We talk IoT – The Internet of Things Business Podcast

Two billion people worldwide lack access to safe drinking water. Traditional pH monitoring relies on slow, manual lab testing – often too late to prevent contamination. In this episode, Fabrizio Librizzi, Senior Product Marketing Manager at NXP Semiconductors, explains how edge AI and analogue front-end technology are transforming water quality monitoring.

Fabrizio discusses how NXP’s AI-assisted pH sensors provide real-time, rugged, and reliable data at the source – eliminating cloud dependency and enabling equity for remote communities. We explore real-world applications in agriculture (protecting crops from pH damage), municipal water systems (transparency for citizens), and industrial processes (cost savings through precise chemical dosing).

Tune in to learn why edge AI is moving beyond vision and voice into environmental monitoring, and how this technology can genuinely improve lives.

 

#AI #EdgeAI #WaterQuality #IoT #NXP #WeTalkIoT #Sustainability

 

Summary of this week's episode:

01:30 The global water crisis and the limitations of traditional pH monitoring

03:45 How analogue front ends convert delicate sensor signals into robust digital data

06:20 Why edge AI is critical for remote areas with intermittent connectivity

08:10 Real-world use cases: Agriculture, municipal water, and industrial applications

10:30 The role of machine learning in spotting pollution patterns and anomalies

12:45 Technical challenges: Surge protection, probe maintenance, and multi-sensor integration

15:00 Advice for water authorities: Start small, validate data, and scale with connectivity

17:30 The future of AI in environmental monitoring—beyond pH levels

 

Show notes:

Fabrizio Librizzi: https://www.linkedin.com/in/fabrizio-librizzi/

Enhancing water quality with AI-assisted pH monitoring: https://www.nxp.com/company/about-nxp/smarter-world-blog/BL-MGZN-ENH-WAT-QUAL-AI-PH-MON

 

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

The EU Cybersecurity Resilience Act is keeping OEMs awake at night. How do you use free and open-source software whilst complying with new obligations around vulnerability management, supply chain transparency, and continuous support?

In this episode, Pierre Gal (Head of Product) from Witekio and Michael Röder (Senior Manager, Software and Services EMEA) from Avnet Silica tackle the urgent questions facing manufacturers: Who counts as a manufacturer under the CRA? What documentation must you maintain? And how do you manage vulnerabilities in components you didn't create?

Pierre explains how Witekio's Embedded Kit provides off-the-shelf solutions based on open-source software like Yocto Linux, helping customers navigate composition, integration, and compliance. Michael shares what he's hearing from customers struggling to interpret regulatory requirements and implement risk-based approaches.

From SBOM (Software Bill of Materials) to supply chain attacks, from secure by default to continuous vulnerability management, we explore the practical realities of making compliance work. The conversation cuts through the confusion to deliver actionable advice: understand your responsibilities, think in terms of composition, and don't wait for a magic bullet.

Tune in to learn how to leverage the power of open-source software whilst meeting your CRA obligations – because "free as in freedom" doesn't mean free from responsibility.

#CRA #cybersecurity #opensource #FOSS #compliance #IoT #wetalkiot

 

Summary of this week's episode:

04:14 Key Dates and Obligations of the CRA

05:27 Challenges Faced by Manufacturers

10:10 The Role of Open Source in CRA Compliance

19:58 The Concept of Software Bill of Materials (SBOM)

22:14 Real-World Example: Casino Attack Case Study

23:28 Documentation and Configuration Issues

24:04 Cybersecurity Layers and CRA Methodology

24:25 Secure by Default and Advanced Concepts

26:50 Implementation and Standard Processes

29:45 Quality, Testing, and Automation

31:53 Vulnerability Management Methodology

37:18 Critical Mistakes to Avoid with CRA

39:36 Supply Chain Attacks

 

Show notes:

Pierre Gal (Witekio): https://www.linkedin.com/in/pierre-gal/

Michael Röder (Avnet Silica): https://www.linkedin.com/in/roednix/

Securing the Future: Understanding the Cyber Resilience Act - We talk IoT #55: https://www.podbean.eu/ew/pb-8kkkd-d4ddfc

 

EU Cybersecurity Resilience Act: https://digital-strategy.ec.europa.eu/en/policies/cyber-resilience-act

National Vulnerability Database (NVD): https://nvd.nist.gov/

 

OWASP Top 10: https://owasp.org/www-project-top-ten/

 

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 an Emmy Award-winning video codec is transforming industries far beyond the silver screen.

