Continuous speech monitoring using smartphones and smartwatches offers numerous opportunities to detect and predict health deterioration. However, the algorithms used to deliver these benefits must account for the realities of periodic audio recording in the wild, including other voices and overlapping noise. To address the former without clean sample voice recordings, we use speaker diarization to identify the person who speaks the most throughout a given day. To address the latter without compromising the validity of extracted speech features, we leverage the intuition that a reliable feature should remain unaltered by a noise-reduction technique when background noise is minimal. We examine both techniques in the context of a longitudinal dataset collected from 16 patients with chronic obstructive pulmonary disease (COPD) over roughly 3 months. Our best model achieved an AUROC of 0.86 when predicting the presence of respiratory symptoms, outperforming baseline models that rely solely on voice activity detection and noise reduction.

Techniques that use speech analysis for tasks like health monitoring and emotion recognition usually operate on moderately sized windows with little regard for what the individual is saying. In this work, we argue that isolating specific phonemes within speech offers greater nuance that leads to more consistent yet natural sounds for analysis. We examine this hypothesis in the context of lung function estimation. We recruited 11 patients with chronic obstructive pulmonary disease (COPD) to read from a script and perform spirometry to quantify their lung function. After segmenting their audio recordings into discrete phonemes, we extracted various phonation, prosodic, and spectral features to summarize their acoustic qualities. We then examined the correlation between those audio features and measurements from spirometry, observing that certain combinations of features and phonemes led to higher correlations than the best-performing phoneme-agnostic baseline for our dataset.

Multimodal Retrieval-Augmented Generation (MRAG) systems depend on geo-distributed vector database management systems (GVDBMS) to deliver low-latency multimedia retrieval. Multimedia content that encodes spatial information (e.g., images from Toronto or audio from the Amazon) is produced worldwide. Consequently, GVDBMS face a fundamental trade-off when serving approximate nearest neighbor (ANN) queries: full data replication or broadcast querying. We hypothesize that embeddings produced by pre-trained models exhibit strong geographic locality. By exploiting this non-IID characteristic, query routing can be optimized to reduce cross-region traffic for these datasets and avoid the costs of full replication or query broadcasting. Our evaluation on real-world datasets shows that 42–93% of queries are satisfied by a single geographic partition, and 65–85% require at most half of the partitions to retrieve the top-10 results. Across five datasets (including street-view images and geo-tagged sounds) and multiple embedding models, our approach yields a 2–4× overall system throughput improvement while maintaining 90% accuracy over broadcast querying.

Many linearizable local read algorithms have been proposed to minimize the read latency of strongly consistent distributed databases deployed in geo-distributed networks. These algorithms do so by enabling reads to be performed immediately against any process' copy of the database in the best case. However, as our analysis shows, worst-case read latency at every process with all existing algorithms is at least the network's relative diameter in terms of the maximum message delay minus a known lower bound on message delay between any two processes. We then show that by leveraging the asymmetric message delays of geo-distributed networks, worst-case read latency can be below the network's relative diameter at processes close to the leader or the network's center by presenting two new linearizable local read algorithms. Our experimental evaluation shows that these new algorithms reduce worst-case read latency by up to 50x compared to existing ones.

Remote patient monitoring is becoming increasingly instrumental to healthcare delivery but can substantially hamper the interpersonal communication that underlies standard clinical practice. In this work, we explore the benefits imparted to patients, clinicians, and researchers by an asynchronous messaging feature within a platform called COVIDFree@Home. We created COVIDFree@Home to assist the healthcare system in a large metropolitan city in North America during the COVID-19 pandemic. Clinicians used COVIDFree@Home to monitor the self-reported symptoms and vital signs of over 350 COVID-19 patients post-infection. Using thematic analysis of user-initiated messages, we found the messaging feature helped maintain protocol adherence while allowing patients to ask questions about their health and clinicians to convey empathetic care. This feedback cycle also led to higher quality data for hospitalization prediction, as the revisions significantly improved the AUROC of a machine learning model trained on demographic variables, vital signs data, and self-reported symptoms from 0.53 to 0.59.

Stream processing is an attractive paradigm for deploying applications in geo-distributed edge-cloud environments. However, the reverse economics of scale in edge networks and the movement of data sources between edges require the ability to dynamically reconfigure the deployment of stateful applications to adapt to workload variations and user mobility. Unfortunately, existing stream processing engines either do not support the reconfiguration of stateful operators or are ill-suited to edge-cloud environments since they stop application processing during reconfiguration or require costly duplication of application state. We propose Falcon, a new stream processing engine. At its core lies a live key migration approach to allow reconfiguration to occur with minimal disruption to processing, even across distant datacenters. Falcon supports the reconfiguration of stateful operators including different windowing approaches and source mobility across different edge regions. It scales gracefully with network latency, the number of datacenters, and the size and number of keys. Our evaluation in geo-distributed edge-cloud deployments shows that Falcon reduces the length of processing interruptions and their impact on latency by 2 to 4 orders of magnitude compared to the existing state-of-the-art frameworks such as Apache Flink, Trisk, and Meces.

