TY - GEN
T1 - Optimized Large AI Model for Real-Time ACEN Detection in Intelligent Mobile Edge Networks
AU - Gaurav, Akshat
AU - Gupta, Brij B.
AU - Zhou, Liang
AU - Arya, Varsha
AU - Hsu, Ching Hsien
AU - Chui, Kwok Tai
N1 - Publisher Copyright:
© 2025 IEEE.
PY - 2025
Y1 - 2025
N2 - The increasing prevalence of dermatological conditions, such as acne, necessitates efficient and real-time detection systems for intelligent mobile edge networks. This paper proposes an optimized large AI model for real-time ACEN (Acne Classification and Enumeration) detection using the YOLO11 architecture. The model's hyper-parameters are optimized using a Genetic Algorithm (GA) to enhance accuracy and computational efficiency. User-uploaded images are processed at edge nodes, such as local hospitals, enabling low-latency detection. Results are synchronized to a cloud layer for collaborative updates and global model improvements. The proposed model achieves a mean Average Precision ([email protected]) of 0.613 after training for 200 epochs. Comprehensive evaluation using precision-recall curves and loss analysis demonstrates the model's robustness, scalability, and suitability for deployment in intelligent edge-based healthcare systems.
AB - The increasing prevalence of dermatological conditions, such as acne, necessitates efficient and real-time detection systems for intelligent mobile edge networks. This paper proposes an optimized large AI model for real-time ACEN (Acne Classification and Enumeration) detection using the YOLO11 architecture. The model's hyper-parameters are optimized using a Genetic Algorithm (GA) to enhance accuracy and computational efficiency. User-uploaded images are processed at edge nodes, such as local hospitals, enabling low-latency detection. Results are synchronized to a cloud layer for collaborative updates and global model improvements. The proposed model achieves a mean Average Precision ([email protected]) of 0.613 after training for 200 epochs. Comprehensive evaluation using precision-recall curves and loss analysis demonstrates the model's robustness, scalability, and suitability for deployment in intelligent edge-based healthcare systems.
KW - ACEN Detection
KW - Edge Computing
KW - Genetic Algorithm
KW - Real-Time Healthcare Systems
KW - YOLO11 Optimization
UR - https://www.scopus.com/pages/publications/105017962399
U2 - 10.1109/INFOCOMWKSHPS65812.2025.11152864
DO - 10.1109/INFOCOMWKSHPS65812.2025.11152864
M3 - Conference contribution
AN - SCOPUS:105017962399
T3 - IEEE Conference on Computer Communications Workshops, INFOCOM WKSHPS 2025
BT - IEEE Conference on Computer Communications Workshops, INFOCOM WKSHPS 2025
T2 - 2025 IEEE Conference on Computer Communications Workshops, INFOCOM WKSHPS 2025
Y2 - 19 May 2025
ER -