User Experience Design for Wearables

🖐️✨ Who needs a mouse when you can just wave your hands dramatically in the air? Just wrapped up my latest project: AirCanvas - a computer vision application that lets you draw using just hand gestures! AirCanvas transforms your webcam into an interactive digital canvas using: • MediaPipe for real-time hand tracking • OpenCV for image processing • Computer vision techniques to interpret gestures as drawing commands 🎮  How it works: • 🤏 Pinch your index finger and thumb to draw • ☝️ Point with your index finger to select colors • 🖐️ Show an open palm to erase 🧠 What I learned: • MediaPipe is surprisingly accurate for hand tracking • The challenges of creating intuitive gesture recognition systems • That waving your hands around in public coffee shops leads to some... interesting conversations with strangers ("No, I'm not summoning spirits, just trying to draw a circle") This project was a fun exploration of creating natural human-computer interfaces. 👉 Check out the code and try it yourself: https://lnkd.in/ebmF28ky #ComputerVision #OpenCV #MediaPipe #GestureRecognition #Python

𝗠𝗼𝘀𝘁 𝘄𝗲𝗮𝗿𝗮𝗯𝗹𝗲𝘀 𝗳𝗮𝗶𝗹 𝗮𝘁 𝗼𝗻𝗲 𝘁𝗵𝗶𝗻𝗴: 𝗺𝗮𝗸𝗶𝗻𝗴 𝘂𝘀𝗲𝗿𝘀 𝗳𝗮𝗹𝗹 𝗶𝗻 𝗹𝗼𝘃𝗲. ❤️ Why? Because the little frustrations pile up. Most users are: – Confused by the setup. – Overwhelmed by notifications. – Unsure what the data even means. 𝟴 𝗧𝗶𝗻𝘆 𝗙𝗶𝘅𝗲𝘀 𝗧𝗵𝗮𝘁 𝗠𝗮𝗸𝗲 𝗨𝘀𝗲𝗿𝘀 𝗟𝗼𝘃𝗲 𝗬𝗼𝘂𝗿 𝗪𝗲𝗮𝗿𝗮𝗯𝗹𝗲 (Instead of abandoning it in a drawer or on the top of the fridge like I did so many times ) 𝟭/ 𝗦𝗶𝗺𝗽𝗹𝗶𝗳𝘆 𝘁𝗵𝗲 𝗦𝗲𝘁𝘂𝗽 ↳ Many wearables assume users are techies. ↳ Make onboarding as easy as wearing it. 𝟮/ 𝗙𝗲𝘄𝗲𝗿 𝗡𝗼𝘁𝗶𝗳𝗶𝗰𝗮𝘁𝗶𝗼𝗻𝘀, 𝗠𝗼𝗿𝗲 𝗠𝗲𝗮𝗻𝗶𝗻𝗴 ↳ Users get annoyed with constant buzzing. ↳ Focus only on what truly matters. 𝟯/ 𝗘𝘅𝗽𝗹𝗮𝗶𝗻 𝘁𝗵𝗲 𝗗𝗮𝘁𝗮 𝗖𝗹𝗲𝗮𝗿𝗹𝘆 ↳ Numbers ≠ insights. ↳ Show what the numbers mean in real life. 𝟰/ 𝗖𝗼𝗺𝗳𝗼𝗿𝘁𝗮𝗯𝗹𝗲 𝘁𝗼 𝗪𝗲𝗮𝗿 𝗔𝗹𝗹 𝗗𝗮𝘆 ↳ Too tight? Too loose? Too itchy? ↳ Design for comfort, not just features. 𝟱/ 𝗦𝗺𝗮𝗿𝘁𝗲𝗿 𝗕𝗮𝘁𝘁𝗲𝗿𝘆 𝗨𝘀𝗲 ↳ No one likes charging every day. ↳ Optimize for longevity & easy charging. 𝟲/ 𝗣𝗲𝗿𝘀𝗼𝗻𝗮𝗹𝗶𝘇𝗮𝘁𝗶𝗼𝗻 ↳ Everyone’s goals are different. ↳ Let them customize what’s tracked & displayed. 𝟳/ 𝗠𝗮𝗸𝗲 𝗜𝘁 𝗙𝗮𝘀𝗵𝗶𝗼𝗻𝗮𝗯𝗹𝗲 ↳ People wear it on their body—it’s part of their identity. ↳ Offer designs they’re proud to show. 𝟴/ 𝗕𝘂𝗶𝗹𝗱 𝗧𝗿𝘂𝘀𝘁 𝗶𝗻 𝗣𝗿𝗶𝘃𝗮𝗰𝘆 ↳ Users hesitate if they feel spied on. ↳ Be transparent about data & give them control.   Imagine if every wearable brand focused on these 8 little things… Because big technology only shines when the little details delight. What other small fixes have you wished for in a wearable? Drop your thoughts below 👇  ♻️ Please share this if you think user love is built on the small stuff.  🔔 And follow João Bocas for more insights on wearable design & user experience. #wearables #engagement #digitalhealth #userdesign

