Integrating AI With IoT Devices

Energy is no longer just delivered; it's produced everywhere. Millions of homes, businesses, and microgrids now generate their own power. The old grid, built for one-way flow, can't coordinate what the energy system has become. AI agents are stepping in. They predict supply fluctuations using weather and satellite data before they happen. They autonomously balance energy flows across distributed networks. Digital twins simulate storms and equipment failures, so operators can prepare rather than react. With these advances, no human team can manage that volume of decisions at that speed. The coordination gap is what makes AI necessary here, not optional. This need for AI-driven coordination applies well beyond energy. Any business running distributed operations across regions, assets, or suppliers faces the same math. The complexity grows faster than headcount ever will. The companies embedding AI into coordination, not just reporting, will handle that growth.   #EnergyTransition #EnterpriseAI #SmartGrid #RenewableEnergy #DistributedSystems #AIAdoption #OperationalExcellence #DigitalTwin #Sustainability #AILeadership #BusinessStrategy

Walking the floors at HLTH Europe, I came across some impressive startups tackling everything from menopause to mouthguards, hormone tracking to hydration. Here are 10 that caught my eye: 🇬🇧 JawSense tackles bruxism with a smart headband that detects clenching and delivers gentle feedback. It offers a non-invasive alternative to mouthguards, with early trials showing up to 80% reduction in grinding 🇫🇷 Theremia uses AI to optimize CNS treatments by identifying how patient subgroups respond to drugs. Combining clinical and real-world data with pharmacology insights, they refine dosing, formulations, and trial design 🇬🇧 TidalSense built a handheld device that analyzes exhaled CO₂ for faster COPD and asthma diagnosis. It uses AI to interpret breathing patterns and delivers point-of-care results in minutes for early detection and monitoring 🇳🇴 Mode Sensors 'Re:Balans' is a wearable patch that tracks hydration via bioimpedance. It monitors shifts over several days and sends data to clinicians, offering a non-invasive alternative to manual fluid tracking 🇰🇪 Xaidi from iZola.life is a free AI app that supports caregivers of neurodivergent children with symptom tracking, therapy tips, and local-language resources. It connects families to vetted therapists and eases day-to-day care 🇳🇱 WSK Medical uses AI for early cancer detection via real-time endoscopy and pathology analysis. Their tools highlight and classify lesions or automate slide review to help clinicians diagnose more quickly and consistently 🇩🇪 Dx365 built a portable device that reads rapid tests, from hormones to infections, via color or fluorescent signals. Results sync to the cloud, enabling consistent point-of-care testing across health and care settings 🇮🇪 Whyze Health offers an AI platform that unifies health records and shares data securely across patients, providers, and pharma. It supports care coordination, trial matching, and real-world research insights 🇦🇹 Menotracker GmbH is an AI app that helps users track menopause-related changes like symptoms, sleep, and mood. It offers personalized insights and education, while ensuring privacy and multi-language access 🇬🇧 Impli is developing a subdermal sensor to track fertility hormones in real time via NFC. Aimed at IVF, it replaces frequent blood tests by enabling continuous, at-home monitoring and clinician alerts. They partnered with Bayer last year #HLTHEurope #DigitalHealth #AI

