Bluetooth audio faces a major challenge due to its limited transmission range in meeting users' demands. This work introduces WiLE-Audio, a novel approach that extends Low Energy Audio (LE Audio) coverage through cross-technology communication (CTC) from WiFi to BLE. We first present a novel symbol mapping technique to enable all-channel and reliable CTC. Then, we present a real-time reverse scrambling method to implement CTC to commodity WiFi devices. Finally, we design a precise timing strategy and a priority scheduling to align with the strict time window requirements of the BLE receiver. These systematic innovations allow WiLE-Audio to be easily implemented into existing commercial devices with only a simple software upgrade on the WiFi side. Furthermore, we achieve seamless switching between Bluetooth classic audio and WiLE-Audio, thus supporting whole-house audio roaming. We implement our work on commercial WiFi and BLE devices and demonstrate that WiLE-Audio extends the transmission distance of LE Audio more than 2x.
Daily eating habits shape our long-term health, but most diet apps focus only on calories or macronutrients and overlook deeper issues like chronic inflammation and its effects on cellular aging. Prior medical literature has demonstrated a significant inverse relationship between Dietary Inflammatory Index (DII) and telomere length (TL), a key marker of cellular age. Inspired by this finding, we design ChronoBite, a closed-loop feedback system that pairs real-time inflammation scores with periodic cellular aging insights. In addition to regular calorie tracking, it uses fast-changing DII signals and slow-moving cellular aging markers to guide users toward age-aware eating habits. ChronoBite is a mobile-based prototype that combines food recognition, DII analysis, and cellular aging insights to deliver age-aware dietary feedback. Powered by large language models (LLMs), it offers real-time recommendations while supporting long-term tracking of inflammation patterns and telomere dynamics.
Conventional pulmonary function tests (PFTs) are important but costly. Hence, prior research has proposed IoT sensor-based solutions to facilitate cost-efficient, at-home PFT. However, these solutions require the subject to perform maximal exhalations, a task often challenging without supervision, compromising test accuracy. In response to this challenge, this study introduces EasySpiro that, for the first time, uses non-maximal exhalations to measure PFT indicators. This is challenging since PFT indicators are only defined for maximal exhalations, and there are no guidelines to derive them from submaximal exhalations. To address that, we observe that pulmonary deficiencies affect all types of breathing, where the underlying pulmonary deficiency should be the same under different breathing efforts. Leveraging this insight, we design a reconstruction model to predict the ideal maximal breathing patterns based on submaximal ones and utilize these reconstructions for PFT. Furthermore, since the body dynamics reflect the exhalation effort, we use self-supervised learning techniques to encode body dynamics into breathing effort representations to guide the reconstruction process. We integrate these designs into earphones with microphones to measure breathing patterns and IMUs to measure body dynamics. We collaborate with a hospital and develop a dataset from 50 patients with various diseases to evaluate EasySpiro's performance, which shows an accurate prediction of PFT indicators based on non-maximal exhalations with an error rate of 7%. In addition, we open-source the collected dataset to encourage future research.
As the adoption of LiDAR expands across various fields such as autonomous driving, robotics, and smart cities, the demand for adaptive scanning capabilities to better capture dynamic and complex scenes becomes paramount. Current LiDAR technologies, limited by fixed uniform scan patterns, struggle to prioritize critical areas, resulting in reduced perception accuracy and performance inefficiencies. This paper introduces SmartLiDAR, an advanced LiDAR system that enhances scanning efficiency and performance by adaptively optimizing scan focus through an intelligent, software-defined micro-mirror controller. Unlike traditional systems, SmartLiDAR dynamically adjusts its scan pattern based on environmental characteristics and application-specific requirements, concentrating sample points on key objects without increasing power consumption or scan time. SmartLiDAR achieves this by integrating a novel quadratic micro-mirror controller, an adaptive algorithm for generating fine-grained attention map with prioritized scan focus, and a carefully designed optimization algorithm that maps attention maps to practical scanning patterns. We prototype SmartLiDAR by building a software-defined LiDAR using commercially available optical components and FPGA. Our experimental results demonstrate that SmartLiDAR significantly enhances resolution in regions of interest by 3x and increases average object detection precision by up to 16.11%. Additionally, SmartLiDAR maintains negligible extra energy consumption and processing latency, making it suitable for real-time applications, such as autonomous vehicles.
