FPGA SoC Implementation of Adaptive Deep Neural Network-Based Multimodal Edge Intelligence for Internet of Medical Things
In emergency healthcare services, accurate and timely decision-making is critical for the patient’s life and death. The emergence of edge intelligence enables these service goals achievable for Internet of Medical Things (IoMT) compared with cloud-centric approaches. To assist medical per...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/11096547/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849240275063406592 |
|---|---|
| author | Nikhil B. Gaikwad Smith K. Khare Dinesh Mendhe Hasan Mir Sokol Kosta U. Rajendra Acharya |
| author_facet | Nikhil B. Gaikwad Smith K. Khare Dinesh Mendhe Hasan Mir Sokol Kosta U. Rajendra Acharya |
| author_sort | Nikhil B. Gaikwad |
| collection | DOAJ |
| description | In emergency healthcare services, accurate and timely decision-making is critical for the patient’s life and death. The emergence of edge intelligence enables these service goals achievable for Internet of Medical Things (IoMT) compared with cloud-centric approaches. To assist medical personnel in intensive care units (ICU), we present the design of a network edge gateway that performs resource-efficient, real-time data analytics. We develop a cloud-configurable deep neural network (DNN) intellectual property (IP) core with an adaptable hardware architecture that executes four different types of analysis on an edge gateway. Our developed IP core adaptively switches from one architecture to another only in one clock cycle, based on the type of input features. The proposed IP core analyzes raw multimodal signals such as ECG, PPG, accelerometer, and other to discover anomalies in critically ill patients and their surroundings. We have validated the robustness of our developed model by comparing it with benchmark machine learning models and their previous implementations. The results show that our adaptive DNN model has obtained a software accuracy of 99.2% for ECG, 91.4% for PPG, 95% for activity classification, and 98.7% for smoke detection with a five-fold cross-validation strategy. Three versions of adaptive DNN IP cores (8-bit, 16-bit, 24-bit) are implemented on SoC/FPGA and compared together to study the effect of bit precision on accuracy, resource utilization, and power consumption. The developed adaptive DNN IP cores with 16-bits require 680 nanoseconds with a power consumption of 309 milliwatts for a single inference with a speed of 1.47 mega samples per second. Our analysis shows that the decentralization of intelligence in the IP core reduces data size from 96.25% to 98.75%. This flexible IP core has achieved significant power and resource utilization performance compared to independent implementation without compromising latency and throughput. |
| format | Article |
| id | doaj-art-13e936ad44cf464d96be294deb33a6a2 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-13e936ad44cf464d96be294deb33a6a22025-08-20T04:00:40ZengIEEEIEEE Access2169-35362025-01-011313404113405610.1109/ACCESS.2025.359272911096547FPGA SoC Implementation of Adaptive Deep Neural Network-Based Multimodal Edge Intelligence for Internet of Medical ThingsNikhil B. Gaikwad0https://orcid.org/0000-0002-6119-2099Smith K. Khare1https://orcid.org/0000-0001-8365-1092Dinesh Mendhe2https://orcid.org/0000-0003-1158-3259Hasan Mir3https://orcid.org/0000-0002-6863-3002Sokol Kosta4https://orcid.org/0000-0002-9441-4508U. Rajendra Acharya5https://orcid.org/0000-0003-2689-8552Department of Electronic Systems, Aalborg Universitet, Copenhagen, DenmarkApplied Artificial Intelligence and Data Science Unit, The Maersk Mc-Kinney Møller Institute, University of Southern Denmark, Odense, DenmarkOffice of Research Computing, Rutgers University, New Brunswick, NJ, USADepartment of Electrical Engineering, American University of Sharjah, Sharjah, United Arab EmiratesDepartment of Electronic Systems, Aalborg Universitet, Copenhagen, DenmarkSchool of Mathematics, Physics, and Computing, University of Southern Queensland, Springfield, AustraliaIn emergency healthcare services, accurate and timely decision-making is