There is a mismatch between IT and OT that sometimes ends in a real Clash of the Clans. Have you noticed that OT people consider IoT to be an IT thing, while IT people consider IoT to be from OT land? Could IoT be the missing link that will reunite the clans? David Ariens, co-creator of the @TheITOTInsider podcast 🎙️ and blog, joins me on the IoT Show to answer this question. 🔗 Checkout the IT/OT Insider sub 👉 https://itotinsider.substack.com 🧑‍🎓 Learn more at the IT/OT Academy 👉 https://itot.academy/ 📚 Chapters 00:00 IT/OT Clash Intro 02:26 Lacking Concepts 04:21 Different Language 06:01 Common Language ️ 07:41 Vertical Differences 09:46 Data: Most Important ℹ️ 11:38 Water World Example 13:27 Data Unification Steps 15:36 Time Series Storage 17:18 Factory Floor Uniqueness 18:59 Data Ops Necessity 20:40 Platform Development 22:37 Software Approach 24:47 Data Driven 26:53 Digital Transform ️ 29:27 Data Ops Platform 31:28 Peace Between IT/OT ️ Powered by https://timeskip.io/?ref=olivier

Dr. Andreas Savvides started his career over a couple of decades ago at Yale, leading research on wireless sensor networks, embedded systems, and sensor-driven applications for energy efficiency, security and healthcare. He rapidly realized the commercial potential of IoT and Edge AI and went on creating a SaaS energy analytics platform before many. Passionate about technology, he joined Cognex in 2018 to lead the company's edge intelligence efforts. Suffice it to say: Andreas knows a thing or two about Vision AI and its applications in the industry and shares with us a unique perspective on how far Edge AI has come, where it's going and how fast. 🔗 Learn more about Cognex: https://www.cognex.com 🤝 Connect with Andreas: https://www.linkedin.com/in/andreasgsavvides 📚 Chapters 00:00:00 - Vision AI Intro 00:01:02 - IoT Show Begins 00:02:06 - Four Key Things 00:02:59 - Vision at Scale ️ 00:03:55 - Cognitive Decline 00:04:37 - Technology Shifts 00:05:33 - Exciting AI Time 00:06:16 - Visiting Cognex 00:07:05 - Parsing Sensor Data 00:08:20 - Edge Reliability ️ 00:08:54 - Lower Edge AI Cost 00:09:37 - Richer Sensors Now 00:10:33 - Agentic AI Impact 00:11:18 - Insights and AI Powered by https://timeskip.io/?ref=olivier

Many IoT devices run on batteries for obvious reasons (remote and mobile location, critical enough to not rely on grid power only, you name it). But batteries have shortcomings: they have a limited lifespan, you need to constantly minimize energy consumption, hence reducing what can be done, which limits the hardware choices as well... More and more IoT devices manufacturers are considering and adopting energy harvesting solutions such as solar, allowing their devices to generate energy from their environment. This is known as Ambient IoT. It's becoming even more important to consider energy production and consumption holistically (tech, cost, AI, ...), it is a system problem, not a component one. And for that you need the right tools. With Jeff Crystal from Voltaic and Björn Rosqvist from Qoitech we delve into the fascinating new world of ambient IoT, discussing considerations, pitfalls, tooling, and more. 🔗 Learn more at https://www.qoitech.com/ and https://voltaicsystems.com/ 🙏 This episode is powered by IoT Stars https://iotstars.com 📚 Chapters 00:00:00 - IoT & Batteries 00:01:29 - Energy Harvesting 00:03:09 - Battery Shortcomings 00:04:54 - Ecological Waste ️ 00:06:57 - Power Management IC ️ 00:09:05 - System Stress 00:10:33 - Solar Power Efficiency ️ 00:12:24 - Energy Harvesting Example 00:15:24 - Renewable Energy Advantages 00:17:11 - Software Optimization Role 00:18:48 - Software Updates Importance ⬆️ 00:21:03 - Data Transmission Costs ️ 00:22:37 - Embedded Developer Tools 00:24:25 - Lower Power Benefits 00:26:12 - Device Design Factors 00:28:14 - Ambient Energy on IoT Powered by https://timeskip.io/?ref=olivier

Is ISA-95 obsolete? Is UNS the next step forward for Industrial data? How does the future of MES look like? Should we also consider a broader adoption of open-source technologies? That's some of the questions we are trying to answer on this new episode of the IoT Show with Alexander Krüger, Co-founder and CEO at United Manufacturing Hub (UMH) and long timer in the business of normalizing industrial data. Learn more at https://learn.umh.app/ 📚 Chapters (Powered by https://timeskip.io/?ref=olivier) 00:00:00 - IoT Data Unification 00:01:52 - Alexander's Background ️ 00:03:35 - U-MAGE Context 00:05:14 - Solving Data Challenges 00:07:13 - Unifying Data Sources ️ 00:08:36 - ISA-95 & UNS Explained 00:09:59 - ISA-95 Compatibility 00:11:56 - Hardware Specifics Removal ️ 00:13:43 - Data Security Benefits ️ 00:14:59 - UNS: Modern Path Forward? 00:16:21 - Underlying Protocol Impact 00:18:18 - Future of MES Perspective 00:19:47 - IoT Platforms Evolution 00:21:03 - Open Source Alternatives 00:22:46 - Open Source Culture Shift 00:24:17 - Learn More and Engage

