MobiCom 2024 论文列表

Pico-satellite (picosat) constellations aim to become the de facto connectivity solution for Internet of Things (IoT) devices. These constellations rely on a large number of small picosats and offer global plug-and-play connectivity at low data rates, without the need for Earth-based gateways. As picosat constellations scale, they run into new bottlenecks due to their traditional medium access designs optimized for single (or few) satellite operations. We present CosMAC - a new constellation-scale medium access and scheduling system for picosat networks. CosMAC includes a new overlap-aware medium access approach for uplink from IoT to picosats and a new network layer that schedules downlink traffic from satellites. We empirically evaluate CosMAC using measurements from three picosats and large-scale trace-driven simulations for a 173 picosat network supporting 100k devices. Our results demonstrate that CosMAC can improve the overall network throughput by up to 6.5X over prior state-of-the-art satellite medium access schemes.

Recent advancement in Frequency Domain Duplexing (FDD) enables wireless systems to use different frequency bands for uplink and downlink communication without explicit channel feedback information. The current state-of-the-art approaches either estimate the underlying variables in the uplink channel or use an artificial neural network architecture to estimate the downlink channel from the uplink channel. However, such techniques fail to perform accurately in multipath-rich environments and environments unseen during training. This paper presents HORCRUX, a physics-based machine learning system that can be generalized and scaled to any environment while predicting downlink channels with high accuracy and applies to single-antenna and MIMO systems. Our approach uses multiple neural networks, trained on the standard wireless channel model, firstly to divide the uplink channel into smaller sub-channels and secondly to generate coarse estimates for the variables for each of the underlying sub-channels. Finally, we use an efficient and fast optimization framework to get fine-tuned variable estimates to predict the downlink channel. We implement our system using software-defined radios. Our evaluations show that HORCRUX performs ~8 dB better than state of the art in downlink channel prediction accuracy in diverse wireless environments. 1

This paper presents a novel approach for crowd analytics using a single monostatic mmWave radar. We propose a new mathematical model that infers the crowd size for dynamic and quasi-dynamic crowd behaviors. More specifically, we derive a novel closed-form mathematical expression that describes the statistical dynamics of undercounting due to crowd shadowing. This new methodical finding allows for significantly improved crowd density estimates. For spatially-patterned crowds where the mathematical solution does not extend, we then develop a Temporal Convolutional Network (TCN) which is purely trained on simulated data. We perform extensive testing over a total of 22 experiments, with up to (and including) 21 people and in 4 different areas, including indoors, and the proposed mathematical solution achieves a Mean Absolute Error (MAE) of 1.53. Lastly, we show how our framework can infer anomalies, bottlenecks, and crowd engagement level. Overall, the paper can have a significant impact on crowd management and urban planning.

We present the design, implementation, and evaluation of SeaScan, an energy-efficient camera for 3D imaging of underwater environments. At the core of SeaScan's design is a trinocular lensing system, which employs three ultra-low-power monochromatic image sensors to reconstruct color images. Each of the sensors is equipped with a different filter (red, green, and blue) for color capture. The design introduces multiple innovations to enable reconstructing 3D color images from the captured monochromatic ones. This includes an ML-based cross-color alignment architecture to combine the monochromatic images. It also includes a cross-refractive compensation technique that overcomes the distortion of the wide-angle imaging of the low-power CMOS sensors in underwater environments. We built an end-to-end prototype of SeaScan, including color filter integration, 3D reconstruction, compression, and underwater backscatter communication. Our evaluation in real-world underwater environments demonstrates that SeaScan can capture underwater color images with as little as 23.6 mJ, which represents 37X reduction in energy consumption in comparison to the lowest-energy state-of-the-art underwater imaging system. We also report qualitative and quantitative evaluation of SeaScan's color reconstruction and demonstrate its success in comparison to multiple potential alternative techniques (both geometric and ML-based) in the literature. SeaScan's ability to image underwater environments at such low energy opens up important applications in long-term monitoring for ocean climate change, seafood production, and scientific discovery.

