Demystifying Edge AI: Unlocking the Potential of Artificial Intelligence at the Edge of the Network


Authors : Ashrafur Rahman Nabil; Reaz Uddin Rayhan; MD Nazim Akther; MD Tusher

Volume/Issue : Volume 9 - 2024, Issue 12 - December

Google Scholar : https://tinyurl.com/3nv4syk2

Scribd : https://tinyurl.com/4zzpdtyc

DOI : https://doi.org/10.69142/IJISRT24DEC1476

Abstract : One of the most exciting but almost invisible technologies underpinning a world of autonomous devices is edge AI that is designed to process data locally thus eliminating centralized cloud computing. This change of paradigm improves the efficiency, the privacy and does not need to suit onto the cloud, what make a notable diminution of the cost of clouds. Edge AI is designed to place AI capabilities as close to the source of data as possible and will lead to widespread efficiency and innovation across multiple industries. In the IoT scenario, it enables smart device communications and shortens the decision-making process. In delivering healthcare services, Edge AI enables rapid diagnosing of a patient’s conditions and provides action on the same since time is critical in these practices. Likewise in the financial business, it helps identify fraud and evaluate risks with a small amount of latency. This article defines Edge AI, brings out its innovative use cases, and analyses the advantages it provides, including low latency, optimizing performance, and scalability. Edge AI is promising to provide industries with more fulfilling operations that revolutionize secure, real-time and economical intelligent solutions that define the future platforms for intelligent systems.

Keywords : Edge AI, Artificial Intelligence, Real-time Processing, Latency Reduction, IoT (Internet of Things).

References :

Reference number 1

Unstructured Citation

Singh, R., & Gill, S. S. (2023). Edge AI: a survey. Internet of Things and Cyber-Physical Systems, 3, 71-92.
https://doi.org/10.1016/j.iotcps.2023.02.004


Reference number 2

Unstructured Citation

Himeur, Y., Sayed, A. N., Alsalemi, A., Bensaali, F., & Amira, A. (2024). Edge AI for Internet of Energy: Challenges and perspectives. Internet of Things, 25, 101035.
https://doi.org/10.1016/j.iot.2023.101035


Reference number 3

Unstructured Citation

Li, E., Zeng, L., Zhou, Z., & Chen, X. (2019). Edge AI: On-demand accelerating deep neural network inference via edge computing. IEEE Transactions on Wireless Communications, 19(1), 447-457.
https://doi.org/10.1145/3523230.3523235


Reference number 4

Unstructured Citation

Gill, S. S., Golec, M., Hu, J., Xu, M., Du, J., Wu, H., ... &Uhlig, S. (2025). Edge AI: A taxonomy, systematic review and future directions. Cluster Computing, 28(1), 1-53.
https://doi.org/10.1007/s10586-024-04686-y


Reference number 5

Unstructured Citation

Surianarayanan, C., Lawrence, J. J., Chelliah, P. R., Prakash, E., &Hewage, C. (2023). A survey on optimization techniques for edge artificial intelligence (ai). Sensors, 23(3), 1279.
https://doi.org/10.3390/s23031279


Reference number 6

Unstructured Citation

Holmes, J., Sacchi, L., &Bellazzi, R. (2004). Artificial intelligence in medicine. Ann R CollSurgEngl, 86, 334-8.
https://doi.org/10.1007/978-3-319-19551-3


Reference number 7

Unstructured Citation

Fetzer, J. H., &Fetzer, J. H. (1990). What is artificial intelligence? (pp. 3-27). Springer Netherlands.
https://doi.org/10.1007/978-94-009-1900-6_1


Reference number 8

Unstructured Citation

Winston, P. H. (1992). Artificial intelligence. Addison-Wesley Longman Publishing Co., Inc..https://dl.acm.org/doi/10.1016/j.jnca.2023.103675


Reference number 9

Unstructured Citation

Jiang, Y., Li, X., Luo, H., Yin, S., &Kaynak, O. (2022). Quo vadis artificial intelligence?. Discover Artificial Intelligence, 2(1), 4.
https://doi.org/10.1007/s44163-021-00009-x


Reference number 10

Unstructured Citation

Holzinger, A., Langs, G., Denk, H., Zatloukal, K., & Müller, H. (2019). Causability and explainability of artificial intelligence in medicine. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 9(4), e1312.
https://doi.org/10.1002/widm.1312


Reference number 11

Unstructured Citation

Liu, X., Iftikhar, N., &Xie, X. (2014, July). Survey of real-time processing systems for big data. In Proceedings of the 18th International Database Engineering & Applications Symposium (pp. 356-361).
https://doi.org/10.1145/2628194.2628251


Reference number 12

Unstructured Citation

Yasumoto, K., Yamaguchi, H., &Shigeno, H. (2016). Survey of real-time processing technologies of iot data streams. Journal of Information Processing, 24(2), 195-202.
https://doi.org/10.2197/ipsjjip.24.195


