Real-Time Diagnostic Integrity Meets Efficiency: A Novel Platform-Agnostic Architecture for Physiological Signal Compression

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Vora, Neel R, Hajighasemi, Amir, Reynolds, Cody T., Radmehr, Amirmohammad, Mohamed, Mohamed, Saurav, Jillur Rahman, Aziz, Abdul, Veerla, Jai Prakash, Nasr, Mohammad S, Lotspeich, Hayden, Guttikonda, Partha Sai, Pham, Thuong, Darji, Aarti, Malidarreh, Parisa Boodaghi, Shang, Helen H, Harvey, Jay, Ding, Kan, Nguyen, Phuc, Luber, Jacob M
Formato: Preprint
Publicado: 2023
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909062381174784
author Vora, Neel R
Hajighasemi, Amir
Reynolds, Cody T.
Radmehr, Amirmohammad
Mohamed, Mohamed
Saurav, Jillur Rahman
Aziz, Abdul
Veerla, Jai Prakash
Nasr, Mohammad S
Lotspeich, Hayden
Guttikonda, Partha Sai
Pham, Thuong
Darji, Aarti
Malidarreh, Parisa Boodaghi
Shang, Helen H
Harvey, Jay
Ding, Kan
Nguyen, Phuc
Luber, Jacob M
author_facet Vora, Neel R
Hajighasemi, Amir
Reynolds, Cody T.
Radmehr, Amirmohammad
Mohamed, Mohamed
Saurav, Jillur Rahman
Aziz, Abdul
Veerla, Jai Prakash
Nasr, Mohammad S
Lotspeich, Hayden
Guttikonda, Partha Sai
Pham, Thuong
Darji, Aarti
Malidarreh, Parisa Boodaghi
Shang, Helen H
Harvey, Jay
Ding, Kan
Nguyen, Phuc
Luber, Jacob M
contents Head-based signals such as EEG, EMG, EOG, and ECG collected by wearable systems will play a pivotal role in clinical diagnosis, monitoring, and treatment of important brain disorder diseases. However, the real-time transmission of the significant corpus physiological signals over extended periods consumes substantial power and time, limiting the viability of battery-dependent physiological monitoring wearables. This paper presents a novel deep-learning framework employing a variational autoencoder (VAE) for physiological signal compression to reduce wearables' computational complexity and energy consumption. Our approach achieves an impressive compression ratio of 1:293 specifically for spectrogram data, surpassing state-of-the-art compression techniques such as JPEG2000, H.264, Direct Cosine Transform (DCT), and Huffman Encoding, which do not excel in handling physiological signals. We validate the efficacy of the compressed algorithms using collected physiological signals from real patients in the Hospital and deploy the solution on commonly used embedded AI chips (i.e., ARM Cortex V8 and Jetson Nano). The proposed framework achieves a 91% seizure detection accuracy using XGBoost, confirming the approach's reliability, practicality, and scalability.
format Preprint
id arxiv_https___arxiv_org_abs_2312_12587
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Real-Time Diagnostic Integrity Meets Efficiency: A Novel Platform-Agnostic Architecture for Physiological Signal Compression
Vora, Neel R
Hajighasemi, Amir
Reynolds, Cody T.
Radmehr, Amirmohammad
Mohamed, Mohamed
Saurav, Jillur Rahman
Aziz, Abdul
Veerla, Jai Prakash
Nasr, Mohammad S
Lotspeich, Hayden
Guttikonda, Partha Sai
Pham, Thuong
Darji, Aarti
Malidarreh, Parisa Boodaghi
Shang, Helen H
Harvey, Jay
Ding, Kan
Nguyen, Phuc
Luber, Jacob M
Signal Processing
Distributed, Parallel, and Cluster Computing
Tissues and Organs
Head-based signals such as EEG, EMG, EOG, and ECG collected by wearable systems will play a pivotal role in clinical diagnosis, monitoring, and treatment of important brain disorder diseases. However, the real-time transmission of the significant corpus physiological signals over extended periods consumes substantial power and time, limiting the viability of battery-dependent physiological monitoring wearables. This paper presents a novel deep-learning framework employing a variational autoencoder (VAE) for physiological signal compression to reduce wearables' computational complexity and energy consumption. Our approach achieves an impressive compression ratio of 1:293 specifically for spectrogram data, surpassing state-of-the-art compression techniques such as JPEG2000, H.264, Direct Cosine Transform (DCT), and Huffman Encoding, which do not excel in handling physiological signals. We validate the efficacy of the compressed algorithms using collected physiological signals from real patients in the Hospital and deploy the solution on commonly used embedded AI chips (i.e., ARM Cortex V8 and Jetson Nano). The proposed framework achieves a 91% seizure detection accuracy using XGBoost, confirming the approach's reliability, practicality, and scalability.
title Real-Time Diagnostic Integrity Meets Efficiency: A Novel Platform-Agnostic Architecture for Physiological Signal Compression
topic Signal Processing
Distributed, Parallel, and Cluster Computing
Tissues and Organs
url https://arxiv.org/abs/2312.12587