Soil monitoring plays an essential role in agricultural systems. Rather than deploying sensors' antennas above the ground, burying them in the soil is an attractive way to retain a non-intrusive aboveground space. Low Power Wide-Area Network (LPWAN) has shown its long-distance and low-power features for aboveground Internet-of-Things (IoT) communication, presenting a potential of extending to underground cross-soil communication over a wide area, which however has not been investigated before. The variation of soil conditions brings significant signal polarization misalignment, degrading communication reliability. In this paper, we propose Demeter, a low-cost low-power programmable antenna design to keep reliable cross-soil communication automatically. First, we propose a hardware architecture to enable polarization adjustment on commercial-off-the-shelf (COTS) single-RF-chain LoRa radio. Moreover, we develop a low-power programmable circuit to obtain polarization adjustment. We further design an energy-efficient heuristic calibration algorithm and an adaptive calibration scheduling method to keep signal polarization alignment automatically. We implement Demeter with a customized PCB circuit and COTS devices. Then, we evaluate its performance in various soil types and environmental conditions. The results show that Demeter can achieve up to 11.6 dB SNR gain indoors and 9.94 dB outdoors, 4× horizontal communication distance, at least 20 cm deeper underground deployment, and up to 82% energy consumption reduction per day compared with the standard LoRa.

Open and virtualized Radio Access Networks (vRANs) are breeding a new market with unprecedented opportunities. However, carrier-grade vRANs today are expensive and energy-hungry, as they rely on hardware accelerators (HAs) that are dedicated to individual distributed units (DUs). In this paper, we argue that sharing pools of heterogeneous processors among DUs leads to more cost- and energy-efficient vRANs. We then design CloudRIC, a system that, powered by lightweight data-driven models, meets specific reliability targets while (i) coordinating access between DUs and heterogeneous computing infrastructure; and (ii) assisting DUs with compute-aware radio scheduling procedures. Experiments on a GPU-accelerated O-Cloud show that CloudRIC can achieve, respectively, 3x and 15x mean gains in energy- and cost-efficiency under real RAN workloads while ensuring 99.999% reliability even in dense scenarios.

Limited-stop service represents a paradigm for enhancing efficiency in transportation systems, with applications spanning public transit, logistics, and supply chain management. This service model operates along a designated route featuring a reduced number of stops in comparison to standard services, thereby facilitating expedited transportation. In this research, we utilize accumulated data from Intelligent Transportation Systems for the development and deployment of a simulation-driven framework tailored towards augmenting the operational efficiency of limited-stop services. To illustrate the practical application of this framework, we focus on the paradigm of limited-stop bus services, elucidating the intricate technical facets of the proposed system. The efficacy and viability of this framework have been validated through a series of empirical investigations conducted within the urban bus transit network of Shenzhen, a prominent metropolis situated in China.

Intracortical brain-computer interfaces (iBCIs) promise to sense brain activity at an unprecedented scale and resolution. However, unlocking this potential for practical, untethered applications remains an unsolved challenge. The major barrier is the significant wireless bandwidth required to stream high-resolution brain signals. Existing approaches rely on extensive on-device processing, which is severely constrained by the limited resources of iBCI devices, the complexity of brain signals, and the dynamic nature of neural activity. This paper introduces Neuralite, a wireless iBCI system that integrates high-fidelity brain signal models and effective brain sensing mechanisms within an efficient server-driven streaming framework. By thoroughly characterizing brain signal variability, Neuralite adaptively optimizes streaming under dynamic neural conditions, minimizing bandwidth consumption without imposing excessive burdens on resource-constrained iBCI devices. Experimental results demonstrate that Neuralite significantly reduces bandwidth consumption while preserving neural decoding precision across key iBCI components and representative applications.

Beyond-5G and 6G wireless networks exploit the millimeter-wave (mmWave) frequency bands to achieve significantly improved data rates, and existing mmWave systems rely on analog single-user beamforming (SUBF) or hybrid multi-user beamforming (MUBF). In this work, we focus on improving the performance of multi-user communication in mmWave networks by exploring analog MUBF using an array of subarrays (ASA) with reduced system overhead and hardware complexity as it eliminates digital beamforming and the need for estimating the channel state information (CSI). We present Mambas, a novel system that maneuvers analog MUBF using an ASA to support simultaneous communication with multiple users located in close proximity, e.g., within the half-power beamwidth of the ASA. In essence, Mambas effectively decouples the user selection, subarray allocation, and beamforming optimization based on a comprehensive understanding of the multi-user support determined by the ASA. We evaluate Mambas using a 28 GHz software-defined radio testbed and show that, compared to existing methods, Mambas can effectively support users that are 2× more closely spaced while achieving an improved sum rate of up to 2×, using only two subarrays. Large-scale ray tracing-based simulations also show that Mambas can achieve a sum rate gain of 1.92--3.86× and is able to maintain consistent performance with significantly increased user density.

