Integrating AI with Edge Computing and Cloud Services for Real-Time Data Processing and Decision Making
DOI:
https://doi.org/10.47709/ijmdsa.v2i1.2559Keywords:
Edge Computing, Multimodal AI, Real-Time Decision-making, AI Optimization, Model Pruning, Quantization, AI AcceleratorsAbstract
Connecting Multimodal AI and Edge computing for better real-time decision making: a paper on their synergy Edge computing is a solution that allows to overcome latency issue and processing data closer to the source, Multimodal AI on the other hand integrates and analyzes different types of data (images, audio, sensor data, etc.) to provide richer insights. Such a combination has a strong significance in autonomous vehicles and healthcare monitoring applications which require timely decision making with informed decisions. However, there are some inherent limitations to edge devices in computational power, energy expense, and data confidentiality. The paper examines several optimization methods such as model pruning that reduces model size, quantization that decreases the limit of precision, and domain specific AI accelerators to increase the processing speed to counteract these difficulties. The purpose of these strategies is to get a complex AI model to deploy on an edge device with limited computing resources at the cost of minimum performance. Combining Multimodal AI with edge computing can potentially transform data driven real-time decision-making applications across various fields. As Development of hardware and software never stops, formulated boundaries continue to expand, enabling more intelligent and responsive systems.
References
[2301.00774v3] SparseGPT: Massive Language Models Can Be Accurately Pruned in OneShot. (n.d). https://arxiv.org/pdf/2301.00774v3.pdf
2019], [O 4 N. (2019, November 4). Smart City Intelligent System Traffic Congestion Optimization using Internet Of Things. https://arxiv.org/abs/1911.01286
2020, M R O D 1. (2020, December 14). MultiModal OnDevice AI: Heterogeneous Computing Once More?
2020, M R O D 1. (2020, December 14). MultiModal OnDevice AI: Heterogeneous Computing Once More?. https://www.sigarch.org/multimodalondeviceaiheterogeneouscomputingoncemore/
Ahmed, S N P W. (2021, July 1). A Review on Edge Analytics: Issues, Challenges, Opportunities, Promises, Future Directions, and Applications. https://arxiv.org/pdf/2107.06835v1.pdf
B, A L O O P R S A S S G. (2023, January 1). Edge AI: A survey. https://www.sciencedirect.com/science/article/pii/S2667345223000196
Bagchi, S., Siddiqui, M., Wood, P., & Zhang, H. (2019, December 20). Dependability in edge computing. Association for Computing Machinery, 63(1), 5866. https://doi.org/10.1145/3362068
Bayoudh, K., Knani, R., Hamdaoui, F., & Mtibaa, A. (2021, June 10). A survey on deep multimodal learning for computer vision: advances, trends, applications, and datasets. Springer Science+Business Media, 38(8), 29392970. https://doi.org/10.1007/s00371021021667
Bhardwaj, K. (2019, October 23). EdgeAI: A Vision for Deep Learning in IoT Era. https://deepai.org/publication/edgeaiavisionfordeeplearninginiotera
Bilal, K., Khalid, O., Erbad, A., & Khan, S U. (2017, October 18). Potentials, trends, and prospects in edge technologies: Fog, cloudlet, mobile edge, and micro data centers. Elsevier BV, 130, 94120. https://doi.org/10.1016/j.comnet.2017.10.002
Cao, K., Liu, Y., Meng, G., & Sun, Q. (2020, January 1). An Overview on Edge Computing Research. Institute of Electrical and Electronics Engineers, 8, 8571485728. https://doi.org/10.1109/access.2020.2991734
Das, A., Dash, P K., & Mishra, B K. (2017, December 30). An Innovation Model for Smart Traffic Management System Using Internet of Things (IoT). Springer International Publishing, 355370. https://doi.org/10.1007/9783319706887_15
Frantar, E., & Alistarh, D. (2023, January 1). SparseGPT: Massive Language Models Can Be Accurately Pruned in OneShot. Cornell University. https://doi.org/10.48550/arxiv.2301.00774
Gossett, S. (2022, May 1). What Is Edge Computing?. https://builtin.com/cloudcomputing/whatisedgecomputing
Gupta, K., & Shukla, S. (2016, February 1). Internet of Things: Security challenges for next generation networks. https://doi.org/10.1109/iciccs.2016.7542301
Hasan, M T., Hossain, M A E., Mukta, M S H., Akter, A., Ahmed, M., & Islam, S. (2023, May 11). A Review on DeepLearningBased Cyberbullying Detection. Multidisciplinary Digital Publishing Institute, 15(5), 179179. https://doi.org/10.3390/fi15050179
Hilmani, A., Maizate, A., & Hassouni, L. (2020, September 11). Automated Real-Time Intelligent Traffic Control System for Smart Cities Using Wireless Sensor Networks. Wiley, 2020, 128. https://doi.org/10.1155/2020/8841893
India, S J A K M P S U C. (2019, November 5). Smart City: Traffic Management System Using Smart Sensor Network.
