MobiCom 2023 Papers

With the turn of new decade, wireless communications face a major challenge on connecting many more new users and devices, at the same time being energy efficient and minimizing its carbon footprint. However, the current approaches to address the growing number of users and spectrum demands, like Massive MIMO, demand exorbitant energy consumption. The reason is that traditionally Massive MIMO requires a digital beamforming architecture that needs a separate RF chain per antenna, so the power consumption scales with number of antennas. Instead, GreenMO creates a new Massive MIMO architecture with just a single physically laid RF chain, shared by all the antennas and introduces for the first time, the concept of virtualizing the RF chain hardware. That is, GreenMO creates an optimal number of virtual RF chains to serve a given number of spatial streams, depending on channel conditions and network load. Due to efficient, softwarized control over the number of virtual RF chains, GreenMO paves the way for green and flexible massive MIMO. We prototype GreenMO on a PCB with eight antennas and evaluate it with a WARPv3 SDR platform in an office environment. The results demonstrate that GreenMO is 3× more power-efficient than traditional Massive MIMO and 4× more spectrum-efficient than traditional OFDMA systems, while multiplexing 4 spatial streams, and can save upto 50% power in modern 5G NR base stations.

Privacy-preserving machine learning (PPML) techniques have allowed remote and private inference for resource-constrained internet-of-things (IoT) devices on the cloud. The main challenge in most of the existing PPML technologies is a severe slowdown in inference latency mainly due to the use of encryption during the computation. To combat this, an emerging method is to leverage encoding as an alternative. While this results in a significant speedup, it imposes the burden of encoding to the resource-constrained IoT/edge device. Despite being feasible for simple workloads where encoding is lightweight, devices with very limited computational capabilities face a tradeoff between latency and privacy when performing complex tasks.

There is much interest in fine-grained RFID localization systems. Existing systems for accurate localization typically require infrastructure, either in the form of extensive reference tags or many antennas (e.g., antenna arrays) to localize RFID tags within their radio range. Yet, there remains a need for fine-grained RFID localization solutions that are in a compact, portable, mobile form, that can be held by users as they walk around areas to map them, such as in retail stores, warehouses, or manufacturing plants.

Toxic gases inhalation is the most common cause of death in fire scenes, which can make people unconscious and unable to save themselves. Hence, discovering the unconscious victims is crucial to improve their survival rate. In this paper, we propose RF-Search, a victim searching system with RF device mounted on the drone. The challenge mainly comes from the fact that drone motion would overwhelm the subtle vital signs utilized for victim identification. To resolve this problem, we have noted that the physical signature of drone motion has been encoded in stationary object reflections. Leveraging this unique physical signature, we propose to identify the unconscious victim through the spatio-temporal correlation between signals reflected from the victim and the surrounding stationary objects. To extract respiration information of the victim, we propose a motion segmentation module and a motion compensation module to suppress the signal variation caused by drone movement. Extensive experiments have demonstrated that our system could achieve an accuracy of 92.5% for victim identification.

Despite the prevalence of GPS services, they still suffer from intermittent positioning with poor accuracy in partially shadowed regions like urban canyons, flyover shadows, and factories' indoor areas. Existing wisdom relies on hardware modifications of GPS receivers or power-hungry infrastructures requiring continuous plug-in power supply which is hard to provide in outdoor regions and some factories. This paper fills the gap with GPSMirror, the first GPS-strengthening system that works for unmodified smartphones with the assistance of newly-designed GPS backscatter tags. The key enabling techniques in GPSMirror include: (i) a meticulous hardware design with microwatt-level power consumption that pushes the limit of backscatter sensitivity to re-radiate extremely weak GPS signals with enough coverage approaching the regulation limit; and (ii) a novel GPS positioning algorithm achieving meter-level accuracy in shadowed regions as well as expanding locatable regions under inadequate satellites where conventional algorithms fail. We build a prototype of the GPSMirror tags and conduct comprehensive experiments to evaluate them. Our results show that a GPSMirror tag can provide coverage up to 27.7 m. GPSMirror achieves median positioning accuracy of 3.7 m indoors and 4.6 m in urban canyon environments, respectively.

