We talk IoT – The Internet of Things Business Podcast

In this episode, we explore how accessible AI vision technology has become - and the surprising challenges that come with it. Luke Walsh from Brainboxes built an AI rock, paper, scissors game using open-source software and hardware costing under £1,000. The playful demo masks serious industrial applications: from catching defects in car seat stitching with 22 cameras to monitoring hazardous environments without putting maintenance engineers at risk. The conversation covers the technical realities of sub-200-millisecond latency, the stubborn resistance of factory maintenance teams, and why Overall Equipment Effectiveness (OEE) has been the missing piece in factory automation. Luke explains how vision systems can now replace invasive sensors, monitor quality without human inconsistency, and prove their worth to sceptical teams - one tote bin at a time. Tune in to learn why the best way to deploy AI in factories is to start small, prove value fast, and never assume your training data covers every possible hand gesture. #AI #computervision #manufacturing #opensource #bias #wetalkiot   Summary of this week's episode: 01:59 What Brainboxes does 05:43 How AI recognises hand gestures in under 200 milliseconds 08:42 Three reasons to choose open source: Latest models, trained engineers, community support 10:58 Real-world applications: Quality control and OEE 13:45 The car seat stitching use case: 22 cameras, one seat, zero tolerance 16:01 Beyond quality: Monitoring hazardous environments and non-invasive throughput measurement 17:39 Winning over sceptical maintenance teams 19:22 The tote bin story: When data settles a night shift dispute 20:35 The bias challenge: When "scissors" becomes a swearing gesture 23:08 The future of industrial AI vision systems and Jevons Paradox 25:13 Advice for manufacturers: Start small, keep it simple, nail first impressions   Show notes: Luke Walsh: https://www.linkedin.com/in/lukewalsh/ The Brainboxes white paper about the demo: https://www.brainboxes.com/white-papers/ai-vision-systems-demo   Listen to the "We Talk IoT" Soundtrack on: Spotify: https://open.spotify.com/playlist/05MOV4OV2MH2in2txsAGtG?si=ad08112cb8d443f4 YouTube: https://www.youtube.com/watch?v=D-NvQ6VJYtE&list=PLLqgVFfZhDRVYmpEqbgajzDvGL4kACRDp   About Avnet Silica: This podcast is brought to you by Avnet Silica—the Engineers of Evolution. Subscribe to our newsletters here: https://my.avnet.com/silica/resources/newsletter/ You can connect with us on LinkedIn: https://www.linkedin.com/company/silica-an-avnet-company/. Or find us at www.avnet-silica.com.

In this episode, we explore how engineers are embedding powerful AI directly into hardware – no cloud connection required. Michaël Uyttersprot from Avnet Silica and Cedric Vincent from Tria Technologies reveal how they run ChatGPT-quality language models on resource-constrained embedded devices. What once demanded data centre infrastructure now fits onto chips with just 2GB of RAM. The conversation covers the technical challenges of cramming billion-parameter models into embedded systems, real-world applications from conference rooms to industrial robotics, and the three compelling reasons driving this shift: data privacy, power efficiency, and cost control. Michaël and Cedric discuss hardware platforms from AMD, NXP, and Qualcomm, explain techniques like quantisation and mixture of experts, and demonstrate applications including a vintage telephone box that lets you call avatars from different time periods. Tune in to learn why the future of AI might not be in the cloud at all – and what that means for industries from manufacturing to healthcare. #AI #LLM #embeddedsystems #IoT #privacy #wetalkiot   Summary of this week's episode: 02:48 What makes large language models special 05:27 Why run LLMs locally on embedded devices 07:42 Real-world applications: Vision LLMs and OCR 11:12 Technical deep dive: How to fit billions of parameters into tiny devices 18:52 Understanding temperature: Making AI creative or accurate 22:41 Industries moving fastest: OCR, security, and robotics 24:52 Future applications: Robotic arms and time series analysis 28:00 The biggest technical hurdle: Power consumption 30:55 Advice for engineers: Start with llama.cpp   Show notes: Michaël Uyttersprot: https://www.linkedin.com/in/micha%C3%ABl-uyttersprot-aaa971211/ Cedric Vincent: https://www.linkedin.com/in/cedric-vincent-19222910/ Tria Technologies: https://www.tria-technologies.com/   Generative AI at the Edge: https://my.avnet.com/silica/solutions/technologies/artificial-intelligence/generative-ai/ The podcast episode where the generative AI examples where discussed: https://www.podbean.eu/ep/pb-9juiy-d4dec4 How to enhance embedded systems with Generative AI and Local LLMs | Michael Uyttersprot at HWPMAX25: https://www.youtube.com/watch?v=wL9g2wJ1a7c   Listen to the "We Talk IoT" Soundtrack on: Spotify: https://open.spotify.com/playlist/05MOV4OV2MH2in2txsAGtG?si=ad08112cb8d443f4 YouTube: https://www.youtube.com/watch?v=D-NvQ6VJYtE&list=PLLqgVFfZhDRVYmpEqbgajzDvGL4kACRDp The Llama song: https://youtu.be/JavZh3y1ue0   About Avnet Silica: This podcast is brought to you by Avnet Silica — the Engineers of Evolution. Subscribe to our newsletters here: https://my.avnet.com/silica/resources/newsletter/ You can connect with us on LinkedIn: https://www.linkedin.com/company/silica-an-avnet-company/. Or find us at www.avnet-silica.com.

