TY - GEN
T1 - SCEH
T2 - 2019 IEEE Global Communications Conference, GLOBECOM 2019
AU - Xu, Chuanhua
AU - Dong, Mianxiong
AU - Ota, Kaoru
AU - Li, Jianhua
AU - Yang, Wu
AU - Wu, Jun
N1 - Funding Information:
VII. ACKNOWLEDGEMENT This work is supported in part by the National Natural Science Foundation of China under Grant 61431008, 61831007 and JSPS KAKENHI Grant Numbers JP16K00117, JP19K20250 and KDDI Foundation.
Publisher Copyright:
© 2019 IEEE.
PY - 2019/12
Y1 - 2019/12
N2 - Due to the shortage and unbalance of medical resources, it is difficult for patients in the countryside to get high-quality and timely medical services from the central medical facility. Existing researches of fog e-health has the potential of providing real-time medical services for the countryside with body sensor networks (BSN), but there are two limitations. On one hand, because of the medical services requiring not only low-latency but also high-quality, constructing an AI e-health service on resource-constrained fog with edge AI is necessary but unsolved. On the other hand, because of the regional differences in disease risk, there is a lack of an effective mechanism to provide a customized fog AI e-health service for patients in different regions. To address these issues, a smart customized e-health (SCEH) framework is proposed in this paper to provide edge-intelligent and customized medical services for the countryside. Firstly, semantics-based lightweight and meticulous load management mechanism is designed to reduce data load and involve medical semantic. Secondly, model-ensemble based fog AI collaborative analysis mechanism is proposed for load balance and knowledge integration. Thirdly, an attention-weight based customized fog AI e-health generation mechanism is devised for regional medical model reconstruction. The simulation results demonstrate the effectiveness of SCEH which ensures both the accuracy and low latency of fog e-health with limited resource.
AB - Due to the shortage and unbalance of medical resources, it is difficult for patients in the countryside to get high-quality and timely medical services from the central medical facility. Existing researches of fog e-health has the potential of providing real-time medical services for the countryside with body sensor networks (BSN), but there are two limitations. On one hand, because of the medical services requiring not only low-latency but also high-quality, constructing an AI e-health service on resource-constrained fog with edge AI is necessary but unsolved. On the other hand, because of the regional differences in disease risk, there is a lack of an effective mechanism to provide a customized fog AI e-health service for patients in different regions. To address these issues, a smart customized e-health (SCEH) framework is proposed in this paper to provide edge-intelligent and customized medical services for the countryside. Firstly, semantics-based lightweight and meticulous load management mechanism is designed to reduce data load and involve medical semantic. Secondly, model-ensemble based fog AI collaborative analysis mechanism is proposed for load balance and knowledge integration. Thirdly, an attention-weight based customized fog AI e-health generation mechanism is devised for regional medical model reconstruction. The simulation results demonstrate the effectiveness of SCEH which ensures both the accuracy and low latency of fog e-health with limited resource.
KW - Body sensor networks
KW - Customized
KW - E-health
KW - Edge artificial intelligence
KW - Fog computing
UR - http://www.scopus.com/inward/record.url?scp=85081980619&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85081980619&partnerID=8YFLogxK
U2 - 10.1109/GLOBECOM38437.2019.9014057
DO - 10.1109/GLOBECOM38437.2019.9014057
M3 - Conference contribution
AN - SCOPUS:85081980619
T3 - 2019 IEEE Global Communications Conference, GLOBECOM 2019 - Proceedings
BT - 2019 IEEE Global Communications Conference, GLOBECOM 2019 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 9 December 2019 through 13 December 2019
ER -