Real-Time Tracking Systems

What if your home #WiFi could care for your loved ones? No wearables. No cameras. Just the existing WiFi signals in the house detecting if they fall or become inactive! In our latest work, we show how our #AI algorithm uses standard WiFi to track 2D #human #skeletons and detect #activities like #falls or inactivity, with accuracy close to camera-based systems, all while preserving privacy. This will be a large step forward in non-intrusive, intelligent elder care. - Paper: Younggeol Cho, Elisa Motta, Olivia Nocentini, Marta Lagomarsino, Andrea Merello, Marco Crepaldi, and Arash Ajoudani. "Wi-Fi based Human Fall and Activity Recognition using Transformer-based Encoder–Decoder and Graph Neural Networks" IEEE Sensors 2025. - Link to paper (open): https://lnkd.in/dpUB4gCS - Full video: https://lnkd.in/d9ji-P-h IEEE SENSORS Istituto Italiano di Tecnologia

The efficiency of modern transportation depends on a seamless flow of data, where real-time insights empower fleet managers to optimize routes, reduce delays, and ensure cargo integrity, making every decision more precise and responsive to unpredictable challenges. The transportation ecosystem relies on interconnected systems that transform raw data into actionable intelligence. Sensors track vehicle performance, cargo conditions, and driver behavior, generating real-time data on fuel consumption, harsh braking, or temperature fluctuations. This data is transmitted through advanced communication networks, where it is aggregated and structured for analysis. AI-driven systems identify inefficiencies, predict maintenance needs, and optimize logistics by adjusting routes dynamically. Fleet managers use these insights to improve safety, reduce costs, and enhance delivery reliability. By leveraging technology, businesses can respond swiftly to disruptions, ensuring supply chains remain resilient and adaptive. #SmartLogistics #DataDriven #FleetManagement #DigitalTransformation #SupplyChain

Real-time visibility is no longer optional in #Logistics. It’s essential for operating efficiently, meeting SLAs, and keeping fleets on the road. #PenskeLogistics shows what’s possible when #DataStreaming meets #AI at scale. Penske processes 190 million #IoT messages every day from over 165,000 #ConnectedVehicles. This data powers predictive maintenance, prevents breakdowns, and keeps deliveries moving. Over 90,000 roadside incidents have already been avoided thanks to streaming intelligence. This isn’t a one-off project. Penske has built a real-time architecture using #ApacheKafka to drive smarter operations across the board from dispatching roadside assistance to automating compliance with IFTA reporting. Data Streaming data is now the backbone of Penske’s business. It fuels diagnostics, automates service decisions, and enables new AI use cases, including conversational assistants and predictive repair planning. For the logistics and transportation industry, this is the blueprint for scalable, event-driven transformation. Real-time isn’t about dashboards. It’s about real results. Read the full story to learn how Penske Logistics built their future with real-time fleet intelligence: https://lnkd.in/e4fUWvXw

🔥Youtube Tutorials can show you how things work. But, Real-World Architecture shows you how things Break & how to Fix them.! 🍃Microservices-based Fleet Management System that was Designed with [Birds Eye View]: - Kafka for real-time location & traffic data streaming - Docker for scalable containerized services - API Gateway to unify access across microservices 🍃Key services: - Vehicle Service: Tracks GPS updates in real-time - Route Optimizer: Dynamically recalculates routes based on Kafka-streamed traffic data - Dispatch Service: Assigns the nearest driver using low-latency Kafka topics - Notification Service: Sends alerts based on delivery/traffic events Everything’s loosely coupled, highly scalable, and built for real-time logistics system. # Lessons That Matter: 1. Kafka isn’t just a buzzword — it’s how modern logistics systems stay reactive. 2. Docker ensures each service is portable and independently deployable. 3. Microservices work best when driven by events, not just REST calls. Connect Sabari Balaji for Tech Insights💡 #MicroservicesArchitecture #Kafka #Docker #SystemDesign ##EventDrivenArchitecture #CloudNative #SpringBoot #APIGateway #RealTimeData