This paper introduces RFIMap, a system that aims to inexpensively characterize the spatial and temporal distribution of RF spectrum occupancy of any indoor space at fine granularity (tens of centimeters). RFIMap builds rich wide-band indoor spectrum occupancy maps using low-cost and battery-free commodity RFID tags. RFIMap's spectrum maps have wide-ranging applications such as monitoring ambient interference in smart manufacturing, and smart hospitals. RFIMap relies on the observation that commodity RFID tags naturally reflect ambient transmission at other frequency bands, without any modification. RFIMap uses these reflections to estimate the ambient signal power originally received at these tags. RFIMap further performs a careful modeling of indoor multipath to build a dense spectrum map with fine spatial granularity. Our experiments demonstrate spatial spectrum measurement with 2.15 dB of median error at 2.4 GHz, 4.45 dB of median error at 470-700 MHz TV whitespace band, 2.1 dB of median error at 1.8-1.9 GHz in diverse industrial and university settings.

Cooperative perception significantly enhances the perception performance of connected autonomous vehicles. Instead of purely relying on local sensors with limited range, it enables multiple vehicles and roadside infrastructures to share sensor data to perceive the environment collaboratively. Through our study, we realize that the performance of cooperative perception systems is limited in real-world deployment due to (1) out-of-sync sensor data during data fusion and (2) inaccurate localization of occluded areas. To address these challenges, we develop RAO, an innovative, effective, and lightweight cooperative perception system that merges asynchronous sensor data from different vehicles through our novel designs of motion-compensated occupancy flow prediction and on-demand data sharing, improving both the accuracy and coverage of the perception system. Our extensive evaluation, including real-world and emulation-based experiments, demonstrates that RAO outperforms state-of-the-art solutions by more than 34% in perception coverage and by up to 14% in perception accuracy, especially when asynchronous sensor data is present. RAO consistently performs well across a wide variety of map topologies and driving scenarios. RAO incurs negligible additional latency (8.5 ms) and low data transmission overhead (10.9 KB per frame), making cooperative perception feasible.

Fast and accurate obstacle avoidance is crucial to drone safety. Yet existing on-board sensor modules such as frame cameras and radars are ill-suited for doing so due to their low temporal resolution or limited field of view. This paper presents BioDrone, a new design paradigm for drone obstacle avoidance using stereo event cameras. At the heart of BioDrone is two simple yet effective system design inspired by the mammalian visual system, namely, a chiasm-inspired signal processing pipeline for fast event filtering and obstacle detection, and a lateral geniculate nucleus (LGN)-inspired event matching algorithm for accurate obstacle localization. To make BioDrone a practical solution, we further take significant engineering efforts to deploy the software stack on FPGA through software and hardware co-design. The performance comparison with two state-of-the-art event-based obstacle avoidance systems shows BioDrone achieves a consistently high obstacle detection rate of 96.1%. The average localization error of BioDrone is 6.8cm with a 4.7ms latency, outperforming both baselines by over 40%.

Designing ultra-low power RFID sensor tags is a major challenge, especially when incorporating a micro-controller (MCU) to operate sensors. While simplifying MCU functionality can reduce power consumption, it has limited effect as the fundamental information transformation is necessary for communication between the RFID reader and the sensor. Unfortunately, information transformation requires baseband sampling and processing, which consumes significant power on passive RFID tags. This paper proposes a novel approach that enables the reader to communicate directly with the sensor, eliminating the need for information transformation of MCU. We address the unique challenges posed by the physical and link layers of the EPC Gen2 protocol and introduce GoodID, a cross-layer design for next-generation RFID sensor tags featuring ultra-low power consumption. We prototype the GoodID tag for proof-of-concept and demonstrate significant power benefits through experimental results.

Search Engines such as Google, Baidu, and Bing have revolutionized the way we interact with the cyber world with a number of applications in recommendations, learning, advertisements, healthcare, entertainment, etc. In this paper, we design search engines for sign languages such as American Sign Language (ASL). Sign languages use hand and body motion for communication with rich grammar, complexity, and vocabulary that is comparable to spoken languages. This is the primary language for the Deaf community with a global population of ≈ 500 million. However, search engines that support sign language queries in native form do not exist currently. While translating a sign language to a spoken language and using existing search engines might be one possibility, this can miss critical information because existing translation systems are either limited in vocabulary or constrained to a specific domain. In contrast, this paper presents a holistic approach where ASL queries in native form as well as ASL videos and textual information available online are converted into a common representation space. Such a joint representation space provides a common framework for precisely representing different sources of information and accurately matching a query with relevant information that is available online. Our system uses low-intrusive wearable sensors for capturing the sign query. To minimize the training overhead, we obtain synthetic training data from a large corpus of online ASL videos across diverse topics. Evaluated over a set of Deaf users with native ASL fluency, the accuracy is comparable with state-of-the-art recommendation systems for Amazon, Netflix, Yelp, etc., suggesting the usability of the system in the real world. For example, the re-call@10 of our system is 64.3%, i.e., among the top ten search results, six of them are relevant to the search query. Moreover, the system is robust to variations in signing patterns, dialects, sensor positions, etc.

