FedHome: Cloud-Edge Based Personalized Federated Learning for In-Home Health Monitoring

Wu, Qiong; Chen, Xu; Zhou, Zhi; Zhang, Junshan

doi:10.1109/tmc.2020.3045266

Cited by 238 publications

(119 citation statements)

References 39 publications

Supporting

Mentioning

119

Contrasting

Order By: Relevance

Section: Dnn Model Partitionmentioning

confidence: 99%

“…Recently, more and more work has adopted DNN model partition in actual intelligent applications [21][22][23]. FedHmome [22] is a joint learning framework for home health detection based on edge-cloud, which learns a shared global model in the cloud from multiple families at the edge of the network. The work of Wang et al [23] proposed a dynamic resource allocation scheme to select the best division point of DNN inference tasks in the intelligent application of vehicles.…”

Section: Dnn Model Partitionmentioning

confidence: 99%

See 1 more Smart Citation

BBNet: A Novel Convolutional Neural Network Structure in Edge-Cloud Collaborative Inference

Zhou

Zhang

Wang

et al. 2021

Sensors

View full text Add to dashboard Cite

Edge-cloud collaborative inference can significantly reduce the delay of a deep neural network (DNN) by dividing the network between mobile edge and cloud. However, the in-layer data size of DNN is usually larger than the original data, so the communication time to send intermediate data to the cloud will also increase end-to-end latency. To cope with these challenges, this paper proposes a novel convolutional neural network structure—BBNet—that accelerates collaborative inference from two levels: (1) through channel-pruning: reducing the number of calculations and parameters of the original network; (2) through compressing the feature map at the split point to further reduce the size of the data transmitted. In addition, This paper implemented the BBNet structure based on NVIDIA Nano and the server. Compared with the original network, BBNet’s FLOPs and parameter achieve up to 5.67× and 11.57× on the compression rate, respectively. In the best case, the feature compression layer can reach a bit-compression rate of 512×. Compared with the better bandwidth conditions, BBNet has a more obvious inference delay when the network conditions are poor. For example, when the upload bandwidth is only 20 kb/s, the end-to-end latency of BBNet is increased by 38.89× compared with the cloud-only approach.

show abstract

Section: Dnn Model Partitionmentioning

confidence: 99%

Section: Dnn Model Partitionmentioning

confidence: 99%

BBNet: A Novel Convolutional Neural Network Structure in Edge-Cloud Collaborative Inference

Zhou

Zhang

Wang

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

“…We witness more advances in the compute power of the wearable devices and also the sensors, which will contribution to expedited FL adoption in eHealth. In the research works along this goal, we find authors in [ 55 ], proposing FedHome, a novel cloud-edge based federated learning framework for in-home health monitoring. It learns a shared global model in the cloud, which serves as our centralized aggregator, from multiple homes at the network edges, and it achieves data privacy protection by keeping user data locally.…”

Section: Selected Iomt-based Health Applicationsmentioning

confidence: 99%

“…IoMT and wearable devices applications and their design requirements [52] survey of commercially available wearables [53] a survey about IoMT [54] ECG monitoring systems [28] communication requirements for IoMT to be provided by 6G [29] communication requirements for IoMT provided by 5G [55] FedHome: a cloud-edge based federated learning framework for in-home health monitoring.…”

Section: Ref Focusmentioning

confidence: 99%

Rebirth of Distributed AI—A Review of eHealth Research

Khan

Alkaabi

2021

Sensors

View full text Add to dashboard Cite

The envisioned smart city domains are expected to rely heavily on artificial intelligence and machine learning (ML) approaches for their operations, where the basic ingredient is data. Privacy of the data and training time have been major roadblocks to achieving the specific goals of each application domain. Policy makers, the research community, and the industrial sector have been putting their efforts into addressing these issues. Federated learning, with its distributed and local training approach, stands out as a potential solution to these challenges. In this article, we discuss the potential interplay of different technologies and AI for achieving the required features of future smart city services. Having discussed a few use-cases for future eHealth, we list design goals and technical requirements of the enabling technologies. The paper confines its focus on federated learning. After providing the tutorial on federated learning, we analyze the Federated Learning research literature. We also highlight the challenges. A solution sketch and high-level research directions may be instrumental in addressing the challenges.

show abstract

“…For these reasons, FL mitigates many security concerns because it retains sensitive and private data while enabling multiple medical institutions to work together. FL holds an excellent promise in healthcare applications to improve medical services for both institutions and patients-for instance, predict autism spectrum disorder [18], mortality and intensive care unit (ICU) stay-time prediction [19], wearable healthcare devices [20,21], and brain tumor segmentation [22]. However, FL algorithms face several challenges, mainly due to the properties of medical data, such as:…”

Section: Introductionmentioning

confidence: 99%

A Systematic Review of Federated Learning in the Healthcare Area: From the Perspective of Data Properties and Applications

et al. 2021

View full text Add to dashboard Cite

Recent advances in deep learning have shown many successful stories in smart healthcare applications with data-driven insight into improving clinical institutions’ quality of care. Excellent deep learning models are heavily data-driven. The more data trained, the more robust and more generalizable the performance of the deep learning model. However, pooling the medical data into centralized storage to train a robust deep learning model faces privacy, ownership, and strict regulation challenges. Federated learning resolves the previous challenges with a shared global deep learning model using a central aggregator server. At the same time, patient data remain with the local party, maintaining data anonymity and security. In this study, first, we provide a comprehensive, up-to-date review of research employing federated learning in healthcare applications. Second, we evaluate a set of recent challenges from a data-centric perspective in federated learning, such as data partitioning characteristics, data distributions, data protection mechanisms, and benchmark datasets. Finally, we point out several potential challenges and future research directions in healthcare applications.

show abstract

FedHome: Cloud-Edge Based Personalized Federated Learning for In-Home Health Monitoring

Cited by 238 publications

References 39 publications

BBNet: A Novel Convolutional Neural Network Structure in Edge-Cloud Collaborative Inference

BBNet: A Novel Convolutional Neural Network Structure in Edge-Cloud Collaborative Inference

Rebirth of Distributed AI—A Review of eHealth Research

A Systematic Review of Federated Learning in the Healthcare Area: From the Perspective of Data Properties and Applications

Contact Info

Product

Resources

About