Like with any other technology, you must be practical when you start with Edge AI. Bringing AI to the Edge has a lot of promise but also requires a lot of consideration. Mahmood Afshari, Business Manager at Softeq, has extensive experience in integrating IoT, Digital Twins and AI at the Edge. Mahmood joined me on the IoT Show to talk about use cases, the importance of focusing on ROI, expectations for AI at the Edge, the business considerations in terms of hardware, infrastructure, security, brownfield, greenfield, ... 🔗 Connect with Mahmood on LinkedIn: https://www.linkedin.com/in/mahmoodafshari 📚 Chapters (Powered by https://timeskip.io/?ref=olivier) 00:00:00 - Practical Edge AI 00:01:00 - Intro to IoT Show 00:01:54 - Achieving Business 00:03:42 - Edge AI Customers ‍‍ 00:05:16 - Expectations for AI 00:06:18 - Generating Use Cases 00:07:45 - Brownfield vs. Green 🫱‍🫲 00:09:21 - Right Infrastructure 00:10:35 - Enhance Efficiency 00:11:51 - Time Equals Money 00:12:47 - Implementation Tips 00:13:59 - Security Discussion ️ 00:15:52 - Wait and See Position 00:16:59 - Quantum Potential ️ 00:18:03 - Thanks For Tuning In

In technology, you have the ones who implement and use it, and you have the ones who invent, innovate, trailblaze. Zach Shelby, whom you might know as the co-founder of Edge Impulse, is one of these trailblazers, and as you'll hear in this episode, when retracing his career, we retrace a large part of IoT history. 🙏This episode is powered by IoT Stars https://iotstars.com 📚 Chapters (Powered by https://timeskip.io/?ref=olivier) 00:00:00 - IoT Show Intro 00:02:42 - Favorite IoT Devices 00:09:31 - Impressive Business 00:12:05 - Move to Finland 00:14:24 - Combining Worlds 00:16:33 - First Project 00:19:18 - Something Missing 00:21:53 - Open Source ML 00:23:47 - Developer Mismatch ‍‍ 00:26:44 - Edge Impulse Plan 00:28:51 - Gen AI Advancements 00:31:31 - Future of Gen AI 00:33:40 - Networking Importance ‍‍ 00:35:46 - Global Perspective

The Edge AI Foundation recently put together a challenge, proposing to Computer vision engineers, Data scientists, AI engineers and researchers to produce the best Vision AI models for the Edge using a large open source dataset. Participants were to approach the problem from the perspective of the models or from the perspective of the data. Kais Bedioui, Computer Vision engineer, was in the later camp and tells us how he used off-the-shelf AI models to clean up the large dataset, identifying non-labelled images or gaps and errors images annotations before even starting to train a model for the Edge. 🔗 Check out Kai's project at https://github.com/kais-bedioui/Wake_Vision_Challenge_Data_Centric_Track 🙏 This special episode is sponsored by the Edge AI Foundation https://www.edgeaifoundation.org/ 📚 Chapters (Powered by https://timeskip.io/?ref=olivier) 00:00:00 - Intro: Edge AI 00:01:35 - Vision Engineer 00:03:02 - Vision AI Evolution 00:04:56 - Privacy & Security 00:06:58 - Challenge Tracks ️ 00:09:28 - Data Quality Talk 00:10:57 - Approach: Data Sets ️ 00:12:40 - Image Labeling ️ 00:14:55 - Fixing Data Sets 00:16:57 - Vision Model CLIP 00:18:35 - Correct Annotations ️ 00:21:09 - Hardware Devices ️ 00:22:53 - Generic Data Sets 00:24:36 - Key Learnings 00:26:11 - Training Models

The Edge AI Foundation recently organized a challenge, inviting data scientists, computer vision engineers, researchers and others to optimize and train vision models based on large open-source datasets. Different approaches were proposed to contestants, whether from the perspective of the models or from the angle of the large datasets. Pandarasamy Arjunan (a.k.a. Samy) was in the models camp and joined me on the IoT Show to discuss his approach and learnings during the challenge. 🔗 Check out Samy's project at https://github.com/samy101/Wake_Vision_Challenge_Model_Centric_Track 🙏 This special episode is sponsored by the Edge AI Foundation https://www.edgeaifoundation.org/ 📚 Chapters (Powered by https://timeskip.io/?ref=olivier) 00:00:00 - Intro: Edge AI 00:01:28 - IoT Show: Samy 00:02:49 - IoT Middleware System 00:04:42 - Edge AI and AIoT 00:06:18 - Image Classification ️ 00:07:43 - Edge AI in the Picture ️ 00:09:14 - Efficient AI Chips 00:10:38 - Model Pruning Use ️ 00:12:15 - Methods Overview 00:13:48 - Challenge Approach 00:15:42 - Network Structure ️ 00:17:15 - Architecture Work 00:18:54 - Transfer Learning 00:20:41 - Generalized Model 00:22:31 - Top Recommendations 00:24:05 - Year of Edge AI

A French and an Italian IoT practitioners enter a (smart) building. What do they talk about? They talk about how to use IoT to change what's not changed for the last 5000 years: the function of buildings. From hospitality to healthcare, from homes to airports, Fabio Zaniboni, Founder and CEO at Bubblynet, is on a mission to create amazing experiences that will not just delight buildings occupants, but also add value. Imagine a hospital room in which lighting, air quality, sounds allow keeping patients in deep sleep at night so they recover faster. Learn more at https://Bubblynet.com Chapters 00:00:00 - Teaser 00:02:26 - Human Perspective 00:03:41 - Building Applications 00:05:57 - Smart Lighting 00:07:22 - Sound Masking 00:08:36 - IoT Applied to Humans 00:10:00 - Fragrance Scents 00:11:37 - Making it Happen 00:13:31 - Building Models 00:15:02 - Mesh Networking 00:16:53 - Ethics in Tech 00:18:11 - DB Intensity 00:20:42 - Tech Right Path 00:23:13 - Contact Fabio Chapters generated with TimeSkip (https://timeskip.io/?ref=olivier)