Reference number 13

Unstructured Citation

Wang, Y. (2002). The real-time process algebra (RTPA). Annals of Software Engineering, 14, 235-274.
https://doi.org/10.1023/A:1020561826073


Reference number 14

Unstructured Citation

Stonebraker, M., Çetintemel, U., &Zdonik, S. (2005). The 8 requirements of real-time stream processing. ACM Sigmod Record, 34(4), 42-47.
https://doi.org/10.1145/1107499.1107504


Reference number 15

Unstructured Citation

Goodman, E. B. J. C. (1997). On the inseparability of grammar and the lexicon: Evidence from acquisition, aphasia and real-time processing. Language and cognitive Processes, 12(5-6), 507-584.
https://doi.org/10.1080/016909697386628


Reference number 16

Unstructured Citation

Joshi, G., Soljanin, E., &Wornell, G. (2017). Efficient redundancy techniques for latency reduction in cloud systems. ACM Transactions on Modeling and Performance Evaluation of Computing Systems (TOMPECS), 2(2), 1-30.
https://doi.org/10.1145/3055281


Reference number 17

Unstructured Citation

La, Q. D., Ngo, M. V., Dinh, T. Q., Quek, T. Q., & Shin, H. (2019). Enabling intelligence in fog computing to achieve energy and latency reduction. Digital Communications and Networks, 5(1), 3-9.
https://doi.org/10.1016/j.dcan.2018.10.008


Reference number 18

Unstructured Citation

Velasquez, K., Abreu, D. P., Curado, M., & Monteiro, E. (2017). Service placement for latency reduction in the internet of things. Annals of Telecommunications, 72, 105-115.
https://doi.org/10.1007/s12243-016-0524-9


Reference number 19

Unstructured Citation

Lee, D., Khan, S., Subramanian, L., Ghose, S., Ausavarungnirun, R., Pekhimenko, G., ... &Mutlu, O. (2017). Design-induced latency variation in modern DRAM chips: Characterization, analysis, and latency reduction mechanisms. Proceedings of the ACM on Measurement and Analysis of Computing Systems, 1(1), 1-36.
https://doi.org/10.1145/3084464


Reference number 20

Unstructured Citation

Hu, Y., Wang, Y., Liu, B., Niu, D., & Huang, C. (2017, September). Latency reduction and load balancing in coded storage systems. In Proceedings of the 2017 Symposium on Cloud Computing (pp. 365-377).
https://doi.org/10.1145/3127479.3131623


Reference number 21

Unstructured Citation

Gubbi, J., Buyya, R., Marusic, S., &Palaniswami, M. (2013). Internet of Things (IoT): A vision, architectural elements, and future directions. Future generation computer systems, 29(7), 1645-1660.
https://doi.org/10.1016/j.future.2013.01.010


Reference number 22

Unstructured Citation

Li, S., Xu, L. D., & Zhao, S. (2015). The internet of things: a survey. Information systems frontiers, 17, 243-259.
https://doi.org/10.1007/s10796-014-9492-7


Reference number 23

Unstructured Citation

Hassan, W. H. (2019). Current research on Internet of Things (IoT) security: A survey. Computer networks, 148, 283-294.
https://doi.org/10.1016/j.comnet.2018.11.025


Reference number 24

Unstructured Citation

Weber, R. H., & Weber, R. (2010). Internet of things (Vol. 12). Heidelberg: Springer.
https://doi.org/10.1007/978-3-642-11710-7


Reference number 25

Unstructured Citation

Zikria, Y. B., Ali, R., Afzal, M. K., & Kim, S. W. (2021). Next-generation internet of things (iot): Opportunities, challenges, and solutions. Sensors, 21(4), 1174.
https://doi.org/10.3390/s21041174

 

One of the most exciting but almost invisible technologies underpinning a world of autonomous devices is edge AI that is designed to process data locally thus eliminating centralized cloud computing. This change of paradigm improves the efficiency, the privacy and does not need to suit onto the cloud, what make a notable diminution of the cost of clouds. Edge AI is designed to place AI capabilities as close to the source of data as possible and will lead to widespread efficiency and innovation across multiple industries. In the IoT scenario, it enables smart device communications and shortens the decision-making process. In delivering healthcare services, Edge AI enables rapid diagnosing of a patient’s conditions and provides action on the same since time is critical in these practices. Likewise in the financial business, it helps identify fraud and evaluate risks with a small amount of latency. This article defines Edge AI, brings out its innovative use cases, and analyses the advantages it provides, including low latency, optimizing performance, and scalability. Edge AI is promising to provide industries with more fulfilling operations that revolutionize secure, real-time and economical intelligent solutions that define the future platforms for intelligent systems.

Keywords : Edge AI, Artificial Intelligence, Real-time Processing, Latency Reduction, IoT (Internet of Things).

Never miss an update from Papermashup

Get notified about the latest tutorials and downloads.

Subscribe by Email

Get alerts directly into your inbox after each post and stay updated.
Subscribe
OR

Subscribe by RSS

Add our RSS to your feedreader to get regular updates from us.
Subscribe