In-home resistance training (RT) is a convenient and effective way to maintain health andwell-being. However, incorrect exercise execution can result in unintended muscle engagement and an increased risk of injury. Without access to professional coaching, an accurate muscle-aware motion feedback system becomes essential for safe and effective training. However, existing visual language models (VLMs) struggle to provide accurate and effective muscle-aware movement guidance due to their limited understanding of RT motion and the absence of related expert knowledge. In this work, we introduce Myo-Trainer, the first vision-based muscle-aware motion feedback system that uses explicit muscle-aware motion analysis and domain-specific expert knowledge to provide corrective guidance on muscle engagement and movement execution. Also, we propose a novel DAGCN-Former network that integrates both spatial and temporal modeling capabilities to capture the complex dynamics of human RT motion. Experiments involving 26 subjects and 1000+ minutes of RT demonstrate that Myo-Trainer improves the accuracy of motion analysis by 17.22%, achieves a 2.5x reduced inference latency and a BertScore of 85.88% of generated feedback compared to those provided by experienced certified trainers, outperforming existing solutions. Additionally, Myo-Trainer received higher satisfaction ratings from participants compared to other AI trainers and video tutorials, highlighting its potential for real-world applications.
The high bandwidth demand of raw sensor data transmission remains a critical bottleneck for scalable Vehicle-to-Everything (V2X) networks. We propose Car2Vec - a selfsupervised contrastive learning framework that generates compact latent embeddings from vehicle CAN bus data. Our initial experiments demonstrate the framework's ability to create visually distinguishable embeddings in latent space, successfully separating clusters for fuel from different suppliers and identifying varying levels of motor oil viscosity. These early results suggest the framework's potential to encode semantic state information including vehicle dynamics and driver context, and serve as efficient communication primitives for V2V/V2I applications, potentially reducing wireless overhead by orders of magnitude compared to raw telemetry. By moving computation to vehicle edge devices, Car2Vec aligns with the AI-RAN co-design vision, offering a promising direction for semantic-aware resource optimization in next-gen transportation networks.
The Wi-Fi-enabled ultra-low power communication system exhibits high asymmetry between uplink and downlink speeds. The uplink can reach up to 1 Mbps, while the downlink throughput is around 100 Kbps. In this paper, we present Wook, a novel high throughput downlink system to empower Commercial Off-The-Shelf (COTS) Wi-Fi devices to transmit high-speed OOK messages. The key innovation underpinning Wook is its ability to achieve sub-symbol level modulation, allowing a single OFDM symbol to carry multiple OOK bits. This is done by profoundly exploring the Wi-Fi PHY layer and identifying optimal input payload to achieve fine-grained Wi-Fi waveform manipulation. We fabricate a PCB prototype and employ the COTS Wi-Fi router to implement the entire system. Experimental results show that with a simulated IC power consumption 76.6 mu W, Wook achieves a data rate of up to 1.1 Mbps, an 8.9X improvement over state-of-the-art systems. Moreover, even at a communication distance of 95 m, Wook maintains a throughput of 82.9 Kbps.
Localization is a critical task for underwater robots, yet today's underwater localization systems are limited by their accuracy, scalability, and/or energy consumption (i.e., longevity). We present the design, implementation, and evaluation of EchoBLUE- an accurate, scalable, and low-power localization system for underwater robots. In EchoBLUE, an underwater robot transmits SONAR-style (FMCW) signals, and leverages ultra-low power underwater backscatter nodes as location anchors. EchoBLUE's design introduces two key innovations. The first is a novel doppler compensation mechanism that enables it to accurately self-localize under mobility: the technique employs a cross-chirp mechanism that exploits the quad-band nature of the resulting backscatter response to overcome the range-doppler ambiguity. Second, it introduces the first semi-active retrodirective underwater backscatter design and uses it for location anchors; this design achieves wide bandwidth to backscatter the full FMCW signal, enabling fine-grained localization. We implemented a proof of concept prototype of EchoBLUE by building a base station mounted on a BlueROV2 underwater robot and custom-designed low-power retrodirective location anchors deployed in a pool. Our evaluation across 700 real-world trials demonstrates that EchoBLUE achieves a median 3D localization accuracy of 28 cm and 90th percentile of 48 cm. Moreover, these anchors consume only 740 mu W for semi-active backscatter, paving the way for truly low-power and scalable underwater localization.
User-level mobile traffic data is essential for fine-grained network planning, but it is difficult to collect due to privacy concerns and deployment costs. A promising solution is to generate synthetic traffic data, however, existing generative methods fail to recover realistic distributions under extreme sparsity. To address this limitation, we propose Multivariate-Imaged Diffusion (MIDiff), which encodes multi-variate mobile-usage and user trajectories data as phase relationships and transforms them into two-dimensional images. By adapting the Gramian Angular Summation Field into a cross-relation computation, MIDiff highlights sparse but important data points as salient image features for diffusion. Experimental results demonstrate that MIDiff achieves higher similarity to real data and reduces temporal consistency error by 72% compared to TTS-GAN.
