Search

Your search keyword '"Post, Allison"' showing total 145 results
Start Over Author "Post, Allison"
145 results on '"Post, Allison"'

3. e-G2C: A 0.14-to-8.31 $\mu$J/Inference NN-based Processor with Continuous On-chip Adaptation for Anomaly Detection and ECG Conversion from EGM

Author

Zhao, Yang, Zhang, Yongan, Fu, Yonggan, Ouyang, Xu, Wan, Cheng, Wu, Shang, Banta, Anton, John, Mathews M., Post, Allison, Razavi, Mehdi, Cavallaro, Joseph, Aazhang, Behnaam, and Lin, Yingyan

Subjects
Electrical Engineering and Systems Science - Signal Processing, Computer Science - Hardware Architecture
Abstract

This work presents the first silicon-validated dedicated EGM-to-ECG (G2C) processor, dubbed e-G2C, featuring continuous lightweight anomaly detection, event-driven coarse/precise conversion, and on-chip adaptation. e-G2C utilizes neural network (NN) based G2C conversion and integrates 1) an architecture supporting anomaly detection and coarse/precise conversion via time multiplexing to balance the effectiveness and power, 2) an algorithm-hardware co-designed vector-wise sparsity resulting in a 1.6-1.7$\times$ speedup, 3) hybrid dataflows for enhancing near 100% utilization for normal/depth-wise(DW)/point-wise(PW) convolutions (Convs), and 4) an on-chip detection threshold adaptation engine for continuous effectiveness. The achieved 0.14-8.31 $\mu$J/inference energy efficiency outperforms prior arts under similar complexity, promising real-time detection/conversion and possibly life-critical interventions, Comment: Accepted by 2022 IEEE Symposium on VLSI Technology and Circuits (VLSI Technology and Circuits)

Published
2022
Full Text
View/download PDF

4. RT-RCG: Neural Network and Accelerator Search Towards Effective and Real-time ECG Reconstruction from Intracardiac Electrograms

Author

Zhang, Yongan, Banta, Anton, Fu, Yonggan, John, Mathews M., Post, Allison, Razavi, Mehdi, Cavallaro, Joseph, Aazhang, Behnaam, and Lin, Yingyan

Subjects
Computer Science - Hardware Architecture, Computer Science - Machine Learning
Abstract

There exists a gap in terms of the signals provided by pacemakers (i.e., intracardiac electrogram (EGM)) and the signals doctors use (i.e., 12-lead electrocardiogram (ECG)) to diagnose abnormal rhythms. Therefore, the former, even if remotely transmitted, are not sufficient for doctors to provide a precise diagnosis, let alone make a timely intervention. To close this gap and make a heuristic step towards real-time critical intervention in instant response to irregular and infrequent ventricular rhythms, we propose a new framework dubbed RT-RCG to automatically search for (1) efficient Deep Neural Network (DNN) structures and then (2)corresponding accelerators, to enable Real-Time and high-quality Reconstruction of ECG signals from EGM signals. Specifically, RT-RCG proposes a new DNN search space tailored for ECG reconstruction from EGM signals, and incorporates a differentiable acceleration search (DAS) engine to efficiently navigate over the large and discrete accelerator design space to generate optimized accelerators. Extensive experiments and ablation studies under various settings consistently validate the effectiveness of our RT-RCG. To the best of our knowledge, RT-RCG is the first to leverage neural architecture search (NAS) to simultaneously tackle both reconstruction efficacy and efficiency., Comment: JETC Special issue on Hardware-Aware Learning for Medical Applications (Waiting assignment to batch)

Published
2021

6. Nonlinear Regression with a Convolutional Encoder-Decoder for Remote Monitoring of Surface Electrocardiograms

Author

Banta, Anton, Cosentino, Romain, John, Mathews M, Post, Allison, Buchan, Skyler, Razavi, Mehdi, and Aazhang, Behnaam

Subjects
Electrical Engineering and Systems Science - Signal Processing
Abstract

We propose the Nonlinear Regression Convolutional Encoder-Decoder (NRCED), a novel framework for mapping a multivariate input to a multivariate output. In particular, we implement our algorithm within the scope of 12-lead surface electrocardiogram (ECG) reconstruction from intracardiac electrograms (EGM) and vice versa. The goal of performing this task is to allow for improved point-of-care monitoring of patients with an implanted device to treat cardiac pathologies. We will achieve this goal with 12-lead ECG reconstruction and by providing a new diagnostic tool for classifying atypical heartbeats. The algorithm is evaluated on a dataset retroactively collected from 14 patients. Correlation coefficients calculated between the reconstructed and the actual ECG show that the proposed NRCED method represents an efficient, accurate, and superior way to synthesize a 12-lead ECG. We can also achieve the same reconstruction accuracy with only one EGM lead as input. We also tested the model in a non-patient specific way and saw a reasonable correlation coefficient. The model was also executed in the reverse direction to produce EGM signals from a 12-lead ECG and found that the correlation was comparable to the forward direction. Lastly, we analyzed the features learned in the model and determined that the model learns an overcomplete basis of our 12-lead ECG space. We then use this basis of features to create a new diagnostic tool for identifying atypical and diseased heartbeats. This resulted in a ROC curve with an associated area under the curve value of 0.98, demonstrating excellent discrimination between the two classes.