In this episode, we explore a hidden crisis affecting thousands of buildings worldwide with Martin Mentzel, CEO of the German company Safesquare. For thirty years, Local Operating Network (LON) technology has quietly powered building automation systems in hospitals, office buildings, and transport infrastructure. Now, critical components face end-of-life as manufacturers discontinue essential neuron chips, leaving companies scrambling for solutions. Some companies need 8,000 replacement controllers per year that simply don't exist. Hospital operating rooms, lift systems, and building HVAC networks all depend on technology becoming impossible to maintain. Martin discusses how Safesquare's babi-LON platform replaces discontinued components without forcing expensive system redesigns. We examine why LON technology has endured for three decades, the scale of the component shortage crisis, and how innovative engineering preserves critical infrastructure investments. Tune in to discover how one company transforms an industry crisis into an opportunity whilst keeping essential systems running. #LON #buildingautomation #infrastructure #iot #wetalkiot   Summary of this week's episode: 01:38 Understanding Local Operating Networks (LON) in Building Automation 03:36 The Component Shortage: A Deep Dive 06:52 Safesquare's Solution 08:06 Challenges and Costs of System Redesign 14:16 Safesquare's Journey and Vision 23:18 Future of LON Technology in Building Automation   Show notes: Safesquare: https://safesquare.eu/ Webinar: https://gateway.on24.com/wcc/eh/2397559/lp/5053037/babi-lon-for-building-automation-safesquare?partnerref=podcast Listen to the "We Talk IoT" Soundtrack on: Spotify: https://open.spotify.com/playlist/05MOV4OV2MH2in2txsAGtG?si=ad08112cb8d443f4 YouTube: https://www.youtube.com/watch?v=D-NvQ6VJYtE&list=PLLqgVFfZhDRVYmpEqbgajzDvGL4kACRDp About Avnet Silica: This podcast is brought to you by Avnet Silica—the Engineers of Evolution. Subscribe to our newsletters here: https://my.avnet.com/silica/resources/newsletter/ You can connect with us on LinkedIn: https://www.linkedin.com/company/silica-an-avnet-company/. Or find us at www.avnet-silica.com.

