Large constellations of low-earth orbit satellites enable frequent high-resolution earth imaging for numerous geospatial applications. They generate large volumes of data in space, hundreds of Terabytes per day, which much be transported to Earth through constrained intermittent connections to ground stations. The large volumes lead to large day-level delay in data download and exorbitant cloud storage costs. We propose DeepSpace, a new deep learning-based super-resolution approach that compresses satellite imagery by over two orders of magnitude, while preserving image quality using a tailored mixture of experts (MoE) super-resolution framework. DeepSpace reduces the network bandwidth requirements for space-Earth transfer, and can compress images for cloud storage. DeepSpace achieves such gains with the limited computational power available on small LEO satellites. We extensively evaluate DeepSpace against a wide range of state-of-the-art baselines considering multiple satellite image datasets and demonstrate the above mentioned benefits. We further demonstrate the effectiveness of DeepSpace through several distinct downstream applications (wildfire detection, land use and cropland classification, and fine-grained plastic detection in oceans).

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 ×.

Implantable and edible medical devices promise to provide continuous, directed, and comfortable healthcare treatments. Communicating with such devices and localizing them is a fundamental, but challenging, mobile networking problem. Recent work has focused on leveraging near field magnetism-based systems to avoid the challenges of attenuation, refraction, and reflection experienced by radio waves. However, these systems suffer from limited range, and require fingerprinting-based localization techniques. We present InnerCompass, a magnetic backscatter system for in-body communication and localization. InnerCompass relies on new magnetism-native design insights that enhance the range of these devices. We design the first analytical model for magnetic-field-based localization, that generalizes across different scenarios. We've implemented InnerCompass and evaluated it in porcine tissue. Our results show that Inner-Compass can communicate at 5 Kbps at a distance of 25 cm, and localize with an accuracy of 5 mm.

The advent of radio sensing that works through walls & obstacles challenges the notion of indoor privacy. An eavesdropper can deploy such sensing to snoop on their neighbors and a smart sensor embedded with such sensing capabilities can perform large scale behavioral and health data mining. We present RF-Protect, a new framework that enables privacy by injecting fake humans in the sensed data. RF-Protect consists of a novel hardware reflector design that modifies radio waves to create reflections at arbitrary locations in the environment and a new generative mechanism to create realistic human trajectories. RF-Protect's design doesn't require any high bandwidth hardware or physical motion. We implement RF-Protect using commodity hardware and validate its ability to generate fake human trajectories.

Given high-speed mobile Internet access today, audiences are expecting much higher video quality than before. Video service providers have deployed dynamic video bitrate adaptation services to fulfill such user demands. However, legacy video bitrate adaptation techniques are highly dependent on the estimation of dynamic bandwidth, and fail to integrate the video quality enhancement techniques, or consider the heterogeneous computing capabilities of client devices, leading to low quality of experience (QoE) for users. In this paper, we present a super-resolution based adaptive video streaming (SRAVS) framework, which applies a Reinforcement Learning (RL) model for integrating the video super-resolution (VSR) technique with the video streaming strategy. The VSR technique allows clients to download low bitrate video segments, reconstruct and enhance them to high-quality video segments while making the system less dependent on estimating dynamic bandwidth. The RL model investigates both the playback statistics and the distinguishing features related to the client-side computing capabilities. Trace-driven emulations over real-world videos and bandwidth traces verify that SRAVS can significantly improve the QoE for users compared to the state-of-the-art video streaming strategies with or without involving VSR techniques.

As computer architecture continues to expand beyond software-agnostic microarchitecture to specialized and heterogeneous logic or even radically different emerging computing models (e.g., quantum cores, DNA storage units), detailed cycle-level simulation is no longer presupposed. Exploring designs under such complex interacting relationships (e.g., performance, energy, thermal, frequency) calls for a more integrative but higher-level approach. We propose Charm, a modeling language supporting closed-form high-level architecture modeling. Charm enables mathematical representations of mutually dependent architectural relationships to be specified, composed, checked, evaluated, reused, and shared. The language is interpreted through a combination of automatic symbolic evaluation, scalable graph transformation, and efficient compiler techniques, generating executable DAGs and optimized analysis procedures. Charm also exploits the advancements in satisfiability modulo theory solvers to automatically search the design space to help architects explore multiple design knobs simultaneously (e.g., different CNN tiling configurations). Through two case studies, we demonstrate that Charm allows one to define high-level architecture models in a clean and concise format, maximize reusability and shareability, capture unreasonable assumptions, and significantly ease design space exploration at a high level.

Online advertisement (ad) recommendation in the mobile social network (MSN) is an uprising interest of research. Compared to traditional recommendation systems, one of its major difference is the presence of explicit negative feedback from users (e.g., a user does not click an ad, or she/he does not like it). On the other hand, most methods utilize negative sampling (e.g., randomly sampling an item that a user never interacts with to avoid overfitting, that is, she/he is assumed to dislike it) while training conventional recommendation systems. This may lead to a conflict between negative feedback and sampling, as they should be treated differently, but they are considered as the same if traditional methods are directly applied for online ad recommendation. In this paper, we present AdRec, a novel framework of online ad recommendation in MSN to address this conflict. We introduce an auxiliary output and modify the loss function to assign different weights to negative samples and feedbacks. A theoretical analysis is applied to show the efficiency of our design, and experiments on real world datasets demonstrate that our proposed method outperforms several state-of-the-art approaches.