The computation and storage requirements of Deep Neural Networks (DNNs) make them challenging to deploy on edge devices, which often have limited resources. Conversely, offloading DNNs to cloud servers incurs high communication overheads. Partitioning and early exiting are attractive solutions for reducing computational costs and improving inference speed. However, current work often addresses these approaches separately and/or ignores common communication intricacies on edge networks such as de(serialization) and data transmission overheads. We present PORTEND, a novel performance model that jointly optimizes partitioning, early exiting, and multi-tier network placement. PORTEND’S novel approach outperforms the state-of-the-art solutions in edge computing setups, reducing the DNN inference latency by 29%.

Next generation applications such as augmented/vir-tual reality, autonomous driving, and Industry 4.0, have tight latency constraints and produce large amounts of data. To address the real-time nature and high bandwidth usage of new applications, edge computing provides an extension to the cloud infrastructure through a hierarchy of datacenters located between the edge devices and the cloud. Outside of the cloud and closer to the edge, the network becomes more dynamic requiring stream processing frameworks to adapt more frequently. Cloud based frameworks adapt very slowly because they employ a stop-the-world approach and it can take several minutes to reconfigure jobs resulting in downtime. In this paper, we propose Shepherd, a new stream processing framework for edge computing. Shepherd minimizes downtime during application reconfiguration, with almost no impact on data processing latency. Our experiments show that, compared to Apache Storm, Shepherd reduces application downtime from several minutes to a few tens of milliseconds.

Continuous monitoring of cough may provide insights into the health of individuals as well as the effectiveness of treatments. Smart-watches, in particular, are highly promising for such monitoring: they are inexpensive, unobtrusive, programmable, and have a variety of sensors. However, current mobile cough detection systems are not designed for smartwatches, and perform poorly when applied to real-world smartwatch data since they are often evaluated on data collected in the lab.In this work we propose CoughWatch, a lightweight cough detector for smartwatches that uses audio and movement data for in-the-wild cough detection. On our in-the-wild data, CoughWatch achieves a precision of 82% and recall of 55%, compared to 6% precision and 19% recall achieved by the current state-of-the-art approach. Furthermore, by incorporating gyroscope and accelerometer data, CoughWatch improves precision by up to 15.5 percentage points compared to an audio-only model.

Chronic pain is often an ongoing challenge for patients to track and collect data. Pain-O-Vision is a smartwatch enabled pain management system that uses computer vision to capture the details of painful events from the user. A natural reaction to pain is to clench ones fist. The embedded camera is used to capture different types of fist clenching, to represent different levels of pain. An initial prototype was built on an Android smartwatch that uses a cloud-based classification service to detect the fist clench gestures. Our results show that it is possible to map a fist clench to different levels of pain which allows the patient to record the intensity of a painful event without carrying a specialized pain management device.

In this paper we propose a new methodology for performance modeling of applications deployed in the cloud based on automatically discovered phases along with their inputs. Our method is based on lightweight sampling that can predict the performance of applications with up to 95% accuracy for previously unseen input configurations at less than 5% overhead. We show the effectiveness of the performance modeling methodology in case of anomaly detection for a variety of real world workloads. As compared to the state-of-the-art, our method gives significant improvements in reducing both false positives and false negatives for anomalous test cases.

It is common for storage systems designed to run on edge datacenters to avoid the high latencies associated with geo-distribution by relying on eventually consistent models to replicate data. Eventual consistency works well for many edge applications because as long as the client interacts with the same replica, the storage system can provide session consistency, a stronger consistency model that has two additional important properties: (i) read-your-writes, where subsequent reads by a client that has updated an object will return the updated value or a newer one; and, (ii) monotonic reads, where if a client has seen a particular value for an object, subsequent reads will return the same value or a newer one. While session consistency does not guarantee that different clients will perceive updates in the same order, it nevertheless presents each individual client with an intuitive view of the world that is consistent with the client's own actions. Unfortunately, these consistency guarantees break down when a client interacts with multiple replicas housed on different datacenters over time, either as a result of application partitioning, or client or code mobility. SessionStore is a datastore for fog/edge computing that ensures session consistency on a top of otherwise eventually consistent replicas. SessionStore enforces session consistency by grouping related data accesses into a session, and using a session-aware reconciliation algorithm to reconcile only the data that is relevant to the session when switching between replicas. This approach reduces data transfer and latency by up to 90% compared to full replica reconciliation.