Klas, G. (2017, January 1). Edge Computing and the Role of Cellular Networks. IEEE Computer Society, 50(10), 4049. https://doi.org/10.1109/mc.2017.3641649
Luo, R C., & Kuo, C. (2016, March 24). Intelligent SevenDoF Robot With Dynamic Obstacle Avoidance and 3D Object Recognition for Industrial Cyber–Physical Systems in Manufacturing Automation. Institute of Electrical and Electronics Engineers, 104(5), 11021113. https://doi.org/10.1109/jproc.2015.2508598
Miz, V., & Hahanov, V. (2014, September 1). Smart traffic light in terms of the cognitive road traffic management system (CTMS) based on the Internet of Things. https://doi.org/10.1109/ewdts.2014.7027102
Mohsen, F., Ali, H., Hajj, N E., & Shah, Z. (2022, October 26). Artificial intelligencebased methods for fusion of electronic health records and imaging data. Nature Portfolio, 12(1)
Mohsen, F., Ali, H., Hajj, N E., & Shah, Z. (2022, October 26). Artificial intelligencebased methods for fusion of electronic health records and imaging data. Nature Portfolio, 12(1). https://doi.org/10.1038/s41598022225144
Narejo, S., Pandey, B., Esenarro, D., Rodríguez, C., & Anjum, M R. (2021, May 11). Weapon Detection Using YOLO V3 for Smart Surveillance System. Hindawi Publishing Corporation, 2021, 19. https://doi.org/10.1155/2021/9975700
Nikolopoulos, B V W B K S. (2016, September 7). Challenges and Opportunities in Edge Computing. https://arxiv.org/pdf/1609.01967v1.pdf
Nyle, D R S N S. (2021, November 22). The Benefits of Edge Computing in Healthcare, Smart Cities, and IoT. https://arxiv.org/abs/2112.01250
Palla, T. (2021, May 29). INTELLIGENT TRAFFIC MANAGEMENT USING BIG DATA ANALYTICS AND IOT. https://tharunpalla43.medium.com/intelligenttrafficmanagementusingbigdataanalyticsandiota5e841f2cf7d?source=post_internal_links2
Pearson, S. (2012, June 27). Privacy, Security and Trust in Cloud Computing. , 342. https://doi.org/10.1007/9781447141891_1
Projects, C T W. (2006, May 24). Edge computing. https://en.wikipedia.org/wiki/Edge_computing
Sethi, P S. (2022, April 11). Opportunities and Challenges in Edge Computing Parminder Singh Sethi Medium. https://medium.com/@singhsethi.parminder/opportunitiesandchallengesinedgecomputing76ff4643edcb?source=read_next_recirc03994cd49_e943_4d72_a119_26b554fd4e95
Shi, D., Tao, C., Jin, Y., Yang, Z., Yuan, C., & Wang, J. (2023, January 1). UPop: Unified and Progressive Pruning for Compressing Vision Language Transformers. Cornell University. https://doi.org/10.48550/arxiv.2301.13741
Sujata, B E B. (2020, December 10). Artificial Intelligence at the Edge. https://arxiv.org/abs/2012.05410
Summaira, J., Li, X., Shoib, A M., Li, S., & Abdul, J. (2021, January 1). Recent Advances and Trends in Multimodal Deep Learning: A Review. Cornell University. https://doi.org/10.48550/arxiv.2105.11087
Traffic Management Case Studies | SMATS. (2020, November 4). https://www.smatstraffic.com/casestudies
Trihinas, D., Thamsen, L., Beilharz, J., & Symeonides, M. (2022, September 1). Towards Energy Consumption and Carbon Footprint Testing for AIdriven IoT Services. https://doi.org/10.1109/ic2e55432.2022.00011
Varghese, B., Lara, E D., Ding, A Y., Hong, C., Bonomi, F., Dustdar, S., Harvey, P., Hewkin, P., Shi, W., Thiele, M., & Willis, P. (2021, July 1). Revisiting the Arguments for Edge Computing Research. IEEE Computer Society, 25(5), 3642. https://doi.org/10.1109/mic.2021.3093924
Wang, Y J. (2011, September 1). A City Intelligent Transportation Management Command System. Trans Tech Publications, 9798, 863866. https://doi.org/10.4028/www.scientific.net/amm.9798.863