Wi-Fi is deemed as a promising sensing media due to its ubiquity, yet Wi-Fi sensing is known to be confined by its limited bandwidth that leads to insufficient range resolution. Though sampling a wider spectrum multiple times can enable wideband sensing, its practicality is still hampered by the need for accessing Wi-Fi firmware. In this paper, we propose mu Ceiver-Fi to exploit spectrum resources for fine-granularity Wi-Fi sensing; it relies solely on a commodity multi-link receiver. Since the channel samples from multiple links under the same receiver can still be misaligned, we first innovate in a comprehensive calibration process to align these samples. This is followed by a novel optimization framework to extend effective sensing bandwidth to GHz-level using only a few channel samples. Finally, we specifically design a spectral representation for sensing information in order to bridge between wideband signals and diversified downstream applications. Through comprehensive evaluations in Wi-Fi pose estimation task, we demonstrate the promising performance of mu Ceiver-Fi in fine-granularity sensing.
This paper proposes a novel FL method called FedFNS, which integrates feature norm regularization and statistical aggregation. Specifically, a local model correction strategy is proposed to reduce client bias through incorporating a regularization term into the loss function. To mitigate the negative effects of unreliable communications on global model performance, a statistical weighted aggregation strategy is proposed, which leverages the transmission success probability of each client. The effectiveness of FedFNS is validated through extensive experiments, demonstrating its superiority over several classic FL methods in terms of accuracy.
With the increasing adoption of unmanned aerial vehicles (UAVs) in critical applications such as infrastructure inspection and emergency response, efficient on-site recognition via live video analytics and streaming has become essential. However, the inherent resource limitation poses significant challenges for performing simultaneous and real-time video analytics and streaming on UAVs. To address this issue, we propose a unified framework that orchestrate the Neural Processing Unit (NPU) and Graph Processing Unit (GPU) of the Systems-on-Chip (SoC) processor to accelerate and carefully schedule the pipeline of video analytics and streaming on UAVs. Additionally, our system incorporates frame interpolation to enable real-time streaming of video analytics results, providing immediate visual feedback to on-site operators. Empirical results on a commercial UAV equipped with Snapdragon 865 SoC platform show that our system reduces per-frame inference latency from 163ms (GPU) to 63ms (NPU), achieving a 2.6x speedup. Combined with optimized pre-processing and frame interpolation, our system increases effective streaming throughput from 2 to 30 FPS, enabling smooth and simultaneous real-time video analytics and streaming.
Joystick has been a major interactive controller for a wide range of devices, e.g., entertainment systems and drones. Recently, the Hall-effect joystick has been gaining traction because of its unique advantages in fine-grained control and durability. Despite the popularity of the Hall-effect joystick, we discovered that this emerging technique is susceptible to controllable magnetic field injection. In this demo, we present MagneCon, a mobile, programmable magnetic injection system capable of hijacking commodity Hall-effect joysticks by injecting carefully crafted magnetic fields. We validate our system on a real-world setup and demonstrate two representative attack scenarios: pre-loaded trajectory injection and real-time untethered hijack of the victim's joystick.
Accurate, ubiquitous indoor localization has long been a central goal in wireless systems, yet most proposed methods remain impractical for large-scale deployment. We present PeepLoc, a scalable Wi-Fi-based system that leverages existing infrastructure and unmodified mobile devices. PeepLoc operates in any indoor space with standards-compliant Wi-Fi APs and regular pedestrian traffic. It combines (a) extracting non-cooperative time-of-flight (ToF) from any AP, and (b) a crowdsourced bootstrapping approach using pedestrian dead reckoning (PDR) to localize APs as anchors. Implemented on commodity hardware, PeepLoc is evaluated across four buildings, achieving 3.41m mean and 3.06m median error, outperforming commercial indoor localization systems and approaching GPS-level accuracy outdoors.
High-Performance Optical Camera Communications (HP-OCC) extends conventional Optical Camera Communication (OCC) by combining single-photon avalanche diode (SPAD) sensors with on-sensor edge processing. This enables high-speed optical communication and centimetre-level localization within a single platform, offering a compelling optical-domain alternative for Integrated Sensing and Communication (ISAC) in RF-restricted or congested environments. In collaboration with Kuehne+Nagel, HP-OCC was deployed in an operational warehouse to evaluate two logistics applications: inventory tracking using passive optical tags and warehouse automation via an AGV equipped with HP-OCC for simultaneous video streaming and localization. Passive tags, operating without dedicated power, were reliably identified despite interference from ambient LED lighting, while AGV trials demonstrated stable 5Mbps video transmission and 10cm localization accuracy over 25m. Higher data rates are possible with advancements in SPAD technology.