𝗗𝗼 𝘆𝗼𝘂 𝗳𝗲𝗲𝗹 𝗪𝗲𝗮𝗿𝗮𝗯𝗹𝗲𝘀 𝗮𝗿𝗲 𝗹𝗶𝘃𝗶𝗻𝗴 𝘂𝗽 𝘁𝗼 𝘁𝗵𝗲𝗶𝗿 𝗲𝘅𝗽𝗲𝗰𝘁𝗮𝘁𝗶𝗼𝗻𝘀? Because this breakthrough just raised the bar significantly. Researchers have developed a wearable device that monitors glucose levels through sweat – and it doesn't stop there. This disposable patch integrates real-time glucose monitoring with automated transdermal drug delivery for diabetes management. 𝗛𝗲𝗿𝗲'𝘀 𝘄𝗵𝘆 𝘁𝗵𝗶𝘀 𝗺𝗮𝘁𝘁𝗲𝗿𝘀: ✅ 𝗡𝗼𝗻-𝗶𝗻𝘃𝗮𝘀𝗶𝘃𝗲 𝗺𝗼𝗻𝗶𝘁𝗼𝗿𝗶𝗻𝗴 – No more painful finger pricks ✅ 𝗖𝗼𝗻𝘁𝗶𝗻𝘂𝗼𝘂𝘀 𝘁𝗿𝗮𝗰𝗸𝗶𝗻𝗴 – Real-time glucose data from sweat analysis ✅ 𝗦𝗺𝗮𝗿𝘁 𝗱𝗿𝘂𝗴 𝗱𝗲𝗹𝗶𝘃𝗲𝗿𝘆 – Automated treatment response when glucose levels spike ✅ 𝗪𝗲𝗮𝗿𝗮𝗯𝗹𝗲 & 𝗱𝗶𝘀𝗽𝗼𝘀𝗮𝗯𝗹𝗲 – Practical for everyday use This isn't science fiction. It's soft bioelectronics on human skin, creating a closed-loop system that monitors AND treats diabetes simultaneously. 𝗧𝗵𝗲 𝗯𝗶𝗴𝗴𝗲𝗿 𝗽𝗶𝗰𝘁𝘂𝗿𝗲? This technology represents the convergence of AI, wearables, and connected care – three pillars transforming healthcare delivery. We're moving from reactive treatment to proactive, personalized health management. For healthcare organizations exploring digital transformation, innovations like this answer the question: wearables aren't just living up to expectations – they're exceeding them by becoming active treatment devices, not just passive monitors. 𝗧𝗵𝗲 𝗿𝗲𝗮𝗹 𝗾𝘂𝗲𝘀𝘁𝗶𝗼𝗻: 𝗛𝗼𝘄 𝗾𝘂𝗶𝗰𝗸𝗹𝘆 𝗰𝗮𝗻 𝘄𝗲 𝘀𝗰𝗮𝗹𝗲 𝘁𝗵𝗶𝘀 𝗳𝗿𝗼𝗺 𝗿𝗲𝘀𝗲𝗮𝗿𝗰𝗵 𝘁𝗼 𝗿𝗲𝗮𝗹-𝘄𝗼𝗿𝗹𝗱 𝗰𝗮𝗿𝗲? What's your take? Are non-invasive biosensors the next frontier in chronic disease management? 📖 Research: Science Advances (DOI: 10.1126/sciadv.1601314) For more Wearables News and Expertise follow João Bocas #DigitalHealth #AIinHealthcare #Wearables #DiabetesCare #HealthTech #ConnectedCare #Innovation #HealthcareTransformation

How can IoT help us use energy smarter? Imagine checking your energy use from your phone, hour by hour, and knowing exactly when your electricity use spikes. For many of us, it might seem like something out of the future—but it’s very much the present thanks to smart meters and IoT integration in energy grids. Smart grids are changing the way we balance energy supply and demand. They’re not just a tech upgrade; they’re a practical response to the need for a cleaner and more efficient energy system. By integrating IoT, utilities are now able to gather real-time data that helps them predict demand, prevent shortages, and ultimately reduce the environmental impact of energy production. For instance, consider solar power. One of the challenges with solar is that it’s intermittent—it depends on the weather and time of day. Smart grids, combined with IoT-enabled meters, allow utilities to manage this by collecting consumption data and forecasting energy needs. This way, they can respond instantly when demand surges, helping reduce the need for power plants to stay on standby, burning fuel unnecessarily. According to a study by the Department of Energy, this kind of smart tech could cut energy waste by up to 20%. And it’s not just a benefit for the grid. Smart meters provide valuable insights into everyday energy use for consumers, showing how much power is being consumed in real time. It’s as simple as seeing which appliances or times of day are responsible for higher bills—and then making small changes that add up. The EPA reports that households with smart meters save an average of 10–15% on their annual energy bills by adjusting usage habits. From a human perspective, this technology isn’t just about data; it’s about giving people the control to make better decisions for their wallets and the environment. Smart grids and IoT are bridging that gap, making energy management a reality for both utilities and everyday users.

AI-enhanced power grid optimization can reduce emissions that are the equivalent of removing 6.5 million (U.S.) gas-powered mid-size passenger vehicles from the road for a year. “AI” is a much broader term than what most people think of—it’s not all LLMs! When it comes to reducing energy waste and operational power grid emissions, AI can help by dispatching generation assets more optimally, reducing losses, congestion, and cost. In our paper, which will be presented at the NeurIPS 2025 Workshop "Tackling Climate Change with Machine Learning," we analyze the operational emissions associated with training CANOS, Google DeepMind’s graph neural network for solving AC Optimal Power Flow (OPF) on a 10,000-bus power system. We then estimate how emissions and energy use would change if these dispatch solutions were used to determine generator (power plant) dispatch decisions, instead of the status-quo linear approximations used in many power markets to set generator output. Especially compared to training something as complex as an LLM, training these GNNs—which have a focused task (learning OPF solutions)—“pays back” all energy and emissions costs associated with the model's training within a single hour. At a country-wide scale, operating the grid more efficiently using these models is approximately equivalent to removing 6.5 million (U.S.) gas-powered mid-size passenger vehicles from the road for a year. Of course, a full analysis would require a lifecycle carbon assessment of training these GNNs. And we'd have to run the actual power grid models themselves across ISOs, not just a 10,000 bus synthetic grid. Additionally, we'd need to model other grid components and concepts like ancillary services, self-schedulers, and more. But even if we’re off by, say, a HUNDRED times, the conclusion is still clear: using a GNN approximation for dispatch can reduce energy use and emissions relative to DC OPF-based approximations. (Even if we're off by the training emissions by a *thousand* times, this holds true.) If you’re at NeurIPS in San Diego this year, please come chat with me at the session if you’re interested in this work! Read more here: https://lnkd.in/g9aqhXpy And stop saying "AI" when you actually mean LLMs. :)