Hyperspectral imaging systems capture information in multiple wavelength bands across the electromagnetic spectrum. These bands provide substantial details based on the optical properties of the materials present in the captured scene. The high cost of hyperspectral cameras and their strict illumination requirements make the technology out of reach for end-user and small-scale commercial applications. We propose MobiSpectral, which turns a low-cost phone into a simple hyperspectral imaging system, without any changes in the hardware. We design deep learning models that take regular RGB images and near-infrared (NIR) signals (which are used for face identification on recent phones) and reconstruct multiple hyperspectral bands in the visible and NIR ranges of the spectrum. Our experimental results show that MobiSpectral produces accurate bands that are comparable to ones captured by actual hyperspectral cameras. The availability of hyperspectral bands that reveal hidden information enables the development of novel mobile applications that are not currently possible. To demonstrate the potential of MobiSpectral, we use it to identify organic solid foods, which is a challenging food fraud problem that is currently partially addressed by laborious, unscalable, and expensive processes. We collect large datasets in real environments under diverse illumination conditions to evaluate MobiSpectral. Our results show that MobiSpectral can identify organic foods, e.g., apples, tomatoes, kiwis, strawberries, and blueberries, with an accuracy of up to 94% from images taken by phones.

Location awareness is the basis for enabling pickup service at ride-hailing platforms. In contrast to the almost pervasive coverage outdoors, indoor localization availability is still sporadic in industry since it largely relies on RF signatures from certain IT infrastructure, e.g., WiFi access points. Based on our 2-year observations at DiDi ride-hailing platform in China, there are 68k orders everyday created at black-hole, i.e., where only cellular signals exist. In this paper, we present the design, development, and deployment of TransparentLoc, a large-scale cellular localization system for pickup position recommendation, and share our 2-year experience with 50 million orders across 13 million devices in 4541 cities to address practical challenges including sparse cell towers, unbalanced user fingerprints, and temporal variations. Our system outperforms the iOS built-in cellular localization system in terms of four major service metrics, regardless of environmental changes, smartphone brands/models, time, and cellular providers.

Low Earth Orbit (LEO) satellite communication is essential for wireless communication. While manufacturing and launching LEO satellites have become efficient and cost-effective, ground stations remain expensive due to complex designs for handling severe path losses and precise beam tracking. Hence, it is important to develop low cost and high-performance ground stations for widespread adoption of LEO satellite communication. Towards realizing this goal, we design a passive metasurface-enhanced LEO ground station system, named PMSat, combining metasurface's fine-grained beamforming capability with a small-size phased array's adaptive steering and focusing. For uplink, we jointly optimize the phase array codebook and uplink metasurface phase profile, and realize electronic steering by switching the codeword. We further jointly optimize the downlink metasurface phase profile to improve the focusing performance and enhance the received signal strength (RSS) over a wide range of incident angles. Our PMSat prototype consists of a single passive metasurface with 21 × 21 elements for uplink and 22 × 22 for downlink, along with 1 × 4 receiving and 1 × 4 transmitting phased array antennas. The effectiveness of our proposed PMSat is validated through extensive experiments, and results demonstrate that the optimized metasurface improves the SNR by 8.32 dB and 16.57 dB for uplink and downlink, respectively.

Earth observation Low Earth Orbit (LEO) satellites collect enormous amounts of data that needs to be transferred first to ground stations and then to the cloud, for storage and processing. Satellites today transmit data greedily to ground stations, with full utilization of bandwidth during each contact period. We show that due to the layout of ground stations and orbital characteristics, this approach overloads some ground stations and underloads others, leading to lost throughput and large end-to-end latency for images. We present a new end-to-end scheduler system called Umbra, which plans transfers from large satellite constellations through ground stations to the cloud, by accounting for both spatial and temporal factors, i.e., orbital dynamics, bandwidth constraints, and queue sizes. At the heart of Umbra is a new class of scheduling algorithms called withhold scheduling, wherein the sender (i.e., satellite) selectively under-utilizes some links to ground stations. We show that Umbra's counter-intuitive approach increases throughput by 13--31% & reduces P90 latency by 3--6 ×.

