Artificial Intelligence as a Service Architecture: an innovative approach for Computer Vision applications
Resumo
In recent years, Artificial Intelligence (AI) has grown significantly across various domains such as transportation, healthcare, and security. However, current implementations of intelligent services face challenges in enhancing the personalized and large-scale use of AI. This work presents Artificial Intelligence as a Service (AIaaS), an innovative approach to effectively manage the lifecycle of diverse AI models and paradigms, while offering them as a service for heterogeneous devices, multiple users, and modern applications. We explored the feasibility of delivering AI resources in different network architectures, such as edge computing and mobile networks, which provide a flexible and scalable environment that allows users to acquire cognitive services in the AI life cycle. Also, our approach facilitates personalized and scalable AI solutions, fostering innovation and expediting the deployment of intelligent applications across diverse contexts, making it suitable for real-world scenarios.
Referências
Baccour, E., Allahham, M. S., Erbad, A., Mohamed, A., Hussein, A. R., and Hamdi, M. (2023). Zero Touch Realization of Pervasive Artificial Intelligence as a Service in 6G Networks. IEEE Communications Magazine, 61(2):110–116.
Baldominos, A., Albacete, E., Saez, Y., and Isasi, P. (2014). A scalable machine learning online service for big data real-time analysis. In 2014 IEEE Symposium on Computational Intelligence in Big Data (CIBD), pages 1–8, Orlando, FL, USA. IEEE.
Cerar, G. and Hribar, J. (2023). Machine learning operations model store: Optimizing model selection for AI as a service. In 2023 International Balkan Conference on Communications and Networking (BalkanCom), pages 1–5, İstanbul, Turkiye. IEEE.
Chan, S., Stone, T., Szeto, K. P., and Chan, K. H. (2013). PredictionIO: A Distributed Machine Learning Server for Practical Software Development. In Proceedings of the 22nd ACM International Conference on Information & Knowledge Management, CIKM ’13, page 2493–2496, New York, NY, USA. Association for Computing Machinery.
De Caro, V., Bano, S., Machumilane, A., Gotta, A., Cassarà, P., Carta, A., Semola, R., Sardianos, C., Chronis, C., Varlamis, I., Tserpes, K., Lomonaco, V., Gallicchio, C., and Bacciu, D. (2022). AI-as-a-service toolkit for human-centered intelligence in autonomous driving. In 2022 IEEE International Conference on Pervasive Computing and Communications Workshops and other Affiliated Events (PerCom Workshops), pages 91–93, Pisa, Italy. IEEE.
Fortuna, C., Mušić, D., Cerar, G., Čampa, A., Kapsalis, P., and Mohorčič, M. (2023). On-premise artificial intelligence as a service for small and medium size setups. In Shinkuma, R., Xhafa, F., and Nishio, T., editors, Advances in Engineering and Information Science Toward Smart City and Beyond, pages 53–73. Springer International Publishing, Cham.
Guntupalli, N. and Rudramalla, V. (2023). Artificial intelligence as a service: Providing integrity and confidentiality. In Morusupalli, R., Dandibhotla, T. S., Atluri, V. V., Windridge, D., Lingras, P., and Komati, V. R., editors, Multi-disciplinary Trends in Artificial Intelligence, pages 309–315, Cham. Springer Nature Switzerland.
Hajipour, V., Hekmat, S., and Amini, M. (2023). A value-oriented Artificial Intelligence-as-a-Service business plan using integrated tools and services. Decision Analytics Journal, page 100302.
Jaffri, A. and Sicular, S. (2023). What’s new in artificial intelligence from the 2023 Gartner Hype Cycle.
Lewicki, K., Lee, M. S. A., Cobbe, J., and Singh, J. (2023). Out of Context: Investigating the Bias and Fairness Concerns of “Artificial Intelligence as a Service”. In Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems, CHI ’23, New York, NY, USA. Association for Computing Machinery.
Li, L. E., Chen, E., Hermann, J., Zhang, P., and Wang, L. (2017). Scaling Machine Learning as a Service. In Hardgrove, C., Dorard, L., Thompson, K., and Douetteau, F., editors, Proceedings of The 3rd International Conference on Predictive Applications and APIs, volume 67 of Proceedings of Machine Learning Research, pages 14–29, Boston, USA. PMLR.
Lomonaco, V., Caro, V. D., Gallicchio, C., Carta, A., Sardianos, C., Varlamis, I., Tserpes, K., Coppola, M., Marmpena, M., Politi, S., Schoitsch, E., and Bacciu, D. (2023). AI-Toolkit: A Microservices Architecture for Low-Code Decentralized Machine Intelligence. In 2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW), pages 1–5, Rhodes Island, Greece. IEEE.
Luxton, R. (2023). Chapter 22 - Challenges and future aspects of sensor technology. In Barhoum, A. and Altintas, Z., editors, Advanced Sensor Technology, pages 853–877. Elsevier.
