search.noResults

search.searching

saml.title
dataCollection.invalidEmail
note.createNoteMessage

search.noResults

search.searching

orderForm.title

orderForm.productCode
orderForm.description
orderForm.quantity
orderForm.itemPrice
orderForm.price
orderForm.totalPrice
orderForm.deliveryDetails.billingAddress
orderForm.deliveryDetails.deliveryAddress
orderForm.noItems
Supplement: Semiconductors


AI will marry the IoT to data analytics


You should really be thinking about AI for your next generation wireless product before your competitors beat you to it, explains Kjetil Holstad, EVP strategy & product management, Nordic Semiconductor


A


rtificial intelligence (AI) and machine learning (ML) in the Internet of things (AIoT) can turn an IoT application from useful to incredibly valuable, if


not invaluable by making it indispensable in a vitally necessary way.


There is no question that AI and ML is going to push the IoT towards being much more intelligent, useful and powerful. And enable new categories and classes of application that were previously unthinkable.


But traditionally AI and ML meant data processing. Lots of data processing. And this meant lots of compute power and high energy consumption. And this is what has traditionally made it almost impossible to combine any kind of AI and ML with the resource-constrained devices typical of the IoT. Let alone battery- powered ones. The solution comes in the form


44 May 2024


of a stripped-down, highly optimized form of AI called tiny machine learning (or TinyML). TinyML is not brand new. It is already making strides all around us. For example, TinyML is a feature of digital services triggered by ‘wake words’ such as the popular virtual assistants Siri and Alexa. But using a smartphone’s main processor to continuously listen for a wake word would be a major drain on the battery. Instead, a separate low power processing device remains continuously vigilant. A TinyML algorithm listens for the specific sound frequencies making up a wake word and, on hearing them, wakes up the smartphone - saving on vital battery power.


AIoT takes ‘nice have’ to ‘must have’ Consider a consumer health and fitness wearable. This can be used to measure your steps, calories burned, heart rate


Components in Electronics


or electrocardiogram (ECG), and sleep patterns, and other physiologically important parameters. Before the advent of wearables, this kind of data has never previously been freely available to consumers in such a convenient and flexible device. Add AI into the mix and that same wearable enters an entirely new league of capabilities and accuracy. Now you have the foundations for a medical wearable that could monitor several vital signs simultaneously. And recognize a ‘red light’ combination of sensor data that could be used to immediately signal and even pre-diagnose a serious medical emergency. An example might be a sudden change in blood oxygen level, heart rate, blood pressure, and breathing which indicates the onset of a cardiac event. By using AI, the user suddenly has a wearable that becomes a 24/7 medical tool.


One that is also critically useful for first responders because it could enable them to arrive pre-equipped for a given diagnosis. This could slash vital time, potentially life-saving seconds, from delivering critical care. By combining low power AI and precise data analytics we suddenly have a transformative medical monitoring product that could optimise stretched healthcare budgets and, above all else, save lives.


Everything happens at the edge In the early days of the IoT there was a notion that everything would revolve around big data: both in its collection from millions of sensors, and its analysis in the Cloud. But it very quickly became clear this approach was a technical and commercial non-starter. Sending vast amounts of raw unfiltered data up the Cloud was time-consuming and


www.cieonline.co.uk


Page 1  |  Page 2  |  Page 3  |  Page 4  |  Page 5  |  Page 6  |  Page 7  |  Page 8  |  Page 9  |  Page 10  |  Page 11  |  Page 12  |  Page 13  |  Page 14  |  Page 15  |  Page 16  |  Page 17  |  Page 18  |  Page 19  |  Page 20  |  Page 21  |  Page 22  |  Page 23  |  Page 24  |  Page 25  |  Page 26  |  Page 27  |  Page 28  |  Page 29  |  Page 30  |  Page 31  |  Page 32  |  Page 33  |  Page 34  |  Page 35  |  Page 36  |  Page 37  |  Page 38  |  Page 39  |  Page 40  |  Page 41  |  Page 42  |  Page 43  |  Page 44  |  Page 45  |  Page 46  |  Page 47  |  Page 48  |  Page 49  |  Page 50  |  Page 51  |  Page 52  |  Page 53  |  Page 54  |  Page 55  |  Page 56  |  Page 57  |  Page 58  |  Page 59  |  Page 60  |  Page 61  |  Page 62  |  Page 63  |  Page 64