Yesterday, we explored how multimodal AI could enhance your perception of the world. Today, we go deeper into your mind. Let's explore the concept of the Cranial Edge AI Node ("CortexPod"). We’re moving from thought to action, like a cognitive copilot at the edge. Much of this is already possible: neuromorphic chips, lightweight brain-sensing wearables, and on-device AI that adapts in real time. The CortexPod is a conceptual leap; a cranial-edge AI node that acts as a cognitive coprocessor. It understands your mental state, adapts to your thinking, and supports you from the inside out. It's a small, discreet, body-worn device, mounted behind the ear or integrated into headgear or eyewear: ⭐ Edge AI Chipset: Neuromorphic hardware handles ultra-low-latency inference, attention tracking, and pattern recognition locally. ⭐ Multimodal Sensing: EEG, skin conductance, gaze tracking, micro-movements, and ambient audio. ⭐ On-Device LLM: A fine-tuned, lightweight language model lives locally. These are some example use cases: 👨⚕️ In Healthcare or Aviation: For high-stakes professions, it detects micro-signs of fatigue or overload, and flags risks before performance is affected. 📚 In Learning: It senses when you’re focused or drifting, and dynamically adapts the pace or style of content in real time. 💬 In Daily Life: It bookmarks thoughts when you’re interrupted. It reminds you of what matters when your mind starts to wander. It helps you refocus, not reactively, but intuitively. This is some recent research... 📚 Cortical Labs – CL1: Blending living neurons with silicon to create biological-silicon hybrid computers; efficient, adaptive, and brain-like. https://corticallabs.com/ 📚 BrainyEdge AI Framework: A lightweight, context-aware architecture for edge-based AI optimized for wearable cognitive interfaces. https://bit.ly/3EsKf1N These are some startups to watch: 🚀 Cortical Labs: Biological computers using neuron-silicon hybrids for dynamic AI. https://corticallabs.com/ 🚀 Cognixion: Brain-computer interfaces that integrate with speech and AR for neuroadaptive assistance. https://www.cognixion.com/ 🚀 Idun Technologies: Developing discreet, EEG-based neuro-sensing wearables that enable real-time brain monitoring for cognitive and emotional state detection. https://lnkd.in/gz7DNaDT 🚀 Synchron: A brain-computer interface designed to enable people to use their thoughts to control a digital device. https://synchron.com/ The timeline ahead of us: 3-5 years: Wearable CortexPods for personalized cognitive feedback and load monitoring. 8-10 years: Integrated “cognitive coprocessors” paired with on-device LLMs become common in work, learning, and well-being settings. This isn’t just a wearable; it’s a thinking companion. A CortexPod doesn’t just help you stay productive; it helps you stay aligned with your energy, thoughts, and intent. Next up: Subdermal Audio Transducer + Laryngeal Micro-Node (“Silent Voice”) 

