scholarly journals Shifting: One-inclusion mistake bounds and sample compression

2009 ◽  
Vol 75 (1) ◽  
pp. 37-59 ◽  
Author(s):  
Benjamin I.P. Rubinstein ◽  
Peter L. Bartlett ◽  
J. Hyam Rubinstein
Keyword(s):  
Mistake Bounds ◽  
Sample Compression

scholarly journals Sample compression, learnability, and the Vapnik-Chervonenkis dimension

1995 ◽  
Vol 21 (3) ◽  
pp. 269-304 ◽  
Author(s):  
Sally Floyd ◽  
Manfred Warmuth
Keyword(s):  
Sample Compression

scholarly journals Mistake bounds on the noise-free multi-armed bandit game

2019 ◽  
Vol 269 ◽  
pp. 104453 ◽  
Author(s):  
Atsuyoshi Nakamura ◽  
David P. Helmbold ◽  
Manfred K. Warmuth
Keyword(s):  
Mistake Bounds

scholarly journals On a Generalized Notion of Mistake Bounds

2001 ◽  
Vol 166 (2) ◽  
pp. 156-166 ◽  
Author(s):  
Sanjay Jain ◽  
Arun Sharma
Keyword(s):  
Mistake Bounds

scholarly journals THE COMPARISON OF SSD ALGORITHM WITH OTHER ECG SAMPLING ALGORITHMS

2006 ◽  
Vol 18 (03) ◽  
pp. 124-127
Author(s):  
HSIAO-HSUAN CHOU ◽  
YU-CHIEN SHIAU ◽  
TE-SON KUO
Keyword(s):  
Sampling Rate ◽  
Polygonal Approximation ◽  
Compression Performance ◽  
Uniform Sampling ◽  
Ecg Signals ◽  
Sample Compression ◽  
Sampling Algorithms ◽  
Two Measures ◽  
Test Equation ◽  
Electrocardiogram Ecg

We had proposed a novel and fast Electrocardiogram (ECG) signal compression algorithm for non-uniform sampling in time domain [1]. It meets the real-time requirement for clinical application. Moreover, the compression performance is stable and uniform even for abnormal ECG signals. A criterion called sum square difference (SSD) is defined as an error test equation. The algorithm using SSD to calculate error tolerance is applied to the records in MIT-BIH database (with 11-bit resolution and 360 Hz sampling rate). It belongs to the threshold-limited algorithm but [1] does not mention much about this kind of algorithm. In this paper we provide more comparisons among SSD, Fan, scan-along polygonal approximation (SAPA), maximum enclosed area (MEA), and optimization algorithm (OPT) using the two measures called sample compression ratio (SCR) and percent root mean squared difference (PRD) with proper mean offset that [1] does not adopt. The results show SSD outperforms the mentioned algorithms with the same computational complexity O(n). Moreover, the comparison with the best but time-consuming coder OPT (O (n3)) shows how much the algorithm can be improved.

Sign in / Sign up

Export Citation Format

Share Document