Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,878 papers · 148 categories

Trend · papers per month

count% of corpus
0.3%0.5%0.8%0.2% · Jan 201819922001200920172026
3 results for “PAA”
Boundary-aware Prototype-driven Adversarial Alignment for Cross-Corpus EEG Emotion Recognitioncs.LG

Unified framework improves cross-corpus EEG emotion recognition by aligning prototypes and refining decision boundaries.

problem Cross-corpus EEG emotion recognition suffers from performance degradation due to physiological variability and device inconsistencies.
method Prototype-driven Adversarial Alignment (PAA) framework with three configurations: local, contrastive, and boundary-aware.
result State-of-the-art performance improvements across four cross-corpus evaluation protocols.
EEG emotion recognitioncross-corpusprototype-drivenadversarial alignmentdecision boundaries
2026-03-18abs ↗pdf ↗
An Improvement of PAA on Trend-Based Approximation for Time Seriescs.LG

Two new methods improve time series analysis by capturing trend information.

problem Missing important information, especially trend, in high-dimensional time series.
method Two new approaches: 1) Relative mean value of each segment, 2) Binary string representing trend.
result Improves accuracy and effectiveness in similarity measurement and anomaly detection.
time seriesdimension reductiontrend featurePAAclassification
2019-06-28abs ↗pdf ↗