AI-based online VoI-aware healthcare and medical monitoring task computing
In recent years, healthcare systems have significantly advanced with the introduction of fifth-generation cellular communications and beyond (5GB). This advancement enables the utilization of telecommunications technologies in healthcare with a reliability of up to 99.999 percent. In this paper, we...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-09-01
|
| Series: | Results in Engineering |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2590123025021735 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849702550627942400 |
|---|---|
| author | Akbar Asgharzadeh-Bonab Jalil Mazloum Ali Nouruzi |
| author_facet | Akbar Asgharzadeh-Bonab Jalil Mazloum Ali Nouruzi |
| author_sort | Akbar Asgharzadeh-Bonab |
| collection | DOAJ |
| description | In recent years, healthcare systems have significantly advanced with the introduction of fifth-generation cellular communications and beyond (5GB). This advancement enables the utilization of telecommunications technologies in healthcare with a reliability of up to 99.999 percent. In this paper, we propose a novel task computing framework to meet the reliability requirements of healthcare systems. We consider IoT devices in healthcare with tasks that have uncertain requirements and healthcare servers with uncertain computing resources. To address these uncertainties, we derive closed-form formulas. Furthermore, we adopt a partial offloading approach to handle IoT device tasks. Our goal is to maximize the total data rate of the healthcare system. We formulate an optimization problem that includes constraints to ensure the minimum value of information (VoI), minimum data rate, and computational capacity. To solve this optimization problem, we employ a deep reinforcement learning (DRL) based solution, outperforming other baselines. We propose a soft actor-critic (SAC)-based algorithm, named SAC-based VoI-aware healthcare networks (SACVAHC), to handle uncertainties in the healthcare network. Our results show that the proposed method can improve the total sum rate by up to 20% compared to other baselines. |
| format | Article |
| id | doaj-art-1c40abe05ed545dabec3c3ff7d1ac3ac |
| institution | DOAJ |
| issn | 2590-1230 |
| language | English |
| publishDate | 2025-09-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Results in Engineering |
| spelling | doaj-art-1c40abe05ed545dabec3c3ff7d1ac3ac2025-08-20T03:17:36ZengElsevierResults in Engineering2590-12302025-09-012710610110.1016/j.rineng.2025.106101AI-based online VoI-aware healthcare and medical monitoring task computingAkbar Asgharzadeh-Bonab0Jalil Mazloum1Ali Nouruzi2Department of Electrical Engineering, Urmia University, Urmia, Postal Code: 5756151818, Iran; Corresponding author.Faculty of Electrical Engineering, Shahid Beheshti University, Tehran, Postal Code: 1983969411, IranDepartment of Electrical and Computer Engineering, Tarbiat Modares University, Tehran, Postal Code: 14115, IranIn recent years, healthcare systems have significantly advanced with the introduction of fifth-generation cellular communications and beyond (5GB). This advancement enables the utilization of telecommunications technologies in healthcare with a reliability of up to 99.999 percent. In this paper, we propose a novel task computing framework to meet the reliability requirements of healthcare systems. We consider IoT devices in healthcare with tasks that have uncertain requirements and healthcare servers with uncertain computing resources. To address these uncertainties, we derive closed-form formulas. Furthermore, we adopt a partial offloading approach to handle IoT device tasks. Our goal is to maximize the total data rate of the healthcare system. We formulate an optimization problem that includes constraints to ensure the minimum value of information (VoI), minimum data rate, and computational capacity. To solve this optimization problem, we employ a deep reinforcement learning (DRL) based solution, outperforming other baselines. We propose a soft actor-critic (SAC)-based algorithm, named SAC-based VoI-aware healthcare networks (SACVAHC), to handle uncertainties in the healthcare network. Our results show that the proposed method can improve the total sum rate by up to 20% compared to other baselines.http://www.sciencedirect.com/science/article/pii/S2590123025021735Health care systemMedical monitoringOnline task offloadingResource allocationDemand uncertaintyResource uncertainty |
| spellingShingle | Akbar Asgharzadeh-Bonab Jalil Mazloum Ali Nouruzi AI-based online VoI-aware healthcare and medical monitoring task computing Results in Engineering Health care system Medical monitoring Online task offloading Resource allocation Demand uncertainty Resource uncertainty |
| title | AI-based online VoI-aware healthcare and medical monitoring task computing |
| title_full | AI-based online VoI-aware healthcare and medical monitoring task computing |
| title_fullStr | AI-based online VoI-aware healthcare and medical monitoring task computing |
| title_full_unstemmed | AI-based online VoI-aware healthcare and medical monitoring task computing |
| title_short | AI-based online VoI-aware healthcare and medical monitoring task computing |
| title_sort | ai based online voi aware healthcare and medical monitoring task computing |
| topic | Health care system Medical monitoring Online task offloading Resource allocation Demand uncertainty Resource uncertainty |
| url | http://www.sciencedirect.com/science/article/pii/S2590123025021735 |
| work_keys_str_mv | AT akbarasgharzadehbonab aibasedonlinevoiawarehealthcareandmedicalmonitoringtaskcomputing AT jalilmazloum aibasedonlinevoiawarehealthcareandmedicalmonitoringtaskcomputing AT alinouruzi aibasedonlinevoiawarehealthcareandmedicalmonitoringtaskcomputing |