Explore recent advancements in machine learning applied to Internet of Things (IoT) in this 33-minute video presentation by Adam McElhinney. Gain insights into the challenges and opportunities presented by the proliferation of sensor technologies and connected machines. Discover the state of machine learning in IoT and industrial equipment applications, including failure prediction and prognostics. Learn about the differences between physics-based and data-driven approaches to IoT, and understand the unique challenges of applying data-driven methods. Examine a real-world case study demonstrating the application of deep learning, gradient boosting, transfer learning, and other machine learning techniques in IoT contexts. Delve into topics such as fleet management, on-time in-fill shipping, and the value of prognostics. Address challenges related to connectivity, unreliable failure and repair data, dispersed failures across various types, and large quantities of signal data. Explore the strengths of neural networks and transfer learning in overcoming sensor limitations. Gain valuable insights into future research opportunities and potential enhancements in the field of machine learning for IoT applications. Read more