Published
2020

8. Synchronized Biventricular Heart Pacing in a Closed-chest Porcine Model based on Wirelessly Powered Leadless Pacemakers.

Author

Lyu, Hongming, John, Mathews, Burkland, David, Greet, Brian, Post, Allison, Babakhani, Aydin, and Razavi, Mehdi

Abstract

About 30% of patients with impaired cardiac function have ventricular dyssynchrony and seek cardiac resynchronization therapy (CRT). In this study, we demonstrate synchronized biventricular (BiV) pacing in a leadless fashion by implementing miniaturized and wirelessly powered pacemakers. With their flexible form factors, two pacemakers were implanted epicardially on the right and left ventricles of a porcine model and were inductively powered at 13.56 MHz and 40.68 MHz industrial, scientific, and medical (ISM) bands, respectively. The power consumption of these pacemakers is reduced to µW-level by a novel integrated circuit design, which considerably extends the maximum operating distance. Leadless BiV pacing is demonstrated for the first time in both open-chest and closed-chest porcine settings. The clinical outcomes associated with different interventricular delays are verified through electrophysiologic and hemodynamic responses. The closed-chest pacing only requires the external source power of 0.3 W and 0.8 W at 13.56 MHz and 40.68 MHz, respectively, which leads to specific absorption rates (SARs) 2-3 orders of magnitude lower than the safety regulation limit. This work serves as a basis for future wirelessly powered leadless pacemakers that address various cardiac resynchronization challenges.

Published
2020

20. RT-RCG: Neural Network and Accelerator Search Towards Effective and Real-time ECG Reconstruction from Intracardiac Electrograms

Author

Zhang, Yongan, Banta, Anton, Fu, Yonggan, John, Mathews M., Post, Allison, Razavi, Mehdi, Cavallaro, Joseph, Aazhang, Behnaam, and Lin, Yingyan

Subjects
FOS: Computer and information sciences, Computer Science - Machine Learning, Hardware and Architecture, Hardware Architecture (cs.AR), Electrical and Electronic Engineering, Computer Science - Hardware Architecture, Article, Software, Machine Learning (cs.LG)
Abstract

There exists a gap in terms of the signals provided by pacemakers (i.e., intracardiac electrogram (EGM)) and the signals doctors use (i.e., 12-lead electrocardiogram (ECG)) to diagnose abnormal rhythms. Therefore, the former, even if remotely transmitted, are not sufficient for doctors to provide a precise diagnosis, let alone make a timely intervention. To close this gap and make a heuristic step towards real-time critical intervention in instant response to irregular and infrequent ventricular rhythms, we propose a new framework dubbed RT-RCG to automatically search for (1) efficient Deep Neural Network (DNN) structures and then (2)corresponding accelerators, to enable Real-Time and high-quality Reconstruction of ECG signals from EGM signals. Specifically, RT-RCG proposes a new DNN search space tailored for ECG reconstruction from EGM signals, and incorporates a differentiable acceleration search (DAS) engine to efficiently navigate over the large and discrete accelerator design space to generate optimized accelerators. Extensive experiments and ablation studies under various settings consistently validate the effectiveness of our RT-RCG. To the best of our knowledge, RT-RCG is the first to leverage neural architecture search (NAS) to simultaneously tackle both reconstruction efficacy and efficiency., Comment: JETC Special issue on Hardware-Aware Learning for Medical Applications (Waiting assignment to batch)

Published
2022

22. e-G2C: A 0.14-to-8.31 µJ/Inference NN-based Processor with Continuous On-chip Adaptation for Anomaly Detection and ECG Conversion from EGM

Author

Zhao, Yang, Zhang, Yongan, Fu, Yonggan, Ouyang, Xu, Wan, Cheng, Wu, Shang, Banta, Anton, John, Mathews M., Post, Allison, Razavi, Mehdi, Cavallaro, Joseph, Aazhang, Behnaam, and Lin, Yingyan

Subjects
Signal Processing (eess.SP), FOS: Computer and information sciences, Hardware Architecture (cs.AR), FOS: Electrical engineering, electronic engineering, information engineering, Electrical Engineering and Systems Science - Signal Processing, Computer Science - Hardware Architecture
Abstract

This work presents the first silicon-validated dedicated EGM-to-ECG (G2C) processor, dubbed e-G2C, featuring continuous lightweight anomaly detection, event-driven coarse/precise conversion, and on-chip adaptation. e-G2C utilizes neural network (NN) based G2C conversion and integrates 1) an architecture supporting anomaly detection and coarse/precise conversion via time multiplexing to balance the effectiveness and power, 2) an algorithm-hardware co-designed vector-wise sparsity resulting in a 1.6-1.7$\times$ speedup, 3) hybrid dataflows for enhancing near 100% utilization for normal/depth-wise(DW)/point-wise(PW) convolutions (Convs), and 4) an on-chip detection threshold adaptation engine for continuous effectiveness. The achieved 0.14-8.31 $\mu$J/inference energy efficiency outperforms prior arts under similar complexity, promising real-time detection/conversion and possibly life-critical interventions, Comment: Accepted by 2022 IEEE Symposium on VLSI Technology and Circuits (VLSI Technology and Circuits)