Wasserblat, O Z L B S. (2021, November 10). Prune Once for All: Sparse PreTrained Language Models. https://arxiv.org/pdf/2111.05754v1.pdf
What is edge computing?. (2023, February 6). https://www.redhat.com/en/topics/edgecomputing/whatisedgecomputing
What Is Multimodal AI? (2023, July 10). https://app.twelvelabs.io/blog/whatismultimodalai
Wu, J., Gan, W., Chen, Z., Wan, S., & Yu, P S. (2023, December 15). Multimodal Large Language Models: A Survey. https://doi.org/10.1109/bigdata59044.2023.10386743
Xu, D., Li, T., Li, Y., Su, X., Tarkoma, S., & Hui, P. (2020, March 26). A Survey on Edge Intelligence
Xu, D., Li, T., Li, Y., Su, X., Tarkoma, S., & Hui, P. (2020, March 26). A Survey on Edge Intelligence. http://dblp.unitrier.de/db/journals/corr/corr2003.html#abs200312172
Xu, U R H G A H E S Z. (n.d). A Case for Elevating the Edge to be a Peer of the Cloud. https://dl.acm.org/doi/10.1145/3447853.3447859
Yan, G., & Qin, Q. (2020, January 1). The Application of Edge Computing Technology in the Collaborative Optimization of Intelligent Transportation System Based on Information Physical Fusion. Institute of Electrical and Electronics Engineers, 8, 153264153272
Yan, G., & Qin, Q. (2020, January 1). The Application of Edge Computing Technology in the Collaborative Optimization of Intelligent Transportation System Based on Information Physical Fusion. Institute of Electrical and Electronics Engineers, 8, 153264153272. https://doi.org/10.1109/access.2020.3008780
Yao, Z., Ma, L., Shen, S., Keutzer, K., & Mahoney, M W. (2021, May 30). MLPruning: A Multilevel Structured Pruning Framework for Transformerbased Models. Cornell University. http://export.arxiv.org/pdf/2105.14636
Zhang, C., Yang, Z., He, X., & Deng, L. (2020, March 1). Multimodal Intelligence: Representation Learning, Information Fusion, and Applications. Institute of Electrical and Electronics Engineers, 14(3), 478493
Zhang, C., Yang, Z., He, X., & Deng, L. (2020, March 1). Multimodal Intelligence: Representation Learning, Information Fusion, and Applications. Institute of Electrical and Electronics Engineers, 14(3), 478493. https://doi.org/10.1109/jstsp.2020.2987728
Zhang, M. (2020, October 17). Deep Learning in the Era of Edge Computing: Challenges and Opportunities
Zhang, M. (2020, October 17). Deep Learning in the Era of Edge Computing: Challenges and Opportunities. https://deepai.org/publication/deeplearningintheeraofedgecomputingchallengesandopportunities
Zhang, Z Z X C E L L Z K L J. (2023, November 10). Edge Intelligence: Paving the Last Mile of Artificial Intelligence with Edge Computing
Zhang, Z Z X C E L L Z K L J. (2023, November 10). Edge Intelligence: Paving the Last Mile of Artificial Intelligence with Edge Computing. https://ieeexplore.ieee.org/document/8736011/
Zhu, M., & Gupta, S. (2017, January 1). To prune, or not to prune: exploring the efficacy of pruning for model compression. Cornell University. https://doi.org/10.48550/arxiv.1710.01878
Zomaya, S D H Z W F J Y S D A Y. (2023, December 4). Edge Intelligence: The Confluence of Edge Computing and Artificial Intelligence
Zomaya, S D H Z W F J Y S D A Y. (2023, December 4). Edge Intelligence: The Confluence of Edge Computing and Artificial Intelligence. https://ieeexplore.ieee.org/document/9052677/
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2023 MD Emran Hossain
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
info@itscience.org, web: 
