Semisupervised Distributed Learning With Non-IID Data for AIoT Service Platform

Chiu, Te-Chuan; Shih, Yuan-Yao; Pang, Ai‐Chun; Wang, Chieh-Sheng; Weng, Wei; Chou, Chun-Ting

doi:10.1109/jiot.2020.2995162

Cited by 68 publications

(28 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, to facilitate the data sharing of nonindependent and identically distributed (non-IID) among edge devices, a HFL scheme is proposed in [55] for the shared learning between edge devices as participants and a cloud server as the aggregator. To deal with the issue of weight divergence caused by traditional FL, a federated swapping model is further developed based on a few shared data during the HFL that can mitigate the adverse impact of non-IID data.…”

Section: A Fl Serving As An Alternative To Iot Data Sharingmentioning

confidence: 99%

“…This kind of on-device processing offered by FL thus can help solve issues related to data ethics, data privacy, and security in smart city services. Meanwhile, the authors in [55] suggest to use FL for building a video data management platform in smart cities. To be specific, videos can be collected as live street videos from connected mobile cameras such as IoT devices on buses, roads and transferred to edge devices.…”

Section: Fl For Smart Citymentioning

confidence: 99%

See 1 more Smart Citation

Federated Learning for Internet of Things: A Comprehensive Survey

Nguyen

Ding

Pathirana

et al. 2021

IEEE Commun. Surv. Tutorials

594

182

View full text Add to dashboard Cite

Section: A Fl Serving As An Alternative To Iot Data Sharingmentioning

confidence: 99%

Section: Fl For Smart Citymentioning

confidence: 99%

Federated Learning for Internet of Things: A Comprehensive Survey

Nguyen

Ding

Pathirana

et al. 2021

IEEE Commun. Surv. Tutorials

594

182

View full text Add to dashboard Cite

“…Xiong et al [31] discussed some design challenges for building a scalable and shared multi-tenant AIoT platform through two edge computing use cases. Chiu et al [32] leveraged federated learning technologies to tackle the network bandwidth limitations and data privacy concerns in an AIoT platform.…”

Section: Applying Ai To Iotmentioning

confidence: 99%

An edge-cloud collaborative computing platform for building AIoT applications efficiently

Rong

Tong³

et al. 2021

J Cloud Comp

View full text Add to dashboard Cite

The convergence of Artificial Intelligence (AI) and the Internet of Things (IoT), or AIoT, has breathed a new life into IoT operations and human-machine interactions. Currently, resource-constrained IoT devices usually cannot provide sufficient capability for data storage and processing so as to support building modern AI models. An intuitive solution is to integrate cloud computing technology into AIoT and exploit the powerful and elastic computing as well as the storage capacity of the servers on the cloud end. Nevertheless, the network bandwidth and communication latency increasingly become serious bottlenecks. The emerging edge computing can complement the cloud-based AIoT in terms of communication latency, and hence attracts more and more attention from the AIoT area. In this paper, we present an industrial edge-cloud collaborative computing platform, namely Sophon Edge, that helps to build and deploy AIoT applications efficiently. As an enterprise-level solution for the AIoT computing paradigm, Sophon Edge adopts a pipeline-based computing model for streaming data from IoT devices. Besides, this platform supports an iterative way for model evolution and updating so as to enable the AIoT applications agile and data-driven. Through a real-world example, we demonstrate the effectiveness and efficiency of building an AIoT application based on the Sophon Edge platform.

show abstract

“…Xiong et al [33] discussed some design challenges for building a scalable and shared multi-tenant AIoT platform through two edge computing use cases. Chiu et al [34] leveraged federated learning technologies to tackle the network bandwidth limitations and data privacy concerns in an AIoT platform.…”

Section: Edge Computing For Iotmentioning

confidence: 99%

An edge-cloud collaborative computing platform for building AIoT applications efficiently

Rong

Tong³

et al. 2021

Preprint

View full text Add to dashboard Cite

The convergence of the Artificial Intelligence (AI) and the Internet of Things (IoT), i.e. the Artificial Intelligence of Things (AIoT), is a very promising technology that redefines the way people interact with the surrounding devices. Practical AIoT applications not only have high demands on computing and storage resources, but also desire for high responsiveness. Traditional cloud-based computing paradigm faces the great pressure on the network bandwidth and communication latency, hence the newly emerged edge computing paradigm gets involved. Consequently, AIoT applications can be implemented in an edge-cloud collaborative manner, where the model building and model inferencing are offloaded to the cloud and the edge, respectively. However, developers still face challenges building AIoT applications in practice due to the inherent heterogeneity of the IoT devices, the declining accuracy of once trained models, the security and privacy issues, etc. In this paper, we present the design of an industrial edge-cloud collaborative computing platform that aims to facilitate building AIoT applications in practice. Furthermore, a real-world use case is presented in this paper, which proved the efficiency of building an AIoT application on the platform.

show abstract

Semisupervised Distributed Learning With Non-IID Data for AIoT Service Platform

Cited by 68 publications

References 14 publications

Federated Learning for Internet of Things: A Comprehensive Survey

Federated Learning for Internet of Things: A Comprehensive Survey

An edge-cloud collaborative computing platform for building AIoT applications efficiently

An edge-cloud collaborative computing platform for building AIoT applications efficiently

Contact Info

Product

Resources

About