Rural AI: Serverless-Powered Federated Learning for Remote Applications

Patros, Panos; Ooi, Melanie Po-Leen; Huang, Victoria; Mayo, Michael; Anderson, Chris; Burroughs, S. M.; Baughman, Matt; Almurshed, Osama; Rana, Omer; Chard, Ryan; Chard, Kyle; Foster, Ian

doi:10.1109/mic.2022.3202764

Cited by 13 publications

(3 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Nvidia Jetson (Nano) and Raspberry Pi are now widely used to support edge-based AI computing. Dependable use of these devices require addressing operational issues such as inconsistent internet, communication delays, and service disruptions -that require proactive strategies [9], [6]. Faulttolerance is a crucial requirement of agricultural robots, especially as they need to be operated by non-experts.…”

Section: Adaptive Edge-cloud Frameworkmentioning

confidence: 99%

“…Recent literature highlights advancements in weed detection and robotic weed management in agriculture, such as studying weed classification using AI [13], or adapting to rural infrastructure to securely train an AI model [14]. However, literature addressing infrastructure unreliability, especially in rural farming areas [6], [15] is limited. Even though there are researchers working on optimising machine learning inference to reduce costs [16], delays [17], [16], and balance workload [17], they often lack solutions tailored for agricultural settings in rural areas.…”

Section: Adaptive Edge-cloud Frameworkmentioning

confidence: 99%

“…1: Architecture of the proposed framework One such application, namely Rural-AI, allows the use of machine learning (ML) within rural communities, with an aim to achieve better performance in terms of productivity, economic growth, impact of climate change and affordability [5]. Rural-AI [6] is the engineering of cyber-physical systems for enabling sovereign, sustainable AI in locations with limited and/or unreliable power/networking infrastructure. Due to the lack of proper development and infrastructure in rural areas, ML/AI applications cannot be utilised to their full potential.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

An Edge-Cloud Infrastructure for Weed Detection in Precision Agriculture

Kaushal,

Almurshed,

Alabbas

et al. 2023

2023 IEEE Intl Conf on Dependable, Autonomic and Secure Computing, Intl Conf on Pervasive Intelligence and Computing, Intl Conf

Self Cite

View full text Add to dashboard Cite

Accurate identification of weeds plays a crucial role in helping farmers achieve efficient agricultural practices. An edge-cloud infrastructure can provide efficient resources for weed detection in resource-constrained rural areas. However, deployed applications in these areas often face challenges such as connectivity failures and network issues that affect their quality of service (QoS). We introduce a signal quality-aware framework for precision agriculture that allocates weed inference tasks to resource nodes based on the current network connectivity and quality. Two Machine Learning (ML) models based on ResNet-50 and MobileNetV2 are trained using the publicly available DeepWeeds image classification dataset. A rule-based approximation algorithm is formulated to execute tasks on resourceconstrained computational nodes. We also designed a testbed setup consisting of Raspberry Pi (RPi), personal laptop, cloud server and Parsl environment for evaluating the framework. Reliability of the framework is tested in a controlled setting, under various dynamically injected faults. Experimental results demonstrate that the proposed setup can accurately identify weeds while ensuring high fault tolerance and low completion time, making it a promising solution for weed management in rural agriculture.

show abstract

Section: Adaptive Edge-cloud Frameworkmentioning

confidence: 99%