IOT CATEGORIES
MOST POPULAR TAGS

Analytics




Episode 105

When talking AI in IoT what we’re really talking about is machine learning in IoT, and the one thing machine learning needs above all else, is data. Lot’s and lots of data. Structured IoT data, when piped in properly can be transformed and loaded efficiently for machine learning to create beautiful, and more important, accurate models.
Listen to this podcast (or read the transcript), where I speak with Anand Rao about the symbiotic relationship between AI and IoT...




Episode 103

Is it just semantics or is there a real difference between artificial intelligence (AI) and analytics; between machine learning (ML) and AI; between deep learning (DL) and ML, and between analytics and DL? Well, it depends on how detailed you want to go.
Listen to this podcast (or read the transcript), where I speak with Bret Greenstein about using AI in IoT and how it’s different from using analytics ...


Analyzing athlete data has been performed in high-level sports for years but it’s only recently that wearables and IoT could be realistically used to deliver useful information to athletes and coaches alike.
Watch this video (or read this transcript) to see Mounir Zok discuss how today’s wearables combined with state of the art Internet of Things technologies are advancing sport ...




Episode 79

There are two types of manufacturing: discrete manufacturing where the output is physical, countable things, and process manufacturing, where the output is chemistry – think oil & gas. Process manufacturing has been consistently instrumented for over two decades so it is not surprising that they’re a little ahead of their discrete counterparts on their path to IoT.
Listen to this podcast (or read the transcript) with Peter Zornio about IoT analytics in process manufacturing, and his advice is applicable to all industries ...




Episode 73

It seems like predictive analytics gets all the attention these days but generally speaking, it requires either a Data Scientist or a machine learning algorithm operating on lots of event data, in order to predict the all-important dimension of time, at least to any degree of useful certainty. Enter prognostic analytics. In a closed system of uniform conditions, prognostic analytics can make better predictions about the “when”.
Listen to this podcast (or read the transcript) with Moritz von Plate about how the characteristics of this older-school stats make it very well suited for predictive maintenance in Industrial IoT ...


Yeah, data analytics can be complicated, but its application doesn’t need to be. Take discrete manufacturing for example. There’s lots of hype around more advanced analytic applications like predictive maintenance but that’s running before you even know how to walk. I know it doesn’t sound as sexy, but let’s start with operational efficiency.
Watch this video (or read this transcript) to see William Sobel discuss data analytics in manufacturing and why to start easy before tackling sexy predictive maintenance ...


Big data analytics is generally answering questions about the past, whereas streaming analytics answers questions about the present. But what if you could bring the two together and answer questions about the present based on what happened in the past?
Watch this video (or read this transcript) to see Eric Tran-Le discuss a state of the art analytics ...




Episode 66

It takes a lot, and I mean a lot, to get me to download yet another app on my phone, especially one that’s going to try to sell me something… but, I’m open to Retail-IoT tech. I’m not much of a physical shopper, probably because I find the whole shopping experience so dreary, but this so called offline-online convergence within retail has piqued my interest.
Listen to this podcast (or read the transcript) where I speak with Oleg Puzanov about proximity marketing and where it’s headed with IoT ...


The key to value creation in the Internet of Things is the model. The model is used by both the app and analytics. It quantifies the value proposition, so the better the model, the higher the value. Developing these models in traditional markets is time consuming enough but given the volume, velocity and variety of IoT data, the load on the IoT data scientist can be overwhelming. Enter machine learning or ML for short. Machine learning can augment the skills of the data scientist by helping to select the algorithms or weighted ensemble of algorithms that provide the underlying structure for the model.
Watch this video (or read the transcript) video to see Rob Patterson discuss how machine learning is being used to help create and maintain Internet of Things models ...