This paper introduces PanoRadar, a novel RF imaging system that brings RF resolution close to that of LiDAR, while providing resilience against conditions challenging for optical signals. Our LiDAR-comparable 3D imaging results enable, for the first time, a variety of visual recognition tasks at radio frequency, including surface normal estimation, semantic segmentation, and object detection. PanoRadar utilizes a rotating single-chip mmWave radar, along with a combination of novel signal processing and machine learning algorithms, to create high-resolution 3D images of the surroundings. Our system accurately estimates robot motion, allowing for coherent imaging through a dense grid of synthetic antennas. It also exploits the high azimuth resolution to enhance elevation resolution using learning-based methods. Furthermore, PanoRadar tackles 3D learning via 2D convolutions and addresses challenges due to the unique characteristics of RF signals. Our results demonstrate PanoRadar's robust performance across 12 buildings. Code, datasets, and demo videos are available on our website.

In this paper, we ask, "Can millimeter-wave (mmWave) radars sense objects not directly illuminated by the radar - for instance, objects located outside the transmit beamwidth, behind occlusions, or placed fully behind the radar?" Traditionally, mmWave radars are limited to sense objects that are directly illuminated by the radar and scatter its signals directly back. In practice, however, radar signals scatter to other intermediate objects in the environment and undergo multiple bounces before being received back at the radar. In this paper, we present Hydra, a framework to explicitly model and exploit multi-bounce paths for sensing. Hydra enables standalone mmWave radars to sense beyond-field-of-view objects without prior knowledge of the environment. We extensively evaluate the localization performance of Hydra with an off-the-shelf mmWave radar in five different environments with everyday objects. Exploiting multi-bounce via Hydra provides 2×-10× improvement in the median beyond-field-of-view localization error over baselines.

The pervasive use of WiFi has driven the recent research in WiFi sensing, converting communication tech into sensing for applications such as activity recognition, user authentication, and vital sign monitoring. Despite the integration of deep learning into WiFi sensing systems, potential security vulnerabilities to adversarial attacks remain unexplored. This paper introduces the first physical attack focusing on deep learning-based WiFi sensing systems, demonstrating how adversaries can subtly manipulate WiFi packet preambles to affect channel state information (CSI), a critical feature in such systems, and thereby influence underlying deep learning models without disrupting regular communication. To realize the proposed attack in practical scenarios, we rigorously analyze and derive the intricate relationship between the pilot symbol and CSI. A novel mechanism is proposed to facilitate quantitive control of receiver-side CSI through minimal modifications to the pilot symbols of WiFi packets at the transmitter. We further develop a perturbation optimization method based on the Carlini & Wagner (CW) attack and a penalty-based training process to ensure the attack's universal efficacy across various CSI responses and noise. The physical attack is implemented and evaluated in two representative WiFi sensing systems (i.e., activity recognition and user authentication) with 35 participants over 3 months. Extensive experiments demonstrate the remarkable attack success rates of 90.47% and 83.83% for activity recognition and user authentication, respectively.

As the primary channel for users to report and resolve service issues, customer care has historically been a critical and resource-intensive aspect of operating cellular networks. However, owing to the inherent complexity in correlating network events with the service performance experienced by individual users, adoption of data-driven solutions leveraging network data for realtime troubleshooting during customer care calls has remained a challenge to cellular service providers (CSPs). In this work, we propose a novel ML aSsisted cEllular sErvice diagNosis (SEEN) solution that infers the cause of user service issues from performance metrics observed from network and assists care agents during customer care calls. Our extensive evaluations demonstrated that SEEN can accurately identify the root cause of user reported performance issues in >80% cases, without relying on information provided by users. Accurate root cause prediction coupled with automated recommended resolution actions implemented in SEEN, lead to significant reduction in handling time to resolve service issues and in trouble tickets volume, improving customer satisfaction and reducing customer care operational expense. Benefit of SEEN is further demonstrated by field deployment in a large CSP.