I was honored to join Axios energy reporter Ben Geman at the Atlantic Council in Washington, DC, for a fireside chat to discuss what it will take to power an economy that’s more electrified, resilient and competitive. The reality is stark: demand for electricity is projected to grow far faster than overall energy use. This is no threat to prosperity; it’s an opportunity - if we act with realism and speed. I have three takeaways from our discussion, and they are based on one simple insight: a successful energy transition needs energy security. We need to put the technologies and infrastructure in place to ensure we have the right energy, at the right time, at the right price. We can achieve this if we: 1. Squeeze more from every kilowatt: Energy efficiency and grid modernization are just as important as energy supply. We can quickly improve energy efficiency in industries and buildings by using high-efficiency motors with variable-speed drives. If widely adopted, this could reduce electricity demand by about 10% - the same as the output from around 100 coal plants or 35 nuclear plants. These savings could meet the growing energy needs of data centers for several years. 2. Modernize and digitalize the grid: We are still trying to run a 21st century economy on 20th century infrastructure. By 2040, the world needs 80 million kilometers (almost 50 million miles) of grid upgrades, plus storage and digital control, to integrate variable renewables, balance peaks, and improve resilience. Permitting is now a critical bottleneck. This is where targeted policy – with smarter approvals, clear standards, and investment in distribution networks – can unlock real capacity quickly. 3. Make AI part of the solution: There are a lot of headlines that Artificial Intelligence is driving up demand for energy. However, AI-enabled energy management – with digital substations and edge control – can also optimize usage, reduce losses and prevent outages. We have to see AI as a crucial tool to manage grids, to forecast, shift and reduce demand. AI can help us align demand growth with grid reliability. None of this scales without people. Resilient energy systems need a skilled workforce, from electricians to data scientists. Upskilling, retraining, and apprenticeships have to be made a priority by both the public and the private sector. The path forward is clear: electrify everything you can; deploy efficiency first; digitalize the grid; and use AI to manage what we add (and have). For regions and countries that do this, energy security will be a competitive advantage creating the foundations for sustainable growth. Listen to the full discussion here: https://lnkd.in/emMu-4zr

Following the wide recognition of Grid-Forming (GFM) inverters as a cornerstone for grid stability, the focus of innovation is rapidly shifting from “forming” the grid to actively orchestrating it. The next frontier blends intelligence, adaptability, and cross-domain interaction — pushing power systems into what experts now call the Grid 3.0 era. Here’s where research and advanced practice are heading : ① Multi-Mode & Hybrid-Compatible Inverters (HC-GFIs) Next-gen converters can seamlessly operate in GFM or GFL modes depending on system strength — enhancing flexibility and resilience under changing conditions (Nature Scientific Reports, 2025; ArXiv Energy Systems, 2024). ② Unified AC/DC & Dual-Port Architectures Dual-port inverters are enabling hybrid microgrids, dynamically balancing AC and DC power flows to integrate solar, storage, and EV systems with unprecedented efficiency. ③ Wide-Area Damping via PMU-Driven Control Using synchronized phasor measurements and edge computing, wide-area damping control (WADC) coordinates multiple GFMs, HVDC links, and FACTS devices — achieving real-time system stabilization even in weak grids. ④ Digital, Predictive & AI-Assisted Operations AI-enabled predictive control is now being used to anticipate voltage instabilities, optimize inertia emulation, and coordinate fleets of distributed GFMs (NREL Digital Twin Grid Initiative, 2024). ⑤ Virtual Power Plants (VPPs) & Hydrogen-Linked Storage Thousands of GFMs, EVs, and hydrogen fuel systems are being aggregated into Virtual Power Plants capable of grid support, black-start, and ancillary services at national scale. ▪️In essence: we’re evolving from grid-forming to grid-intelligent systems — adaptive, self-healing, and data-driven. The future grid will not only be stable; it will be strategically aware. #GridForming #GridIntelligence #PowerSystems #BESS #HybridGrids #AIinEnergy #VPP #EnergyTransition #IEEE_PES

