No abstract

No abstract

Increasing user comfort and reducing operation costs have always been two primary objectives of building operations and control strategies. Current building control strategies are unable to incorporate occupant level comfort and meet the operation goals simultaneously. In this paper, we present a novel utility-based building control strategy that optimizes the tradeoff between meeting user comfort and reduction in operation cost by reducing energy usage. We present an implementation of the proposed approach as an intelligent lighting control strategy that significantly reduces energy cost. Our approach is based on a principled, decision theoretic formulation of the control task. We demonstrate the use of mobile wireless sensor networks to optimize the tradeoff between fulfilling different occupants' light preferences and minimizing energy consumption. We further extend our approach to optimally exploit external light sources for additional energy savings, a process called daylight harvesting. Also we demonstrate that an active sensing approach can maximize the mobile sensor network's lifetime by sensing only during most informative situations. We provide efficient algorithms for solving the underlying complex optimization problems, and extensively evaluate our proposed approach in a proof-of-concept testbed using MICA2 motes and dimmable lamps. Our results indicate a significant improvement in user utility and reduced energy expenditure.

We present a multiresolution classification framework with semi-supervised learning on graphs with application to the indirect bridge structural health monitoring. Classification in real-world applications faces two main challenges: reliable features can be hard to extract and few labeled signals are available for training. We propose a novel classification framework to address these problems: we use a multiresolution framework to deal with nonstationarities in the signals and extract features in each localized time-frequency region and semi-supervised learning to train on both labeled and unlabeled signals. We further propose an adaptive graph filter for semi-supervised classification that allows for classifying unlabeled as well as unseen signals and for correcting mislabeled signals. We validate the proposed framework on indirect bridge structural health monitoring and show that it performs significantly better than previous approaches.Index Terms-Multiresolution classification, semi-supervised learning, discrete signal processing on graphs, adaptive graph filter, indirect bridge structural health monitoring.

Uncertainty due to spatial variability of hydraulic conductivity is an important issue in the design of reliable groundwater remediation strategies. Using groundwater management models based on a stochastic approach to groundwater flow, where the log‐hydraulic conductivity is represented as a random field, is a frequently studied technique for the design of aquifer remediation in the presence of uncertainty. Such an approach employs the solution of a management model for a large set of equally probable realizations of the hydraulic conductivity. However, only a few out of the large set of realizations are critical to the final outcome of the design. The spatial distribution of the hydraulic conductivity values in a realization, and the degree of variation of the hydraulic conductivity values within a realization are identified as two important features that determine the level of criticalness of a realization. The association between the hydraulic conductivity pattern and the level of criticalness is not known explicitly and needs to be captured for efficient screening. The screening approach presented here utilizes the pattern classification capability of a neural network and its ability to learn from examples. It is shown that incorporation of only a few critical realizations in a groundwater management model can yield highly reliable remediation designs. The application of the screening tool in a pump‐and‐treat design problem is illustrated via two examples.

No abstract

We present Sensor Andrew, a multidisciplinary campus-wide scalable sensor network that is designed to host a wide range of sensor, actuator and low-power applications. The goals of Sensor Andrew are to support ubiquitous large-scale monitoring, operation and control of infrastructure in a way that is extensible, easy to use, and secure while maintaining privacy. Target applications currently being developed as part of Sensor Andrew include builing emergency, first-responder support, quality of life for the disabled, monitoring and optimization of water distribution systems, building power monitoring and control, social networking, and biometric sensors for campus security. Sensing devices that are used range from cameras and batteryoperated sensor nodes to energy-monitoring devices wired into building power supplies. Some of these sensing devices may also be mobile and require hand-off between different networked regions. Supporting multiple applications and heterogeneous devices requires a standardized communication medium capable of scaling to tens of thousands of sources. In this technical report, we present the architecture underlying Sensor Andrew for managing sensor data collection as well as server-side application interactions. Sensors and actuators are modeled as event nodes in a push-based publish-subscribe architecture. A data handler provides registration, discovery and data logging facilities for each device. The major elements of this architecture have been deployed in five buildings at Carnegie Mellon University, and are comprised of over 1000 sensing points reporting data from multiple communication interfaces. Finally, we describe two different case study applications currently using the infrastructure that benefit from shared information. Design choices, limitations and enhancements across various layers and protocols are also discussed.

We explore a data-driven approach for monitoring rail infrastructure from the dynamic response of a train in revenue-service. Presently, track inspection is performed either visually or with dedicated track geometry cars. In this study, we examine a more economical approach where track inspection is performed by analyzing vibration data collected from an operational passenger train. The high frequency with which passenger trains travel each section of track means that faults can be detected sooner than with dedicated inspection vehicles, and the large number of passes over each section of track makes a data-driven approach statistically feasible. We have deployed a test-system on a light-rail vehicle and have been collecting data for the past two years. The collected data underscores two of the main challenges that arise in train-based track monitoring: the speed of the train at a given location varies from pass to pass and the position of the train is not known precisely. In this study, we explore which feature representations of the data best characterize the state of the tracks despite these sources of uncertainty (i.e., in the spatial domain or frequency domain), and we examine how consistently change detection approaches can identify track changes from the data. We show the accuracy of these different representations, or features, and different change detection approaches on two types of track changes, track replacement and tamping (a maintenance procedure to improve track geometry), and two types of data, simulated data and operational data from our