Merluzzi, M., Borsos, T., Rajatheva, N., Benczúr, A. A., Farhadi, H., Yassine, T., Müeck, M. D., Barmpounakis, S., Strinati, E. C., Dampahalage, D., Demestichas, P., Ducange, P., Filippou, M. C., Baltar, L. G., Haraldson, J., Karaçay, L., Korpi, D., Lamprousi, V., Marcelloni, F., Mohammadi, J., Rajapaksha, N., Renda, A., and Uusitalo, M. A. (2023). The Hexa-X Project Vision on Artificial Intelligence and Machine Learning-Driven Communication and Computation Co-Design for 6G. IEEE Access, 11:65620–65648.
Nadar, A. and Härri, J. (2024). Enhancing Network Data Analytics Functions: Integrating AIaaS with ML Model Provisioning. In 2024 22nd Mediterranean Communication and Computer Networking Conference (MedComNet), pages 1–4, Nice, France. IEEE.
Napisa, K., Mababangloob, G. R., Lubag, M., Concepcion II, R., and Redillas, M. M. (2023). Explainable and Interpretable Artificial Intelligence as a Service for Green Smart Cities and Communities. In 2023 IEEE 15th International Conference on Humanoid, Nanotechnology, Information Technology, Communication and Control, Environment, and Management (HNICEM), pages 1–5, Coron, Palawan, Philippines. IEEE.
Oliveira, J., Almeida, J., Macedo, D., and Nogueira, J. (2024a). Um framework NWDAF para algoritmos de análise de dados de rede 5G e além. In Anais do IV Workshop de Redes 6G, pages 9–14, Porto Alegre, RS, Brasil. SBC.
Oliveira, J. M., Almeida, J., De Britto e Silva, E., Rodrigues Moreira, L. F., Moreira, R., Silva, F. O., Macedo, D. F., and Nogueira, J. M. (2024b). Anomaly Detection Employing a 5G Core Data Analytics Framework. In 2024 IEEE 13th International Conference on Cloud Networking (CloudNet), pages 1–9.
Ribeiro, M., Grolinger, K., and Capretz, M. A. (2015). MLaaS: Machine Learning as a Service. In 2015 IEEE 14th International Conference on Machine Learning and Applications (ICMLA), pages 896–902, Miami, FL, USA. IEEE.
Rodrigues, L. F., Backes, A. R., Travençolo, B. A. N., and de Oliveira, G. M. B. (2022). Optimizing a Deep Residual Neural Network with Genetic Algorithm for Acute Lymphoblastic Leukemia Classification. Journal of Digital Imaging, 35(3):623–637.
Rodrigues, Moreira, L. F., Moreira, R., Travençolo, B. A. N., and Backes, A. R. (2023). An Artificial Intelligence-as-a-Service Architecture for deep learning model embodiment on low-cost devices: A case study of COVID-19 diagnosis. Applied Soft Computing, 134:110014.
Rodrigues Moreira, L. F. (2024). Artificial Intelligence as a Service Architecture: an innovative approach for Computer Vision applications. PhD thesis, Universidade Federal de Uberlândia, Uberlândia.
Rodrigues Moreira, L. F., Moreira, R., de Oliveira Silva, F., and Backes, A. R. (2024a). Towards Cognitive Service Delivery on B5G through AIaaS Architecture. In Anais do IV Workshop de Redes 6G, pages 1–8, Porto Alegre, RS, Brasil. SBC.
Rodrigues Moreira, L. F., Moreira, R., Martins, E. T., Jansen, V. F., Lima, Y. S., Rodrigues, L., Travençolo, B., and Backes, A. (2024b). Maximizing the power of cognitive services with an AI-as-a-Service architecture for seamless delivery. In 2024 IEEE 13th International Conference on Cloud Networking (CloudNet) (IEEE CloudNet 2024), page 8, Rio de Janeiro, Brazil. IEEE.
Rodrigues Moreira, L. F., Moreira, R., Travençolo, B. A. N., and Backes, A. R. (2025). Deep learning based image classification for embedded devices: A systematic review. Neurocomputing, 623:129402.
Rodrigues Moreira, L. F., Saar, L., Moreira, R., Rodrigues, L., Travençolo, B., and Backes, A. (2024c). Enabling intelligence on edge through an artificial intelligence as a service architecture. In 2024 IEEE 13th International Conference on Cloud Networking (CloudNet) (IEEE CloudNet 2024), page 8, Rio de Janeiro, Brazil. IEEE.
Shah, F., Anwar, A., ul Haq, I., AlSalman, H., Hussain, S., and Al-Hadhrami, S. (2022). Artificial Intelligence as a Service for Immoral Content Detection and Eradication. Scientific Programming, 2022:6825228.
Yao, T., Wang, J., Wan, M., Xin, Z., Wang, Y., Cao, R., Li, S., and Chi, X. (2022). VenusAI: An artificial intelligence platform for scientific discovery on supercomputers. Journal of Systems Architecture, 128:102550.
Zhang, W., Zeadally, S., Li, W., Zhang, H., Hou, J., and Leung, V. C. M. (2023). Edge AI as a Service: Configurable Model Deployment and Delay-Energy Optimization With Result Quality Constraints. IEEE Transactions on Cloud Computing, 11(2):1954–1969.
