Homes constitute more than one-thirds of the total energy consumption. Producing an energy breakdown for a home has been shown to reduce household energy consumption by up to 15%, among other benefits. However, existing approaches to produce an energy breakdown require hardware to be installed in each home and are thus prohibitively expensive. In this paper, we propose a novel application of feature-based matrix factorisation that does not require any additional hard- ware installation. The basic premise of our approach is that common design and construction patterns for homes create a repeating structure in their energy data. Thus, a sparse basis can be used to represent energy data from a broad range of homes. We evaluate our approach on 516 homes from a publicly available data set and find it to be more effective than five baseline approaches that either require sensing in each home, or a very rigorous survey across a large number of homes coupled with complex modelling. We also present a deployment of our system as a live web application that can potentially provide energy breakdown to millions of homes.

The first step to saving energy in the home is often to create an energy breakdown: the amount of energy used by each individual appliance in the home. Unfortunately, current techniques that produce an energy breakdown are not scalable: they require hardware to be installed in each and every home. In this paper, we propose a more scalable solution called Gemello that estimates the energy breakdown for one home by matching it with similar homes for which the breakdown is already known. This matching requires only the monthly energy bill and household characteristics such as square footage of the home and the size of the household. We evaluate this approach using 57 homes and results indicate that the accuracy of Gemello is comparable to or better than existing techniques that use sensing infrastructure in each home. The information required by Gemello is often publicly available and, as such, it can be immediately applied to many homes around the world.

Residential buildings account for a significant proportion of overall energy consumption across the world. Decentralized room level Air Conditioners (ACs) are a commonplace in developing countries such as India, contributing a major share (34% in India) of the total residential energy consumption. Option to independently control each AC presents a prime opportunity for an energy saving system. Thus, we propose PACMAN to non-intrusively (using only the temperature information) predict AC energy consumption prior to usage and estimate energy consumption post-usage. We discuss various possible applications and use cases of such feedback for the occupants. To empirically validate the performance of PACMAN, we conducted an in-situ study across seven homes in Delhi (India). We collected around 2200 hours of usage data from the different ACs, room types, and thermostat temperatures. We achieved an average accuracy of 85.3% and 83.7% with the best accuracy of 97.0% and 93.3% for the estimation and prediction of AC energy consumption respectively, across all homes. Towards the end, we discuss various outlier scenarios, opening up multiple directions for further research in this domain.

An unprecedented rate of growth in the number of vehicles has resulted in acute road congestion problems worldwide, especially in many developing countries. In this article, we present Road-RFSense, a practical RF sensing--based road traffic estimation system for developing regions. Our first contribution is a new mechanism to sense road occupancy, based on variation in RF link characteristics, when line of sight between a transmitter-receiver pair is obstructed. We design algorithms to classify traffic states into two classes, free-flow versus congested, at timescales of 20 seconds with greater than 90% accuracy. We also present a traffic queue length measurement system, where a network of RF sensors can correlate the traffic state classification decisions of individual sensors and detect traffic queue length in real time. Deployment of our system on a Mumbai road gives correct estimates, validated against 9 hours of image-based ground truth. Our third contribution is a large-scale data-driven study, in collaboration with city traffic authorities, to answer questions regarding road-specific classification model training. Finally, we explore multilevel classification into seven different traffic states using a larger set of RF-based features and careful choice of classification algorithms.

Residential buildings contribute significantly to the overall energy consumption across most parts of the world. While smart monitoring and control of appliances can reduce the overall energy consumption, management and cost associated with such systems act as a big hindrance. Prior work has established that detailed feedback in the form of appliance level consumption to building occupants improves their awareness and paves the way for reduction in electricity consumption. Non-Intrusive Load Monitoring (NILM), i.e. the process of disaggregating the overall home electricity usage measured at the meter level into constituent appliances, provides a simple and cost effective methodology to provide such feedback to the occupants. In this paper we present Improved Non-Intrusive load monitoring using load Division and Calibration (INDiC) that simplifies NILM by dividing the appliances across multiple instrumented points (meters/phases) and calibrating the measured power. Proposed approach is used together with the Combinatorial Optimization framework and evaluated on the popular REDD dataset. Empirical results demonstrate significant improvement in disaggregation accuracy, achieved by using INDiC based Combinatorial Optimization, demonstrate significant improvement in disaggregation accuracy.

