Principal Components Analysis Preprocessing for Improved Classification Accuracies in Pattern-Recognition-Bases Myoelectric Control

Hargrove, LJ, Li, G, Englehart, KB, Hudgins, BS, "Principal Components Analysis Preprocessing for Improved Classification Accuracies in Pattern-Recognition-Bases Myoelectric Control," IEEE Transactions on Biomedical Engineering, 56(5), 2009.

Links:  Xplore Entry

Key Finding:  Pattern classification error can be reduced by applying principal component analysis before extracting features.

ANNSTLF-Artificial Neural Network Short-Term Load Forecaster- generation three

 A. Khotanzad, R. Afkhami-Rohani and D. Maratukulam, "ANNSTLF-Artificial Neural Network Short-Term Load Forecaster- generation three," in IEEE Transactions on Power Systems, vol. 13, no. 4, pp. 1413-1422, Nov. 1998, doi: 10.1109/59.736285.

Links: Xplore Entry

Key Findings:  Load forecasting is improved by adaptively combining only 2 ANNs - a load forecaster, and a change in load forecaster.  This is an improvement over earlier generations which used more than 2 ANNs.  It also provides specialty training for holidays.

GenderMag: A Method for Evaluating Software's Gender Inclusiveness

 in Interaction with Computers, Volume 28, Issue 6, 2016.

M Burnett, S Stumpf, J Macbeth, S Makri, L Beckwith, I Kwan, A Peters, W Jernigan, "GenderMag: A Method for Evaluating Software's Gender Inclusiveness", Interacting with Computers, 28(6), pp 760–787, 2016. 

Links:  Oxford Academic Entry, GenderMag Homepage

Key Findings: 

Key Topics Covered:

A Probabilistic Model behind Self-Supervised Learning

 A bizeul, B Scholkopf, C Allen, A Probabilistic Model behind Self-Supervised Learning, https://arxiv.org/abs/2402.01399v2, submitted 2024-02-02, revised 2024-06--04.