LeBron James and Michael Phelps wear it. But it has no screen. No step counter. No clock. No notifications. But even the U.S. military use it to track recovery and performance... That’s WHOOP. And here’s what they did differently: 1. They didn’t chase consumers. Their GTM strategy was anti-scale. No retail. No Facebook ads. No DTC hype machine. They started with pro athletes — people who already have a full team monitoring their health and performance. If you can prove value to them? You can prove value to anyone. This gave them: ✅ Signal over noise ✅ Credibility over clicks ✅ Precision over vanity metrics 2. They killed the transaction. The original WHOOP band? $500. But they saw the ceiling. So they flipped the model: → Hardware became free → The data became the product → Recovery became the subscription It was strategic. - Recurring revenue - Predictable LTV - Better CAC payback - SaaS-style behavior from a hardware company 3. They focused relentlessly. No step counts. No calls. No smartwatch distractions. WHOOP doubled down on: → HRV → Sleep → Strain One question: “How recovered are you today, and what should you do about it?” That’s it. They created a product that said no to 95% of user expectations, and built deeper trust with the 5% who actually needed it. 4. They didn’t try to “do more.” They just did next. Once they nailed product-market fit with athletes, the playbook expanded: – WHOOP Unite → B2B wellness & teams – WHOOP Live → Data-powered broadcast integrations – WHOOP Podcast → Thought leadership pipeline – Affiliate flywheel → Referral-based growth But they earned expansion after they nailed the wedge. 5. They monetized belief, not features. $30/month isn’t cheap. But WHOOP users don’t think they’re paying for a wearable. They believe they’re paying to: ✅ Understand their body ✅ Train smarter ✅ Sleep better ✅ Win longer-term That level of perceived value changes the math: → Lower churn → Higher LTV → More room to invest in the product → More investor interest (SaaS multiples on a wearable company? Come on.) WHOOP didn’t scale by doing more. They scaled by doing less, better, longer. They didn’t ask “How do we reach more people?” They asked: “How do we become indispensable to the right ones?” That’s the kind of focus that compounds.

📢 Check out our new paper entitled "AI‐Based #Metamaterial Design for #Wearables" in Advanced Sensor Research (Wiley). Congratulations to Defne Yigci & Abdollah Ahmadpour Full paper: https://lnkd.in/dhcDSMpr Abstract: Continuous monitoring of physiological parameters has remained an essential component of patient care. With an increased level of consciousness regarding personal health and #wellbeing, the scope of physiological monitoring has extended beyond the hospital. From implanted rhythm devices to non-contact video monitoring for critically ill patients and at-home health monitors during Covid-19, many applications have enabled continuous health monitorization. Wearable health sensors have allowed chronic patients as well as seemingly healthy individuals to track a wide range of physiological and pharmacological parameters including movement, heart rate, blood glucose, and sleep patterns using smart watches or textiles, bracelets, and other accessories. The use of metamaterials in wearable sensor design has offered unique control over electromagnetic, mechanical, acoustic, optical, or thermal properties of matter, enabling the development of highly sensitive, user-friendly, and lightweight wearables. However, metamaterial design for wearables has relied heavily on manual design processes including human-intuition-based and bio-inspired design. Artificial intelligence (AI)-based metamaterial design can support faster exploration of design parameters, allow efficient analysis of large data-sets, and reduce reliance on manual interventions, facilitating the development of optimal metamaterials for wearable health sensors. Here, AI-based metamaterial design for wearable #healthcare is reviewed. Current challenges and future directions are discussed. #metamaterials #ai #machinelearning #wearables #biomedicalengineering

⌚️ Wearables lead to healthier people. For a few years, there has been a movement (by some) in the wellness community to downplay wearables and their effectiveness. New research might be a reason to rethink that view point. I was first introduced to the role that wearables can play in creating healthy lives in 2007 from the landmark research conducted by Ghent university on the effectiveness of the physical activity promotion project “10,000 Steps Ghent.” Ultimately, what the study found was that 3 factors, when done together, had a significant role in achieving healthy wellness goals - 1. Established a goal (in this case, 10,000 steps) 2. Monitoring or Tracking progress (the study utilized a pedometer) 3. Community intervention (achieve the goal together) Since then, wearables have become ubiquitous around the world and not just in western nations. The two fastest growing markets for wearables are India and China, respectively. Furthermore, the growth of the category (11% YOY) has not been led by industry leaders, such as Apple and Fitbit, but rather new players including Huawei in China and low-cost startups in India - Noise and Fireboltt - where wearables are under $50 USD. . . Last week, I had an opportunity to review an insightful paper on the impact of wearables published on the The Lancet - an international weekly general medical journal that has been in active publication since 1823. The paper was a systematic review of 39 studies that covered nearly 165,000 people over a period of several years. The meta-analysis drew to the conclusion that wearables led to positive changes several areas including: - Physical Activity - Body Composition - 1800 more steps per day - Improved physiological benefits including blood pressure, cholesterol, and glycosylated hemoglobin - Improved psychosocial benefits (quality of life and pain) With nearly two decades of data, there is no question that wearables will lead to improved health outcomes.   . . 💡 How can brands integrate wearables into their user journey? Here are some quick wins that we have incorporated into several of our brands and partners: - If you have a mobile app, integrate with Apple Health or Google Fit - Enhance the experience with data collected from wearables - Built a community that is either digital or physical - Implement gamification and rewards to help drive positive behavior - Personalize the journey - Do an assessment: Think of this as the GPS for your user’s health. You cannot create a pathway for achieving their goals if you do not know where they are starting from. Wearables alone are impactful. However, when integrated with a brand that serves as the “front-end” for the user - they can supercharge progress. Let me know how you have incorporated wearables into your life or brand below. 👇 #wearables #health #wellness #activity #tracking #research #innovation #india #china #growth #apple #fitbit #brands 