The ability to assess the quality of fruit and vegetables at scale can revolutionize the agriculture sector and significantly reduce food waste. In this paper, we present AgriTera, a novel solution for accurate non-invasive, and contract-free fruit ripeness sensing via sub-terahertz wireless signals. The key idea is that sugar and water concentrations in fruit (that are associated with fruit ripening) leave unique non-uniform footprints in the wide band spectrum of the reflected signal off of the fruits. AgriTera utilizes the sub-THz bands for its wide bandwidth, sensitivity to water, mm-scale penetration depth, and non-ionizing features that offer high-resolution inferences from the peel as well as the pulp underneath the peel. We develop a chemometric model that translates the reflection spectra to well-known ripeness metrics, namely Dry Matter and Brix. We conduct extensive over-the-air experiments with commercially available sub-THz transceivers. We compare our results with ground truth values captured by a specialized quality sensor and a vision-based scheme that infers ripeness based on changes in the appearance of the fruit. We demonstrate that AgriTera can accurately estimate Brix and Dry Matter in three different types of fruit with an average Normalized RMSE value of 0.55%, an error that yields a negligible impact on taste and is imperceivable by the consumer.

Mapping 3D airflow fields is important for many HVAC, industrial, medical, and home applications. However, current approaches are expensive and time-consuming. We present Anemoi, a sub-$100 drone-based system for autonomously mapping 3D airflow fields in indoor environments. Anemoi leverages the effects of airflow on motor control signals to estimate the magnitude and direction of wind at any given point in space. We introduce an exploration algorithm for selecting optimal waypoints that minimize overall airflow estimation uncertainty. We demonstrate through microbenchmarks and real deployments that Anemoi is able to estimate wind speed and direction with errors up to 0.41 m/s and 25.1° lower than the existing state of the art and map 3D airflow fields with an average RMS error of 0.73 m/s.

While recent work explored streaming volumetric content on-demand, there is little effort on live volumetric video streaming that bears the potential of bringing more exciting applications than its on-demand counterpart. To fill this critical gap, in this paper, we propose MetaStream, which is, to the best of our knowledge, the first practical live volumetric content capture, creation, delivery, and rendering system for immersive applications such as virtual, augmented, and mixed reality. To address the key challenge of the stringent latency requirement for processing and streaming a huge amount of 3D data, MetaStream integrates several innovations into a holistic system, including dynamic camera calibration, edge-assisted object segmentation, cross-camera redundant point removal, and foveated volumetric content rendering. We implement a prototype of MetaStream using commodity devices and extensively evaluate its performance. Our results demonstrate that MetaStream achieves low-latency live volumetric video streaming at close to 30 frames per second on WiFi networks. Compared to state-of-the-art systems, MetaStream reduces end-to-end latency by up to 31.7% while improving visual quality by up to 12.5%.

GPU cryptojacking is an attack that hijacks GPU resources of victims for cryptocurrency mining. Such attack is becoming an emerging threat to both local hosts and cloud platforms. These attacks result in huge economic losses for the victims due to significant power consumption by cryptomining applications. Unfortunately, there are no adequate solutions to detect such attacks. In this paper, we propose MagTracer, a novel GPU cryptojacking detection system that leverages magnetic leakage signals emanating from GPUs. We make a key observation that GPUs emanate a distinct magnetic signal while mining, which can be attributed to the core feature of all cryptomining algorithms (as they are compute-intensive as well as memory-bounded). We design and implement a proof-of-concept detection system to demonstrate MagTracer's feasibility. We evaluate MagTracer on 14 heterogeneous GPU models and achieve a high average true positive rate of over 98% and a low false positive rate below 0.7% in all cases. Furthermore, our comprehensive evaluation confirms that MagTracer is scalable across different mining applications and robust against several targeted attacks.

Optimizing performance inefficiencies in memory hierarchies is well-known for native languages, such as C and C++. There are few studies, however, on exploring memory inefficiencies in Android Runtime (ART). Running in ART, managed languages, such as Java and Kotlin, employ various abstractions, such as runtime support, ahead-of-time (AOT) compilation, and garbage collection (GC), which hide important execution details from the plain source code.