scholarly journals k-Labelsets Method for Multi-Label ECG Signal Classification Based on SE-ResNet

2021 ◽  
Vol 11 (16) ◽  
pp. 7758
Author(s):  
Jihye Yoo ◽  
Yeongbong Jin ◽  
Bonggyun Ko ◽  
Min-Soo Kim
Keyword(s):  
Cardiovascular Diseases ◽  
Performance Improvement ◽  
Signal Classification ◽  
Ecg Signal ◽  
Classification Problems ◽  
Improve Performance ◽  
Exact Match ◽  
Residual Learning ◽  
Overall Performance ◽  
Match Accuracy

Cardiovascular diseases are the leading cause of death globally. The ECG is the most commonly used tool for diagnosing cardiovascular diseases, and, recently, there are a number of attempts to use deep learning to analyze ECG. In this study, we propose a method for performing multi-label classification on standard ECG (12-lead with duration of 10 s) data. We used the ResNet model that can perform residual learning as a base model for classification in this work, and we tried to improve performance through SE-ResNet, which added squeeze and excitation blocks on the plain ResNet. As a result of the experiment, it was possible to induce overall performance improvement through squeeze and excitation blocks. In addition, the random k-labelsets (RAKEL) algorithm was applied to improve the performance in multi-label classification problems. As a result, the model that applied soft voting through the RAKEL algorithm to SE-ResNet-34 represented the best performance, and the average performances according to the number of label divisions k were achieved 0.99%, 88.49%, 92.43%, 90.54%, and 93.40% in exact match, accuracy, F1-score, precision, and recall, respectively.

scholarly journals An Optimized Solution: Deep Residual Learning for ECG Signal Classification

Helix ◽  
2020 ◽  
Vol 10 (5) ◽  
pp. 81-86
Author(s):  
Rama Santosh Naidu P ◽  
Lavanya Devi G
Keyword(s):  
Signal Classification ◽  
Ecg Signal ◽  
Residual Learning

Reduction in High-Frequency Hearing Aid Gain Can Improve Performance in Patients With Contralateral Cochlear Implant: A Pilot Study

2015 ◽  
Vol 24 (4) ◽  
pp. 462-468 ◽  
Author(s):  
Jessica J. Messersmith ◽  
Lindsey E. Jorgensen ◽  
Jessica A. Hagg
Keyword(s):  
Speech Perception ◽  
Cochlear Implant ◽  
Chart Review ◽  
Hearing Aid ◽  
Retrospective Chart Review ◽  
Improve Performance ◽  
Bimodal Condition ◽  
Overall Performance ◽  
Age Range ◽  
Clinic Population

Purpose The purpose of this study was to determine whether an alternate fitting strategy, specifically adjustment to gains in a hearing aid (HA), would improve performance in patients who experienced poorer performance in the bimodal condition when the HA was fit to traditional targets. Method This study was a retrospective chart review from a local clinic population seen during a 6-month period. Participants included 6 users of bimodal stimulation. Two performed poorer in the cochlear implant (CI) + HA condition than in the CI-only condition. One individual performed higher in the bimodal condition, but the overall performance was low. Three age range–matched users whose performance increased when the HA was used in conjunction with a CI were also included. The HA gain was reduced beyond 2000 Hz. Speech perception scores were obtained pre- and postmodification to the HA fitting. Results All listeners whose HA was programmed using the modified approach demonstrated improved speech perception scores with the modified HA fit in the bimodal condition when compared with the traditional HA fit in the bimodal condition. Conclusion Modifications to gains above 2000 Hz in the HA may improve performance for bimodal listeners who perform more poorly in the bimodal condition when the HA is fit to traditional targets.

ECG Signal De-Noising with Asynchronous Averaging and Filtering Algorithm

2012 ◽  
pp. 199-205
Author(s):  
Alka Gautam ◽  
Hoon-Jae Lee ◽  
Wan-Young Chung
Keyword(s):  
Signal To Noise Ratio ◽  
Random Noise ◽  
Noise Cancellation ◽  
Peak Detection ◽  
Lms Algorithm ◽  
Ecg Signal ◽  
Maximum Point ◽  
Signal To Noise ◽  
Filtering Algorithm ◽  
Overall Performance

In this study, a new algorithm is proposed—Asynchronous Averaging and Filtering (AAF) for ECG signal de-noising. R-peaks are detected with another proposed algorithm—Minimum Slot and Maximum Point selecting method (MSMP). AAF algorithm reduces random noise (major component of EMG noise) from ECG signal and provides comparatively good results for baseline wander noise cancellation. Signal to noise ratio (SNR) improves in filtered ECG signal, while signal shape remains undistorted. The authors conclude that R-peak detection with MSMP method gives comparable results from existing algorithm like Pan-Tomkins algorithm. AAF algorithm is advantageous over adaptation algorithms like Wiener and LMS algorithm. Overall performance of proposed algorithms is comparatively good.

A Decade's Worth

2020 ◽  
pp. 179-200
Author(s):  
Ria Roy
Keyword(s):  
Construction Industry ◽  
Performance Improvement ◽  
Cash Flow ◽  
Employee Turnover ◽  
Turnover Rate ◽  
Improve Performance ◽  
Deep Dive ◽  
Construction Company ◽  
Financing Costs

After witnessing a year-on-year growth of 50% since its inception in 1993, Ziggurat Developers was well on its way to being the next niche, technically sophisticated, and edgy construction company in Mumbai, India. This case takes a deep dive into how winning a prestigious construction contract in the country led to Ziggurat's loss of revenue, cash flow deficits, year-on-year losses, high financing costs, loss of banking, idling of resources, loss of credibility, and high employee turnover rate. Instead of these significant contracts providing a strong foothold in the construction industry, it destroyed Ziggurat and the recovery took a decade. Performance improvement is often the study of how to improve performance when discrepancies are confined to a silo or a subset of functions within an organization. But how do you get back to exemplary performance when you are boxed in and there is no way out?

Sign in / Sign up

Export Citation Format

Share Document