Social programs often require collection of demographic and program related information. Pen-paper surveys have been the most favorable way of collecting such information. However, with proliferation of smartphones, low cost mobile connectivity with good coverage and availability of several data collection applications that can even work around the connectivity concerns, pen-paper surveys are now being replaced by mobile based data collection. In this work, we discuss the enhancement of Open Data Kit (ODK), an existing mobile based data collection application, with features such as pre-filling and validation SMS. The additional features were motivated from the real world requirements of reducing the data collection effort and minimizing the discrepancies in records for a project requiring information dissemination to beneficiaries of National Rural Employment Guarantee Scheme (NREGS), a government of India scheme. Data collection exercise, using our extended tool, is currently ongoing in two districts across two different states in India. Preliminary results from one deployment indicate that even with 8% of pre-filled fields in a form, there was a 16.1% decrease in the errors. Additionally, time per survey reduced with the pre-filling option. Preliminary results from another deployment indicate that 35% of the pre-filled forms had mismatched or changed information when compared with the data available in government records.

Activist groups have taken up information dissemination and feedback collection as a means of rights advocacy in India. However, it is not easy given the difficulty in procuring and disseminating information at a large scale. Beneficiaries are often not able to help themselves as information systems are administration facing, because of poor literacy and the inability to access the Internet. Further, beneficiaries are not well informed of their rights and entitlements under different government schemes to know how and when to file grievances. We aim to solve these problems by designing and testing prototypes for information dissemination and feedback collection in various contexts. In our current prototype we describe an automated tool that sifts through the data on an MIS and conveys personalised information to the beneficiaries through voice calls. This is a work in progress, and our first exercise on providing MIS-extracted information to people through phone calls led to 70% of the beneficiaries who noticed a discrepancy in the data to agree to file a grievance on their behalf. We are continuing to scale the work, make it more automated, and run qualitative interviews with all stakeholders to understand causality linkages with transparency led grievance filing, assisted by appropriate ICTs, to increase accountability.

Increasing use of telephone devices has made the Interactive Voice Response (IVR), a technology for accessing information over phone, popular among the commercial organizations. IVR systems are used for critical applications like flight reservation, tele-banking, etc. which requires to have well tested IVR systems. Manual testing of an IVR application requires dialing number, listening and responding to voice prompts through key-press or speech.

One of the primary aspects of sustainable development involves accurate understanding and modeling of environmental phenomena. Many of these phenomena exhibit variations in both space and time and it is imperative to develop a deeper understanding of techniques that can model space-time dynamics accurately. In this paper we propose NOSTILL-GP - NOn-stationary Space TIme variable Latent Length scale GP, a generic non-stationary, spatio-temporal Gaussian Process (GP) model. We present several strategies, for efficient training of our model, necessary for real-world applicability. Extensive empirical validation is performed using three real-world environmental monitoring datasets, with diverse dynamics across space and time. Results from the experiments clearly demonstrate general applicability and effectiveness of our approach for applications in environmental monitoring.

Cardio-Vascular Diseases (CVD) are one of the major healthcare problems across the world, causing deaths for nearly 17 million people every year. With more than 80% of all CVD cases occurring in developing countries, it is a big challenge that needs immediate attention. Specifically for India, World Health Organization (WHO) and many other organizations have predicted rapid growth of CVD patients in near future. It is known that CVD can be prevented or deferred, if detected in its earlier stages and by subsequently adapting to appropriate preventive methods. Cost and availability of lab equipments -- for early diagnosis of CVD -- act as deterrents in controlling the spread of CVD cases in India, particularly in the rural parts.