Containers are an emerging approach for application deployment on the edge, as they are modular, lightweight, and easy to use for development and maintenance. However, deploying containers in an edge computing environment brings new challenges: high latency links, limited resources, and user mobility. This work proposes a new edge deployment architecture that accelerates deployment and updates for edge applications. By overcoming the design limitations of current registries, the accelerator would reduce the deployment, start-up, and update times of container-based applications.

In many edge computing scenarios data is generated over a wide geographic area and is stored near the edges, before being pushed upstream to a hierarchy of data centers. Querying such geo-distributed data traditionally falls into two general approaches: push incoming queries down to the edge where the data is, or run them locally in the cloud. Feather is a hybrid querying scheme that exploits the hierarchical structure of such geo-distributed systems to trade temporal accuracy (freshness) for improved latency and reduced bandwidth. Rather than pushing queries to the edge or executing them in the cloud, Feather selectively pushes queries towards the edge while guaranteeing a user-supplied per-query freshness limit. Partial results are then aggregated along the path to the cloud, until a final result is provided with guaranteed freshness. We evaluate Feather in controlled experiments using real-world geo-tagged traces, as well as a real system running across 10 datacenters in 3 continents. Feather combines the best of cloud and edge execution, answering queries with a fraction of edge latency, providing fresher answers than cloud, while reducing network bandwidth and load on edges.

No abstract available.

No abstract available.

No abstract available.

General purpose GPU (GPGPU) computing in virtualized environments leverages PCI passthrough to achieve GPU performance comparable to bare-metal execution. However, GPU passthrough prevents service administrators from performing virtual machine migration between physical hosts.

With DevOps automation and an everything-as-code approach to lifecycle management for cloud-native applications, challenges emerge from an operational visibility and control perspective. Once a VM is deployed in production it typically becomes a hands-off entity in terms of restrictions towards inspecting or tuning it, for the fear of negatively impacting its operation. We present CIVIC (Cloning and Injection based VM Inspection for Cloud), a new mechanism that enables safe inspection of unmodified production VMs on-the-fly. CIVIC restricts all impact and side-effects of inspection or analysis operations inside a live clone of the production VM. New functionality over the replicated VM state is introduced using code injection. In this paper, we describe the design and implementation of our solution over KVM/QEMU. We demonstrate four of its use-cases-(i) safe reuse of system monitoring agents, (ii) impact-heavy problem diagnostics and troubleshooting, (iii) attaching an intrusive anomaly detector to a live service, and (iv) live tuning of a webserver's configuration parameters. Our evaluation shows CIVIC is nimble and lightweight in terms of memory footprint as well as clone activation time (6.5s), and has a low impact on the original VM (< 10%).

Applications that perform continuous sensing on mobile phones have the potential to revolutionize everyday life. Examples range from medical and health monitoring applications, such as pedometers and fall detectors, to participatory sensing applications, such as noise pollution, traffic and seismic activity monitoring. Unfortunately, current mobile devices are a poor match for continuous sensing applications as they require the device to remain awake for extended periods of time, resulting in poor battery life. This paper presents Sidewinder, a new approach towards offloading sensor data processing to a low-power processor and waking up the main processor when events of interest occur. This approach differs from other heterogeneous architectures in that developers are presented with a programming interface that lets them construct application specific wake-up conditions by linking together and parameterizing predefined sensor data processing algorithms. Our experiments indicate performance that is comparable to approaches that provide fully programmable offloading, but do so with a much simpler programming interface that facilitates deployment and portability.

Cloud data centers operate at very low utilization rates resulting in significant energy waste. Oasis is a new approach for energy-oriented cluster management that enables dense server consolidation. Oasis achieves high consolidation ratios by combining traditional full VM migration with partial VM migration. Partial VM migration is used to densely consolidate the working sets of idle VMs by migrating on-demand only the pages that are accessed by the idle VMs to a consolidation host. Full VM migration is used to dynamically adapt the placement of VMs so that hosts are free from active VMs. Oasis sizes the cluster and saves energy by placing hosts without active VMs into sleep mode. It uses a low-power memory server design to allow the sleeping hosts to continue to service memory requests. In a simulated VDI server farm, our prototype saves energy by up to 28% on weekdays and 43% on weekends with minimal impact on the user productivity.

Smartphones and tablets are easily lost or stolen. This makes them susceptible to an inexpensive class of memory attacks, such as cold-boot attacks, using a bus monitor to observe the memory bus, and DMA attacks. This paper describes Sentry, a system that allows applications and OS components to store their code and data on the System-on-Chip (SoC) rather than in DRAM. We use ARM-specific mechanisms originally designed for embedded systems, but still present in today's mobile devices, to protect applications and OS subsystems from memory attacks.