Published
2022

31. Towards prevention of re-entrant arrhythmias: Injectable hydrogel electrodes enable direct capture of previously inaccessible cardiac tissue

Author

Rodriguez-Rivera, Gabriel J., primary, Post, Allison, additional, John, Mathews, additional, Buchan, Skylar, additional, Wancura, Megan, additional, Chwatko, Malgorzata, additional, Waldron, Christina, additional, Nkansah, Abbey, additional, Bernard, Drew, additional, Kalkunte, Nikhith, additional, Zoldan, Janet, additional, Arseneault, Mathieu, additional, Razavi, Mehdi, additional, and Cosgriff-Hernandez, Elizabeth, additional

Published
2021
Full Text
View/download PDF

41. Establishment of a non-invasive method for the measurement of water-borne corticosterone in conservation efforts of imperiled species of newts.

Author

Post, Allison and Racine, Holly

Subjects
*CORTICOSTERONE, *NEWTS, *ANIMAL populations, *METHANOL, *STEROIDS
Abstract

Wildlife endocrinology monitors hormones to assess the impacts of stressors on wildlife populations. Studies include investigating how stress affects the welfare and reproduction of at-risk species. Measuring water-borne stress hormones, or glucocorticoids, has been validated as a non-invasive method for accurately quantifying stress in a variety of species. It has previously been shown that higher levels of corticosterone, the primary glucocorticoid identified in amphibians, can be detected within hours following a stressful event. The goal of this study was to quantify corticosterone levels in water-borne samples from the Orianne Center for Indigo Conservation (OCIC) Striped Newt (Notophthalmusperstriatus) population to assess their ability to cope with stressors and improve captive-breeding efforts to better conserve them. Our methodology of corticosterone quantification from water-borne samples was first tested in a population of Emperor Spotted Newts (Neurergus kaiseri). Water samples were collected for testing from 6 group housed individuals. Corticosterone collection was successfully accomplished using C18 solid phase extraction columns under vacuum pressure with distilled water and HPLC-grade methanol. They were then eluted with methanol under positive pressure and extracts were quantified using an ELISA kit (Arbor Assays). Following this effective methodology, we collected water samples from 7 individually housed Striped Newts at the OCIC. Samples were collected prior to handling, and then every 60 minutes for three hours after handling. Ultimately, the results were inconclusive. However, the methodology was shown to be effective for extracting and analyzing water-borne steroids, and efforts will continue to establish a stress baseline for the Striped Newt. Acknowledgment of NASA West Virginia Space Grant Consortium. [ABSTRACT FROM AUTHOR]

Published
2024

42. RT-RCG: Neural Network and Accelerator Search Towards Effective and Real-time ECG Reconstruction from Intracardiac Electrograms.

Author

YONGAN ZHANG, BANTA, ANTON, YONGGAN FU, JOHN, MATHEWS M., POST, ALLISON, RAZAVI, MEHDI, CAVALLARO, JOSEPH, AAZHANG, BEHNAAM, and YINGYAN LIN

Subjects
ELECTROCARDIOGRAPHY, ELECTRONIC design automation, SIGNAL reconstruction
Abstract

There exists a gap in terms of the signals provided by pacemakers (i.e., intracardiac electrogram (EGM)) and the signals doctors use (i.e., 12-lead electrocardiogram (ECG)) to diagnose abnormal rhythms. Therefore, the former, even if remotely transmitted, are not sufficient for doctors to provide a precise diagnosis, let alone make a timely intervention. To close this gap and make a heuristic step towards real-time critical intervention in instant response to irregular and infrequent ventricular rhythms, we propose a new framework dubbed RT-RCG to automatically search for (1) efficient Deep Neural Network (DNN) structures and then (2) corresponding accelerators, to enable Real-Time and high-quality Reconstruction of ECG signals from EGM signals. Specifically, RT-RCG proposes a new DNN search space tailored for ECG reconstruction from EGM signals and incorporates a differentiable acceleration search (DAS) engine to efficiently navigate over the large and discrete accelerator design space to generate optimized accelerators. Extensive experiments and ablation studies under various settings consistently validate the effectiveness of our RT-RCG. To the best of our knowledge, RT-RCG is the first to leverage neural architecture search (NAS) to simultaneously tackle both reconstruction efficacy and efficiency. [ABSTRACT FROM AUTHOR]

Published
2021
Full Text
View/download PDF

50. The adoption alternative

Author

Post, Allison

Subjects
Environmental issues, Home and garden
Abstract

I applaud the decision to publish 'Making a Green Choice: Childfree Living.' This is a conversation that needs to be had more often, as the Earth's population is spiraling to [...]

Published
2014

Catalog

Books, media, physical & digital resources
See catalog results