In this episode of the IoT For All Podcast, we sat down with Ramya Ravichandar, VP of Products at Foghorn to talk about edge AI and how it ensures value for IIoT and commercial IoT deployments. We cover some of the use cases where edge AI really shines, how machine learning and edge computing enable real-time analytics, and how companies can ensure that their IoT deployments create real value on install.

Ramya has a decades experience in IoT and started in the industry at Cisco, where she headed its streamlining analytics platform. She has a rare combination of technical expertise in real-time analytics, machine learning, and AI, combined with a wealth of experience in Industrial IoT.

To start the episode, Ramya gave us some background on FogHorn. FogHorn was founded in 2014 to address the IoT data deluge at the edge, empowering industrial and commercial sectors to achieve transformational business outcomes through AI and ML capabilities at the edge.

Ramya also shared a couple of use cases to illustrate the power of edge AI when applied in an industrial setting, including the real-time identification of defects on the manufacturing floor, enabling operators to take action immediately to prevent product loss. Ramya said that this represents the fundamental premise of all of the solutions FogHorn is involved with.

One of the big differences over the past several years, Ramya said, was the level of education of customers. The customer journey has evolved alongside technology. Customers used to find it hard to find the use case, Ramya said, today, our customers are more savvy and knowledgeable. When they come to us they know exactly the problems they have and how they want to use IoT to address them. But the key to success, according to Ramya, was embracing the concept of a proof of value, rather than a proof of concept. If you dont have that spark in your first few deployments, youre probably working on the wrong use cases, Ramya said.

Ramya walked us through edge AI at its core and how it enables some of the key features that customers need. At its core, Ramya said that edge AI is about taking a step beyond data collection and applying models to incoming data to gain new insights. FogHorn seeks to be the bridge between the data science expertise companies already have and bringing that data into practice on the manufacturing floor.

She also spoke to the continued importance of the cloud and how it works together with edge computing and edge AI to create more powerful models. As an example, Ramya used a drilling rig. A drilling rig, she said, can generate up to a terabyte of data daily, but less than 1% of that data may end up being analyzed. Moving all of that data could take days, so being able to sort and parse that data at the edge is imperative to putting that data to work in real-time. And while edge computing and edge AI are imperative to that fast turnaround, the only place those models can be trained is in the cloud so, you have a model being trained and retrained in the cloud and pushed to each of those edge devices.

To wrap up the episode, Ramya walked us through some of the challenges FogHorn has faced while building its platform as well as what we can expect on the horizon for FogHorn.

Interested in connecting with Ramya? Reach out to her on Linkedin!

About FogHorn: FogHorn is a leading developer of intelligence edge computing software for industrial and commercial IoT application solutions. FogHorns software platform brings the power of advanced analytics and machine learning to the on-premises edge environment enabling a new class of applications for advanced monitoring and diagnostics, machine performance optimization, proactive maintenance, and operational intelligence use cases. FogHorns technology is ideally suited for OEMs, systems integrators and end customers in manufacturing, power and water, oil and gas, renewable energy, mining, transportation, healthcare, retail, as well as smart grid, smart city, smart building, and connected vehicle applications.

(02:01) Intro to Ramya

(02:54) Intro to Foghorn

(04:34) Do you have any use cases or customer journey experiences you can share?

(06:49) How does edge computing help organizations move their IIoT projects toward full deployment?

(08:32) How do edge computing and AI play into delivering ROI to these use cases?

(11:04) What role does edge AI play in enabling an IIoT solution? What are the benefits?

(13:05) How does your platform integrate into the cloud structure?

(16:46) How does edge computing help with real-time functionality and accelerating automation?

(20:20) As youve been developing this platform, what are some of the challenges you and your clients have encountered?

(23:06) What stage are your customers usually coming to you in?

(24:32) Is there a stage thats too early to get a company like FogHorn involved?

(26:00) How do you handle IoT devices or deployments that have a smaller footprint?

Read the original:

Foghorn's Ramya Ravichandar | Ensuring Value with Edge AI in IIoT Applications - IoT For All