Abstract not found

Urban street-parking availability statistics are challenging to obtain in real-time but would greatly benefit society by reducing traffic congestion. In this paper we present the design, implementation and evaluation of ParkNet, a mobile system comprising vehicles that collect parking space occupancy information while driving by. Each ParkNet vehicle is equipped with a GPS receiver and a passenger-side-facing ultrasonic rangefinder to determine parking spot occupancy. The data is aggregated at a central server, which builds a real-time map of parking availability and could provide this information to clients that query the system in search of parking. Creating a spot-accurate map of parking availability challenges GPS location accuracy limits. To address this need, we have devised an environmental fingerprinting approach to achieve improved location accuracy. Based on 500 miles of road-side parking data collected over 2 months, we found that parking spot counts are 95 % accurate and occupancy maps can achieve over 90 % accuracy. Finally, we quantify the amount of sensors needed to provide adequate coverage in a city. Using extensive GPS traces from over 500 San Francisco taxicabs, we show that if ParkNet were deployed in city taxicabs, the resulting mobile sensors would provide adequate coverage and be more cost-effective by an estimated factor of roughly 10-15 when compared to a sensor network with a dedicated sensor at every parking space, as is currently being tested in San Francisco.

This paper is concerned with reducing communication costs when executing distributed user tasks in a sensor network. We take a service-oriented abstraction of sensor networks, where a user task is composed of a set of data processing modules (called services) with dependencies. Communications in sensor networks consume significant energy and introduce uncertainty in data fidelity due to high bit error rate. These constraints are abstracted as costs on the communication graph. The goal is to place the services within the sensor network so that the communication cost in performing the task is minimized. In addition, since the lifetime of a node, the quality of network links, and the composition of the service graph may change over time, the quality of the placement must be maintained in the face of these dynamics. In this paper, we take a fresh look at what is generally considered a simple but poor performance approach for service placement, namely the greedy algorithm. We prove that a modified greedy algorithm is guaranteed to have cost at most 8 times the optimum placement. In fact, the guarantee is even stronger if there is a high degree of data reduction in the service graph. The advantage of the greedy placement strategy is that when there are local changes in the service graph or when a hosting node fails, the repair only affects the placement of services that depend on the changes. Simulations suggest that in practice the greedy algorithm finds a low cost placement. Furthermore, the cost of repairing a greedy placement decreases rapidly as a function of the proximity of the services to be aggregated.

This paper presents smart camera network research in the context of a unique new synthesis of advanced computer graphics and vision simulation technologies. We design and experiment with simulated camera networks within visually and behaviorally realistic virtual environments. Specifically, we demonstrate a smart camera network comprising static and active simulated video surveillance cameras that provides perceptive coverage of a large virtual public space, a train station populated by autonomously self-animating virtual pedestrians. In the context of human surveillance, we propose a camera network control strategy that enables a collection of smart cameras to provide perceptive scene coverage and perform persistent surveillance with minimal intervention. Our novel control strategy naturally addresses camera aggregation and camera handoff, it does not require camera calibration, a detailed world model, or a central controller, and it is robust against camera failures and communication errors.

Abstract — Existing stream processing systems are optimized for a specific metric, which may limit their applicability to diverse applications and environments. This paper presents XFlow, a generic data stream collection, processing, and dissemination system that addresses this limitation efficiently. XFlow can express and optimize a variety of optimization metrics and constraints by distributing stream processing queries across a wide-area network. It uses metric-independent decentralized algorithms that work on localized, aggregated statistics, while avoiding local optima. To facilitate light-weight dynamic changes on the query deployment, XFlow relies on a loosely-coupled, flexible architecture consisting of multiple publish-subscribe overlay trees that can gracefully scale and adapt to changes to network and workload conditions. Based on the desired performance goals, the system progressively refines the query deployment, the structure of the overlay trees, as well as the statistics collection process. We provide an overview of XFlow’s architecture and discuss its decentralized optimization model. We demonstrate its flexibility and the effectiveness using real-world streams and experimental results obtained from XFlow’s deployment on PlanetLab. The experiments reveal that XFlow can effectively optimize various performance metrics in the presence of varying network and workload conditions. I.

Abstract — This paper introduces a new challenge problem, designing robotic systems to recover after disassembly from high energy events. Implementation of a camera-based localization algorithm for self-reassembly is discussed. The control architecture for the various states of the robot, from fully-assembled to the modes for sequential docking, are explained and inter-module communication details for the robotic system are described. T I.

Spatio-temporal consistency is essential to ensure validity in coordinated replies generated from a wide area distributed sensor system. Consistency requirements are particularly stringent for analyzing composite images from a network of smart cameras, where even modest inconsistency in either space or time often results in misinterpretations of the composite scene. In this paper, we describe techniques to ensure spatio-temporally consistent analysis of composite images from distributed camera networks. We have incorporated our techniques into IrisNet, a prototype wide-area distributed system for cameras and other sensors. We demonstrate how our techniques apply in the context of two real-world applications, nearshore oceanography and parking space finder, which require spatio-temporal consistency.

Abstract not found

Existing stream processing systems are designed for clustered deployments, and cannot adequately meet the scalability and adaptivity requirements of Internet-scale monitoring applications. Furthermore, these systems commonly optimize for a specific QoS metric, which may limit their applicability to diverse applications and environments. This paper presents XFlow, a generic distributed data collection, processing, and dissemination system that addresses these limitations. XFlow integrates a pub-sub model with data flows for stream processing. The underlying pub-sub model decouples sources and clients, as well as the processing operators, leading to a loosely-coupled architecture that can gracefully scale, adapt to churn in system membership and workload, and facilitate sophisticated optimizations. We first provide an overview of XFlow’s architecture. We then describe XFlow’s optimization model that changes the placement and implementation of operators to meet application-specific performance goals and constraints. Finally, we demonstrate the flexibility and the effectiveness using real-world streams and experimental results obtained from our PlanetLab deployment. 1.

The convergence of embedded sensors and pervasive highperformance networking is giving rise to a new class of distributed applications, which we refer to as Internet-scale sensing (ISS). ISS systems consist of a large number of geographically distributed data sources tied into a framework for collecting, filtering, and processing potentially large volumes of real-time data. In this paper, we discuss the issues involved in building dependable ISS systems. ISS systems differ from conventional distributed systems in a number of respects, including the number of data sources, differing data quality requirements, and necessity to continue operating despite intermittent link and node failures. Such failures should result in graceful degradation of the quality of the results returned by the system, rather than loss of results. In this paper, we argue that conventional approaches to achieving consistency do not scale to the requirements of ISS systems. We outline a lightweight approach to dependability based on a set of metrics that reflect on the quality of the answers returned by the system. We argue that answers returned by an ISS system should include a measure of the harvest and freshness of the data sources participating in the result, and these metrics in turn can be used to drive fault-tolerance mechanisms in the system. We also propose three simple techniques to achieve scalability and graceful degradation in the face of failure. 1