Despite large language models (LLMs) being an essential part of our lives, training of LLMs still needs to be done in cloud data centers due to the large requirements of data and computing power, leaving fine-tuning pre-trained LLMs on resource-constrained mobile devices remains highly underexplored. In this demo, we present Confidant, a practical collaborative training system that allows modern LLMs to be fine-tuned across multiple off-the-shelf mobile devices. Confidant partitions an LLM into several sub-models, deploying each of them to a mobile device. Multiple mobile devices then collaborate to train the LLM by employing a novel pipeline parallel training approach. Specifically, Confidant encompasses a memory-aware dynamic model partitioning and intra-device multi-processor scheduler to minimize the training time across heterogeneous platforms. A hybrid fault tolerance mechanism is also devised to proactively manage potential device and network failures. By building a cross-framework adapter and fully implementing Confidant on smartphones and laptops, we present the demo of collaborative training on a variety of mobile platforms.
Various wireless technologies have been utilized for sensing. Although promising, these wireless sensing technologies have inherent limitations. Prior research mainly focuses on overcoming the limitations of an individual wireless sensing technology, and little attention has been paid to the potential benefits of sensing with more than one wireless technology. In this paper, we introduce the concept of cross-technology sensing for the first time, and propose LoFiSen to enable LoRa-to-WiFi sensing. LoFiSen leverages the strengths of both LoRa and WiFi-combining LoRa's long-range capability with WiFi's pervasiveness. The chirp characteristic of LoRa signal significantly improves the sensing range of WiFi, and the widespread availability of WiFi devices makes LoRa sensing more pervasive. LoFiSen is fully compatible with LoRa and WiFi protocols, and can work on commodity LoRa and WiFi hardware. The key component of our design is enabling the WiFi receiver to capture fine-grained LoRa signal variations for sensing. Real-world experiments demonstrate that LoFiSen improves the WiFi sensing range for respiration monitoring from 8 m to 41 m, and pushes the walking sensing range from 16 m to 73.5 m. Through-wall passive respiration monitoring, previously infeasible with state-of-the-art WiFi sensing, is now possible with LoFiSen.
3D human pose estimation is a key technology for applications like healthcare and robotics, but its performance in real-world deployments is often compromised by viewpoint variations. We propose FreePose, a novel framework that achieves viewpoint invariance by explicitly disentangling motion and view features. The core of FreePose is a lightweight view estimator that predicts camera viewpoint from intermediate pose features. This information is then used to guide robust feature alignment and enable a view-aware inference pipeline that adaptively optimizes for latency on edge devices. We will demonstrate our system using a single Intel RealSense D435 camera, capturing from varying viewpoints throughout the demo, with real-time pose inference performed on a PC and an NVIDIA Jetson Orin NX. By leveraging FreePose, our framework achieves consistent accuracy and high frame rates across varying camera angles and positions. A video demonstration of FreePose's performance is available at https://youtu.be/tDIpCcbaRXc.
We propose a blockchain-enabled lightweight federated learning (BlockFL-Med) framework tailored for smart medical spaces, e.g., the Internet of Medical Things (IoMT), addressing key challenges, e.g., privacy preservation, trust management, and scalability. The framework ensures the privacy of sensitive patient data by employing federated learning, where only model updates are shared instead of raw data. To enhance trust, the framework integrates blockchain technology, creating a decentralized and tamper-proof network that verifies client contributions and mitigates risks from malicious participants. Experimental results demonstrate the scalability and efficiency issues by optimizing communication costs, e.g., transmitting lightweight kilobyte-sized model updates instead of larger megabyte-sized models, making it well-suited for heterogeneous and resource-constrained IoMT environments.
Personalized Federated Learning (PFL) targets client-specific models under heterogeneous and limited data. However, conventional methods often use heuristic or data-size-based averaging and overlook the true contributions of client updates. We propose a contribution-oriented PFL framework that quantifies client contributions via gradient alignment and prediction discrepancy for informed aggregation. We further develop a parameter-wise personalization mechanism for adaptive local updates and a mask-aware momentum optimizer for stable training. Preliminary results on CIFAR10 validate its effectiveness.