While there are a variety of existing virtual machine introspection (VMI) techniques, their latency, overhead, complexity and consistency trade-offs are not clear. In this work, we address this gap by first organizing the various existing VMI techniques into a taxonomy based upon their operational principles, so that they can be put into context. Next we perform a thorough exploration of their trade-offs both qualitatively and quantitatively. We present a comprehensive set of observations and best practices for efficient, accurate and consistent VMI operation based on our experiences with these techniques. Our results show the stunning range of variations in performance, complexity and overhead with different VMI techniques.We further present a deep dive on VMI consistency aspects to understand the sources of inconsistency in observed VM state and show that, contrary to common expectation, pause-and-introspect based VMI techniques achieve very little to improve consistency despite their substantial performance impact.

Modern offices are crowded with personal computers. While studies have shown these to be idle most of the time, they remain powered, consuming up to 60% of their peak power. Hardware-based solutions engendered by PC vendors (e.g., low-power states, Wake-on-LAN) have proved unsuccessful because, in spite of user inactivity, these machines often need to remain network active in support of background applications that maintain network presence. Recent proposals have advocated the use of consolidation of idle desktop Virtual Machines (VMs). However, desktop VMs are often large, requiring gigabytes of memory. Consolidating such VMs creates large network transfers lasting in the order of minutes and utilizes server memory inefficiently. When multiple VMs migrate concurrently, networks become congested, and the resulting migration latencies are prohibitive. We present partial VM migration, an approach that transparently migrates only the working set of an idle VM. It creates a partial replica of the desktop VM on the consolidation server by copying only VM metadata, and it transfers pages to the server on-demand, as the VM accesses them. This approach places desktop PCs in low-power mode when inactive and switches them to running mode when pages are needed by the VM running on the consolidation server. To ensure that desktops save energy, we have developed sleep scheduling and prefetching algorithms, as well as the context-aware selective resume framework, a novel approach to reduce the latency of power mode transition operations in commodity PCs. Jettison, our software prototype of partial VM migration for off-the-shelf PCs, can deliver 44--91% energy savings during idle periods of at least 10 minutes, while providing low migration latencies of about 4 seconds and migrating minimal state that is under an order of magnitude of the VM’s memory footprint.

The dramatic proliferation of virtual machines (VMs) in datacenters and the highly-dynamic and transient nature of VM provisioning has revolutionized datacenter operations. However, the management of these environments is still carried out using re-purposed versions of traditional agents, originally developed for managing physical systems, or most recently via newer virtualization-aware alternatives that require guest cooperation and accessibility. We show that these existing approaches are a poor match for monitoring and managing (virtual) systems in the cloud due to their dependence on guest cooperation and operational health, and their growing lifecycle management overheads in the cloud.

Virtualization provides many benefits for data intensive workloads including security, performance isolation, and ease of management and configuration. Unfortunately, current VM technology prevents taking advantage of sharing opportunities, resulting in substantial network traffic and application slowdown. Octopus is a new framework for running data intensive applications on virtualized datacenters. Octopus provides efficient file sharing across VMs running on the same physical host and optimizes the placement of VMs in the cluster to maximize sharing opportunities. Our experiments with a suite of bioinformatics and natural language processing applications show that Octopus reduces network transfer by up to 83% and total runtime by up to 55%.

Idle desktop systems are frequently left powered, often because of applications that maintain network presence or to enable potential remote access. Unfortunately, an idle PC consumes up to 60% of its peak power. Solutions have been proposed that perform consolidation of idle desktop virtual machines. However, desktop VMs are often large requiring gigabytes of memory. Consolidating such VMs, creates bulk network transfers lasting in the order of minutes, and utilizes server memory inefficiently. When multiple VMs migrate simultaneously, each VM's experienced migration latency grows, and this limits the use of VM consolidation to environments in which only a few daily migrations are expected for each VM. This paper introduces Partial VM Migration, a technique that transparently migrates only the working set of an idle VM. Jettison, our partial VM migration prototype, can deliver 85% to 104% of the energy savings of full VM migration, while using less than 10% as much network re- sources, and providing migration latencies that are two to three orders of magnitude smaller.

We introduce cloud micro-elasticity, a new model for cloud Virtual Machine (VM) allocation and management. Current cloud users over-provision long-lived VMs with large memory footprints to better absorb load spikes, and to conserve performance-sensitive caches. Instead, we achieve elasticity by swiftly cloning VMs into many transient, short-lived, fractional workers to multiplex physical resources at a much finer granularity. The memory of a micro-elastic clone is a logical replica of the parent VM state, including caches, yet its footprint is proportional to the workload, and often a fraction of the nominal maximum. We enable micro-elasticity through a novel technique dubbed VM state coloring, which classifies VM memory into sets of semantically-related regions, and optimizes the propagation, allocation and deduplication of these regions. Using coloring, we build Kaleidoscope and empirically demonstrate its ability to create micro-elastic cloned servers. We model the impact of micro-elasticity on a demand dataset from AT&T's cloud, and show that fine-grained multiplexing yields infrastructure reductions of 30% relative to state-of-the art techniques for managing elastic clouds.