America is building an AI-powered grid management system that can predict electricity demand across the entire country 72 hours in advance — giving grid operators time to prepare for anything before it arrives. Grid operators have always needed to forecast demand. Every power system requires advance knowledge of how much electricity will be consumed tomorrow so that the right mix of generation can be committed, ramped, and dispatched. Traditional forecasting models used historical patterns, weather data, and calendar effects to predict demand with reasonable accuracy one to six hours ahead. The AI revolution is extending that window dramatically — to 24, 48, and 72 hours — with accuracy that matches or exceeds traditional models at a fraction of the computational cost. The Electric Power Research Institute's AI Forecasting Initiative has developed machine learning models that incorporate hundreds of variables beyond the traditional weather-and-calendar approach. Social media activity patterns, mobility data from smartphone location services, industrial production schedules shared by major manufacturing customers, electric vehicle charging behaviour patterns, and real-time distributed solar generation estimates all feed into ensemble models that predict demand with sub-percentage error rates at 24-hour horizons across regional grids. PJM Interconnection — the largest grid operator in North America, managing electricity for 65 million people across 13 states — has integrated AI demand forecasting into its core operational systems, using the extended forecast windows to pre-position generation reserves, coordinate interstate power flows, and schedule maintenance activities that would otherwise create operational constraints during high-demand periods. The improved forecast accuracy has reduced PJM's operating reserve requirements — the excess generation held on standby for unexpected demand spikes — saving hundreds of millions of dollars in annual system costs. America's grid knows what tomorrow looks like. AI made it possible to see that far ahead. Source: Electric Power Research Institute (EPRI) & PJM Interconnection, 2024

🏥 Two #wearable companies. Combined valuation: over $20 billion. And we're just getting started. WHOOP has just raised $575 million in a Series G round at a $10.1 billion valuation. What is especially notable is not only the size of the round, but the signal behind it: investors include Abbott and Mayo Clinic. That suggests wearables are increasingly being seen not merely as consumer wellness products, but as strategically relevant assets in the future of healthcare. Meanwhile, ŌURA has been reported at roughly an $11 billion valuation, reinforcing the scale of market confidence in continuous, consumer-facing health monitoring. What makes this shift important is not just the hardware. It is the growing clinical relevance of continuous, real-world data. Recent literature shows that wearable technologies are moving beyond lifestyle tracking into more serious remote monitoring use cases. A new Nature Portfolio study demonstrated that #smartwatch-based monitoring can support the remote assessment of heart failure patients using continuous physiologic and behavioral data. A JMIR mHealth and uHealth systematic review further showed that wearables are increasingly used for chronic disease monitoring, especially in cardiovascular and neurological applications. At the same time, the real acceleration comes from analytics. As #AI-enabled interpretation improves, wearable data is becoming more actionable: not just raw signals, but contextualized information about recovery, stress, rhythm, activity, and deterioration risk. A JMIR systematic review on AI-enabled medical devices highlights wearable monitoring as one of the domains where AI is enabling more continuous, #personalized health management. This is why wearables are becoming strategically relevant beyond consumer tech. They are helping to push healthcare away from a model that mainly reacts to illness, and toward one that increasingly supports prevention, early detection, and continuous management. A recent European Heart Journal – Digital Health review describes wearable technologies as part of a transformation in cardiovascular care through continuous monitoring outside traditional clinical settings, while also making clear that large-scale impact still depends on validation, workflow integration, and governance. For those of us working in healthcare IT, the key question is no longer whether wearable-generated data will matter. The real question is: Are our health IT systems ready to receive, contextualize, and operationalize this data? #DigitalHealth #Wearables #RemotePatientMonitoring #PreventiveCare #AIinHealthcare #HealthcareIT #Interoperability #DigitalTransformation #Virgobit

The wearable industry is quietly shifting direction. WHOOP focused on recovery. Oura focused on sleep and readiness. Now Google’s new Fitbit Air is pushing AI-powered passive health tracking into the mainstream. Interesting part? The future of wearables may not be smartwatches with more screens and notifications. It may be: • screenless • lightweight • continuous • AI-driven • focused on nervous system health Science is also supporting this trend. HRV, sleep quality, temperature, respiration, and recovery patterns are becoming meaningful digital biomarkers instead of just “fitness metrics.” The real competition is no longer hardware. It is who builds the best long-term health intelligence system from continuous physiological data. Wearables are slowly evolving from fitness gadgets into early health prediction systems. Still very early days but a fascinating direction.