A technical breakthrough from Australia is able to track DynamicMicroData (DMD), the basis for Gen-3 Wearables, a major shift in trackers which we predicted recently. A team from the University of New South Wales has created tiny ultra-thin cantilevered sensors that can detect multiple physiological mechano-acoustic signals over an outstanding bandwidth of 15.5 octaves, yes octaves! These sensors are integrated into small adhesive wearables. With a power demand of under 5mW they are able to continuously capture subtle vibrations produced by the heart, lungs, blood flow, an even vocal chords. An AI layer allows these signals to be segregated and analyzed for clinical decision-making. The high sensor bandwidth enables the device to detect signals that are way beyond the capability of today’s trackers. The ability to acquire DMD for example, allows the wearable to ‘listen’ to heart-valves opening and closing, or track the transitions between sleep stages which are rich in information related to central nervous system functionality. As just one example, the attached chart shows details of breathing transitions which are important in diagnosing the occurrence and causes of sleep disturbed breathing, a field of great interest to our team and one which is ripe for new innovations in both diagnoses and therapies. This Australian development is a clear marker for the future of healthcare and a sign that major changes are likely to come faster than originally thought. We can anticipate a time when our key health markers are tracked continuously enabling a shift to early preventative care from late symptom treatment. For those wanting to learn more, access the full Nature report. You will find the future shining bright!

I published a new case study on employee surveillance technology. It explores behavioral monitoring and profiling in the workplace, with a focus on indoor location and desk occupancy tracking. To illustrate wider practices, it investigates how the network technology giant Cisco offers to turn Wi-Fi access points installed in offices and other buildings into a system that tracks the location of employees, customers, smartphones, laptops and other devices for a wide range of purposes. Cisco's "Spaces" system goes far beyond aggregate analysis. The company promotes several applications that involve identifying, singling out and targeting individuals. Cisco claims that it has so far processed 24.7 trillion location data points on almost 100,000 devices collected via 3.8 million Wi-Fi access points. The fact that Cisco is able to provide these numbers raises the question about how a global core infrastructure vendor processes data for its own purposes. To make things worse, the system can also turn Cisco’s security cameras into sensors that help analyze indoor movement. Repurposing data collected from an employer's networking infrastructure or even from video surveillance systems for indoor location tracking raises serious concerns about the normalization of intrusive behavioral surveillance, privacy and data protection in the workplace. Juniper, another network technology vendor, offers a similar indoor location tracking system. Its Wi-Fi access points can locate people either via their devices or via Bluetooth/BLE badges carried by them. Juniper suggests to use the system to “track personnel and equipment”, “locate key human resources such as nurses, security guards, and sales associates”, “optimize workflows” and “enable data-driven decision making”. In my case study, I examine a second category of systems that also enable employers to profile employee behavior in physical spaces. Several vendors provide systems that use motion sensors installed under desks or in the ceilings of rooms to track desk and room attendance. The Belgian-German vendor Spacewell offers a system for “real-time office space monitoring” and “workplace analytics” that tracks how employees use desks, meeting rooms and entire offices. It uses motion sensors that detect heat emitted by humans and 'low-resolution' cams with computer vision. The 'workplace analytics' system offered by the Swiss vendor Locatee combines motion sensors with badge data and device location data, collected e.g. via Cisco Spaces. These systems mostly focus on aggregate analysis, but still utilize behavioral profiling based on extensive personal data. In my view, they do not adequately engage with the risks posed by behavioral monitoring. Not least, I summarize in my case study how employers installing under-desk motion sensors led to worker protests and media debates, ultimately leading to their removal. Here's my 25-page case study: https://lnkd.in/d_ZbjbYx

Everyday Wi-Fi routers can track and identify you with 99.5% accuracy — even if you aren't carrying a phone. Imagine walking into your living room or passing by a local café, completely disconnected from your devices, only for an invisible network to instantly map your physical identity. Cybersecurity researchers have revealed that ordinary, off-the-shelf Wi-Fi routers can do exactly that. By exploiting unencrypted data called "beamforming feedback information"—a standard feature introduced in Wi-Fi 5 to help direct signals to connected devices—anyone with cheap, monitoring-enabled hardware can passively map the surroundings. This breakthrough research demonstrates that radio wave reflections can be compiled to identify individuals walking through a room with an astonishing 99.5% accuracy rate, creating an invisible, highly accurate tracking infrastructure. The security implications are profound because this tracking method bypasses traditional defenses. Even when individuals altered their walking style or carried bulky items like backpacks and crates, the experimental system still maintained a 50% to 60% identification rate. Because beamforming signals are broadcast unencrypted across millions of homes, offices, and public spaces, researchers warn that this loophole turns everyday networks into ready-made surveillance tools without requiring any specialized hardware. As wireless standards evolve, privacy experts are urgently calling for robust encryption updates to patch this invisible threat before it can be exploited on a mass scale. Source : Todt, J., Morsbach, F., & Strufe, T. (2025). BFId: Identity Inference Attacks Utilizing Beamforming Feedback Information. Karlsruhe Institute of Technology.