Stateless services are easy to scale in the cloud since new replicas of these services can be created at any time and they operate completely independently of other instances. In contrast, scaling stateful services, such as a database system, can take minutes or even hours due to the need to present a consistent view of the system for users of the service. Currently, this problem is addressed by resource over-provisioning in anticipation of demand spikes. FlurryDB uses virtual machine cloning to improve resource utilization by drastically reducing the latency required to add a new replica. We also show that FlurryDB is capable of handling updates to resources in a fashion that preserves consistency across the cloning boundary.

A basic building block of cloud computing is virtualization. Virtual machines (VMs) encapsulate a user’s computing environment and efficiently isolate it from that of other users. VMs, however, are large entities, and no clear APIs exist yet to provide users with programatic, fine-grained control on short time scales. We present SnowFlock, a paradigm and system for cloud computing that introduces VM cloning as a first-class cloud abstraction. VM cloning exploits the well-understood and effective semantics of UNIX fork. We demonstrate multiple usage models of VM cloning: users can incorporate the primitive in their code, can wrap around existing toolchains via scripting, can encapsulate the API within a parallel programming framework, or can use it to load-balance and self-scale clustered servers. VM cloning needs to be efficient to be usable. It must efficiently transmit VM state in order to avoid cloud I/O bottlenecks. We demonstrate how the semantics of cloning aid us in realizing its efficiency: state is propagated in parallel to multiple VM clones, and is transmitted during runtime, allowing for optimizations that substantially reduce the I/O load. We show detailed microbenchmark results highlighting the efficiency of our optimizations, and macrobenchmark numbers demonstrating the effectiveness of the different usage models of SnowFlock.

Mapping applications on mobile devices have gained widespread popularity as a means for enhancing user mobility and ability to explore new locations and venues. Visually impaired users currently rely on computer text-to-speech or human-spoken descriptions of maps and indoor spaces. Unfortunately, speech-based descriptions are limited in their ability to succinctly convey complex layouts or spacial positioning.

Ensemble is a system that uses a collection of trusted personal devices to provide proximity-based authentication in pervasive environments. Users are able to securely pair their personal devices with previously unknown devices by simply placing them close to each other (e.g., users can pair their phones by just bringing them into proximity). Ensemble leverages a user's growing collection of trusted devices, such as phones, music players, computers and personal sensors to observe transmissions made by pairing devices. These devices analyze variations in received signal strength (RSS) in order to determine whether the pairing devices are in physical proximity to each other. We show that, while individual trusted devices can not properly distinguish proximity in all cases, a collection of trusted devices can do so reliably. Our Ensemble prototype extends Diffie-Hellman key exchange with proximity-based authentication. Our experiments show that an Ensemble-enabled collection of Nokia N800 Internet Tablets can detect devices in close proximity and can reliably detect attackers as close as two meters away.

Virtual Machine (VM) fork is a new cloud computing abstraction that instantaneously clones a VM into multiple replicas running on different hosts. All replicas share the same initial state, matching the intuitive semantics of stateful worker creation. VM fork thus enables the straightforward creation and efficient deployment of many tasks demanding swift instantiation of stateful workers in a cloud environment, e.g. excess load handling, opportunistic job placement, or parallel computing. Lack of instantaneous stateful cloning forces users of cloud computing into ad hoc practices to manage application state and cycle provisioning. We present SnowFlock, our implementation of the VM fork abstraction. To evaluate SnowFlock, we focus on the demanding scenario of services requiring on-the-fly creation of hundreds of parallel workers in order to solve computationally-intensive queries in seconds. These services are prominent in fields such as bioinformatics, finance, and rendering. SnowFlock provides sub-second VM cloning, scales to hundreds of workers, consumes few cloud I/O resources, and has negligible runtime overhead.

Mobility footprint refers to the size, weight, and energy demand of the hardware that must be carried by a mobile user to be effective at any time and place. The ideal of a zero mobility footprint is achievable by encapsulating personal computing state in a virtual machine (VM) and delivering it over the Internet to a locally-obtained computer close to the user. In locations with poor Internet connectivity, the demands placed on WAN bandwidth can result in unacceptable user experience. We show how this challenge can be overcome by using nascent smart phone technology as a trusted personal assistant called Horatio that serves as a self-cleaning portable cache for VM state. Since most users already carry cell phones for voice calls and texting, Horatio does not increase the size or weight aspects of a user's mobility footprint - there is only a small increase in the energy aspect. We have built an experimental prototype of Horatio, and measurements confirm its ability to improve user experience even with current smart phone limitations.