Soil carbon is a critical factor in maintaining soil health and combating climate change. Understanding and managing soil carbon levels is essential for sustainable agriculture and environmental protection. However, current methods for measuring soil carbon are time-consuming and costly, hindering efforts to monitor soil health and increase carbon sequestration. In this paper, we propose Scarf, a novel soil carbon sensing approach that combines widely accessible radio frequency (RF) and optical signals to detect soil carbon contents without dedicated hardware. Our key insight is that soil carbon content closely correlates with two indicators: the effective permittivity derived from RF signals and soil lightness determined from soil surface images. We mathematically model the correlations and leverage the non-linear correlation between the two signal modalities to compute soil carbon content. We employ machine learning to model relationships that cannot be captured by traditional mathematical equations. Our experimental results indicate that Scarf can achieve high soil carbon prediction accuracy that is comparable to the state-of-the-art soil carbon sensing techniques which cost US$1000s.

In modern mobile applications, users frequently encounter various new contexts, necessitating on-device continual learning (CL) to ensure consistent model performance. While existing research predominantly focused on developing lightweight CL frameworks, we identify that data scarcity is a critical bottleneck for on-device CL. In this work, we explore the potential of leveraging abundant cloud-side data to enrich scarce on-device data, and propose a private, efficient and effective data enrichment framework Delta. Specifically, Delta first introduces a directory dataset to decompose the data enrichment problem into device-side and cloud-side sub-problems without sharing sensitive data. Next, Delta proposes a soft data matching strategy to effectively solve the device-side sub-problem with sparse user data, and an optimal data sampling scheme for cloud server to retrieve the most suitable dataset for enrichment with low computational complexity. Further, Delta refines the data sampling scheme by jointly considering the impact of enriched data on both new and past contexts, mitigating the catastrophic forgetting issue from a new aspect. Comprehensive experiments across four typical mobile computing tasks with varied data modalities demonstrate that Delta could enhance the overall model accuracy by an average of 15.1%, 12.4%, 1.1% and 5.6% for visual, IMU, audio and textual tasks compared with few-shot CL, and consistently reduce the communication costs by over 90% compared to federated CL.

This paper proposes an Emergency Battery Service (EBS) for drones in which an EBS drone flies to a drone in the field with a depleted battery and transfers a fresh battery to the exhausted drone. The authors present a unique battery transfer mechanism and drone localization that uses the Cross Marker Position (CMP) method. The main challenges include a stable and balanced transfer that precisely localizes the receiver drone. The proposed EBS drone mitigates the effects of downwash due to the vertical proximity between the drones by implementing diagonal alignment with the receiver, reducing the distance to 0.5 m between the two drones. CFD analysis shows that diagonal instead of perpendicular alignment minimizes turbulence, and the authors verify the actual system for change in output airflow and thrust measurements. The CMP marker-based localization method enables position lock for the EBS drone with up to 0.9 cm accuracy. The performance of the transfer mechanism is validated experimentally by successful mid-air transfer in 5 seconds, where the EBS drone is within 0.5 m vertical distance from the receiver drone, wherein 4m/s turbulence does not affect the transfer process.

People with Dementia (PwD) suffer from a high risk of getting lost due to their cognitive deterioration, leading to potential safety hazards and significant search efforts. In this paper, we propose DEmentia Caring System (DECS), an effective crowdsourcing platform to search for missing PwD. Specifically, PwD carry our customized Bluetooth Low Energy (BLE) tags that broadcast BLE packets, which are detected and then uploaded by mobile volunteers via their smartphones. To further enhance search efficiency, DECS deploys BLE gateways as its infrastructure and analyzes PwD's daily spatial-temporal mobility patterns. DECS has been deployed in Hong Kong since 2019, supporting 3,100+ PwD's families with over 45,000 app downloads by volunteers. More importantly, it has successfully served the search for 254 missing cases. This paper reports the unique lessons and experiences learned through our 4-year citywide deployment of DECS.

We present the design, implementation, and evaluation of RFlect, a mmWave imaging system capable of producing around-the-corner high-resolution images in practical environments. RFlect leverages signals reflected off complex surfaces (e.g., poles, concave surfaces, or composition of multiple surfaces) to image objects that are not in the RF line-of-sight. RFlect models the reflections and introduces reconstruction algorithms for different types of surfaces. It also leverages a novel method for precisely mapping the location and geometry of the reflecting surface. We also derive the theoretical resolution and coverage for different reflecting surface geometries. We built a prototype of RFlect and performed extensive evaluations to demonstrate its ability to reconstruct the shape of objects around the corner, with an average Chamfer Distance of 2cm and 3D F-Score of 88.6%.