In this episode, we explore the remarkable growth of LoRaWAN with Alper Yegin, CEO of the LoRa Alliance. This non-profit consortium has spent a decade building the world's most successful long-range, low-power network standard outside China. With 350 members, including Amazon, Comcast, Verizon, and Airbus, the Alliance has created technology that now connects 125 million devices globally - from temperature sensors in over half of North America's Starbucks stores to tracking collars on endangered black rhinos across 35 African national parks. Alper discusses how LoRaWAN achieves ranges up to 600 kilometres whilst consuming as little power as a garage door opener, why major enterprises choose between public and private networks, and how satellite integration creates planet-wide IoT coverage. We explore real-world deployments that save lives and bottom lines, including 700,000 panic buttons across North American schools and hospitals and 5 million water meters across France. Learn why this open-standard technology has outpaced competitors like NB-IoT and Sigfox, and how AI and edge computing are shaping the future of industrial IoT. #lorawan #iot #lpwan #smartbuildings #satellite #wetalkiot #connectivity #iiot #sustainability   Summary of this week's episode: 01:34 The Journey and Achievements of LoRa Alliance 02:22 Why LoRaWAN is Ideal for Enterprise IoT 06:55 Comparing LoRaWAN with Other Technologies 15:05 Real-World Use Cases of LoRaWAN 19:43 Environmental Innovations 22:23 Challenges in IoT Integration 26:05 The Future of IoT with AI and Edge Computing 29:43 Public vs. Private Networks 33:30 Collaborative Ecosystem and Open Standards   Show notes: Alper Yegin: https://www.linkedin.com/in/alperyegin/ LoRa Alliance: https://lora-alliance.org/ Episode 34: How IoT Protects Forest and Combats Climate Change: https://www.podbean.eu/ep/pb-64tnj-d4d765   Listen to the "We Talk IoT" Soundtrack on: Spotify: https://open.spotify.com/playlist/05MOV4OV2MH2in2txsAGtG?si=ad08112cb8d443f4 YouTube: https://www.youtube.com/watch?v=D-NvQ6VJYtE&list=PLLqgVFfZhDRVYmpEqbgajzDvGL4kACRDp About Avnet Silica: This podcast is brought to you by Avnet Silica—the Engineers of Evolution. Subscribe to our newsletters here: https://my.avnet.com/silica/resources/newsletter/ You can connect with us on LinkedIn: https://www.linkedin.com/company/silica-an-avnet-company/. Or find us at www.avnet-silica.com.

In this episode, we explore the future of kitchen efficiency with David Riding from Heatle, a Berlin-based startup revolutionising how we heat liquids through smart induction technology. Heatle has developed an innovative smart heating system that uses magnetic induction and IoT connectivity to heat liquids directly in their containers, promising energy savings of up to 80% compared to traditional kettles. The system learns user patterns, integrates with smart home ecosystems, and opens new possibilities for subscription-based business models around energy data. David discusses the journey from aerospace engineering to solving fundamental power electronics problems that previous startups couldn't crack. We explore the technical breakthrough that enabled Heatle to surpass the 300-watt power barrier, the role of energy harvesting in their temperature sensors, and how NFC technology simplifies user interaction. From Bialetti coffee pots with automatic temperature control to smart hot water bottles, discover how IoT transforms everyday heating into precision experiences. We examine the challenges of marketing to diverse customer segments, the importance of listening to user feedback, and the transition from startup to full European production. Tune in to learn how hardware innovation, customer collaboration, and smart technology integration create new business opportunities in the connected kitchen ecosystem. #induction #heating #iot #smartkitchen #energyefficiency #wetalkiot Summary of this week's episode: 01:46 Meet David Riding and Heatle's Origin Story 03:47 Why Kettles? The Energy Waste Problem 05:33 How Induction Heating Works vs Traditional Kettles 09:10 Breaking the 300-Watt Power Barrier 15:30 NFC Technology and Smart Tea Integration 19:26 Expanding Use Cases: Bialetti Coffee Pots and Beyond 22:35 Smart Home Integration Strategy 24:40 Data Analytics and German Privacy Standards 26:29 Software Updates and Customer Feedback Loops 32:36 Enterprise Integration: Kitchen Counters and Commercial Applications 35:59 Soundtrack Selection: From James Lavelle to Canned Heat Show notes: David Riding: https://www.linkedin.com/in/david-riding-engineer/ Heatle: https://heatle.de/   Listen to the "We Talk IoT" Soundtrack on: Spotify: https://open.spotify.com/playlist/05MOV4OV2MH2in2txsAGtG?si=ad08112cb8d443f4 YouTube: https://www.youtube.com/watch?v=D-NvQ6VJYtE&list=PLLqgVFfZhDRVYmpEqbgajzDvGL4kACRDp About Avnet Silica: You can connect with us on LinkedIn: https://www.linkedin.com/company/silica-an-avnet-company/. Or find us at www.avnet-silica.com.Subscribe to our newsletters here: https://my.avnet.com/silica/resources/newsletter/