Smart City Gnosys

Smart city article details

Title	Ai-Optimized Hardware Design For Internet Of Things (Iot) Devices
ID_Doc	7082
Authors	Vishnu Kumar P.; Kulkarni A.; Mendhe D.; Keshar D.K.; Tilak Babu S.B.G.; Rajesh N.
Year	2024
Published	5th International Conference on Recent Trends in Computer Science and Technology, ICRTCST 2024 - Proceedings
DOI	http://dx.doi.org/10.1109/ICRTCST61793.2024.10578352
Abstract	The Internet of Things (IoT) has emerged as a transformative paradigm, connecting billions of devices to the Internet and enabling seamless communication and data exchange. As the IoT ecosystem continues to expand, there is an increasing demand for energy-efficient, high-performance hardware tailored to the unique requirements of AI-powered applications deployed on IoT devices. This research focuses on the design and optimization of hardware architectures to meet the computational demands of AI algorithms in IoT environments. The proposed AI-optimized hardware design leverages the latest advancements in semiconductor technology and integrates specialized processing units for efficient execution of machine learning tasks. The architecture is tailored to address the constraints of IoT devices, including limited power resources, stringent size constraints, and the need for real-time processing. Key components of the design include low-power processors, hardware accelerators, and memory hierarchies optimized for AI workloads. Additionally, the system employs advanced algorithms for task offloading and distributed processing, enabling collaborative and energy-efficient execution of AI tasks across a network of interconnected IoT devices. The proposed AI-optimized hardware design is evaluated through simulations and real-world experiments, demonstrating superior performance in terms of energy efficiency, processing speed, and scalability. The results showcase the potential of the designed hardware to unlock new possibilities for AI applications in diverse IoT scenarios, ranging from smart cities and industrial automation to healthcare and environmental monitoring. The proposed research serves as a foundation for the development of next-generation IoT devices capable of seamlessly integrating AI capabilities while meeting the stringent requirements of the IoT ecosystem. © 2024 IEEE.
Author Keywords	Custom Hardware Accelerators; Edge Computing; Hardware-Software Co-design; Low-power Design; Memory Optimization; Neural Processing Unit (NPU); Quantum Computing; Security and Privacy; Sensor Fusion

Similar Articles

Id	Similarity	Authors	Title	Published
6706	0.877	Pazmiño Ortiz L.A.; Maldonado Soliz I.F.; Guevara Balarezo V.K.	Advancing Tinyml In Iot: A Holistic System-Level Perspective For Resource-Constrained Ai	Future Internet, 17, 6 (2025)
6522	0.86	Dhanalakshmi M.; Nand Kishor Kumar G.; Himabindu G.; Gosavi V.R.; Sundar Ganesh C.S.; Premanand R.	Advanced Machine Learning Innovations In Embedded Systems And Narrowband Internet Of Things (Nb-Iot) Devices	Integrating Artificial Intelligence Into the Energy Sector (2025)
10471	0.858	Thillaiarasu N.; Tripathi S.L.; Dhinakaran V.	Artificial Intelligence For Internet Of Things: Design Principle, Modernization, And Techniques	Artificial Intelligence for Internet of Things: Design Principle, Modernization, and Techniques (2022)
5918	0.854	Mohammadi Makrani H.; He Z.; Rafatirad S.; Sayadi H.	Accelerated Machine Learning For On-Device Hardware-Assisted Cybersecurity In Edge Platforms	Proceedings - International Symposium on Quality Electronic Design, ISQED, 2022-April (2022)
7584	0.852	Yugank H.K.; Sharma R.; Gupta S.H.	An Approach To Analyse Energy Consumption Of An Iot System	International Journal of Information Technology (Singapore), 14, 5 (2022)
34110	0.85	Agnihotri P.; Luthra M.; Rodriguez M.; Koldehofe B.	Iot-Opt: The Swiss Army Knife To Model And Validate The Performance Of Iot Products	Middleware 2022 - Proceedings of the 23rd International Middleware Conference Demos and Posters, Part of Middleware 2022 (2022)