CILoS is an indoor localization system based on CDMA mobile phone signal fingerprinting. CDMA networks vary their transmission power to accommodate fluctuations in network load. This affects signal intensity and therefore limits the practicality of traditional fingerprinting approaches based on receiver signal strength (RSSI) measurements. Instead, CILoS uses fingerprints of signal delay that are robust to cell resizing. We demonstrate that CILoS achieves a median accuracy of 5 meters, and compares favourably to RSSI fingerprinting systems. We highlight the significance of wide fingerprints, constructed through scanning multiple channels, for achieving high localization accuracy. We also show that our system can accurately differentiate between floors of a multifloor building.

Most pages on the Web are designed for the desktop environment and render poorly on the small screens available on handheld devices. We introduce Reusable End-User Customization (REUC), a technique that lets end users adapt the layout of Web pages by removing, resizing and moving page elements. REUC records the user's customizations and automatically reapplies them on subsequent visits to the same page or to other, similar pages, on the same Web site. We present PageTailor, a REUC prototype based on the Minimo Web browser that runs on Windows Mobile PDAs. We show that users can utilize PageTailor to adapt sophisticated Web sites, such as Amazon, BBC and MSN, for browsing on a PDA. Moreover, the customizations remain effective for up to a year, even as the content of pages is updated, and can be reused across similar pages, limiting the customization effort required to browse a site.

When a mobile user dials 911, a key to arriving to the emergency scene promptly is knowing the location of the mobile user. This paper presents SkyLoc, a GSM fingerprinting-based localization system that runs on a mobile phone and identifies the current floor of a user in tall multi-floor buildings. Knowing the floor in a tall building significantly reduces the area that emergency service personnel have to canvas to locate the individuals in need. We evaluated our system in three multi-floor buildings located in Washington DC, Seattle and Toronto. Our system identifies the floor correctly in up to 73% of the cases and is within 2 floors in 97% of the cases. The system is robust as it works for different network operators, when the training and testing sets were collected with different hardware and up to one month apart. In addition, we show that feature selection techniques that select a subset of highly relevant radio sources for fingerprint matching nearly double the localization accuracy of our system

Graphical processing units (GPUs) are critical to high-quality visualization in many application domains. Running such applications in virtual machine monitor (VMM) environments is difficult for a number of reasons, all relating to the fact that the GPU hardware interface is proprietary rather than standardized. This paper describes the design, implementation, and evaluation of VMGL, a VMM-independent, GPU-independent, cross-platform solution to this problem. VMGL virtualizes at the OpenGL software interface, recognizing its widespread use in graphics-intensive applica-tions. Our experiments confirm excellent rendering performance with VMGL, coming within 14% or better of native hardware accelerated performance measured in frames per second. This is two orders of magnitude better than software rendering, which is the commonly available alternative today for graphics-intensive applications running in virtualized environments. Our results confirm VMGL’s portability across VMware Workstation and Xen (on VT and non-VT hardware), and across Linux (with and without paravirtualization), FreeBSD, and Solaris. Our results also show

Usage-awaRe Interactive Content Adaptation (URICA) is an automatic technique that adapts content for display on mobile devices based on usage semantics. URICA allows users who are unsatisfied with the system's adaptation decision to take control of the adaptation process and make changes until the content is suitably adapted for their purposes. The successful adaptation is recorded and used in making future adaptation decisions. To validate URICA, we implemented a prototype system called Chameleon that performs fidelity adaptation on web images. We conducted a user study in which participants used Chameleon to browse image-rich web pages on bandwidth-limited cellular links and used the collected traces to evaluate our system. We show that Chameleon reduces the latency for browsing web content by up to 65% and reduces bandwidth consumption by up to 80%. Chameleon also allows users to exchange bandwidth consumption for user interaction based on their personal preferences.