🚀 Enabling Precise Positioning in 6G Networks Imagine a world where your smartphone, autonomous car, or drone can locate itself with sub-meter accuracy—even in complex urban areas with no GPS signal. This is a critical capability for the future of 6G wireless networks, powering everything from smart factories to augmented reality. In our latest research, "Dynamical Multimodal Fusion with Mixture-of-Experts for Localizations", we introduce a new AI-based approach—SCADF-MoE—that achieves this level of precision by: ✅ Dynamically learning which signals are most reliable at different frequencies (2.6, 6, 28 GHz) ✅ Leveraging the spatial relationship between neighboring locations to reduce confusion in tricky environments ✅ Performing consistently—even in non-line-of-sight scenarios where traditional methods fail 📊 The results? A 63% improvement in accuracy and sub-meter localization, even under the hardest conditions. 💡 Why it matters: Accurate localization is the foundation of many 6G applications—like self-driving cars, digital twins, and robotics. Our work provides a scalable, AI-native solution that adapts across environments and frequency bands. Great collaboration with amazing colleagues from Zhejiang University, University of Michigan, and Khalifa University. You can read more here: https://lnkd.in/dnMj5abP #6G #AI #Localization #WirelessInnovation #SmartCities #AutonomousSystems #DeepLearning #MixtureOfExperts

Will future mobile networks do more than connect us, will they be able to “sense” the environment around them? 5G networks, with wider channel bandwidth options, brings the possibility of more accurate device positioning. However, future networks are considering going far beyond this, with technologies such as RF sensing and Integrated Sensing and Communication (ISAC) being explored for 6G. RF sensing uses radio frequency signals to detect and analyse objects and movements within an environment by measuring changes in the radio waves' propagation, reflection, and scattering. This technology extends beyond accurate positioning by gathering detailed data on object movement, speed, and even material properties. ISAC represents a broader integration of sensing and communication technologies. It combines RF sensing with other types of sensors, such as cameras, LIDAR, and motion sensors, to create a comprehensive system capable of both high-precision communication and detailed environmental sensing. This integration enables networks to function as both communication platforms and environmental sensors, opening up new possibilities and use cases. An application within ISAC is Simultaneous Localisation and Mapping (SLAM), which uses data from these diverse sensors to create real-time 2D and 3D maps of the environment while simultaneously determining the precise location of objects and devices, enhancing navigation and positioning capabilities (see paper in comments). 3GPP (TR 22.837) calls out 32 potential use cases for ISAC, such as smart homes, flood detection, factory floor ground vehicle detection, tracking and collision avoidance, and use cases for Unmanned Aerial Vehicles (UAVs). Nokia Bell Labs has called this area “Network as a Sensor” and is working with Bosch on 5G positioning trials along with considerations for ISAC. Qualcomm has tested and simulated RF sensing over an outdoor 28GHz network. What are your thoughts on the likelihood of this being a real use case for networks in the future? Anyone have any other details of trials in this area? #technology #6G #innovation #sensors #telecoms [Video: Qualcomm]

📢 Excited to share our latest paper published in ACS Applied Materials & Interfaces! Huge kudos to our PhD students Maria Sattar and Yoon Jae Phillip Lee, along with our esteemed collaborator Dr. Shannon Yee. Find the paper here: https://lnkd.in/gzN_BM5T ℹ️ Our paper introduces a groundbreaking wearable, self-powered, thermoelectric flexible system architecture. This innovative system allows for wireless portable monitoring of physiological signals without the need for recharging batteries. 🔋 The system harnesses an impressive open circuit voltage of 175–180 mV from the human body, enabling the wireless wearable bioelectronics to continuously detect electrophysiological signals on the skin. 🌟 By showcasing a self-sustainable wearable system capable of detecting electromyograms and electrocardiograms, we highlight the platform's potential to revolutionize continuous biosignal monitoring, remote health tracking, and automated disease diagnosis. Special thanks to our research sponsors: WISH Center, National Science Foundation (NSF), National Research Foundation of Korea, and Ministry of Trade, Industry, and Energy #GeorgiaTech #Flexible #Thermoelectric #Research #WearableTech #HealthTech #Innovation