Location-aware mobile applications are steadily gaining popularity across the world. However, lack of Global Positioning System (GPS) and absence of Wi-Fi infrastructure prevent users with non-Smart phones (majority of population in developing countries) from using location-aware applications as their phones do not have access to their current location. Existing GSM based approaches such as Cell ID-based works on non-Smart phones but they require access to a comprehensive database of Cell IDs. Such a database either does not exist or is very limited in developing countries. In this paper, we propose a novel GSM-based approach of using Cell Broadcast Service (CBS) messages for getting current location on the phone. Proposed approach does not depend on a comprehensive database and can run on programmable low end phones. We demonstrate the effectiveness of our approach on data collected in New Delhi, India across two different operators and propose two space-time history based algorithms to improve upon the localization accuracy of our baseline CBS approach. The proposed algorithms provide up to 35% improvement in accuracy over the baseline method. Further, we compare accuracy of our CBS-based approach with that of Cell ID-based approach and also, present a multimodal approach that uses combination of both CBS and Cell ID (wherever available) to improve the localization accuracy.

No abstract available.

The need for efficient monitoring of spatio-temporal dynamics in large environmental surveillance applications motivates the use of robotic sensors to achieve sufficient spatial and temporal coverage. A common approach in machine learning to model spatial dynamics is to use the nonparametric Bayesian framework known as Gaussian Processes (GPs) (c.f., [1]) which are fully specified by a mean and a covariance function. However, defining suitable covariance functions that are able to appropriately model complex space-time dependencies in the environment is a challenging task. In this paper, we develop a generic approach for constructing several classes of covariance functions for spatio-temporal GP modeling. The GP models are then extended to perform efficient path planning in continuous space while maximizing the information gain. Extensive empirical evaluation for the different classes of covariance functions using real world sensing datasets is discussed, including experiments on a tethered robotic system - Networked Info Mechanical System (NIMS).

Many sensing applications require monitoring phenomena with complex spatio-temporal dynamics spread over large spatial domains. Efficient monitoring of such phenomena would require an impractically large number of static sensors; therefore, actuated sensing - mobile robots carrying sensors - is required. Path planning for these robots, i.e., deciding on a subset of locations to observe, is critical for high fidelity monitoring of expansive areas with complex dynamics. We propose MUST - a multiscale approach with stochastic modeling. MUST is a hierarchical approach that models the phenomena as a stochastic Gaussian process that is exploited to select a near-optimal subset of observation locations. We discuss in detail our proposed algorithm for the application of monitoring light intensity in a forest understory. We performed extensive empirical evaluations both in simulation using field data and on an actual cabled robotic system to validate the effectiveness of our proposed algorithm.

The need for efficient monitoring of spatio-temporal dynamics in large environmental applications, such as the water quality monitoring in rivers and lakes, motivates the use of robotic sensors in order to achieve sufficient spatial coverage. Typically, these robots have bounded resources, such as limited battery or limited amounts of time to obtain measurements. Thus, careful coordination of their paths is required in order to maximize the amount of information collected, while respecting the resource constraints. In this paper, we present an efficient approach for near-optimally solving the NP-hard optimization problem of planning such informative paths. In particular, we first develop eSIP (efficient Single-robot Informative Path planning), an approximation algorithm for optimizing the path of a single robot. Hereby, we use a Gaussian Process to model the underlying phenomenon, and use the mutual information between the visited locations and remainder of the space to quantify the amount of information collected. We prove that the mutual information collected using paths obtained by using eSIP is close to the information obtained by an optimal solution. We then provide a general technique, sequential allocation, which can be used to extend any single robot planning algorithm, such as eSIP, for the multi-robot problem. This procedure approximately generalizes any guarantees for the single-robot problem to the multi-robot case. We extensively evaluate the effectiveness of our approach on several experiments performed in-field for two important environmental sensing applications, lake and river monitoring, and simulation experiments performed using several real world sensor network data sets.

As concern for water resource availability increases, so does the need for intelligent aquatic sensing applications. The requirements, and complexity of such applications has also increased due to demands for: 1) broad spatial coverage and high spatial resolution monitoring, 2) capability for resolving fine scale spatiotemporal dynamics and 3) the need for rapid system deployment with semi-autonomous operation. With these criteria in mind, we present the Aquatic Networked InfoMechanical System (NIMS-AQ). NIMS-AQ was developed based on experience gained from engineering research and collaboration with aquatic scientists and environmental engineers during several in-field measurement campaigns [1], [2], [3]. In this paper we demonstrate the effectiveness of NIMS- AQ through two experimental sensing campaigns encompassing both river and lake environments. Each campaign is centered around critical water resource monitoring objectives such as temperature, flow and contaminant levels. Experimental results for autonomous depth profiling using a submersible sonar system as well as adaptive sampling algorithms guided by phenomena models are presented herein. The found results conform with our objectives for rapid and systematic operation. Preliminary studies also indicate the systems viability for use with an autonomous iterative experiment design for environmental applications (A-IDEA) methodology that is currently under development. The IDEA methodology [1] provides effective characterization of spatiotemporal dynamics in aquatic environments. A-IDEA, as it is to be implemented on the NIMS-AQ platform, is also described.