Radio equipped mobile devices have enjoyed tremendous growth in the past few years. We observe that in the near future it might be possible to build a network that routes delay-tolerant packets by harnessing user mobility and the pervasive availability of wireless devices. Such a delay-tolerant network could be used to supplement wireless infrastructure or provide service where none is available. Since mobile devices in a delay-tolerant network forward packets to nearby users, the devices can use short-range radio, which potentially reduces device power consumption and radio contention. The design of a user mobility based delay-tolerant network raises two key challenges: determining; the connectivity of such a network, and determining the latency characteristics and replication requirements of routing algorithms in such a network. To determine realistic contact patterns, we collected user mobility data by conducting two user studies. We outfitted groups of students with instrumented wireless-enabled PDAs that logged pairwise contacts between study participants over a period of several weeks. Experiments conducted on these traces show that it is possible to form a delay-tolerant network based on human mobility. The network has good connectivity, so that routes exist between almost all study participants via some multi-hop path. Moreover, it is possible to effectively route packets with modest replication

We introduce a novel infrastructure supporting automatic updates for dynamic content browsing on resource constrained mobile devices. Currently, the client is forced to continuously poll for updates from potentially different data sources, such as, e-commerce, on-line auctions, stock and weather sites, to stay up to date with potential changes in content. We employ a pair of proxies, located on the mobile client and on a fully-connected edge server, respectively, to minimize the battery consumption caused by wireless data transfers to and from the mobile device. The client specifies her interest in changes to specific parts of pages by highlighting portions of already loaded web pages in her browser. The edge proxy polls the web servers involved, and if relevant changes have occurred, it aggregates the updates as one batch to be sent to the client. The proxy running on the mobile device can pull these updates from the edge proxy, either on-demand or periodically, or can listen for "pushed" updates initiated by the edge proxy. We also use SMS messages to indicate available updates and inform the user of which pages have changed. Our approach is fully implemented using two alternative wireless networking technologies, 802.11 and GPRS, and evaluated on real world dynamic content traces. Our evaluation explores the data transfer savings enabled by our proxy-based infrastructure and the energy consumption when using each of the two networking capabilities. Our results show that our proxy system saves data transfers to and from the mobile device by an order of magnitude and battery consumption by up to a factor of 4.5, compared to the client-initiated continuous polling approach. Our results also show even in the case where users never visit the same page twice, energy consumption is reduced by the pre-fetching and batching or our proxy system.

Automatic adaptation of content for mobile devices is a challenging problem because optimal adaptation often depends on the usage semantics of content, as well as the context of users (e.g., screen size of device being used, network connectivity, location, etc.). UsageawaRe Interactive Content Adaptation (URICA) is an automatic technique that adapts content for mobile devices based on usage semantics. URICA allows a user who is unsatisfied with the system’s current adaptation prediction to take control of the adaptation process and make changes until the content is suitably adapted for her purposes. The adaptation system learns from the user’s modifications and adjusts its prediction for future accesses by other users. This paper shows that it is possible to exploit user interaction to learn how to adapt content based on context. We introduce Feedback-driven Context Selection (FCS), an automatic technique that leverages user interaction to identify the context that has the most impact on adaptation requirements. We added contextawareness to URICA so that it makes adaptation predictions for a user based only on the history of the community of users that share the context identified by FCS. The result is an automatic adaptation system that provides fine grain adaptations that reflect both the user’s context and the content’s usage semantics. This level of fine grain adaptation was previously available only in content that was customized manually. Experiments with two context-aware URICA prototypes show that FCS correctly identifies the contextual characteristics that impact adaptation requirements, and that grouping users into communities based on context improves the performance of the adaptation system by up to 79%.

When a service is offered by multiple servers in a mobile ad hoc network (MANETs), the manner in which clients and servers are paired together, referred to as service selection, is crucial to network performance. Good service selection groups clients with nearby servers, localizing communication, which in turn reduces inter-node interference and allows for multiple concurrent transmissions in different parts of the network. Although much previous research has concentrated on service discovery in MANETs, not much effort has gone into understanding the effects of service selection. This paper demonstrates that service selection in MANETs has profound implications for network performance. Specifically, we show that effective service selection can improve network throughput by up to 400%. We show that to maximize performance service selection decisions need to be continuously reassessed to offset the effects of topology changes. We argue that effective service selection in MANETs requires a cross-layer approach that integrates service discovery and selection functionality with network ad hoc routing mechanisms. The cross-layer approach leverages existing routing traffic and allows clients to switch to better servers as network topology changes.

Recovery from intrusions is typically a very time-consuming operation in current systems. At a time when the cost of human resources dominates the cost of computing resources, we argue that next generation systems should be built with automated intrusion recovery as a primary goal. In this paper, we describe the design of Taser, a system that helps in selectively recovering legitimate file-system data after an attack or local damage occurs. Taser reverts tainted, i.e. attack-dependent, file-system operations but preserves legitimate operations. This process is difficult for two reasons. First, the set of tainted operations is not known precisely. Second, the recovery process can cause conflicts when legitimate operations depend on tainted operations. Taser provides several analysis policies that aid in determining the set of tainted operations. To handle conflicts, Taser uses automated resolution policies that isolate the tainted operations. Our evaluation shows that Taser is effective in recovering from a wide range of intrusions as well as damage caused by system management errors.

