Mobile Edge Computing Based Internet of Agricultural Things: A Systematic Review and Future Directions

Sengupta, Anirbit; Gill, Sukhpal Singh; Das, Abhijit; De, Debashis

doi:10.1007/978-3-030-69893-5_17

Cited by 8 publications

(6 citation statements)

References 87 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Currently, an intelligent transportation environment uses cloud computing, where all the processing is done at remote data centres, but cloud computing lacks key safety features in smart transportation [56]. For example, if a driverless car needs to stop in case of a dangerous situation, it has to upload the data to the cloud, which then performs a computing process and sends the "stop" command to the car when the car finally acts upon the instruction [90]. A more rapid solution is to bring computation capability close and Edge Computing can provide limited computation capability to make quick (lower latency) decisions.…”

Section: Smart Transportmentioning

confidence: 99%

“…Edge Computing architectures and systems run an increased risk of failure because computing resources are not contained in a controlled environment with a single set of emergency and backup protocols [181]. The authors propose a resilient application platform to provide core services (for example, distributed data management) and mechanisms to monitor and optimize functionality in relatively long-lived distributed applications [90]. An alternative argument is to improve the resilience by moving the functionality closer to the end devices by relying less on any less reliable links (wireless in particular) [89].…”

Section: Network Resiliencementioning

confidence: 99%

“…MEC and ICN are complementary concepts but independent: both are solutions with, for example, 5G mobile networks, which could utilize ICN for content distribution, transparent mobility among multiple technologies, or to retransmit lost packets over an unreliable radio link, but without a commitment to developing a full MEC scenario [90]. Conversely, MEC could be used to reduce latency for AR applications without resorting to ICN.…”

Section: Information Centric Networking (Icn)mentioning

confidence: 99%

See 2 more Smart Citations

Edge AI: A survey

Singh

Gill

2023

Internet of Things and Cyber-Physical Systems

135

View full text Add to dashboard Cite

Section: Smart Transportmentioning

confidence: 99%

Section: Network Resiliencementioning

confidence: 99%

Section: Information Centric Networking (Icn)mentioning

confidence: 99%

See 1 more Smart Citation

Edge AI: A survey

Singh

Gill

2023

Internet of Things and Cyber-Physical Systems

135

View full text Add to dashboard Cite

“…For example, in healthcare there are issues with data privacy, the regulatory environment, data integration and data access (Coulby et al, 2021). In precision agriculture, there are challenges for data integration, high up-front capital investment costs, and problems with measuring the return on investment (ROI; Sengupta et al, 2021). Communication issues from IoT devices are widespread causing dropouts and data loss (Brun-Laguna et al, 2018).…”

Section: Related Workmentioning

confidence: 99%

Realizing Smart City Infrastructure at Scale, in the Wild: A Case Study

James

Jonczyk²,

Smith³

et al. 2022

Front. Sustain. Cities

View full text Add to dashboard Cite

The smart city term has been widely used for a number of years and many pilot projects and limited scale, sector independent initiatives have been progressed, but comprehensive, long-term, city wide, multi-sector systems are much less evident. This paper examines one such case study in Newcastle, UK highlighting the challenges and opportunities that realizing “smart city” concepts at scale present. The paper provides the background to the Newcastle Urban Observatory project and discusses the socio-technical and practical challenges of developing and maintaining smart city networks of sensors in the plurality that is a modern city. We discuss the organizational requirements, governance, data quality and volume issues, big data management and discuss the current and future needs of decision makers and other city stakeholders. Finally, we propose areas where smart cities can have a positive impact on public outcomes through the discussion of two case studies related to COVID-19 and pedestrianization initiatives.

show abstract

“…While utilizing deep learning in both phases enhances accuracy and generalizability, it demands considerable computational resources. This poses challenges in achieving optimal performance on edge computing [8,9] devices, such as the RK3399Pro platform discussed in this study.…”

Section: Introductionmentioning

confidence: 99%

Greenhouse Ventilation Equipment Monitoring for Edge Computing

Feng,

Zhang,

Chen

2024

Applied Sciences

View full text Add to dashboard Cite

Digital twins based on real-world scenarios are heavily reliant on extensive on-site data, representing a significant investment in information technology. This study aims to maximize the capabilities of visual sensors, like cameras in controlled-environment agriculture, by acquiring more target-specific information at minimal additional cost. This approach not only reduces investment but also increases the utilization rate of existing equipment. Utilizing YOLOv7, this paper introduces a system with rotatable pan-tilt cameras for the comprehensive monitoring of large-scale greenhouse ventilation systems. To mitigate the computational load on edge servers at greenhouse sites caused by an abundance of video-processing tasks, a Region of Interest (ROI) extraction method based on tracking is adopted. This method avoids unnecessary calculations in non-essential areas. Additionally, we integrate a self-encoding approach into the training phase, combining object detection and embedding to eliminate redundant feature extraction processes. Experimental results indicate that ROI extraction significantly reduces the overall inference time by more than 50%, and by employing LSTM to classify the state of the fan embedding sequences, a 100% accuracy rate was achieved.

show abstract

Mobile Edge Computing Based Internet of Agricultural Things: A Systematic Review and Future Directions

Cited by 8 publications

References 87 publications

Edge AI: A survey

Edge AI: A survey

Realizing Smart City Infrastructure at Scale, in the Wild: A Case Study

Greenhouse Ventilation Equipment Monitoring for Edge Computing

Contact Info

Product

Resources

About