Google's innovative venture, Project Soli, is set to redefine how we interact with technology. Utilizing a hand gesture recognition sensor powered by machine learning is a transformation in user interface design. 𝐂𝐨𝐫𝐞 𝐅𝐞𝐚𝐭𝐮𝐫𝐞𝐬 𝐨𝐟 𝐏𝐫𝐨𝐣𝐞𝐜𝐭 𝐒𝐨𝐥𝐢 - Innovative Sensor Technology: At the heart of Soli lies a tiny sensor that can fit onto a chip, capable of tracking sub-millimeter hand gestures with exceptional speed and accuracy. This is achieved through the use of advanced radar technology. - Machine Learning at Its Core: Soli isn't just about hardware. The real magic happens with its custom-built machine learning models, which are designed through robust data collection pipelines. These models are tailored for various use cases, enabling Soli to understand and interpret a wide range of hand movements. - Touchless Interaction: Imagine controlling your electronic devices with a simple wave of your hand or the flick of a finger - no need to touch, just gesture in the air. This capability could change everything from how we manage home appliances to how we interact with car infotainment systems or public kiosks, offering a more hygienic and accessible form of interaction. Project Soli has significant implications for user accessibility, convenience, and the overall user experience. By removing the need to touch, it opens up new avenues for users with mobility or tactile limitations and presents a more intuitive way for everyone to interact with their devices. Beyond consumer electronics, this technology could be integrated into medical devices, enhancing accessibility for patients with limited mobility, or even in industrial settings, where clean or touch-free environments are critical. What possibilities do you see opening up with touchless gesture technology? How do you think Project Soli could change the landscape of device interaction in your industry? #innovation #technology #future #management #startups

𝐆𝐨𝐨𝐠𝐥𝐞’𝐬 𝐍𝐞𝐱𝐭 𝐅𝐫𝐨𝐧𝐭𝐢𝐞𝐫: 𝐅𝐨𝐮𝐧𝐝𝐚𝐭𝐢𝐨𝐧𝐚𝐥 𝐌𝐨𝐝𝐞𝐥𝐬 𝐟𝐨𝐫 𝐖𝐞𝐚𝐫𝐚𝐛𝐥𝐞 𝐃𝐚𝐭𝐚 Wearable devices—like smartwatches and fitness trackers—generate 𝐯𝐚𝐬𝐭 𝐚𝐦𝐨𝐮𝐧𝐭𝐬 of physiological and behavioral data. But raw sensor readings (heart rate, movement, etc.) are often noisy and hard to interpret. Traditionally, AI models for wearables have been 𝐧𝐚𝐫𝐫𝐨𝐰𝐥𝐲 𝐭𝐫𝐚𝐢𝐧𝐞𝐝 for single tasks (e.g., detecting runs or sleep), requiring 𝐡𝐞𝐚𝐯𝐲 𝐥𝐚𝐛𝐞𝐥𝐢𝐧𝐠 and struggling to generalize. 𝐄𝐧𝐭𝐞𝐫 𝐟𝐨𝐮𝐧𝐝𝐚𝐭𝐢𝐨𝐧𝐚𝐥 𝐦𝐨𝐝𝐞𝐥𝐬—large AI systems trained on massive datasets to learn universal patterns. Inspired by breakthroughs in language (like Gemini) and vision models, Google is now applying this approach to 𝐰𝐞𝐚𝐫𝐚𝐛𝐥𝐞 𝐬𝐞𝐧𝐬𝐨𝐫 𝐝𝐚𝐭𝐚. 𝐇𝐨𝐰 𝐈𝐭 𝐖𝐨𝐫𝐤𝐬: 𝐓𝐡𝐞 𝐋𝐚𝐫𝐠𝐞 𝐒𝐞𝐧𝐬𝐨𝐫 𝐌𝐨𝐝𝐞𝐥 (𝐋𝐒𝐌) Google trained 𝐋𝐒𝐌 on 𝟒𝟎 𝐦𝐢𝐥𝐥𝐢𝐨𝐧 𝐡𝐨𝐮𝐫𝐬 of multimodal data from 𝟏𝟔𝟓,𝟎𝟎𝟎 𝐮𝐬𝐞𝐫𝐬, using self-supervised learning (SSL). Instead of relying on labeled data, the model learns by: 🔹 𝐌𝐚𝐬𝐤𝐞𝐝 𝐫𝐞𝐜𝐨𝐧𝐬𝐭𝐫𝐮𝐜𝐭𝐢𝐨𝐧 – Predicting missing sensor values (e.g., filling in gaps in heart rate data). 🔹 𝐆𝐞𝐧𝐞𝐫𝐚𝐭𝐢𝐯𝐞 𝐭𝐚𝐬𝐤𝐬 – Imputing, interpolating, and even forecasting future sensor readings. 𝐖𝐡𝐲 𝐓𝐡𝐢𝐬 𝐌𝐚𝐭𝐭𝐞𝐫𝐬 ✅ 𝐒𝐜𝐚𝐥𝐢𝐧𝐠 𝐋𝐚𝐰𝐬 𝐀𝐩𝐩𝐥𝐲 – Just like in NLP/vision, bigger models + more data = better performance (up to 38% gains over traditional methods). ✅ 𝐋𝐚𝐛𝐞𝐥 𝐄𝐟𝐟𝐢𝐜𝐢𝐞𝐧𝐜𝐲 – With few-shot learning, LSM can recognize activities (running, biking, etc.) with just 5-10 labeled examples—dramatically reducing manual annotation needs. ✅ 𝐆𝐞𝐧𝐞𝐫𝐚𝐥-𝐏𝐮𝐫𝐩𝐨𝐬𝐞 𝐖𝐞𝐚𝐫𝐚𝐛𝐥𝐞 𝐀𝐈 – One model can handle multiple tasks, from activity recognition to health monitoring. Read the full research here: https://lnkd.in/eFTaHe_j

