Seeing Further into IoT Data with Machine Learning

Seeing Further into IoT Data with Machine Learning

Episode 106

Through its different techniques, machine learning allows us to look deep into our IoT data, giving us the hindsight, insight and foresight we need to transform that data into useful information, and ultimately value.  But what’s the mechanism to do that?  In this episode of the IoT business show I speak with Vish Pai about the relationship between ML and the IoT platform.

In this episode of the IoT Business Show, I speak with Vish Pai about the relationship between ML and the IoT platform.

Vish leads Samsung’s ARTIK end-to-end IoT Cloud Platform as a Director of Product Management – managing product portfolios including cloud services, analytics and applications. Vish also has over 10 years of experience working in Fortune 500 companies and growth-stage start-ups.

The IoT platform is enigmatic.  At its most basic self, it’s plumbing – middleware to move data from its sources (internal and external) to the application and analytics where it’s transformed into useful information.  Going beyond basic connectivity platforms are provisioning platforms, mostly used in cellular and LPWA use cases.  And then there are AEPs or Application Enablement Platforms.  AEPs also include an application development environment custom built to work with the middleware.  A subset of AEPs also provide an analytic development environment that interface with the most popular analytic scripting languages such as R and Python.  Some go further and include point and click interfaces for analytics, ranges from simple rules engines to more sophisticated machine learning tools that allow informed users to develop and then deploy ML on their data.  This is where the value is in IoT platforms.  The plumbing will eventually be commoditized but anything that enables the application and/or analytics and/or ML, is central to the success of any IoT platform buyer.

Here’s What We’ll Cover in this Episode

  • The definition of AI and how it is different from analytics.
  • The four phases in the spectrum of machine learning (ML).
  • Differences between Narrow AI and General AI.
  • The machine learning framework Samsung uses for its customers.
  • The change in the users of ML.
  • How to incorporate ML into your product.
  • A framework for choosing the right ML modeling technique.

Mentioned in this Episode and Other Useful Links

Support this Podcast

If you have been enjoying this podcast, there are a few ways you can support it:

  1. Share it on social by clicking on the widget on the left or bottom of the page.
  2. Click here to open iTunes and leave a one-click review or write your thoughts.
  3. Consider becoming a Certified IoT Professional by enrolling in the ICIP online training program.


Ways to Subscribe to the IoT Business Show

Like what you hear?  Subscribe to get each episode delivered to your device via iTunes, SpotifyGoogle PlayStitcher Radio or RSS (non-iTunes feed).

Have an opinion? Join the discussion in our LinkedIn group

What’s your experience with AI/ML as part of the IoT platform?