critical for the patient’s life and death. The emergence of edge intelligence enables these service goals achievable for Internet of Medical Things (IoMT) compared with cloud-centric approaches. To assist medical personnel in intensive care units (ICU), we present the design of a network edge gateway that performs resource-efficient, real-time data analytics. We develop a cloud-configurable deep neural network (DNN) intellectual property (IP) core with an adaptable hardware architecture that executes four different types of analysis on an edge gateway. Our developed IP core adaptively switches from one architecture to another only in one clock cycle, based on the type of input features. The proposed IP core analyzes raw multimodal signals such as ECG, PPG, accelerometer, and other to discover anomalies in critically ill patients and their surroundings. We have validated the robustness of our developed model by comparing it with benchmark machine learning models and their previous implementations. The results show that our adaptive DNN model has obtained a software accuracy of 99.2% for ECG, 91.4% for PPG, 95% for activity classification, and 98.7% for smoke detection with a five-fold cross-validation strategy. Three versions of adaptive DNN IP cores (8-bit, 16-bit, 24-bit) are implemented on SoC/FPGA and compared together to study the effect of bit precision on accuracy, resource utilization, and power consumption. The developed adaptive DNN IP cores with 16-bits require 680 nanoseconds with a power consumption of 309 milliwatts for a single inference with a speed of 1.47 mega samples per second. Our analysis shows that the decentralization of intelligence in the IP core reduces data size from 96.25% to 98.75%. This flexible IP core has achieved significant power and resource utilization performance compared to independent implementation without compromising latency and throughput.https://ieeexplore.ieee.org/document/11096547/FPGA SoCdeep neural networkedge intelligenceelectrocardiogramphotoplethysmographyblood pressure |
| spellingShingle | Nikhil B. Gaikwad Smith K. Khare Dinesh Mendhe Hasan Mir Sokol Kosta U. Rajendra Acharya FPGA SoC Implementation of Adaptive Deep Neural Network-Based Multimodal Edge Intelligence for Internet of Medical Things IEEE Access FPGA SoC deep neural network edge intelligence electrocardiogram photoplethysmography blood pressure |
| title | FPGA SoC Implementation of Adaptive Deep Neural Network-Based Multimodal Edge Intelligence for Internet of Medical Things |
| title_full | FPGA SoC Implementation of Adaptive Deep Neural Network-Based Multimodal Edge Intelligence for Internet of Medical Things |
| title_fullStr | FPGA SoC Implementation of Adaptive Deep Neural Network-Based Multimodal Edge Intelligence for Internet of Medical Things |
| title_full_unstemmed | FPGA SoC Implementation of Adaptive Deep Neural Network-Based Multimodal Edge Intelligence for Internet of Medical Things |
| title_short | FPGA SoC Implementation of Adaptive Deep Neural Network-Based Multimodal Edge Intelligence for Internet of Medical Things |
| title_sort | fpga soc implementation of adaptive deep neural network based multimodal edge intelligence for internet of medical things |
| topic | FPGA SoC deep neural network edge intelligence electrocardiogram photoplethysmography blood pressure |
| url | https://ieeexplore.ieee.org/document/11096547/ |
| work_keys_str_mv | AT nikhilbgaikwad fpgasocimplementationofadaptivedeepneuralnetworkbasedmultimodaledgeintelligenceforinternetofmedicalthings AT smithkkhare fpgasocimplementationofadaptivedeepneuralnetworkbasedmultimodaledgeintelligenceforinternetofmedicalthings AT dineshmendhe fpgasocimplementationofadaptivedeepneuralnetworkbasedmultimodaledgeintelligenceforinternetofmedicalthings AT hasanmir fpgasocimplementationofadaptivedeepneuralnetworkbasedmultimodaledgeintelligenceforinternetofmedicalthings AT sokolkosta fpgasocimplementationofadaptivedeepneuralnetworkbasedmultimodaledgeintelligenceforinternetofmedicalthings AT urajendraacharya fpgasocimplementationofadaptivedeepneuralnetworkbasedmultimodaledgeintelligenceforinternetofmedicalthings |