Cabled robotic systems have been used for a diverse set of applications such as environmental sensing, search and rescue, sports and entertainment and air vehicle simulators. In this paper, we introduce a new cabled robot- Networked Info Mechanical System for Planar actuation (NIMS-PL), with energy profiling capabilities. Accurate energy measurements supported by NIMS-PL enable path planning that optimizes the robotpsilas path subject to an upper bound on energy consumption. We performed extensive empirical validation of the optimized path planning approach in simulation using an environmental sensing application as an example. We also validated the simulation results using NIMS-PL, demonstrating significant improvements in the sensing task when accounting with accurate energy measurements as opposed to Euclidean distance, which is typically used for modeling energy spent in path traversal.

Distributed, high-density spatiotemporal observations are proposed for answering many river related questions, including those pertaining to hydraulics and multi-dimensional river modeling, geomorphology, sediment transport and riparian habitat restoration. In spite of the recent advancements in technology, currently available systems have many constraints that preclude long term, remote, autonomous, high resolution monitoring in the real environment. We present here a case study of an autonomous, high resolution robotic spatial mapping of cross-sectional velocity and salt concentration in a river basin. The scientific objective of this investigation was to characterize the transport and mixing phenomena at the confluence of two distinctly different river streams - San Joaquin River and its tributary Merced River. Several experiments for analyzing the spatial and temporal trends at multiple cross-sections of the San Joaquin River were performed during the campaign from August 21-25, 2006. These include deterministic dense raster scans and in-field adapted experimental design. Preliminary analysis from these experiments illustrating the range of investigations is presented with the focus on adaptive experiments that enable sparse sampling to provide larger spatial coverage without discounting the dynamics in the phenomena. Lessons learned during the campaign are discussed to provide useful insights for similar robotic investigations in aquatic environments.

A broad range of embedded networked sensor (ENS) systems for critical environmental monitoring applications now require complex, high peak power dissipating sensor devices, as well as on-demand high performance computing and high bandwidth communication. Embedded computing demands for these new platforms include support for computationally intensive image and signal processing as well as optimization and statistical computing. To meet these new requirements while maintaining critical support for low energy operation, a new multiprocessor node hardware and software architecture, Low Power Energy Aware Processing (LEAP), has been developed. The LEAP architecture integrates fine-grained energy dissipation monitoring and sophisticated power control scheduling for all subsystems including sensor subsystems. The LEAP2 platform is a second generation LEAP system with even higher resolution energy monitoring as well as the unique ability to do per process and per application energy profiling via a dedicated high performance ASIC. This poster will demonstrate the hardware platform capabilities as well as the energy-aware software currently available for LEAP2.

Many environmental applications require high temporal frequency (rapidly changing) and spatially distributed phenomena to be sampled with high fidelity. This requires mobile sensing elements to perform guided sampling in regions of high variability. We propose a multiscale approach for efficiently sampling such phenomena. This approach introduces a hierarchy of sensors according to the sampling fidelity, spatial coverage, and mobility characteristics. In this paper, we report the development of a two-tier multiscale system where information from a low-fidelity, high spatial (global) sensor actuates a mobile robotic node, carrying a high-fidelity, low spatial coverage (spot measurement) sensor, to perform guided sampling in the regions of high phenomenon variability. As a case study of the proposed multiscale paradigm, we investigated the spatiotemporal distribution of the light intensity in a forest understory. The performance of the multiscale approach is verified in simulation and on a physical system. Results suggest that our approach is adequate for the problem of high-frequency spatiotemporal phenomena sampling and significantly outperforms traditional sampling approaches such as a raster scan