I built this project to play Subway Surfers using nothing but hand gestures and computer vision. 🚄✋ Gesture-based interaction with computer vision is always a fun challenge. In this project, I combined OpenCV, MediaPipe, and PyAutoGUI to build a system where hand gestures are translated into real-time commands for applications and games. ⚙️ The implementation uses OpenCV and MediaPipe to detect and track face landmarks and hand movements. ⌨️ PyAutoGUI maps the recognized gestures into keyboard actions. 🌌 Selfie segmentation enables dynamic background replacement. 🕶️ Face mesh detection overlays virtual elements such as glasses, a hat, or a mustache in real time. 👉 The core idea is to transform simple hand signals into meaningful actions. The right hand can move right or up, while the left hand can move left or down. By combining gesture detection with visual overlays, the project creates an interactive experience that blends control and creativity. 🚀 This prototype shows how computer vision can support touchless interaction. The same methodology could be extended to education for interactive learning, to gaming for immersive controls, or to healthcare for hands-free operation. 🎥 The attached video demonstrates the system in action, highlighting the potential of gesture recognition in real-world applications. #ComputerVision #AI #MachineLearning #DeepLearning #GestureRecognition #OpenCV #MediaPipe #SubwaySurfers #Python

🎙️ How Smart Glasses Understand the World We’re entering a world where hands-free communication and AI search through smart glasses is becoming the new normal. But have you ever wondered: How do these glasses actually understand our world? Let’s break it down with an example of multimodal search👇 Say you’re pre-diabetic and want to track your food. You’re holding a croissant and you ask, “What is the glycemic index?” How do your smart glasses interpret that? 🥐 Step 1: Visual Encoding The camera captures an image of the croissant and sends it to a Visual Encoder (like OpenAI's CLIP encoder). This generates a visual embedding that represents the image in machine-understandable form. 🎤 Step 2: Speech Encoding At the same time, your audio input is processed through a Speech-to-Text model (like LAION's CLAP), converting your question into text and then into a text embedding. 🔁 Step 3: Multimodal Fusion These two streams : the image and the text, are sent to a Multimodal Fusion Core, (like Meta / AI at Meta's AnyMAL model). This fusion aligns your question with what you’re looking at: “What is the glycemic index of a croissant? 🔎 Step 4: Knowledge Lookup The fused result triggers a Knowledge Lookup, fetching the nutritional data. 📢 Step 5: Response Delivery  Finally, the Response Generator delivers the answer: 👉 “The glycemic index of a croissant is approximately 67.” This is a very simple example of how combination of AI and smart glasses is used to understand the world around you.