Embedded IoT World, is a virtual event on April 28 – 29 that is designed for developers, architects, engineers, and technicians building end-to-end IoT solutions. The embedded community will have the opportunity to join technical workshops, roundtables, and speaker Q&A covering key topics: AI & ML, Security, Edge Computing, Industrial IoT, Connectivity, and Processors/Enablement. Delivered by industry experts, conference sessions will help you design and develop embedded systems to fuel the future of IoT.
LF Edge is a media partner of Embedded IoT World and will be represented by EdgeX Foundry and Home Edge.
On April 29 at 9:15 am, Jim White, Chair of the EdgeX Foundry Technical Steering Committee and CTO of IOTech, will participate in a panel discussion about “The relationship between connectivity, edge computing, AI and machine learning in embedded systems” with Aditya Kumar, Facebook; Colleen Josephson, Stanford University; and Edoardo Gallizio, STMicroelectronics.
On April 29 at 10:40 am, Suresh LC, one of the leaders of Home Edge from Samsung, will give a presentation about Intelligent Smart Home Work Distribution.
With more and more homes become smart and IoT devices become powerful, most cloud computing jobs can be shifted inside the home, saving the user on privacy and latency. When heavier AI models are deployed on IoT Devices, Data Parallelism using multiple devices minimizes the latency further. Models behave differently on different devices due to a variety of factors, some being user-based, others being device-specific. Analysis of these patterns helps identify the best devices for specific models. In a smart home scenario ‘device churn’ on powerful devices like mobiles is a factor that needs to be considered using a cost-benefit analysis to prevent any device currently in use from churning out.
We propose a heuristic-based methodology for tracking and using “user-device interaction patterns”, “Model Specific device behaviours” and “Static and Dynamic device capability scores” to estimate runtimes of models on various devices. Using the Estimates of time and Churn probability of devices selecting best devices and distributing data in the most optimal way to get the overall fastest response times. The technique also proposed a self-learning process for the system to become better over time, with the flexibility of adding and removing devices dynamically.
Suresh will also be taking questions during the AI and ML Speaker Q&A at April 29 at 1:55 pm.
For more information about the conference, visit the main conference page.
