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.

169,181 papers · 148 categories

Trend · papers per month

count % of corpus

5 results for “EEMD”

On Transfer Learning For Chatter Detection in Turning Using Wavelet Packet Transform and Empirical Mode Decompositioneess.SP

Transfer learning improves chatter detection accuracy with EEMD over WPT.

problem Improving chatter detection accuracy in metal cutting using transfer learning.

method Wavelet Packet Transform (WPT) and Ensemble Empirical Mode Decomposition (EEMD) for feature extraction; Support Vector Machine (SVM), Logistic Regression, Random Forest Classification, and Gradient Boosting with RFE for classification; Transfer learning applied to different turning configurations.

result EEMD outperforms WPT in transfer learning applications, achieving up to 95% accuracy.

chatter detection metal cutting wavelet packet transform empirical mode decomposition transfer learning

2019-05-03abs ↗pdf ↗

Forecasting the U.S. Real House Price Indexq-fin.CP

Paper proposes a new hybrid model for forecasting house prices.

problem Forecasting sudden house price drops to prevent financial crises.

method Combines EEMD signal processing with SVR machine learning.

result Proposed model outperforms other models with half the error.

house prices financial crises forecasting EEMD SVR

2017-07-16abs ↗pdf ↗

Next-Day Bitcoin Price Forecast Based on Artificial intelligence Methodsq-fin.ST

Paper uses AI methods to forecast Bitcoin prices.

problem Inaccurate Bitcoin price predictions in previous studies.

method Combines EEMD and LSTM for next-day price forecast.

result Improves Bitcoin price prediction accuracy.

Bitcoin Price Forecast Machine Learning Deep Learning Ensemble Empirical Mode Decomposition

2021-06-21abs ↗pdf ↗

Topological Feature Vectors for Chatter Detection in Turning Processeseess.SP

New method uses topological features for chatter detection in turning processes.

problem Chatter detection in turning processes using complex dynamical systems.

method Embedding time series as point clouds, using persistence diagrams, and applying machine learning classifiers.

result TDA-based features yield high accuracy (97%) for two out of four cutting configurations.

chatter detection topological features turning processes persistent homology support vector machine

2019-05-21abs ↗pdf ↗

Chatter Detection in Turning Using Machine Learning and Similarity Measures of Time Series via Dynamic Time Warpingeess.SP

New chatter detection method using DTW and kNN outperforms existing techniques.

problem Chatter detection from sensor signals using machine learning and similarity measures.

method K-Nearest Neighbor (kNN) algorithm for classification and Dynamic Time Warping (DTW) for time series similarity.

result DTW-based approach achieves high accuracy in three out of four cutting configurations, reaching up to 99%.

Chatter detection Machine learning Time series Dynamic Time Warping k-Nearest Neighbor

2019-08-05abs ↗pdf ↗