Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
Review
. 2022 Jul 25;22(15):5544.
doi: 10.3390/s22155544.

Context-Aware Edge-Based AI Models for Wireless Sensor Networks-An Overview

Ahmed A Al-Saedi  1 , Veselka Boeva  1 , Emiliano Casalicchio  1   2 , Peter Exner  3
Affiliations
Review

Context-Aware Edge-Based AI Models for Wireless Sensor Networks-An Overview

Ahmed A Al-Saedi et al. Sensors (Basel). .

Abstract

Recent advances in sensor technology are expected to lead to a greater use of wireless sensor networks (WSNs) in industry, logistics, healthcare, etc. On the other hand, advances in artificial intelligence (AI), machine learning (ML), and deep learning (DL) are becoming dominant solutions for processing large amounts of data from edge-synthesized heterogeneous sensors and drawing accurate conclusions with better understanding of the situation. Integration of the two areas WSN and AI has resulted in more accurate measurements, context-aware analysis and prediction useful for smart sensing applications. In this paper, a comprehensive overview of the latest developments in context-aware intelligent systems using sensor technology is provided. In addition, it also discusses the areas in which they are used, related challenges, motivations for adopting AI solutions, focusing on edge computing, i.e., sensor and AI techniques, along with analysis of existing research gaps. Another contribution of this study is the use of a semantic-aware approach to extract survey-relevant subjects. The latter specifically identifies eleven main research topics supported by the articles included in the work. These are analyzed from various angles to answer five main research questions. Finally, potential future research directions are also discussed.

Keywords: artificial intelligence; context-awareness; edge computing; wireless sensor network.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure 1
Figure 1
A schematic illustration of the paper organization.
Figure 2
Figure 2
Context-aware framework layers.
Figure 3
Figure 3
EC ecosystem.
Figure 4
Figure 4
A schematic presentation of the general WSN architecture.
Figure 5
Figure 5
The main methodological phases of the study.
Figure 6
Figure 6
The number of papers selected after applying each filter of the survey’s related papers is given for WoS and Scopus databases, respectively.
Figure 7
Figure 7
Flowchart describing the different steps of the semantic-aware approach applied to identify the main subjects covered by the included papers.
Figure 8
Figure 8
Relative popularity of the identified subjects assessed on the based of the keywords’ frequency. The most popular subject is AI, ML and DL followed by Edge Computing and Smart Monitoring, Smart Healthcare and Smart and Wearable Devices.
Figure 9
Figure 9
Percentage of papers of sample studied per the main identified subjects. The most represented subjects are AI, ML and DL and Smart Healthcare followed by Smart and Wearable Devices, Edge Computing and Smart Monitoring and Sensors and WSN. These well reflect the survey theme.
Figure 10
Figure 10
Included papers per year (publishing trend) normalized on monthly base. There was a significant increase in the number of included papers published after 2019.
Figure 11
Figure 11
Included papers per year are distributed in four categories based on the used computational techniques, i.e., ML, DL, ML and DL and AI.
Figure 12
Figure 12
Main challenges addressed by the papers included in the survey.
Figure 13
Figure 13
Percentage of papers of sample studies per domain of applications. The most popular category is healthcare followed by smart cities, autonomous driving, environment monitoring and transportation (logistics).
Figure 14
Figure 14
The relationship between HAR and top five most studied application domains.
Figure 15
Figure 15
The relationship between QoS and top five most studied application domains.
Figure 16
Figure 16
The relationship between HAR challenge and AI techniques categories used to address it.
Figure 17
Figure 17
The relationship between QoS challenge and corresponding AI techniques categories used to deal with it.
Figure 18
Figure 18
The relationship between Energy Saving challenge and AI techniques categories applied to address it.
Figure 19
Figure 19
Specific ML and DL algorithms more frequently used in addressing the HAR challenge.
Figure 20
Figure 20
Specific ML and DL algorithms more frequently used in addressing the Monitoring challenge.
Figure 21
Figure 21
Specific ML and DL algorithms more frequently used in addressing Activity Recognition challenge.
Figure 22
Figure 22
Percentage of papers per ML category of algorithms found in the sample studied. The most used ML techniques are SVM, RF, DT and K-NN.
Figure 23
Figure 23
Percentage of papers per DL category of algorithms found in the sample studied. The three most applied DL techniques are CNN, NN and LSTM.
Figure 24
Figure 24
Overview of ML and/or DL techniques that have been used in the included papers.
Figure 25
Figure 25
Motivations of adopting AI solutions to context awareness.
Figure 26
Figure 26
Main challenges in logistics addressed by the papers included in the survey.
Figure 27
Figure 27
Main AI techniques in logistics addressed by the papers included in the survey.
See this image and copyright information in PMC

References

    1. Mahdavinejad M.S., Rezvan M., Barekatain M., Adibi P., Barnaghi P., Sheth A.P. Machine Learning for Internet of Things Data Analysis: A Survey. Digit. Commun. Netw. 2018;4:161–175. doi: 10.1016/j.dcan.2017.10.002. - DOI
    1. Razzaque M.A., Milojevic-Jevric M., Palade A., Clarke S. Middleware for Internet of Things: A Survey. IEEE Internet Things J. 2016;3:70–95. doi: 10.1109/JIOT.2015.2498900. - DOI
    1. Dastjerdi A.V., Buyya R. Fog Computing: Helping the Internet of Things Realize Its Potential. Computer. 2016;49:112–116. doi: 10.1109/MC.2016.245. - DOI
    1. Gubbi J., Buyya R., Marusic S., Palaniswami M. Internet of Things (IOT): A Vision, Architectural Elements, and Future Directions. Future Gener. Comput. Syst. 2013;29:1645–1660. doi: 10.1016/j.future.2013.01.010. - DOI
    1. Sakr F., Bellotti F., Berta R., De Gloria A. Machine Learning on Mainstream Microcontrollers. Sensors. 2020;20:2638. doi: 10.3390/s20092638. - DOI - PMC - PubMed

LinkOut - more resources