Iterative adaptation is a novel approach to adaptation for resource-limited mobile and wireless environments that supports powerful application-specific adaptations without requiring modifications to the application's source code. Common productivity applications, such as browsers, word processors, and presentation tools, export APIs that allow external applications to control their operation. The novel premise in iterative adaptation is that these APIs are sufficient to support a wide range of adaptation policies for applications running on resource-limited devices. In addition to allowing adaptation without having to change the application's source code, this approach has a unique combination of advantages. First, it supports centralized management of resources across multiple applications. Second, it makes it possible to modify application behavior after the application has been deployed. This paper evaluates the extent to which existing APIs can be used for the purposes of adapting document-based applications to run on bandwidth-limited devices. In particular, we implement a large number of bandwidth adaptations for applications from the Microsoft Office and the OpenOffice productivity suites and for Internet Explorer. Although we find limitations in their APIs, we are able to implement many adaptation policies without much complexity and with good performance. Moreover, iterative adaptation achieves performance similar to an approach that implements adaptation by modifying the application, while requiring only a fraction of the coding effort.

The decoupling of producers and consumers in time and space in the publish/subscribe paradigm lends itself well to the support of mobile users who roam about the environment and have intermittent network connectivity. This paper identifies the factors that affect the performance of a distributed publish/subscribe architecture supporting mobility; formalizes mobility algorithms for distributed publish/subscribe systems and develops and evaluates optimizations that reduce the costs associated with supporting mobility in publish/subscribe systems. In our analysis, we focus on the "unicast" traffic generated to support mobile users, as opposed to the regular "multicast" traffic used for event dissemination to stationary clients. We find that the network capacity must be doubled to handle the extra load of just 10% of mobile users.

We evaluate the robustness of simplified mobility and radio propagation models for indoor MANET simulations. A robust simplification allows researchers to extrapolate simulation results and reach reliable conclusions about the expected performance of protocols in real life. We show that common simplified mobility and radio propagation models are not robust. Experiments with DSR and DSDV, two representative MANET routing protocols, show that the simplifications affect the two protocols in very different manners. Even for a single protocol, the effects on perceived performance can vary erratically as parameters change. These results cast doubt on the soundness of evaluations of MANET routing protocols based on simplified mobility and radio propagation models, and expose the urgent need for more research on realistic MANET simulation.

This paper introduces adaptation-aware editing and progressive update propagation, two novel mechanisms that enable authoring multimedia content and collaborative work on mobile devices. Adaptation-aware editing enables editing content that was adapted to reduce download time to the mobile device. Progressive update propagation reduces the time for propagating content generated at the mobile device by transmitting either a fraction of the modifications or transcoded versions thereof.With application-aware editing and progressive update propagation, an object present at a mobile device is characterized not only by a particular version, as in conventional replication, but also by a particular fidelity. We demonstrate that replication models can be extended to account for fidelity independently of the mechanisms used for concurrency control and consistency maintenance. As a result, the two techniques described in this paper can easily be added to any replication protocol, whether optimistic or pessimistic.We report on our experience implementing adaptation-aware editing and progressive update propagation. Experiments with two multimedia applications, an email reader and a presentation software package, show that both mechanisms can be added with modest programming effort and achieve substantial reductions in upload and download latencies.

Modern systems need support for adaptation, typically responding to changes in system resources such as available network bandwidth. If an adaptation system is implemented strictly at the system layer, data adaptations can be added within the network or file system. This makes the adaptation system portable across applications, but sacrifices opportunities to change an application's behavior. It's not possible, for example, to first return a low-quality version of an image and later upgrade it should excess network capacity be available. On the flip side, the adaptation logic could be built into each and every application, with the system providing information to the applications in order to help them adapt their behavior. This becomes impractical because many applications will never be written to perform adaptation, and an application writer may not be able to foresee all possible adaptations that may be desirable. We argue that adaptation systems should be centralized, where they can make global observations about system usage and resource availability. We further argue that applications should not be written to perform adaptation. Instead, applications should support an interface where the adaptation system can dynamically modify an application's behavior as it runs.

In this paper, we compare the performance of two multiple-writer protocols based on lazy release consistency. In particular, we compare the performance of Princeton's home-based protocol and TreadMarks' protocol on a 32-processor platform. We found that the performance difference between the two protocols was less than 4% for four out of seven applications. For the three applications on which performance differed by more than 4%, the TreadMarks protocol performed better for two because most of their data were migratory, while the home-based protocol performed better for one. For this one application, the explicit control over the location of data provided by the home-based protocol resulted in a better distribution of communication load across the processors. These results differ from those of a previous comparison of the two protocols. We attribute this difference to (1) a different ratio of memory to network bandwidth on our platform and (2) lazy diffing and request overlapping, two optimizations used by TreadMarks that were not used in the previous study.