic normal flares finds 30-36% of Kepler events and 15-32% of STIX events as anomalous, more often in higher-energy channels.
Time series classification from scratch with deep neural networks: A strong baseline
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 1
baseline 1
method 1
citation-polarity summary
years
2026 7representative citing papers
Pruning hybrid time series classifiers including the new Hydrant combination can reduce energy consumption by up to 80% while keeping accuracy loss below 5%.
A TSC framework separates historical attendance sequences from future labels and uses LSTM-FCN with BFL or G-Mean loss to achieve approximately 80% balanced accuracy for proactive absenteeism prediction on simulated data.
A neural network detector applied to 2011 solar radio spectra identified 50 QFP wave train candidates, with 13 associated with global coronal EUV waves.
Transformer models classify seven wildlife species from daily GPS trajectories, outperforming LSTM, CNN, and TCN baselines by 8-22 percentage points in balanced accuracy under region-holdout evaluation.
PaAno+ extends the original PaAno with multiscale feature extraction, cross-variable fusion attention, and a temporal patch sorting pretext task to report state-of-the-art results on the TSB-AD benchmark for univariate and multivariate anomaly detection.
citing papers explorer
-
Time-domain anomalies in solar and stellar flares
Deep SVDD anomaly detection on synthetic normal flares finds 30-36% of Kepler events and 15-32% of STIX events as anomalous, more often in higher-energy channels.
-
Pruning Extensions and Efficiency Trade-Offs for Sustainable Time Series Classification
Pruning hybrid time series classifiers including the new Hydrant combination can reduce energy consumption by up to 80% while keeping accuracy loss below 5%.
-
A time-series classification framework for individual-level absenteeism prediction under severe class imbalance
A TSC framework separates historical attendance sequences from future labels and uses LSTM-FCN with BFL or G-Mean loss to achieve approximately 80% balanced accuracy for proactive absenteeism prediction on simulated data.
-
Detector for fast wave trains in the solar radio emission
A neural network detector applied to 2011 solar radio spectra identified 50 QFP wave train candidates, with 13 associated with global coronal EUV waves.
-
Transformer-Based Wildlife Species Classification from Daily Movement Trajectories
Transformer models classify seven wildlife species from daily GPS trajectories, outperforming LSTM, CNN, and TCN baselines by 8-22 percentage points in balanced accuracy under region-holdout evaluation.
-
PaAno+: Multiscale Encoding and Cross-Variable Attention for Time Series Anomaly Detection
PaAno+ extends the original PaAno with multiscale feature extraction, cross-variable fusion attention, and a temporal patch sorting pretext task to report state-of-the-art results on the TSB-AD benchmark for univariate and multivariate anomaly detection.
- PaAno: Patch-Based Representation Learning for Time-Series Anomaly Detection