Dr. Siegfried Fößel from Fraunhofer IIS explains how JPEG XS – a compression standard designed for broadcast production – now enables breakthrough applications in autonomous vehicles, industrial automation, and remote healthcare.

With a latency of just 32 lines end-to-end and visual lossless quality, JPEG XS solves a critical challenge: how to process high-resolution video in real time without introducing delay. When autonomous cars need to analyse multiple camera feeds in real time, when factory robots require split-second reactions, or when surgeons control remote instruments, every millisecond matters.

Siegfried discusses the journey from keyboard-video-mouse extenders to ISO standardisation, the technology's adoption in sports broadcasting, and why tier-one automotive suppliers are testing it for sensor fusion. We explore how the codec integrates into FPGAs for embedded cameras, its constant bitrate advantage for IP transmission, and the future of AI-based video compression.

Tune in to discover how low-latency video compression unlocks applications that weren't possible before – and what's coming next in the race to process visual data faster.

#jpegxs #automotive #machinevinevision #healthcare #compression #fraunhofer #iot #wetalkiot

 

Summary of this week's episode:

01:30 What is JPEG XS and why it matters beyond broadcast

02:53 How JPEG XS differs from other codecs

03:39 The origin story: From KVM extender to ISO standard

05:00 The trade-off: Compression ratio vs latency

06:47 Autonomous vehicles: Processing 10 cameras without loss

08:27 Beyond self-driving: Electronic mirrors and driver monitoring

09:42 Industrial automation: Real-time quality control and robotics

11:25 Factory integration: FPGA IP cores and embedded cameras

12:53 ISO standardisation and software development kits

14:14 Healthcare applications: Edition 3's lossless approach

15:49 Remote surgery possibilities

18:50 Implementation advice: When to choose JPEG XS

20:33 Looking ahead: AI-based video codecs at 10 kbit/s

22:43 The constant bitrate advantage

 

Show notes:

Dr. Siegfried Fößel: https://www.linkedin.com/in/siegfried-foessel-a158574/

JPEG XS: https://www.iis.fraunhofer.de/en/ff/amm/content-production/jpegxs.html

Emmy Award announcement: https://www.iis.fraunhofer.de/en/pr/2025/pressrelease-emmy-jpegxs.html

 

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.

Artificial intelligence is moving to the edge - and it's changing how factories operate, farms grow crops, and robots navigate the world.

In this episode, Monica Houston from Tria Technologies walks us through Tria's Vision AI Kit 6490, an industrial-grade edge computing board that processes five camera feeds simultaneously, runs inference locally, and handles demanding tasks like image segmentation - all without needing cloud connectivity or even a cooling fan.

Monica discusses real-world deployments in agriculture (spot-treating crops to reduce pesticide use), factory robotics (autonomous mobile robots and robotic arms), and the practical challenges of moving AI from comfortable data centres to harsh industrial environments. We explore why latency matters, what happens when you can't rely on internet connections, and why power efficiency is the unsung hero of edge AI.

If you've wondered whether edge AI is ready for industrial prime time, this conversation delivers the answer - with hardware in hand.

#EdgeAI #IndustrialIoT #Robotics #Agriculture #Qualcomm #WeTalkIoT

 

Summary of this week's episode:

01:57 Monica's Background at Hackster.io and Tria Technologies

02:38 What the Vision AI Kit Actually Does

04:01 Why Edge Processing Matters for Robotics

07:46 Agricultural Use Cases: Spot-Treating Crops

09:55 Autonomous Vehicles and VSLAM Technology

12:32 Factory Floor vs Self-Driving Cars

14:09 Real-World Deployment: Robot Arms in Action

16:44 ROS 2 and Robotics Applications

17:36 Edge Impulse: Making Model Deployment Easier

19:08 The 15-Year Lifecycle Question

22:18 Power Efficiency: Why No Fan Matters

 

Show notes:

Monica Houston: https://www.linkedin.com/in/houstonmonica/

How the Vision AI Kit 6490 could be used for agriculture:https://www.globalagtechinitiative.com/digital-farming/ai-takes-center-stage-in-agriculture/

 

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 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.